In remote control systems, transmitting large data volumes (e.g., images, video frames) from wireless sensors to remote controllers is challenging when uplink capacity is limited (e.g., RedCap devices or massive wireless sensor networks). Furthermore, controllers often need only information-rich representations of the original data. To address this, we propose a semantic-driven predictive control combined with a channel-aware scheduling to enhance control performance for multiple devices under limited network capacity. At its core, the proposed framework, coined Time-Series Joint Embedding Predictive Architecture (TS-JEPA), encodes high-dimensional sensory data into low-dimensional semantic embeddings at the sensor, reducing communication overhead. Furthermore, TS-JEPA enables predictive inference by predicting future embeddings from current ones and predicted commands, which are directly used by a semantic actor model to compute control commands within the embedding space, eliminating the need to reconstruct raw data. To further enhance reliability and communication efficiency, a channel-aware scheduling is integrated to dynamically prioritize device transmissions based on channel conditions and age of information (AoI). Extensive simulations on inverted cart-pole systems demonstrate that the proposed framework achieves a 98.95% reduction in communication cost, a normalized prediction error of 0.004, and 74.48% control accuracy, outperforming conventional control baselines. Furthermore, the proposed framework maintains robust control performance on 15-step prediction horizons and supports up to 16× more devices than round-robin and opportunistic scheduling schemes with conventional control baselines under similar network conditions.

Neural network-based medium access control (MAC) protocol models (NPMs) improve goodput through site-specific operations but are vulnerable to shifts from their training network environments, such as changes in the number of user equipments (UEs) severely degrading goodput. To enhance resilience against such environmental shifts, we propose three novel token-based MAC protocol frameworks empowered by large language models (LLMs). First, we introduce a token-based protocol model (TPM), where an LLM generates MAC signaling messages. By editing LLM instruction prompts, TPM enables instant adaptation, which can be further enhanced by TextGrad, an LLM-based automated prompt optimizer. TPM inference is fast but coarse due to the lack of real interactions with the changed environment, and computationally intensive due to the large size of the LLM. To improve goodput and computation efficiency, we develop T2NPM, which transfers and augments TPM knowledge into an NPM via knowledge distillation (KD). Integrating TPM and T2NPM, we propose T3NPM, which employs TPM in the early phase and switches to T2NPM at a later stage. To optimize this phase switching, we design a novel metric of meta-resilience, which quantifies resilience to unknown target goodput after environmental shifts. Simulations corroborate that T3NPM achieves 20.56% higher meta-resilience than NPM with 19.8× lower computation cost than TPM in FLOPs.

Fine-tuning (FT) large language models (LLMs) is crucial for adapting general-purpose models to specific tasks, enhancing accuracy and relevance with minimal resources. To further enhance generalization ability while reducing training costs, this paper proposes Federated LoRA with Dropout (FedLoDrop), a new framework that applies dropout to the rows and columns of the trainable matrix in Federated LoRA. A generalization error bound and convergence analysis under sparsity regularization are obtained, which elucidate the fundamental trade-off between underfitting and overfitting. The error bound reveals that a higher dropout rate increases model sparsity, thereby lowering the upper bound of pointwise hypothesis stability (PHS). While this reduces the gap between empirical and generalization errors, it also incurs a higher empirical error, which, together with the gap, determines the overall generalization error. On the other hand, though dropout reduces communication costs, deploying FedLoDrop at the network edge still faces challenges due to limited network resources. To address this issue, an optimization problem is formulated to minimize the upper bound of the generalization error, by jointly optimizing the dropout rate and resource allocation subject to the latency and per-device energy consumption constraints. To solve this problem, a branch-and-bound (B&B)-based method is proposed to obtain its globally optimal solution. Moreover, to reduce the high computational complexity of the B&B-based method, a penalized successive convex approximation (P-SCA)-based algorithm is proposed to efficiently obtain its high-quality suboptimal solution. Finally, numerical results demonstrate the effectiveness of the proposed approach in mitigating overfitting and improving the generalization capability.

In this paper, a novel three dimensional (3D) positioning framework of fluid antenna system (FAS)-enabled unmanned aerial vehicles (UAVs) is developed. In the proposed framework, a set of controlled UAVs including an active UAV and four FAS-enabled passive UAVs cooperatively estimate the real-time 3D position of a target UAV. Here, the active UAV transmits a measurement signal to the passive UAVs via the reflection from the target UAV. Each passive UAV estimates the distance of the active-target-passive UAV link and selects an antenna port to share the distance information with the base station (BS), which calculates the real-time position of the target UAV. As the target UAV is moving due to its task operation, the controlled UAVs must optimize their trajectories and select optimal antenna port for transmitting the positioning information, aiming to estimate the real-time position of the target UAV. We formulate this problem as an optimization problem whose goal is to minimize the target UAV positioning error via optimizing the trajectories of all controlled UAVs and antenna port selection of passive UAVs. To address this problem, an attention-based recurrent multi-agent reinforcement learning (AR-MARL) scheme is proposed, which enables each controlled UAV to use the local Q function to determine its trajectory and antenna port while optimizing the target UAV positioning performance without knowing the trajectories and antenna port selections of other controlled UAVs. Different from current MARL methods that use feedforward neural networks to approximate Q functions, the proposed method uses a recurrent neural network (RNN) that incorporates historical state-action pairs of each controlled UAV, and an attention mechanism to analyze the importance of these historical state-action pairs, thus improving the global Q function approximation accuracy and the target UAV positioning accuracy. Simulation results show that the proposed scheme can reduce the average positioning error by up to 17.5% and 58.5% compared to the value decomposition based-MARL scheme with FAS and the proposed AR-MARL method without FAS.

In this work, we study the joint scheduling and power allocation problem of vision-based remote control systems, where multiple devices upload their image states to a central controller and receive control actions. Due to the high dimensionality of the image states and to manage the lack of radio resources, we propose a novel self-supervised learning approach to predict the devices’ joint control and wireless dynamics in latent space, enabling wireless resource optimization without compromising the control objectives of the remote control system. Our method leverages two coupled joint-embedding predictive architectures (JEPAs): a control JEPA models the control transition dynamics and guides the predictions of a wireless JEPA, which captures the dynamics of the device’s channel state information (CSI) through cross-modal conditioning. We then train a deep reinforcement learning (RL) algorithm to derive a control policy from latent control dynamics and a power predictor to estimate scheduling slots with favorable channel conditions based on latent CSI representations. To enhance control reliability, we employ an efficient ensemble technique to estimate the uncertainty of JEPA predictions. The two JEPAs are used by the remote controller to forecast future latent trajectories of the devices’ control and wireless states, allowing the controller to proactively plan its scheduling policy using model predictive control (MPC). Simulation results, conducted in a customized image-based control environment with ray tracing, demonstrate that our proposed approach converges three times faster and reduces transmit power by over 50% while maintaining control performance comparable to baseline methods that do not account for wireless resource optimization.

Stacked intelligent metasurfaces (SIMs), composed of a multi-layered structure, have emerged as a powerful computing tool and analog signal processing platform for enabling task-oriented semantic communications (SemCom). However, SIMs lack nonlinear inference capabilities, thus motivating the emergence of the hybrid optical-electronic neural network (HOENN) that cascades a SIM and an electronic neural network (ENN). In this work, we investigate a disaster recognition taskoriented SemCom setting by leveraging the HOENN technology. Specifically, the HOENN is made of an optical neural network (ONN) using SIM mounted on an unmanned aerial vehicle (UAV) and a shallow ENN at the ground receiving station (GRS). The SIM automatically processes semantic information modulated on electromagnetic waves, with reduced energy consumption and ultrafast processing speed. At the GRS, the energy signals are processed by the shallow ENN to enhance the system's inference capability. The aim is to recognize the disaster according to the captured geomorphic images. To this end, we utilize a stochastic gradient descent algorithm to train the HOENN efficiently to minimize the cross-entropy between the recognized and actual semantics. Numerical results show that the HOENN surpasses the performance of using either ONN or ENN alone, achieving$\mathbf{9 7 \%}$recognition accuracy.

In this work, we consider the radio resource allocation problem in a wireless system with various integrated functionalities, such as communication, sensing and computing. We design suitable resource management techniques that can simultaneously cater to those heterogeneous requirements, and scale appropriately with the high-dimensional and discrete nature of the problem. We propose a novel active learning framework where resource allocation patterns are drawn sequentially, evaluated in the environment, and then used to iteratively update a surrogate model of the environment. Our method leverages a generative flow network (GFlowNet) to sample favorable solutions, as such models are trained to generate compositional objects proportionally to their training reward, hence providing an appropriate coverage of its modes. As such, GFlowNet generates diverse and high return resource management designs that update the surrogate model and swiftly discover suitable solutions. We provide simulation results showing that our method can allocate radio resources achieving 20% performance gains against benchmarks, while requiring less than half of the number of acquisition rounds.

In this work, we aim to optimize the radio resource management of a communication system between a remote controller and its device, whose state is represented through image frames, without compromising the performance of the control task. We propose a novel machine learning (ML) technique to jointly model and predict the dynamics of the control system as well as the wireless propagation environment in latent space. Our method leverages two coupled joint-embedding predictive architectures (JEPAs): a control JEPA models the control dynamics and guides the predictions of a wireless JEPA, which captures the dynamics of the device’s channel state information (CSI) through cross-modal conditioning. We then train a deep reinforcement learning (RL) algorithm to derive a control policy from latent control dynamics and a power predictor to estimate scheduling intervals with favorable channel conditions based on latent CSI representations. As such, the controller minimizes the usage of radio resources by utilizing the coupled JEPA networks to imagine the device’s trajectory in latent space. We present simulation results on synthetic multimodal data and show that our proposed approach reduces transmit power by over 50% while maintaining control performance comparable to baseline methods that do not account for wireless optimization.

This paper presents Sheaf-DMFL, a novel decentralized multimodal federated learning framework leveraging sheaf theory to enhance collaborative learning among clients with diverse modalities. By framing the multimodal federated learning problem as multitask learning, Sheaf-DMFL leverages learnable restriction maps to capture relationships between clients’ models. Specifically, each client has a set of local feature encoders for its different modalities, whose outputs are concatenated before passing through a task-specific layer. Encoders corresponding to the same modality are shared among clients, while the intrinsic correlation among their task-specific layers is captured by using the sheaf structure. Numerical experiments in a mmWave beamforming prediction scenario show that the proposed algorithm surpasses baseline methods, delivering improved convergence rates and test accuracy.

In this paper, we propose novel architecture supporting artificial intelligence-based multimodal semantic communication and distributed computing. The proposed architecture is built on existing concepts in adopted mobile networks, including cloud radio access network (C-RAN) and open-RAN (O-RAN). On top of current architectures, we introduce new key features including block for artificial intelligence (AI) training models for semantic encoding and decoding, semantic modules, and hierarchical edge cloud for distributed and parallel processing. Then, we formulate a delay minimization problem for processing of semantically encoded tasks by the hierarchical edge cloud. First, we derive optimal closed-form solutions for splitting the tasks between individual tiers of the hierarchical edge cloud while assuming actual communication and computing queues. Second, we propose a low-complexity algorithm selecting place, where the individual tasks are processed while adopting the optimal splitting of the tasks. Via simulations, we demonstrate that the proposed solution decreases average processing time and energy consumption due to computing by up to 50 % and 23 % when compared to the best performing state-of-the-art scheme.

We introduce CSI-Inpainter, a novel approach for obstacle removal using Wi-Fi CSI. This method harnesses CSI data to reconstruct obscured visual elements, regardless of lighting conditions. Extensive empirical evaluation in both office and industrial settings demonstrates the effectiveness of CSI-Inpainter’s exceptional ability to identify and reconstruct occluded segments, outperforming traditional baselines and our received signal strength indicator (RSSI)-based work, RF-Inpainter in terms of visual quality. Our findings emphasize the superiority of CSI data over RSSI for providing richer visual information and underscore the critical role of optimal sensor placement and data fusion from multiple CSI sensors in enhancing the performance. CSI-Inpainter represents a significant advancement in obstacle removal for various applications like surveillance, offering new insights into the integration of wireless sensing and visual scene recovery, expanding the potential applications of Computer Vision in real-world environments.

Federated averaging (FedAvg) is a well-recognized framework for distributed learning that efficiently manages communication. Several algorithms have emerged to enhance the communication efficiency of FedAvg and its variations. Some of these algorithms focus on reducing the number of communication rounds by allowing clients to skip frequent interactions with the parameter server. In this work, our primary concern is the overall energy consumption during model training in federated learning. We challenge the conventional notion that reducing the frequency of communication leads to energy savings and present evidence that for nonindependent and nonidentical (non-IID) data distribution, increasing the frequency of communication can, in fact, result in greater energy conservation. Our contribution comprises two key aspects: first, we introduce a quantized version of the recently proposed algorithm called federated primal-dual (FedPD) (Zhang et al., 2021), which we refer to as quantized FedPD (QFedPD). Importantly, we substantiate the convergence guarantees for QFedPD. Second, we explore the tradeoff between quantization and communication skipping in the proposed approach. Our analysis demonstrates that applying quantization without skipping communication, using QFedPD, yields the most significant energy-saving benefits for non-IID data distribution. Intriguingly, when dealing with non-IID data distribution, the preferred strategy is to maximize energy efficiency, allowing all clients to transmit at every iteration while quantizing their updates.

Federated learning (FL) offers a promising approach for collaborative machine learning (ML) across distributed devices. However, its adoption is hindered by the complexity of building reliable communication architectures and the need for expertise in both ML and network programming. This article presents a comprehensive solution that simplifies the orchestration of FL tasks while integrating intent-based automation. A user-friendly web application is developed supporting the federated averaging (FedAvg) algorithm, enabling users to configure parameters through an intuitive interface. The backend solution efficiently manages communication between the parameter server and edge nodes. Model compression and scheduling algorithms are implemented to optimize FL performance. Additionally, intent-based automation in FL is explored using a fine-tuned Language Model (LLM) trained on a tailored dataset, enabling users to perform FL tasks through high-level prompts. It is shown that the LLM-based automated solution achieves comparable test accuracy to the standard web-based solution while reducing transferred bytes by up to 64% and CPU time by up to 46% for FL tasks. Furthermore, neural architecture search (NAS) and hyperparameter optimization (HPO) are leveraged using the LLM to enhance performance, resulting in a 10%–20% improvement in test accuracy for the conducted FL tasks.

According to the advances in quantum computing and distributed learning, quantum federated learning (QFL) has recently become an emerging field of study. In QFL, each quantum computer or device locally trains its quantum neural network (QNN) with trainable gates, and communicates only these gate parameters over classical channels, without costly quantum communications. To successfully opeate QFL under various and dynamic channel conditions in Internet of Things (IoT) environments, this article develops a novel depth-controllable architecture of entangled slimmable QNNs (eSQNNs), and thus, proposes an entangled slimmable QFL (eSQFL) that communicates the superposition-coded parameters of eSQNNs. Even though the proposed eSQNN-based eSQFL is superior, training the depth-controllable eSQNN architecture is challenging due to high-entanglement entropy and interdepth interference. Therefore, the proposed method in this article mitigates the interference using entanglement controlled universal (CU) gates and an inplace fidelity distillation (IPFD) regularizer penalizing interdepth quantum state differences, respectively. Furthermore, the proposed method optimizes the superposition coding power allocation by deriving and minimizing the convergence bound of eSQFL. The novelty of this work is evaluated via extensive simulations in terms of prediction accuracy, fidelity, and entropy compared to Vanilla QFL as well as under different channel conditions and various data distributions.

In this letter, we formulate a compositional distributed learning framework for multi-view perception by leveraging the maximal coding rate reduction principle combined with subspace basis fusion. In the proposed algorithm, each agent conducts a periodic singular value decomposition on its learned subspaces and exchanges truncated basis matrices, based on which the fused subspaces are obtained. By introducing a projection matrix and minimizing the distance between the outputs and its projection, the learned representations are enforced towards the fused subspaces. It is proved that the trace on the coding-rate change is bounded and the consistency of basis fusion is guaranteed theoretically. Numerical simulations validate that the proposed algorithm achieves high classification accuracy while maintaining representations' diversity, compared to baselines showing correlated subspaces and coupled representations.

Split Federated Learning (SFL) improves scalability of Split Learning (SL) by enabling parallel computing of the learning tasks on multiple clients. However, state-of-the-art SFL schemes neglect the effects of heterogeneity in the clients’ computation and communication performance as well as the computation time for the tasks offloaded to the cloud server. In this paper, we propose a fine-grained parallelization framework, called PipeSFL, to accelerate SFL on heterogeneous clients. PipeSFL is based on two key novel ideas. First, we design a server-side priority scheduling mechanism to minimize per-iteration time. Second, we propose a hybrid training mode to reduce per-round time, which employs asynchronous training within rounds and synchronous training between rounds. We theoretically prove the optimality of the proposed priority scheduling mechanism within one round and analyze the total time per round for PipeSFL, SFL and SL. We implement PipeSFL on PyTorch. Extensive experiments on seven 64-client clusters with different heterogeneity demonstrate that at training speed, PipeSFL achieves up to 1.65x and 1.93x speedup compared to EPSL and SFL, respectively. At energy consumption, PipeSFL saves up to 30.8% and 43.4% of the energy consumed within each training round compared to EPSL and SFL, respectively.

Satellite-ground twin networks (SGTNs) are regarded as a promising service paradigm, which can provide mega access services and powerful computation offloading capabilities via cloud-fog automation functions. Specifically, cloud-fog automation technologies are collaboratively leveraged to enable dense connectivity, pervasive computing, and intelligent control in terrestrial industrial cyber-physical systems, whose system-level privacy security can be strengthened via blockchain based consensus protocol. Moreover, digital twin (DT) can shorten the gap between physical unities and digital space to enable instant data mapping in SGTNs environments. However, complex multi-modal network environments, such as stochastic task size, dynamic low earth orbit location, and time-varying channel gains, hinder better performance metrics in terms of energy consumption, throughput and privacy overhead. Hence, we establish a SGTN integrated cloud-fog automation model to transfer task data to low earth orbit satellites, and then execute broad communication access, powerful computation offloading, and efficient twin control. Next, we propose a Lyapunov stability theory based multi-modal federated learning (LST-MMFL) method to optimize the battery energy, the size of block, computation frequency, and the number of twin control for minimizing the total energy consumption and privacy overhead. Furthermore, we design a novel blockchain based transaction verification protocol to strengthen privacy security, derive performance upper bounds of SGTN model, and fulfill the long-term average task as well as energy queue constraints. Finally, massive simulation results show that the proposed LST-MMFL algorithm outperforms existing state-of-the-art benchmarks in line with energy consumption, available battery level, networked control and privacy protection overhead.

By integrating recent advances in large language models (LLMs) and generative models into the emerging semantic communication (SC) paradigm, in this article we put forward to a novel framework of language-oriented semantic communication (LSC). In LSC, machines communicate using human language messages that can be interpreted and manipulated via natural language processing (NLP) techniques for SC efficiency. To demonstrate LSC’s potential, we introduce three innovative algorithms: 1) semantic source coding (SSC) which compresses a text prompt into its key head words capturing the prompt’s syntactic essence while maintaining their appearance order to keep the prompt’s context; 2) semantic channel coding (SCC) that improves robustness against errors by substituting head words with their lenghthier synonyms; and 3) semantic knowledge distillation (SKD) that produces listener-customized prompts via in-context learning the listener’s language style. In a communication task for progressive text-to-image generation, the proposed methods achieve higher perceptual similarities with fewer transmissions while enhancing robustness in noisy communication channels.

Federated learning is a machine learning approach where multiple devices collaboratively learn with the help of a parameter server by sharing only their local updates. While gradient-based optimization techniques are widely adopted in this domain, the curvature information that second-order methods exhibit is crucial to guide and speed up the convergence. This paper introduces a scalable second-order method, allowing the adoption of curvature information in federated large models. Our method, coined Fed-Sophia, combines a weighted moving average of the gradient with a clipping operation to find the descent direction. In addition to that, a lightweight estimation of the Hessian's diagonal is used to incorporate the curvature information. Numerical evaluation shows the superiority, robustness, and scalability of the proposed Fed-Sophia scheme compared to first and second-order baselines.

In this work, we compare emergent communication (EC) built upon multi-agent deep reinforcement learning (MADRL) and language-oriented semantic communication (LSC) empowered by a pre-trained large language model (LLM) using human language. In a multi-agent remote navigation task, with multimodal input data comprising location and channel maps, it is shown that EC incurs high training cost and struggles when using multimodal data, whereas LSC yields high inference computing cost due to the LLM's large size. To address their respective bottlenecks, we propose a novel framework of language-guided EC (LEC) by guiding the EC training using LSC via knowledge distillation (KD). Simulations corroborate that LEC achieves faster travel time while avoiding areas with poor channel conditions, as well as speeding up the MADRL training convergence by up to 61.8% compared to EC.

To effectively express and satisfy network application requirements, intent-based network management has emerged as a promising solution. In intent-based methods, users and applications express their intent in a high-level abstract language to the network. Although this abstraction simplifies network operation, it induces many challenges to efficiently express applications' intents and map them to different network capabilities. Therefore, in this work, we propose an AI-based framework for intent profiling and translation. We consider a scenario where applications interacting with the network express their needs for network services in their domain language. The machine-to-machine communication (i.e., between applications and the network) is complex since it requires networks to learn how to understand the domain languages of each application, which is neither practical nor scalable. Instead, a framework based on emergent communication is proposed for intent profiling, in which applications express their abstract quality-of-experience (QoE) intents to the network through emergent communication messages. Subsequently, the network learns how to interpret these communication messages and map them to network capabilities (i.e., slices) to guarantee the requested Quality-of-Service (QoS). Simulation results show that the proposed method outperforms self-learning slicing and other baselines, and achieves a performance close to the perfect knowledge baseline.

Future 6G wireless networks of connected intelligence will require ultra-high throughput, ultra-low latency, extreme reliability, high levels of scalability and decentralized heterogeneous AI networking. To meet such stringent requirements, high-performing communication protocols become the foundation for the upcoming 6G use-cases. Recently, multi-agent reinforcement learning (MARL) has demonstrated its potential to provide viable alternatives to classical networking for such scenarios. However, while highly competitive, such emerged protocols are not fully explainable and fail to scale to large numbers of users. To bridge this gap, we leverage the advantages of the contention-free MAC protocol, optimize it for two users and integrate it in a hierarchical network architecture, to ensure its high scalability and decreased latency.

In this paper, we quantitatively compare these two effective communication schemes, i.e., digital and analog ones, for wireless federated learning (FL) over resource-constrained networks, highlighting their essential differences as well as their respective application scenarios. We first examine both digital and analog transmission methods, together with a unified and fair comparison scheme under practical constraints. A universal convergence analysis under various imperfections is established for FL performance evaluation in wireless networks. These analytical results reveal that the fundamental difference between the two paradigms lies in whether communication and computation are jointly designed or not. The digital schemes decouple the communication design from specific FL tasks, making it difficult to support simultaneous uplink transmission of massive devices with limited bandwidth. In contrast, the analog communication allows over-the-air computation (AirComp), thus achieving efficient spectrum utilization. However, computation-oriented analog transmission reduces power efficiency, and its performance is sensitive to computational errors. Finally, numerical simulations are conducted to verify these theoretical observations.

This work introduces a solution to enhance human-robot interaction over limited wireless connectivity. The goal is to enable remote control of a robot through a virtual reality (VR) interface, ensuring a smooth transition to autonomous mode in the event of connectivity loss. The VR interface provides access to a dynamic 3D virtual map that undergoes continuous updates using real-time sensor data collected and transmitted by the robot. Furthermore, the robot monitors wireless connectivity and automatically switches to a autonomous mode in scenarios with limited connectivity. By integrating four key functionalities: real-time mapping, remote control through glasses VR, continuous monitoring of wireless connectivity, and autonomous navigation during limited connectivity, we achieve seamless end-to-end operation.

This work presents a use case of federated learning (FL) applied to discovering a maze with LiDAR sensors-equipped robots. Goal here is to train classification models to accurately identify the shapes of grid areas within two different square mazes made up with irregular shaped walls. Due to the use of different shapes for the walls, a classification model trained in one maze that captures its structure does not generalize for the other. This issue is resolved by adopting FL framework between the robots that explore only one maze so that the collective knowledge allows them to operate accurately in the unseen maze. This illustrates the effectiveness of FL in real-world applications in terms of enhancing classification accuracy and robustness in maze discovery tasks.

Achieving control stability is one of the key design challenges of scalable Wireless Networked Control Systems (WNCS) under limited communication and computing resources. This paper explores the use of an alternative control concept defined as tail-based control, which extends the classical Linear Quadratic Regulator ($\mathbf{L Q R}$) cost function for multiple dynamic control systems over a shared wireless network. We cast the control of multiple control systems as a network-wide optimization problem and decouple it in terms of sensor scheduling, plant state prediction, and control policies. Toward this, we propose a solution consisting of a scheduling algorithm based on Lyapunov optimization for sensing, a mechanism based on Gaussian Process Regression (GPR) for state prediction and uncertainty estimation, and a control policy based on Reinforcement Learning (RL) to ensure tail-based control stability. A set of discrete time-invariant mountain car control systems is used to evaluate the proposed solution and is compared against four variants that use state-of-the-art scheduling, prediction, and control methods. The experimental results indicate that the proposed method yields 22% reduction in overall cost in terms of communication and control resource utilization compared to state-of-the-art methods.

Mounting a reconfigurable intelligent surface (RIS) on an unmanned aerial vehicle (UAV) holds promise for improving traditional terrestrial network performance. Unlike conventional methods deploying passive RIS on UAVs, this study delves into the efficacy of an aerial active RIS (AARIS). Specifically, the downlink transmission of an AARIS network is investigated, where the base station (BS) leverages rate-splitting multiple access (RSMA) for effective interference management and benefits from the support of an AARIS for jointly amplifying and reflecting the BS’s transmit signals. Considering both the non-trivial energy consumption of the active RIS and the limited energy storage of the UAV, we propose an innovative element selection strategy for optimizing the on/off status of active RIS elements, which adaptively and remarkably manages the system’s power consumption. To this end, a resource management problem is formulated, aiming to maximize the system energy efficiency (EE) by jointly optimizing the transmit beamforming at the BS, the element activation, the phase shift and the amplification factor at the active RIS, the RSMA common data rate at users, as well as the UAV’s trajectory. Due to the dynamicity nature of UAV and user mobility, a deep reinforcement learning (DRL) algorithm is designed for resource allocation, utilizing meta-learning to adaptively handle fast time-varying system dynamics. According to simulations, integrating meta-learning yields a notable 36% increase in system EE. Additionally, substituting AARIS for fixed terrestrial active RIS results in a 26% EE enhancement.

In this study, we delve into the intricacies of semantic communication-control codesign (CoCoCo) for wireless mixed logical dynamical (MLD) systems operating under signal temporal logic (STL) specifications. Our novel contribution, the MLD-Koopman autoencoder (AE), emerges as a method to linearize the progression of system states within a feature space. This linearization effectively mitigates the communication and computation costs associated with MLD system control. To surmount the challenges posed by multiple correlated MLD systems that possess distinct logical control rules while sharing baseline dynamics, we present the compositional logical dynamical (CLD)-Koopman AE as a remedy to the scalability limitations of the MLD-Koopman AE. This innovative approach incorporates two pivotal models—the dynamics semantic Koopman (DSK) model, capturing semantic correlations among MLD systems, and the logical semantic Koopman (LSK) model, encoding logical control rules. These models portray the linear evolution of baseline dynamics and control rules within a feature space, facilitating predictions of future states for multiple MLD systems with constrained communication. Validation comes from simulations on large-scale inverted cart-pole systems, demonstrating the prowess of the CLD-Koopman AE in achieving an average state prediction performance 82.77% higher than other predictive benchmarks, particularly evident at a signal-to-noise ratio (SNR) of 10 dB.

Amid the global rollout of fifth-generation (5G) services, researchers in academia, industry, and national laboratories have been developing proposals for the sixth-generation (6G), whose materialization is fraught with many fundamental challenges. To alleviate these challenges, a deep learning (DL)-enabled semantic communication (SemCom) has emerged as a promising 6G technology enabler, which embodies a paradigm shift that can change the status quo viewpoint that wireless connectivity is an opaque data pipe carrying messages whose context-dependent meanings have been ignored. Since 6G is also critical for the materialization of major SemCom use cases, the paradigms of 6G for SemCom and SemCom for 6G call for a tighter integration of 6G and SemCom. For this purpose, this comprehensive article provides the fundamentals of semantic information, semantic representation, and semantic entropy; details the state-of-the-art SemCom research landscape; presents the major SemCom trends and use cases; discusses current SemCom theories; exposes the fundamental and major challenges of SemCom; and offers future research directions for SemCom. We hope this article stimulates many lines of research on SemCom theories, algorithms, and implementation.

In recent years, split learning (SL) has emerged as a promising distributed learning framework that can utilize big data in parallel without privacy leakage while reducing client-side computing resources. In the initial implementation of SL, however, the server serves multiple clients sequentially incurring high latency. Parallel implementation of SL can alleviate this latency problem, but existing Parallel SL algorithms compromise scalability due to its fundamental structural problem. To this end, our previous works have proposed two scalable Parallel SL algorithms, dubbed SGLR and LocFedMix-SL, by solving the aforementioned fundamental problem of the Parallel SL structure. In this article, we propose a novel Parallel SL framework, coined Mix2SFL, that can ameliorate both accuracy and communication-efficiency while still ensuring scalability. Mix2SFL first supplies more samples to the server through a manifold mixup between the smashed data uploaded to the server as in SmashMix of LocFedMix-SL, and then averages the split-layer gradient as in GradMix of SGLR, followed by local model aggregation as in SFL. Numerical evaluation corroborates that Mix2SFL achieves improved performance in both accuracy and latency compared to the state-of-the-art SL algorithm with scalability guarantees. Moreover, its convergence speed as well as privacy guarantee are validated through the experimental results.

Cooperative multi-agent reinforcement learning (MARL) for navigation enables agents to cooperate to achieve their navigation goals. Using emergent communication, agents learn a communication protocol to coordinate and share information that is needed to achieve their navigation tasks. In emergent communication, symbols with no pre-specified usage rules are exchanged, in which the meaning and syntax emerge through training. Learning a navigation policy along with a communication protocol in a MARL environment is highly complex due to the huge state space to be explored. To cope with this complexity, this work proposes a novel neural network architecture, for jointly learning an adaptive state space abstraction and a communication protocol among agents participating in navigation tasks. The goal is to come up with an adaptive abstractor that significantly reduces the size of the state space to be explored, without degradation in the policy performance. Simulation results show that the proposed method reaches a better policy, in terms of achievable rewards, resulting in fewer training iterations compared to the case where raw states or fixed state abstraction are used. Moreover, it is shown that a communication protocol emerges during training which enables the agents to learn better policies within fewer training iterations.

Satellite-ground integrated heterogeneous networks can relieve network congestion, release network resources and provide ubiquitous intelligence services for terrestrial users. Furthermore, digital twin technology can enable nearly-instant data mapping from the physical world to digital systems. The integration between satellite-ground integrated heterogeneous networks and digital twin alleviates the gap between data analyses and physical unities. However, the current challenges, such as the pricing policy, the stochastic task arrivals, the time-varying satellite locations, mutual channel interference, and resource scheduling mechanisms between the users and cloud servers, severely affect the improvement of quality of service. Hence, we establish a blockchain-aided Stackelberg game model for maximizing the pricing profits and network throughput in terms of minimizing privacy overhead, which is able to perform computation offloading, decrease channel interference, and improve privacy protection. Due to the long-term task queue in Stackelberg model, we propose a Lyapunov stability theory-based model-agnostic meta-learning aided multi-agent deep federated reinforcement learning framework to transfer the long-term task queue into the single time slot, and then optimize the central processing unit frequency, channel selection, task-offloading decision, block size, and cloud server price, which facilitate the integration of communication, computation, and block resources. Subsequently, several performance analyses show that the proposed learning framework can strengthen the privacy protection, approach the optimal time average function, and fulfill the long-term average queue size via lower computational complexity. Finally, our simulation results indicate that the proposed learning framework is superior to the existing baseline methods in terms of network throughput, channel interference, cloud server profits, and privacy overhead.

This work deals with a heterogeneous semantics-native communication (SNC) problem. When agents do not share the same communication context, the effectiveness of contextual reasoning (CR) is compromised calling for agents to infer other agents’ context before communication. This article proposes a novel framework for solving the inverse problem of CR in SNC using two Bayesian inference methods, namely: Bayesian inverse CR (iCR) and Bayesian inverse linearized CR (iLCR). The first proposed Bayesian iCR method utilizes Markov Chain Monte Carlo (MCMC) sampling to infer the agent’s context while being computationally expensive. To address this issue, a Bayesian iLCR method is leveraged which obtains a linearized CR (LCR) model by training a linear neural network. Experimental results show that the Bayesian iLCR method requires less computation and achieves higher inference accuracy compared to Bayesian iCR. Additionally, heterogeneous SNC based on the context obtained through the Bayesian iLCR method shows better communication effectiveness than that of Bayesian iCR. Overall, this work provides valuable insights and methods to improve the effectiveness of SNC in situations where agents have different contexts.

Unmanned aerial vehicles (UAVs) are envisioned to provide diverse services from the air. The service quality may rely on the wireless performance which is affected by the UAV’s position. In this paper, we focus on the UAV placement problem in the Internet of Vehicles, where the UAV is deployed to monitor the road traffic and sends the monitored videos to vehicles. The studied problem is formulated as video resolution maximization by optimizing over the UAV’s position. Moreover, we take into account the maximal transmission delay and impose a probabilistic constraint. To solve the formulated problem, we first leverage the techniques in extreme value theory (EVT) and Gaussian process regression (GPR) to characterize the influence of the UAV’s position on the delay performance. Based on this characterization, we subsequently propose a proactive resolution selection and UAV placement approach, which adaptively places the UAV according to the geographic distribution of vehicles. Numerical results justify the joint usage of EVT and GPR for maximal delay characterization. Through investigating the maximal transmission delay, the proposed approach nearly achieves the optimal performance when vehicles are evenly distributed, and reduces 10% and 19% of the 999-th 1000-quantile over two baselines when vehicles are biased distributed.

Federated learning (FL) is recognized as a promising privacy-preserving distributed machine learning paradigm, given its potential to enable collaborative model training among distributed devices without sharing their raw data. However, supporting FL over wireless networks confronts the critical challenges of periodically executing power-hungry training tasks on energy-constrained devices and transmitting high-dimensional model updates over spectrum-limited channels. In this paper, we reap the benefits of both energy harvesting (EH) and over-the-air computation (AirComp) to alleviate the battery limitation by harvesting ambient energy to support both the training and transmission of local models, and to achieve low-latency model aggregation by concurrently transmitting local gradients via AirComp. We characterize the convergence of the proposed FL by deriving an upper bound of the expected optimality gap, revealing that the convergence depends on the accumulated errors due to partial device participation and model distortion, both of which further depend on dynamic energy levels. To accelerate the convergence, we formulate a joint AirComp transceiver design and device scheduling problem, which is then tackled by developing an efficient Lyapunov-based online optimization algorithm. Simulations demonstrate that, by appropriately scheduling devices and allocating energy across multiple communication rounds, our proposed algorithm achieves a much better learning performance than benchmarks.

Although deep learning (DL)-enabled semantic communication (SemCom) has emerged as a 6G enabler by minimizing irrelevant information transmission – minimizing power usage, bandwidth consumption, and transmission delay, its benefits can be limited by radio frequency interference (RFI) that causes substantial semantic noise. Such semantic noise’s impact can be alleviated using an interference-resistant and robust (IR2) SemCom design, though no such design exists yet. To stimulate fundamental research on IR2SemCom, the performance limits of a popular text SemCom system namedDeepSCare studied in the presence of (multi-interferer) RFI. By introducing a principled probabilistic framework for SemCom, we show that DeepSC produces semantically irrelevant sentences as the power of (multi-interferer) RFI gets very large. We also derive DeepSC’s practical limits and a lower bound on its outage probability under multi-interferer RFI, and propose a (generic) lifelong DL-based IR2SemCom system. We corroborate the derived limits with simulations and computer experiments, which also affirm the vulnerability of DeepSC to a wireless attack using RFI.

Satellite-Ground integrated networks (SGINs) are regarded as promising network architecture, which can provide global coverage, large broadband and mega access services for massive terrestrial users. Furthermore, it is beneficial to reducing network congestion, releasing network resources and achieving computation offloading functions. However, the SGIN graph structure is time-varying and highly complex, lack of fixed node orders or reference nodes, which result in dynamic multi-modal features. Hence, we consider a SGIN directed graph model to minimize the total latency while improving the model prediction accuracy, and then perform the computation offloading and quantization schemes. Specifically, we envision a spatial graph convolutional neural network framework to adapt to the dynamic SGIN graph nodes and size, and then propose a centrally deep reinforcement learning aided multi-node federated learning (CDRFL) framework to optimize the CPU cycle frequency, transmission bandwidth and the number of quantization bits to accelerate the convergence round. Extensive theoretical analyses verify the graph permutation property between SGIN graph structure and optimization problems, and demonstrate the upper bound of quantization error via massive mathematical derivation. Finally, the experimental results indicate that the proposed CDRFL framework outperforms some existing benchmarks with reference to FL convergence analysis, average latency and transmission energy consumption for all independent identically distribution (IID) and non-IID data.

Wireless networked control systems (WNCS) offer great potential for revolutionizing the industrial automation by enabling wireless coordination between sensors, decision centers, and actuators. However, inefficient access control and resource allocation in WNCS are two critical factors that limit closed-loop performance and control stability, especially when the spectral and energy resources are limited. In this paper, we first analyze the optimal scheduling condition for maintaining control stability of a WNCS and then formulate a long-term optimization problem that jointly optimizes the access policy of edge devices, and grant policy and resource allocation at the edge server. We employ Lyapunov optimization to decompose the long-term optimization problem into a sequence of independent sub-problems, and propose a heterogeneous attention graph based multi-agent deep reinforcement learning algorithm that jointly optimizes the access and resource allocation policy. By leveraging the attention mechanism to project the graph representations from heterogeneous agents into a unified space, our proposed algorithm facilitates coordination among heterogeneous agents, thereby enhancing the overall system performance. Simulation results demonstrate that our proposed framework outperforms several benchmarks, validating its effectiveness.

Semantic-aware communication is a novel paradigm that draws inspiration from human communication focusing on the delivery of the meaning of messages. It has attracted significant interest recently due to its potential to improve the efficiency and reliability of communication and enhance users’ quality-of-experience (QoE). Most existing works focus on transmitting and delivering the explicit semantic meaning that can be directly identified from the source signal. This paper investigates the implicit semantic-aware communication in which the hidden information, e.g., hidden relations, concepts and implicit reasoning mechanisms of users, that cannot be directly observed from the source signal must be recognized and interpreted by the intended users. To this end, a novel implicit semantic-aware communication (iSAC) architecture is proposed for representing, communicating, and interpreting the implicit semantic meaning between source and destination users. A graph-inspired structure is first developed to represent the complete semantics, including both explicit and implicit, of a message. A projection-based semantic encoder is then proposed to convert the high-dimensional graphical representation of explicit semantics into a low-dimensional semantic constellation space for efficient physical channel transmission. To enable the destination user to learn and imitate the implicit semantic reasoning process of source user, a generative adversarial imitation learning-based solution, called G-RML, is proposed. Different from existing communication solutions, the source user in G-RML does not focus only on sending as much of the useful messages as possible; but, instead, it tries to guide the destination user to learn a reasoning mechanism to map any observed explicit semantics to the corresponding implicit semantics that are most relevant to the semantic meaning. By applying G-RML, we prove that the destination user can accurately imitate the reasoning process of the source user and automatically generate a set of implicit reasoning paths following the same probability distribution as the expert paths. Compared to the existing solutions, our proposed G-RML requires much less communication and computational resources and scales well to the scenarios involving the communication of rich semantic meanings consisting of a large number of concepts and relations. Numerical results show that the proposed solution achieves up to 92% accuracy of implicit meaning interpretation.

To enable wireless federated learning (FL) in communication resource-constrained networks, two communication schemes, i.e., digital and analog ones, are effective solutions. In this paper, we quantitatively compare these two techniques, highlighting their essential differences as well as respectively suitable scenarios. We first examine both digital and analog transmission schemes, together with a unified and fair comparison framework under imbalanced device sampling, strict latency targets, and transmit power constraints. A universal convergence analysis under various imperfections is established for evaluating the performance of FL over wireless networks. These analytical results reveal that the fundamental difference between the digital and analog communications lies in whether communication and computation are jointly designed or not. The digital scheme decouples the communication design from FL computing tasks, making it difficult to support uplink transmission from massive devices with limited bandwidth and hence the performance is mainly communication-limited. In contrast, the analog communication allows over-the-air computation (AirComp) and achieves better spectrum utilization. However, the computation-oriented analog transmission reduces power efficiency, and its performance is sensitive to computation errors from imperfect channel state information (CSI). Furthermore, device sampling for both schemes are optimized and differences in sampling optimization are analyzed. Numerical results verify the theoretical analysis and affirm the superior performance of the sampling optimization.

In this paper, the cooperative edge caching problem is studied in fog radio access networks (F-RANs). Given the non-deterministic polynomial hard (NP-hard) nature of the problem, a dueling deep Q network (Dueling DQN) based caching update algorithm is proposed to make an optimal caching decision by learning the dynamic network environment. In order to protect user data privacy and solve the problem of slow convergence of the single deep reinforcement learning (DRL) model training, we propose a communication-efficient federated deep reinforcement learning (CE-FDRL) method to implement cooperative training of models from multiple fog access points (F-APs) in F-RANs. To address the excessive consumption of communication resources caused by model transmission, we propose to prune and quantize the shared DRL models to reduce the number of transferred model parameters. The communication interval is increased and the communication round is reduced by periodic model aggregation. The global convergence and computational complexity of our proposed method are also analyzed. Simulation results verify that our proposed method can offer better performance in reducing user request delay and improving cache hit rate and the transmitted parameters of our proposed method can drop to 60% compared to the existing benchmark schemes. Our proposed method is also shown to have faster training speed and higher communication efficiency.

In this paper, we investigate the problem of robust Reconfigurable Intelligent Surface (RIS) phase-shifts configuration over heterogeneous communication environments. The problem is formulated as a distributed learning problem over different environments in a Federated Learning (FL) setting. Equivalently, this corresponds to a game played between multiple RISs, as learning agents, in heterogeneous environments. Using Invariant Risk Minimization (IRM) and its FL equivalent, dubbed FL Games, we solve the RIS configuration problem by learning invariant causal representations across multiple environments and then predicting the phases. The solution corresponds to playing according to Best Response Dynamics (BRD) which yields the Nash Equilibrium of the FL game. The representation learner and the phase predictor are modeled by two neural networks, and their performance is validated via simulations against other benchmarks from the literature. Our results show that causality-based learning yields a predictor that is 15 % more accurate in unseen Out-of-Distribution (OoD) environments.

In this paper, we leverage a multi-agent reinforcement learning (MARL) framework to jointly learn a computation of-floading decision and multichannel access policy with corresponding signaling. Specifically, the base station and industrial Internet of Things mobile devices are reinforcement learning agents that need to cooperate to execute their computation tasks within a deadline constraint. We adopt an emergent communication protocol learning framework to solve this problem. The numerical results illustrate the effectiveness of emergent communication in improving the channel access success rate and the number of successfully computed tasks compared to contention-based, contention-free, and no-communication approaches. Moreover, the proposed task offloading policy outperforms remote and local computation baselines.

In this paper, we investigate the semantic-aware efficient sampling policy for remote state estimation in a digital twin (DT) empowered smart factory with multiple wireless sensing devices and an edge server. In this setting, wireless sensing devices must continuously sample the factory states and transmit semantic-aware sensing data to the server. Using the received sensing data, the server builds a realtime DT mapping remotely that analyzes and predicts the events in the factory. Since the DT requires continuous data transmission, maintaining the DT inevitably consumes significant amounts of limited wireless resources. To address this issue, we reduce the required amount of data transmission by making wireless devices only send the semantic-aware sensing data that indicates the occurrence of events, otherwise stay idle. In particular, we first invoke the age of incorrect information (AoII) to measure the semantic of the sensing data, which represents the freshness of the concerned events. Next, we formulate an optimization problem that minimizes the long-term AoII of remote state estimation through the devices deciding whether to sample the factory states at each time slot. To solve this problem, we first transform the original problem into a state-wise constrained Markov decision programming (CMDP) and then propose a soft actor-critic (SAC) based algorithm to learn a sampling policy to take sample actions within the sampling rate constraint, while considering packet error. Simulation results show that, the proposed algorithm can reduce the number of samples by up to 44% compared to the error-based sampling scheme, with the same estimation accuracy.

In this work, we study the problem of semantic communication and inference, in which a student agent (i.e. mobile device) queries a teacher agent (i.e. cloud sever) to generate higher-order data semantics living in a simplicial complex. Specifically, the teacher first maps its data into a k-order simplicial complex and learns its high-order correlations. For effective communication and inference, the teacher seeks minimally sufficient and invariant semantic structures prior to conveying information. These minimal simplicial structures are found via judiciously removing simplices selected by the Hodge Laplacians without compromising the inference query accuracy. Subsequently, the student locally runs its own set of queries based on a masked simplicial convolutional autoencoder (SCAE) leveraging both local and remote teacher's knowledge. Numerical results corroborate the effectiveness of the proposed approach in terms of improving inference query accuracy under different channel conditions and simplicial structures. Experiments on a coauthorship dataset show that removing simplices by ranking the Laplacian values yields a 85% reduction in payload size without sacrificing accuracy. Joint semantic communication and inference by masked SCAE improves query accuracy by 25% compared to local student based query and 15% compared to remote teacher based query. Finally, incorporating channel semantics is shown to effectively improve inference accuracy, notably at low signal-to-noise ratio (SNR) values.

In this paper, we consider a decentralized consensus optimization problem defined over a network of inter-connected devices that collaboratively solve the problem using only local data and information exchange with their neighbours. Despite their fast convergence, Newton-type methods require sending Hessian information between devices, making them communication inefficient while violating the devices' privacy. By formulating the Newton direction learning problem as a sum of separable functions subjected to a consensus constraint, our proposed approach learns an inexact Newton direction alongside the global model using the proximal primal-dual (Prox-PDA) algorithm. Our algorithm, coined DIN, avoids sharing Hessian information between devices since each device shares a model-sized vector, concealing the first- and second-order information, reducing the network's burden and improving communication and energy efficiencies. Numerical simulations corroborate that DIN exhibits higher communication efficiency in terms of communication rounds while consuming less communication and computation energy compared to existing second-order decentralized baselines.

In this paper, the computation offloading problem in reconfigurable intelligent surface (RIS)-aided mobile edge computing (MEC)-enabled cell-free radio access network (CF-RAN) is investigated. To minimize the average task execution delay, we propose to formulate a joint optimization problem of computation offloading and RIS phase shifts. Considering the non-deterministic polynomial hard (NP-hard) property of this problem and time-varying network environment, we further propose a meta reinforcement learning (meta-RL)-based computation offloading policy, which can adapt to new environment quickly with only a few gradient updates. By aggregating powerful decision-making ability of conventional RL and rapid environment learning ability of meta-learning, our proposed policy can find the optimal strategy in very fast speed. Simulation results show that our proposed meta-RL-based computation offloading policy reduces the average task execution delay by 25% compared to the considered two state-of-the-art benchmark policies.

Semantic communication is a novel communication paradigm that focuses on recognizing and delivering the desired meaning of messages to the destination users. Most existing works in this area focus on delivering explicit semantics, labels or signal features that can be directly identified from the source signals. In this paper, we consider the implicit semantic communication problem in which hidden relations and closely related semantic terms that cannot be recognized from the source signals need to also be delivered to the destination user. We develop a novel adversarial learning-based implicit semantic-aware communication (iSAC) architecture in which the source user, instead of maximizing the total amount of information transmitted to the channel, aims to help the recipient learn an inference rule that can automatically generate implicit semantics based on limited clue information. We prove that by applying iSAC, the destination user can always learn an inference rule that matches the true inference rule of the source messages. Experimental results show that the proposed iSAC can offer up to a 19.69 dB improvement over existing non-inferential communication solutions, in terms of symbol error rate at the destination user.

In this paper, we propose a novel framework for designing a fast convergent multi-agent reinforcement learning (MARL)-based medium access control (MAC) protocol operating in a single cell scenario. The user equipments (UEs) are cast as learning agents that need to learn a proper signaling policy to coordinate the transmission of protocol data units (PDUs) to the base station (BS) over shared radio resources. In many MARL tasks, the conventional centralized training with decentralized execution (CTDE) is adopted, where each agent receives the same global extrinsic reward from the environment. However, this approach involves a long training time. To overcome this drawback, we adopt the concept of learning a per-agent intrinsic reward, in which each agent learns a different intrinsic reward signal based solely on its individual behavior. Moreover, in order to provide an intrinsic reward function that takes into account the long-term training history, we represent it as a long short-term memory (LSTM) network. As a result, each agent updates its policy network considering both the extrinsic reward, which characterizes the cooperative task, and the intrinsic reward that reflects local dynamics. The proposed learning framework yields a faster convergence and higher transmission performance compared to the baselines. Simulation results show that the proposed learning solution yields 75% improvement in convergence speed compared to the most performing baseline.

This paper presents a demo focusing on developing a robot capable of autonomously bypassing obstacles in cluttered environments using a camera as its sole sensing mechanism. The robot is programmed to follow a predetermined path via a line following module while using a custom object detection model to detect and differentiate obstacles on the road from other objects in the environment. The obstacle detection module based on YOLOv5 architecture can accurately detect obstacles from the surrounding. Upon obstacle detection, the robot initiates an obstacle avoidance maneuver by adjusting its steering based on error measurement, allowing it to navigate around the obstacle smoothly. The proposed design is validated with extensive experimentation, demonstrating its ability to navigate cluttered environments while avoiding obstacles.

Multi-modal data collected from various sensors is instrumental in enhancing proactive handover management, beam directions and received powers prediction. However, what essential information to extract and how to effectively allocate wireless resources to transmit the information to a central processor (e.g., a base station (BS)) for decision making is a challenging task. In this work, we consider an uplink multi-user goal-oriented system, where images extracted from users’ depth cameras reflect blockage status between users and their serving BS, which are then used for future received power prediction. In the system, we employ a convolutional neural network to learn a joint semantic source and channel encoder such that essential information is extracted from images. Subsequently, we model the multi-user subcarrier communication system as a hypergraph and use hyper-edge graph neural networks to learn precoders at the user side and detector at the BS side. Simulation results demonstrate that by jointly training a deep neural network-based encoder, decoder, precoder and detector, the communication system can achieve lower prediction errors than traditional precoder and detector, especially in low signal-to-noise ratio scenarios. We also show a trade-off between prediction performance and the computational complexity.

Metaverse over wireless networks is an emerging use case of the sixth generation (6G) wireless systems, posing unprecedented challenges in terms of its multi-modal data transmissions with stringent latency and reliability requirements. Towards enabling this wireless metaverse, in this article we propose a novel semantic communication (SC) framework by decomposing the metaverse into human/machine agent-specific semantic multiverses (SMs). An SM stored at each agent comprises a semantic encoder and a generator, leveraging recent advances in generative artificial intelligence (AI). To improve communication efficiency, the encoder learns the semantic representations (SRs) of multi-modal data, while the generator learns how to manipulate them for locally rendering scenes and interactions in the metaverse. Since these learned SMs are biased towards local environments, their success hinges on synchronizing heterogeneous SMs in the background while communicating SRs in the foreground, turning the wireless metaverse problem into the problem of semantic multiverse communication (SMC). Based on this SMC architecture, we propose several promising algorithmic and analytic tools for modeling and designing SMC, ranging from distributed learning and multi-agent reinforcement learning (MARL) to signaling games and symbolic AI.

In this paper, we suggest a method to transform a communication protocol based on deep neural network (NN) into a semantic communication protocol. We need such transformation to alleviate the issues posed by NN's lack of interpretability and redundant parameters due to overparametrization. However, transformation process is challenging because it is difficult to disambiguate the semantics while reducing the protocol's complexity. We solve the challenge by employing NN's activation patterns and probabilistic logic. Lastly, we validate our method by transforming an NN trained for a medium access control (MAC) protocol and verifying its contention performance compared to ALOHA based protocols.

In this paper, we propose a decentralized Newton-type approach to solve the problem of decentralized federated learning (FL). Notably, our proposed algorithm leverages the fast convergence of the second-order methods while avoid sending the hessian matrix at each iteration. Therefore, the proposed approach significantly reduces the communication cost and preserves the privacy. Specifically, we alternate between two problems. The inner problem approximates the inverse Hessian-gradient product which is formulated as a quadratic optimization problem and approximately solved in a decentralized manner using one step of the group alternating direction method of multipliers (GADMM) method. The outer problem learns the model, which is solved by performing one decentralized Newton step at every iteration. Moreover, to reduce the communication-overhead per iteration, a quantized version (leveraging stochastic quantization) is also proposed. Simulation results illustrate that our algorithm outperforms the baselines of GADMM, Q-GADMM, Newton tracking, and Decentralized SGD, and provides energy and communication-efficient solutions for bandwidth-limited systems under different SNR regimes.

Classical medium access control (MAC) protocols are interpretable, yet their task-agnostic control signaling messages (CMs) are ill-suited for emerging mission-critical applications. By contrast, neural network (NN) based protocol models (NPMs) learn to generate task-specific CMs, but their rationale and impact lack interpretability. To fill this void, in this article we propose, for the first time, a semantic protocol model (SPM) constructed by transforming an NPM into an interpretable symbolic graph written in the probabilistic logic programming language (ProbLog). This transformation is viable by extracting and merging common CMs and their connections, while treating the NPM as a CM generator. By extensive simulations, we corroborate that the SPM tightly approximates its original NPM while occupying only 0.02% memory. By leveraging its interpretability and memory-efficiency, we demonstrate several SPM-enabled applications such as SPM reconfiguration for collision-avoidance, as well as comparing different SPMs via semantic entropy calculation and storing multiple SPMs to cope with non-stationary environments.

Long range (LoRa) is one of the most popular technologies for low-power wide area networks. It offers long-range communication with a low energy consumption, which makes it ideal for many applications in the Internet of Things. The performance of LoRa networks depends on the communication parameters used by individual nodes. Several works have proposed different solutions, typically running on a central network server, to select these parameters. However, existing approaches have not addressed the need to (re-)assign parameters when channel conditions suddenly vary due to additional traffic, changes in the weather or the presence of obstacles. Moreover, allocation strategies that require a central entity to decide communication parameters do not scale due to the large number of configuration packets that must be sent to the nodes. To address these issues, this article proposesNoReL, a distributed game-theoretic approach that allows nodes to autonomously update their parameters and maximize their packet delivery ratio.NoReLis based on a stochastic variant of no-regret learning, which is proven to reach an$\epsilon$-coarse correlated equilibrium in LoRa networks. Extensive simulations show thatNoReLachieves a higher delivery ratio than the state of the art in both static and dynamic environments, with an improvement up to 12%.

Federated learning (FL) is a key enabler for efficient communication and computing, leveraging devices’ distributed computing capabilities. However, applying FL in practice is challenging due to the local devices’ heterogeneous energy, wireless channel conditions, and non-independently and identically distributed (non-IID) data distributions. To cope with these issues, this paper proposes a novel learning framework by integrating FL and width-adjustable slimmable neural networks (SNN). Integrating FL with SNNs is challenging due to time-varying channel conditions and data distributions. In addition, existing multi-width SNN training algorithms are sensitive to the data distributions across devices, which makes SNN ill-suited for FL. Motivated by this, we propose a communication and energy-efficient SNN-based FL (namedSlimFL) that jointly utilizessuperposition coding (SC)for global model aggregation andsuperposition training (ST)for updating local models. By applying SC, SlimFL exchanges the superposition of multiple-width configurations decoded as many times as possible for a given communication throughput. Leveraging ST, SlimFL aligns the forward propagation of different width configurations while avoiding inter-width interference during backpropagation. We formally prove the convergence of SlimFL. The result reveals that SlimFL is not only communication-efficient but also deals with non-IID data distributions and poor channel conditions, which is also corroborated by data-intensive simulations.

In this paper, we propose a Bayesian channel estimator for intelligent reflecting surface-aided (IRS-aided) millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems with semi-passive elements that can receive the signal in the active sensing mode. Ultimately, our goal is to minimize the channel estimation error using the received signal at the base station and additional information acquired from a small number of active sensors at the IRS. Unlike recent works on channel estimation with semi-passive elements that require both uplink and downlink training signals to estimate the UE-IRS and IRS-BS links, we only use uplink training signals to estimate all the links. To compute the minimum mean squared error (MMSE) estimates of all the links, we propose a novel variational inference-sparse Bayesian learning (VI-SBL) channel estimator that performs approximate posterior inference on the channel using VI with the mean-field approximation under the SBL framework. The simulation results show that VI-SBL outperforms the state-of-the-art baselines for IRS with passive reflecting elements in terms of the channel estimation accuracy and training overhead. Furthermore, VI-SBL with semi-passive elements is shown to be more spectral- and energy-efficient than the baselines with passive reflecting elements.

In the Internet of Things (IoT) environment, edge computing can be initiated at anytime and anywhere. However, in an IoT environment, edge computing sessions are often ephemeral, i.e., they last for a short period of time and can often be discontinued once the current application usage is completed or the edge devices leave the system due to factors such as mobility. Therefore, in this paper, the problem of ephemeral edge computing in an IoT is studied by considering scenarios in which edge computing operates within a limited time period. To this end, a novel online framework is proposed in which a source edge node offloads its computing tasks from sensors within an area to neighboring edge nodes for distributed task computing, within the limited period of time of an ephemeral edge computing system. The online nature of the framework allows the edge nodes to optimize their task allocation and decide on which neighbors to use for task processing, even when the tasks are revealed to the source edge node in an online manner, and the information on future task arrivals is unknown. The proposed framework essentially maximizes the number of computed tasks by jointly considering the communication and computation latency. To solve the joint optimization, an online greedy algorithm is proposed and solved by using the primal-dual approach. Since the primal problem provides an upper bound of the original dual problem, the competitive ratio of the online approach is analytically derived as a function of the task sizes and the data rates of the edge nodes. Simulation results show that the proposed online algorithm can achieve a near-optimal task allocation with an optimality gap that is no higher than 7.1% compared to the offline, optimal solution with complete knowledge of all tasks.

A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) are envisaged to provide a global coverage SAT network in beyond fifth-generation (5G) cellular systems. LEO SAT networks exhibit extremely long link distances of many users under time-varying SAT network topology. This makes existing multiple access protocols, such as random access channel (RACH) based cellular protocol designed for fixed terrestrial network topology, ill-suited. To overcome this issue, in this paper, we propose a novel contention-based random access solution for LEO SAT networks, dubbed emergent random access channel protocol (eRACH). In stark contrast to existing model-based and standardized protocols, eRACH is a model-free approach that emerges through interaction with the non-stationary network environment, using multi-agent deep reinforcement learning (MADRL). Furthermore, by exploiting known SAT orbiting patterns, eRACH does not require central coordination or additional communication across users, while training convergence is stabilized through the regular orbiting patterns. Compared to RACH, we show from various simulations that our proposed eRACH yields 54.6% higher average network throughput with around two times lower average access delay while achieving 0.989 Jain’s fairness index.

Device-to-device (D2D)-assisted decentralized learning has been proposed for mobile devices to collaboratively train artificial intelligence networks without the centralized parameter server. However, a densely connected network will cause large learning latency and energy consumption due to the limited computation and communication resources. In addition, link selection and aggregation weight have a significant impact on the learning performance. To cope with these challenges, we propose a joint computing power adjustment, wireless resource allocation, link selection, and aggregation weight adaptation mechanism to improve both communication and energy efficiencies. Specifically, the learning performances including the convergence rate, per-iteration learning latency, and per-iteration energy consumption are first analyzed. Then, an optimization problem is formulated to minimize the total learning cost, which is defined as the weighted sum of total learning latency and energy consumption. Given a network topology, the computing power and wireless resource allocation are optimized by the alternating optimization algorithm. Moreover, the optimal aggregation weight is obtained by semidefinite programming. With respect to link selection, we propose a tabu search based meta-heuristic algorithm to approximately achieve feasible solutions with a low computational complexity. Finally, extensive experiments demonstrate that the proposed link selection algorithm can significantly reduce the learning cost under the given learning accuracy requirement.

Over-the-air federated learning (FL) is a promising privacy-preserving edge artificial intelligence paradigm, where over-the-air computation enables spectral-efficient model aggregation by achieving simultaneous communication and aggregation. However, due to limited transmit power, the performance of over-the-air FL is limited by the device with the worst channel condition toward the edge server. In this paper, we leverage reconfigurable intelligent surface (RIS) to mitigate the communication bottleneck of over-the-air FL and explicitly characterize the corresponding convergence upper bound. The convergence analysis illustrates the detrimental impact of the accumulated aggregation error over all rounds and inspires us to formulate a time-average transmission distortion minimization problem by jointly optimizing the transceiver and RIS phase-shifts. To reduce the computation complexity and enhance the model aggregation accuracy, we develop a graph neural network (GNN) based learning algorithm to directly map channel coefficients to the optimized network parameters. By exploiting permutation equivalence and invariance properties of graphs, the parameter dimension of the proposed algorithm is independent of the number of edge devices, which reduces the computational complexity and improves the algorithmic scalability. Simulations show that the proposed algorithm speeds up the computation by three orders of magnitude compared to the baselines, while achieving performance superiority and algorithmic robustness.

To meet the growing mobility needs in intra-city transportation, the concept of urban air mobility (UAM) has been proposed in which vertical takeoff and landing (VTOL) aircraft are used to provide a ride-hailing service. In UAM, aircraft can operate in designated air spaces known as corridors, that link the aerodromes, thus avoiding the use of complex routing strategies such as those of modern-day helicopters and alleviating the burden on the ground transportation system. For safety, a UAM aircraft must use air-to-ground communications to report flight plan, off-nominal events, and real-time movement to ground base stations (GBSs). A reliable communication network between GBSs and aircraft enables UAM to adequately utilize the airspace and create a fast, efficient, and safe transportation system. In this paper, to characterize the wireless connectivity performance for UAM, a suitable spatial model is proposed. For the considered setup, assuming that any given aircraft communicates with the closest GBS, the distribution of the distance between an arbitrarily selected GBS and its associated aircraft and the Laplace transform of the interference experienced by the GBS are derived. Using these results, the signal-to-interference ratio (SIR)-based connectivity probability is determined to capture the connectivity performance of the UAM aircraft-to-ground communication network. Then, leveraging these connectivity results, a wireless-enabled asynchronous federated learning (AFL) framework that uses a Fourier neural network is proposed to tackle the challenging problem of turbulence prediction during UAM operations. For this AFL scheme, a staleness-aware global aggregation scheme is introduced to expedite the convergence to the optimal turbulence prediction model used by UAM aircraft. Simulation results validate the theoretical derivations for the UAM wireless connectivity. The results also demonstrate that the proposed AFL framework converges to the optimal turbulence prediction model faster than the synchronous federated learning baselines and a staleness-free AFL approach. Furthermore, the results characterize the performance of wireless connectivity and convergence of the aircraft’s turbulence model under different parameter settings, offering useful UAM design guidelines.

To tackle the heterogeneous requirements of beyond 5G (B5G) and future 6G wireless networks, conventional medium access control (MAC) procedures need to evolve to enable base stations (BSs) and user equipments (UEs) to automatically learn innovative MAC protocols catering to extremely diverse services. This topic has received significant attention, and several reinforcement learning (RL) algorithms, in which BSs and UEs are cast as agents, are available with the aim of learning a communication policy based on agents' local observations. However, current approaches are typically overfitted to the environment they are trained in, and lack robustness against unseen conditions, failing to generalize in different environments. To overcome this problem, in this work, instead of learning a policy in the high dimensional and redundant observation space, we leverage the concept of observation abstraction (OA) rooted in extracting useful information from the environment. This in turn allows learning communication protocols that are more robust and with much better generalization capabilities than current baselines. To learn the abstracted information from observations, we propose an architecture based on autoencoder (AE) and imbue it into a multi-agent proximal policy optimization (MAPPO) framework. Simulation results corroborate the effectiveness of leveraging abstraction when learning protocols by generalizing across environments, in terms of number of UEs, number of data packets to transmit, and channel conditions.

Wireless hierarchical federated learning (HFL) has been proposed for large-scale model training over multi-cell network while preserving the data privacy. However, the imbalanced data distribution and load have a significant impact on the convergence rate, the learning accuracy, and the learning latency in wireless HFL with non-independent identically distributed training data. To cope with these challenges, we first derive the learning latency and the upper bound of the model error. Then, an optimization problem is formulated to minimize the weighted sum of total data distribution distance and learning latency. Joint user association and wireless resource allocation algorithms are investigated to achieve the optimal learning performance. Finally, the effectiveness of the proposed algorithms are demonstrated by the simulations.

Next-generation wireless systems are rapidly evolving from communication-only systems to multi-modal systems with integrated sensing and communications. In this paper a novel joint sensing and communication framework is proposed for enabling wireless extended reality (XR) at terahertz (THz) bands. To gather rich sensing information and a higher line-of-sight (LoS) availability, THz-operated reconfigurable intelligent surfaces (RISs) acting as base stations are deployed. The sensing parameters are extracted by leveraging THz’s quasi-opticality and opportunistically utilizing uplink communication waveforms. This enables the use of the same waveform, spectrum, and hardware for both sensing and communication purposes. The environmental sensing parameters are then derived by exploiting the sparsity of THz channels via tensor decomposition. Hence, a high-resolution indoor mapping is derived so as to characterize the spatial availability of communications and the mobility of users. Simulation results show that in the proposed framework, the resolution and data rate of the overall system are positively correlated, thus allowing a joint optimization between these metrics with no tradeoffs. Results also show that the proposed framework improves the system reliability in static and mobile systems. In particular, the highest reliability gains of 10% are achieved in a walking speed mobile environment compared to communication only systems with beam tracking.

In this paper, the cooperative edge caching problem in fog radio access networks (F-RANs) is investigated. To minimize the content transmission delay, we formulate the cooperative caching optimization problem to find the globally optimal caching strategy. By considering the non-deterministic polynomial hard (NP-hard) property of this problem, a Multi Agent Reinforcement Learning (MARL)-based cooperative caching scheme is proposed. Our proposed scheme applies a double deep Q-network (DDQN) in every fog access point (F-AP), and introduces the communication process in a multi-agent system. Every F-AP records the historical caching strategies of its associated F-APs as the observations of communication procedure. By exchanging the observations, F-APs can leverage the cooperation and make the globally optimal caching strategy. Simulation results show that the proposed MARL-based cooperative caching scheme has remarkable performance compared with the benchmark schemes in minimizing the content transmission delay.

In this paper, the cooperative caching problem in fog radio access networks (F-RANs) is investigated to jointly optimize the transmission delay and energy consumption. Exploiting the potential social relationships among fog access points (F-APs), we firstly propose a clustering scheme based on hedonic coalition game (HCG) to improve the potential cooperation gain. Then, considering that the optimization problem is non-deterministic polynomial hard (NP-hard), we further propose an improved firefly algorithm (FA) based cooperative caching scheme, which utilizes a mutation strategy based on local content popularity to avoid pre-mature convergence. Simulation results show that our proposed scheme can effectively reduce the content transmission delay and energy consumption in comparison with the baselines.

The emergent technology of Reconfigurable Intelligent Surfaces (RISs) has the potential to transform wireless environments into controllable systems, through programmable propagation of information-bearing signals. Techniques stemming from the field of Deep Reinforcement Learning (DRL) have recently gained popularity in maximizing the sum-rate performance in multi-user communication systems empowered by RISs. Such approaches are commonly based on Markov Decision Processes (MDPs). In this paper, we instead investigate the sum-rate design problem under the scope of the Multi-Armed Bandits (MAB) setting, which is a relaxation of the MDP framework. Nevertheless, in many cases, the MAB formulation is more appropriate to the channel and system models under the assumptions typically made in the RIS literature. To this end, we propose a simpler DRL approach for orchestrating multiple metasurfaces in RIS-empowered multi-user Multiple-Input Single-Output (MISO) systems, which we numerically show to perform equally well with a state-of-the-art MDP-based approach, while being less demanding computationally.

In this paper, we investigate maximum distance separable (MDS) codes based group coded caching in fog radio access networks (F-RANs). The goal is to minimize the average fronthaul rate under nonuniform file popularity. Firstly, an MDS codes and file grouping based coded placement scheme is proposed to provide coded packets and allocate more cache to the most popular files simultaneously. Next, a fog access point (F-AP) grouping based coded delivery scheme is proposed to meet the requests for files from different groups. Furthermore, a closed-form expression of the average fronthaul rate is derived. Finally, the parameters related to the proposed coded caching scheme are optimized to fully utilize the gains brought by MDS codes and file grouping. Simulation results show that our proposed scheme obtains significant performance improvement over several existing caching schemes in terms of fronthaul rate reduction.

In this paper, the content popularity prediction problem in fog radio access networks (F-RANs) is investigated. Based on clustered federated learning, we propose a novel mobility-aware popularity prediction policy, which integrates content popularities in terms of local users and mobile users. For local users, the content popularity is predicted by learning the hidden representations of local users and contents. Initial features of local users and contents are generated by incorporating neighbor information with self information. Then, dual-channel neural network (DCNN) model is introduced to learn the hidden representations by producing deep latent features from initial features. For mobile users, the content popularity is predicted via user preference learning. In order to distinguish regional variations of content popularity, clustered federated learning (CFL) is employed, which enables fog access points (F-APs) with similar regional types to benefit from one another and provides a more specialized DCNN model for each F-AP. Simulation results show that our proposed policy achieves significant performance improvement over the traditional policies.

The newly emerging federated learning (FL) framework offers a new way to train machine learning models in a privacy-preserving manner. However, traditional FL algorithms are based on an event-triggered aggregation, which suffers from stragglers and communication overhead issues. To address these issues, in this paper, we present a time-triggered FL algorithm (TT-Fed) over wireless networks, which is a generalization of classic synchronous and asynchronous FL. Taking the resource-constrained and unreliable nature of wireless networks into account, we jointly consider the user selection and bandwidth optimization problem to minimize the FL training loss. The optimization problem is decomposed into tractable sub-problems with respect to each global aggregation round, and finally solved by our proposed greedy search algorithm. Simulation results show that compared to asynchronous FL (FedAsync) and FL with asynchronous tiers (FedAT) benchmarks, our proposed TT-Fed algorithm improves the converged test accuracy by up to 12.5% and 5%, respectively, under highly imbalanced and non-IID data, while substantially reducing the communication overhead.

Newton-type methods are popular in federated learning due to their fast convergence. Still, they suffer from two main issues, namely: low communication efficiency and low privacy due to the requirement of sending Hessian information from clients to parameter server (PS). In this work, we introduced a novel framework called FedNew in which there is no need to transmit Hessian information from clients to PS, hence resolving the bottleneck to improve communication efficiency. In addition, FedNew hides the gradient information and results in a privacy-preserving approach compared to the existing state-of-the-art. The core novel idea in FedNew is to introduce a two level framework, and alternate between updating the inverse Hessian-gradient product using only one alternating direction method of multipliers (ADMM) step and then performing the global model update using Newton’s method. Though only one ADMM pass is used to approximate the inverse Hessian-gradient product at each iteration, we develop a novel theoretical approach to show the converging behavior of FedNew for convex problems. Additionally, a significant reduction in communication overhead is achieved by utilizing stochastic quantization. Numerical results using real datasets show the superiority of FedNew compared to existing methods in terms of communication costs.

This paper aims to integrate two synergetic technologies, federated learning (FL) and width-adjustable slimmable neural network (SNN) architectures. FL preserves data privacy by exchanging the locally trained models of mobile devices. By adopting SNNs as local models, FL can flexibly cope with the time-varying energy capacities of mobile devices. Combining FL and SNNs is however non-trivial, particularly under wireless connections with time-varying channel conditions. Furthermore, existing multi-width SNN training algorithms are sensitive to the data distributions across devices, so are ill-suited to FL. Motivated by this, we propose a communication and energy efficient SNN-based FL (named SlimFL) that jointly utilizes superposition coding (SC) for global model aggregation and superposition training (ST) for updating local models. By applying SC, SlimFL exchanges the superposition of multiple width configurations that are decoded as many as possible for a given communication throughput. Leveraging ST, SlimFL aligns the forward propagation of different width configurations, while avoiding the inter-width interference during back propagation. We formally prove the convergence of SlimFL. The result reveals that SlimFL is not only communication-efficient but also can counteract non-IID data distributions and poor channel conditions, which is also corroborated by simulations.

Recent advances in Federated Learning (FL) have paved the way towards the design of novel strategies for solving multiple learning tasks simultaneously, by leveraging cooperation among networked devices. Multi-Task Learning (MTL) exploits relevant commonalities across tasks to improve efficiency compared with traditional transfer learning approaches. By learning multiple tasks jointly, significant reduction in terms of energy footprints can be obtained. This article provides a first look into the energy costs of MTL processes driven by the Model-Agnostic Meta-Learning (MAML) paradigm and implemented in distributed wireless networks. The paper targets a clustered multi-task network setup where autonomous agents learn different but related tasks. The MTL process is carried out in two stages: the optimization of a meta-model that can be quickly adapted to learn new tasks, and a task-specific model adaptation stage where the learned meta-model is transferred to agents and tailored for a specific task. This work analyzes the main factors that influence the MTL energy balance by considering a multi-task Reinforcement Learning (RL) setup in a robotized environment. Results show that the MAML method can reduce the energy bill by at least 2 × compared with traditional approaches without inductive transfer. Moreover, it is shown that the optimal energy balance in wireless networks depends on uplink/downlink and sidelink communication efficiencies.

A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) are envisaged to provide a global coverage SAT network in beyond fifth-generation (5G) cellular systems. However, such wide coverage rather makes it difficult to apply existing multiple access protocols, such as random access channel (RACH). To overcome this issue, in this paper, we propose a novel random access solution for LEO SAT networks, called as S-RACH. In contrast to existing standardized protocols, S-RACH is a model-free approach using deep reinforcement learning (DRL). Compared to RACH, we show from various simulations that our proposed S-RACH yields around 2x lower average access delay.

Multi-access edge computing (MEC) is viewed as an integral part of future wireless networks to support new applications with stringent service reliability and latency requirements. However, guaranteeing ultra-reliable and low-latency MEC (URLL MEC) is very challenging due to uncertainties of wireless links, limited communications and computing resources, as well as dynamic network traffic. Enabling URLL MEC man-dates taking into account the statistics of the end-to-end (E2E) latency and reliability across the wireless and edge computing systems. In this paper, a novel framework is proposed to optimize the reliability of MEC networks by considering the distribution of E2E service delay, encompassing over-the-air transmission and edge computing latency. The proposed framework builds on correlated variational autoencoders (VAEs) to estimate the full distribution of the E2E service delay. Using this result, a new optimization problem based on risk theory is formulated to maximize the network reliability by minimizing the Conditional Value at Risk (CVaR) as a risk measure of the E2E service delay. To solve this problem, a new algorithm is developed to efficiently allocate users’ processing tasks to edge computing servers across the MEC network, while considering the statistics of the E2E service delay learned by VAEs. The simulation results show that the proposed scheme outperforms several baselines that do not account for the risk analyses or statistics of the E2E service delay.

In this paper, we propose a communication-efficient alternating direction method of multipliers (ADMM)-based algorithm for solving a distributed learning problem in the stochastic non-convex setting. Our approach runs a few stochastic gradient descent (SGD) steps to solve the local problem at each worker instead of finding the exact/approximate solution as proposed by existing ADMM-based works. By doing so, the proposed framework strikes a good balance between the computation and communication costs. Extensive simulation results show that our algorithm significantly outperforms existing stochastic ADMM in terms of communication-efficiency, notably in the presence of non-independent and identically distributed (non-IID) data.

In this paper, we propose an accurate two-phase millimeter-Wave (mmWave) beamspace channel tracking mechanism. Particularly in the first phase, we train an extreme reservoir machine (ERM) for tracking the historical features of the mmWave beamspace channel and predicting them in upcoming time steps. Towards a more accurate prediction, we further fine-tune the ERM by means of Xavier initializer technique, whereby the input weights in ERM are initially derived from a zero mean and finite variance Gaussian distribution, leading to 49% degradation in prediction variance of the conventional ERM. The proposed method numerically improves the achievable spectral efficiency (SE) of the existing counterparts, by 13%, when signal-to-noise-ratio (SNR) is 15dB. We further investigate an ensemble learning technique in the second phase by sequentially incorporating multiple ERMs to form an ensembled model, namely adaptive boosting (AdaBoost), which further reduces the prediction variance in conventional ERM by 56%, and concludes in 21% enhancement of achievable SE upon the existing schemes at SNR = 15dB.

Split learning (SL) is a promising distributed learning framework that enables to utilize the huge data and parallel computing resources of mobile devices. SL is built upon a model-split architecture, wherein a server stores an upper model segment that is shared by different mobile clients storing its lower model segments. Without exchanging raw data, SL achieves high accuracy and fast convergence by only uploading smashed data from clients and downloading global gradients from the server. Nonetheless, the original implementation of SL sequentially serves multiple clients, incurring high latency with many clients. A parallel implementation of SL has great potential in reducing latency, yet existing parallel SL algorithms resort to compromising scalability and/or convergence speed. Motivated by this, the goal of this article is to develop a scalable parallel SL algorithm with fast convergence and low latency. As a first step, we identify that the fundamental bottleneck of existing parallel SL comes from the model-split and parallel computing architectures, under which the server-client model updates are often imbalanced, and the client models are prone to detach from the server’s model. To fix this problem, by carefully integrating local parallelism, federated learning, and mixup augmentation techniques, we propose a novel parallel SL framework, coined LocFedMix-SL. Simulation results corroborate that LocFedMix-SL achieves improved scalability, convergence speed, and latency, compared to sequential SL as well as the state-of-the-art parallel SL algorithms such as SplitFed and LocSplitFed.

Wireless virtual reality (VR), a key 3GPP use case of emerging cellular systems, imposes new visual and haptic requirements directly linked to the Quality of Experience (QoE) of VR users. These QoE requirements can only be met by wireless connectivity that offers high-rate and high-reliability low-latency communications (HR2LLC), unlike the low rates commonly associated with ultrareliable low-latency communication. The high rates for VR over short distances can only be supported by an enormous bandwidth, available in the terahertz (THz)-frequency bands. To explore the potential of THz for meeting HR2LLC requirements, a quantification of the risk for an unreliable VR performance is conducted through a novel and rigorous characterization of the tail of the end-to-end (E2E) delay. Then, a thorough analysis of the Tail-Value-at-Risk (TVaR) is performed to concretely characterize the behavior of extreme wireless events crucial to the real-time VR experience. In particular, the probability distribution function of the THz transmission delay is derived and then used to infer the system reliability scenarios with guaranteed Line of Sight (LoS) as a function of THz network parameters. Numerical results show that abundant bandwidth and low molecular absorption are necessary to improve the reliability. However, their effect remains secondary compared to the availability of LoS, which significantly affects the THz HR2LLC performance. In particular, for scenarios with guaranteed LoS, a reliability of 99.999% (with an E2E delay threshold of 20 ms) for a bandwidth of 15 GHz along with data rates of 18.3 Gbps can be achieved by the THz network, compared to a reliability of 96% for twice the bandwidth, when blockages are considered.

Real-time remote control over wireless is an important yet challenging application in fifth-generation and beyond due to its mission-critical nature under limited communication resources. Current solutions hinge on not only utilizing ultrareliable and low-latency communication (URLLC) links but also predicting future states, which may consume enormous communication resources and struggle with a short prediction time horizon. To fill this void, in this article we propose a novel two-way Koopman autoencoder (AE) approach wherein: 1) a sensing Koopman AE learns to understand the temporal state dynamics and predicts missing packets from a sensor to its remote controller and 2) a controlling Koopman AE learns to understand the temporal action dynamics and predicts missing packets from the controller to an actuator co-located with the sensor. Specifically, each Koopman AE aims to learn the Koopman operator in the hidden layers while the encoder of the AE aims to project the nonlinear dynamics onto a lifted subspace, which is reverted into the original nonlinear dynamics by the decoder of the AE. The Koopman operator describes the linearized temporal dynamics, enabling long-term future prediction and coping with missing packets and closed-form optimal control in the lifted subspace. Simulation results corroborate that the proposed approach achieves a$38\times $lower mean squared control error at 0-dBm signal-to-noise ratio (SNR) than the nonpredictive baseline.

This is Part II of a double-part special issue on distributed learning over wireless edge networks. This two-part special issue features papers dealing with two main research challenges: optimization of wireless network performance for efficient implementation of distributed learning in wireless networks, and distributed learning for solving communication problems and optimizing network performance. The accepted papers in this special issue have been grouped into three topics: 1) network optimization for federated learning (FL), 2) network optimization for other distributed learning methods, and 3) distributed reinforcement learning (RL) for wireless network optimization. In Part I (vol. 39, no. 12, Dec. 2021), the focus is on the first cluster (network optimization for FL). The focus of Part II is on the second and third clusters (network optimization for other distributed learning methods and RL for wireless network optimization). The readers are referred to Part I for an overview paper [A1] by the team of guest editors where a comprehensive study of how distributed learning can be efficiently deployed over wireless edge networks is provided. The contributions made by the papers in Part II are summarized as follows.

This paper investigates an air-ground integrated multi-access edge computing system, which is deployed by an infrastructure provider (InP). Under a business agreement with the InP, a third-party service provider provides computing services to the subscribed mobile users (MUs). MUs compete for the shared spectrum and computing resources over time to achieve their distinctive goals. From the perspective of an MU, we deliberately define the age of update to capture the staleness of information from refreshing computation outcomes. Given the system dynamics, we model the interactions among MUs as a stochastic game. In the Nash equilibrium without cooperation, each MU behaves in accordance with the local system states and conjectures. We can hence transform the stochastic game into a single-agent Markov decision process. As another major contribution, we develop an online deep reinforcement learning (RL) scheme that adopts two separate double deep Q-networks to approximate the Q-factor and the post-decision Q-factor, respectively. The deep RL scheme allows each MU to optimize the behaviours with unknown dynamic statistics. Numerical experiments show that our proposed scheme outperforms the baselines in terms of the average utility under various system conditions.

Future 5G/6G wireless networks will be increasingly using millimeter waves (mmWaves), where fast and efficient beamforming is vital for providing continuous service to highly mobile devices in the presence of interference and signal attenuation, manifested by blockage. In this paper, we propose a novel and efficient method for mmWave beamforming in massive multiple-input multiple-output (MIMO) systems to achieve the aforementioned goals with low complexity in such scenarios. In doing so, we utilize deep reinforcement learning (DRL) to maximize the network’s energy efficiency subject to the quality of service (QoS) constraint for each user equipment (UE) and obtain its hybrid beamforming matrices. In doing so, we assume each UE is simultaneously associated with multiple access points (APs), i.e., simultaneous beamforming to/from multiple APs (coordinated multipoints) is needed for each UE. We also propose a low-complexity training algorithm, based on approximate message passing, which is well suited for the network edge. Besides, we develop a distributed scheme to reduce communications overhead via federated DRL. Extensive simulations show significant performance improvement over existing methods.

The emerging technology of reconfigurable intelligent surfaces (RISs) is provisioned as an enabler of smart wireless environments, offering a highly scalable, low-cost, hardware-efficient, and almost energy-neutral solution for dynamic control of the propagation of electromagnetic signals over the wireless medium, ultimately providing increased environmental intelligence for diverse operation objectives. One of the major challenges with the envisioned dense deployment of RISs in such reconfigurable radio environments is the efficient configuration of multiple metasurfaces with limited, or even the absence of, computing hardware. In this article, we consider multiuser and multi-RIS-empowered wireless systems and present a thorough survey of the online machine learning approaches for the orchestration of their various tunable components. Focusing on the sum-rate maximization as a representative design objective, we present a comprehensive problem formulation based on deep reinforcement learning (DRL). We detail the correspondences among the parameters of the wireless system and the DRL terminology, and devise generic algorithmic steps for the artificial neural network training and deployment while discussing their implementation details. Further practical considerations for multi-RIS-empowered wireless communications in the sixth-generation (6G) era are presented along with some key open research challenges. Different from the DRL-based status quo, we leverage the independence between the configuration of the system design parameters and the future states of the wireless environment, and present efficient multiarmed bandits approaches, whose resulting sum-rate performances are numerically shown to outperform random configurations, while being sufficiently close to the conventional deep$Q$network (DQN) algorithm, but with lower implementation complexity.

Cooperative perception plays a vital role in extending a vehicle's sensing range beyond its line-of-sight. However, exchanging raw sensory data under limited communication resources is infeasible. Towards enabling an efficient cooperative perception, vehicles need to address the following fundamental question: What sensory data needs to be shared?, at which resolution?, and with which vehicles? To answer this question, in this paper, a novel framework is proposed to allow reinforcement learning (RL)-based vehicular association, resource block (RB) allocation, and content selection of cooperative perception messages (CPMs) by utilizing a quadtree-based point cloud compression mechanism. Furthermore, a federated RL approach is introduced in order to speed up the training process across vehicles. Simulation results show the ability of the RL agents to efficiently learn the vehicles' association, RB allocation, and message content selection while maximizing vehicles' satisfaction in terms of the received sensory information. The results also show that federated RL improves the training process, where better policies can be achieved within the same amount of time compared to the non-federated approach.

Real-time environment monitoring is a key application in Industrial Internet of Things, where sensors proactively collect and transmit environmental data to the controller. However, due to limited wireless resources, keeping sensors’ sampled data fresh at the controller is critical. This work aims to investigate the trade-off between the sensor’s data-sampling frequency and long-term data transmission energy consumption while maintaining information freshness. Leveraging the entropic risk measure (ERM), we jointly minimize the global transmission energy’s mean and variance subject to probabilistic constraints on information freshness. Furthermore, while jointly saving the model training energy, we adopt the federated learning (FL) paradigm and propose an FL-based two-stage iterative optimization framework to optimize the aforementioned objective. Specifically, we iteratively learn the sampling frequency via Bayesian optimization and minimize the long-term ERM of the global energy consumption via Lyapunov optimization. Numerical results show that the proposed FL-based scheme saves substantial executing energy with less performance loss. Quantitatively, compared with the centralized learning baseline, the proposed FL-based framework saves up to 69% model training energy at the expense of a mere increased objective outcome, i.e., 6.3% in the global data transmission energy consumption ($9.936\times 10^{-5}$in ERM) under 0.4% bias from the global optimal data-sampling frequency.

In this paper, we propose a communication-efficiently decentralized machine learning framework that solves a consensus optimization problem defined over a network of inter-connected workers. The proposed algorithm, Censored and Quantized Generalized GADMM (CQ-GGADMM), leverages the worker grouping and decentralized learning ideas of Group Alternating Direction Method of Multipliers (GADMM), and pushes the frontier in communication efficiency by extending its applicability to generalized network topologies, while incorporating link censoring for negligible updates after quantization. We theoretically prove that CQ-GGADMM achieves the linear convergence rate when the local objective functions are strongly convex under some mild assumptions. Numerical simulations corroborate that CQ-GGADMM exhibits higher communication efficiency in terms of the number of communication rounds and transmit energy consumption without compromising the accuracy and convergence speed, compared to the censored decentralized ADMM, and the worker grouping method of GADMM.

In this paper, the content popularity prediction problem in fog radio access networks (F-RANs) is investigated. In order to obtain accurate prediction with low complexity, we propose a novel context-aware popularity prediction policy based onfederated learning(FL). Firstly, user preference learning is applied by considering that users prefer to request the contents they are interested in. Then, users’ context information is utilized to cluster users efficiently by adaptive context space partitioning. After that, we formulate a popularity prediction optimization problem to learn the local model parameters by using the stochastic variance reduced gradient (SVRG) algorithm. Finally, FL based model integration is proposed to learn the global popularity prediction model based on local models using the distributed approximate Newton (DANE) algorithm with SVRG. Our proposed popularity prediction policy not only can predict content popularity accurately, but also can significantly reduce computational complexity. Moreover, we theoretically analyze the convergence bound of our proposed FL based model integration algorithm. Simulation results show that our proposed policy increases the cache hit rate by up to 21.5 % compared to existing policies.

In this paper, we investigate maximum-distance separable (MDS) codes and weighted graph based coded caching in fog radio access networks (F-RANs). In the placement phase, the redundant MDS based coded placement scheme is used to provide redundant coded packets and homogeneous cached contents. The redundant coded packets can be used to construct multicast opportunities for similar requests. In the delivery phase, the weighted graph based coded delivery scheme is conducted based on homogeneous cached contents, which can induce considerable multicast opportunities. By integrating the above two schemes, a joint MDS codes and weighted graph based coded caching policy is proposed to minimize the fronthaul load. Finally, we theoretically analyze the performance of the proposed policy by deriving the lower and upper bounds of the fronthaul load. Simulation results show that our proposed policy can provide 44% savings in the fronthaul load compared to the MDS-based uncoded delivery policy.

In this work, hierarchical federated learning (HFL) over wireless multi-cell networks is proposed for large-scale model training while preserving data privacy. However, the imbalanced data distribution has a significant impact on the convergence rate and learning accuracy. In addition, a large learning latency is incurred due to the traffic load imbalance among base stations (BSs) and limited wireless resources. To cope with these challenges, we first provide an analysis of the model error and learning latency in wireless HFL. Then, joint user association and wireless resource allocation algorithms are investigated under independent identically distributed (IID) and non-IID training data, respectively. For the IID case, a learning latency aware strategy is designed to minimize the learning latency by optimizing user association and wireless resource allocation, where a mobile device selects the BS with the maximal uplink channel signal-to-noise ratio (SNR). For the non-IID case, the total data distribution distance and learning latency are jointly minimized to achieve the optimal user association and resource allocation. The results show that both data distribution and uplink channel SNR should be taken into consideration for user association in the non-IID case. Finally, the effectiveness of the proposed algorithms are demonstrated by the simulations.

The deployment of future intelligent transportation systems is contingent upon seamless and reliable operation of connected and autonomous vehicles (CAVs). One key challenge in developing CAVs is the design of an autonomous controller that can accurately execute near real-time control decisions, such as a quick acceleration when merging to a highway and frequent speed changes in a stop-and-go traffic. However, the use of conventional feedback controllers or traditional learning-based controllers, solely trained by each CAV’s local data, cannot guarantee a robust controller performance over a wide range of road conditions and traffic dynamics. In this paper, a new federated learning (FL) framework enabled by large-scale wireless connectivity is proposed for designing the autonomous controller of CAVs. In this framework, the learning models used by the controllers are collaboratively trained among a group of CAVs. To capture the varying CAV participation in the FL training process and the diverse local data quality among CAVs, a novel dynamic federated proximal (DFP) algorithm is proposed that accounts for the mobility of CAVs, the wireless fading channels, as well as the unbalanced and non-independent and identically distributed data across CAVs. A rigorous convergence analysis is performed for the proposed algorithm to identify how fast the CAVs converge to using the optimal autonomous controller. In particular, the impacts of varying CAV participation in the FL process and diverse CAV data quality on the convergence of the proposed DFP algorithm are explicitly analyzed. Leveraging this analysis, an incentive mechanism based on contract theory is designed to improve the FL convergence speed. Simulation results using real vehicular data traces show that the proposed DFP-based controller can accurately track the target CAV speed over time and under different traffic scenarios. Moreover, the results show that the proposed DFP algorithm has a much faster convergence compared to popular FL algorithms such as federated averaging (FedAvg) and federated proximal (FedProx). The results also validate the feasibility of the contract-theoretic incentive mechanism and show that the proposed mechanism can improve the convergence speed of the DFP algorithm by 40% compared to the baselines.

In this paper, a novel framework is proposed to perform data-driven air-to-ground channel estimation for millimeter wave (mmWave) communications in an unmanned aerial vehicle (UAV) wireless network. First, an effective channel estimation approach is developed to collect mmWave channel information, allowing each UAV to train a stand-alone channel model via a conditional generative adversarial network (CGAN) along each beamforming direction. Next, in order to expand the application scenarios of the trained channel model into a broader spatial-temporal domain, a cooperative framework, based on a distributed CGAN architecture, is developed, allowing each UAV to collaboratively learn the mmWave channel distribution in a fully-distributed manner. To guarantee an efficient learning process, necessary and sufficient conditions for the optimal UAV network topology that maximizes the learning rate for cooperative channel modeling are derived, and the optimal CGAN learning solution per UAV is subsequently characterized, based on the distributed network structure. Simulation results show that the proposed distributed CGAN approach is robust to the local training error at each UAV. Meanwhile, a larger airborne network size requires more communication resources per UAV to guarantee an efficient learning rate. The results also show that, compared with a stand-alone CGAN without information sharing and two other distributed schemes, namely: A multi-discriminator CGAN and a federated-learning CGAN method, the proposed distributed CGAN approach yields a higher modeling accuracy while learning the environment, and it achieves a larger average data rate in the online performance of UAV downlink mmWave communications.

In this paper, a novel framework is proposed to optimize the downlink multi-user communication of a millimeter wave base station, which is assisted by a reconfigurable intelligent reflector (IR). In particular, a channel estimation approach is developed to measure the channel state information (CSI) in real-time. First, for a perfect CSI scenario, the precoding transmission of the BS and the reflection coefficient of the IR are jointly optimized, via an iterative approach, so as to maximize the sum of downlink rates towards multiple users. Next, in the imperfect CSI scenario, a distributional reinforcement learning (DRL) approach is proposed to learn the optimal IR reflection and maximize the expectation of downlink capacity. In order to model the transmission rate’s probability distribution, a learning algorithm, based on quantile regression (QR), is developed, and the proposed QR-DRL method is proved to converge to a stable distribution of downlink transmission rate. Simulation results show that, in the error-free CSI scenario, the proposed approach yields over 30% and 2-fold increase in the downlink sum-rate, compared with a fixed IR reflection scheme and direct transmission scheme, respectively. Simulation results also show that by deploying more IR elements, the downlink sum-rate can be significantly improved. However, as the number of IR components increases, more time is required for channel estimation, and the slope of increase in the IR-aided transmission rate will become smaller. Furthermore, under limited knowledge of CSI, simulation results show that the proposed QR-DRL method, which learns a full distribution of the downlink rate, yields a better prediction accuracy and improves the downlink rate by 10% for online deployments, compared with a Q-learning baseline.

The newly emerging federated learning (FL) framework offers a new way to train machine learning models in a privacy-preserving manner. However, traditional FL algorithms are based on an event-triggered aggregation, which suffers from stragglers and communication overhead issues. To address these issues, in this paper, we present a time-triggered FL algorithm (TT-Fed) over wireless networks, which is a generalized form of classic synchronous and asynchronous FL. Taking the constrained resource and unreliable nature of wireless communication into account, we jointly study the user selection and bandwidth optimization problem to minimize the FL training loss. To solve this joint optimization problem, we provide a thorough convergence analysis for TT-Fed. Based on the obtained analytical convergence upper bound, the optimization problem is decomposed into tractable sub-problems with respect to each global aggregation round, and finally solved by our proposed online search algorithm. Simulation results show that compared to asynchronous FL (FedAsync) and FL with asynchronous user tiers (FedAT) benchmarks, our proposed TT-Fed algorithm improves the converged test accuracy by up to 12.5% and 5%, respectively, under highly imbalanced and non-IID data, while substantially reducing the communication overhead.

In this paper, we propose an energy-efficient federated meta-learning framework. The objective is to enable learning a meta-model that can be fine-tuned to a new task with a few number of samples in a distributed setting and at low computation and communication energy consumption. We assume that each task is owned by a separate agent, so a limited number of tasks is used to train a meta-model. Assuming each task was trained offline on the agent's local data, we propose a lightweight algorithm that starts from the local models of all agents, and in a backward manner using projected stochastic gradient ascent (P-SGA) finds a meta-model. The proposed method avoids complex computations such as computing hessian, double looping, and matrix inversion, while achieving high performance at significantly less energy consumption compared to the state-of-the-art methods such as MAML and iMAML on conducted experiments for sinusoid regression and image classification tasks.

In this article, we study the problem of robust reconfigurable intelligent surface (RIS)-aided downlink communication over heterogeneous RIS types in the supervised learning setting. By modeling downlink communication over heterogeneous RIS designs as different workers that learn how to optimize phase configurations in a distributed manner, we solve this distributed learning problem using a distributionally robust formulation in a communication-efficient manner, while establishing its rate of convergence. By doing so, we ensure that the global model performance of the worst-case worker is close to the performance of other workers. Simulation results show that our proposed algorithm requires fewer communication rounds (about 50% lesser) to achieve the same worst-case distribution test accuracy compared to competitive baselines.

Wireless channels can be inherently privacy preserving by distorting the received signals due to channel noise, and superpositioning multiple signals over-the-air. By harnessing these natural distortions and superpositions by wireless channels, we propose a novel privacy-preserving machine learning (ML) framework at the network edge, coined over-the-air mixup ML (AirMixML). In AirMixML, multiple workers transmit analog-modulated signals of their private data samples to an edge server who trains an ML model using the received noisy-and-superpositioned samples. AirMixML coincides with model training using mixup data augmentation achieving comparable accuracy to that with raw data samples. From a privacy perspective, AirMixML is a differentially private (DP) mechanism limiting the disclosure of each worker's private sample information at the server, while the worker's transmit power determines the privacy disclosure level. To this end, we develop a fractional channel-inversion power control (PC) method, a-Dirichlet mixup PC (DirMix(a)-PC), wherein for a given global power scaling factor after channel inversion, each worker's local power contribution to the superpositioned signal is controlled by the Dirichlet dispersion ratio a. Mathematically, we derive a closed-form expression clarifying the relationship between the local and global PC factors to guarantee a target DP level. By simulations, we provide DirMix(α)-PC design guidelines to improve accuracy, privacy, and energy-efficiency. Finally, AirMixML with DirMix(a)-PC is shown to achieve reasonable accuracy compared to a privacy-violating baseline with neither superposition nor PC.

Split-learning (SL) has recently gained popularity due to its inherent privacy-preserving capabilities and ability to enable collaborative inference for devices with limited computational power. Standard SL algorithms assume an ideal underlying digital communication system and ignore the problem of scarce communication bandwidth. However, for a large number of agents, limited bandwidth resources, and time-varying commu-nication channels, the communication bandwidth can become the bottleneck. To address this challenge, in this work, we propose a novel SL framework to solve the remote inference problem that introduces an additional layer at the agent side and constrains the choices of the weights and the biases to ensure over the air aggregation. Hence, the proposed approach maintains constant communication cost with respect to the number of agents enabling remote inference under limited bandwidth. Numerical results show that our proposed algorithm significantly outper-forms the digital implementation in terms of communication-efficiency” especially as the number of agents grows large.

In this paper, the content popularity prediction problem in cache-enabled fog radio access networks (F-RANs) is investigated. In order to predict the content popularity with high accuracy and low complexity, we propose a Gaussian process based Poisson regressor to model the content request pattern. Firstly, the relationship between content features and popularity is captured by our developed model. Then, we utilize Bayesian learning to learn the model parameters, which are robust to over-fitting. However, Bayesian methods are usually unable to find a closed-form expression of the posterior distribution. To tackle this issue, we apply a Stochastic Variance Reduced Gradient Hamiltonian Monte Carlo (SVRG-HMC) to approximate the posterior distribution. Two types of predictive content popularity are formulated for the requests of existing contents and newly-added contents. Simulation results show that the performance of our proposed policy outperforms the policy based on other Monte Carlo based method.

To meet the growing mobility needs in intra-city transportation, urban air mobility (UAM) has been proposed in which vertical takeoff and landing (VTOL) aircraft are used to provide on-demand service. In UAM, an aircraft can operate in the corridors, i.e., the designated airspace, that link the aerodromes, thus avoiding the use of complex routing strategies such as those of modern-day helicopters. For safety, a UAM aircraft will use air-to-ground communications to report flight plan, off-nominal events, and real-time movements to ground base stations (GBSs). A reliable communication network between GBSs and aircraft enables UAM to adequately utilize the airspace and create a fast, efficient, and safe transportation system. In this paper, to characterize the wireless connectivity performance in UAM, a stochastic geometry-based spatial model is developed. In particular, the distribution of GBSs is modeled as a Poisson point process (PPP), and the aircraft are distributed according to a combination of PPP, Poisson cluster process (PCP), and Poisson line process (PLP). For this setup, assuming that any given aircraft communicates with the closest GBS, the distribution of distance between an arbitrarily selected GBS and its associated aircraft and the Laplace transform of the interference experienced by the GBS are derived. Using these results, the signal-to-interference ra-tio (SIR)-based connectivity probability is determined to capture the connectivity performance of the aircraft-to-ground communication network in UAM. Simulation results validate the theoretical derivations for the UAM wireless connectivity and provide useful UAM design guidelines by showing the connectivity performance under different parameter settings.

Cooperative perception plays a vital role in extending a vehicle’s sensing range beyond its line-of-sight. However, exchanging raw sensory data under limited communication resources is infeasible. Towards enabling an efficient cooperative perception, vehicles need to address fundamental questions such as: what sensory data needs to be shared? at which resolution? with which vehicles? In this view, this paper proposes a reinforcement learning (RL)-based vehicular association, resource block (RB) allocation, and content selection of cooperative perception messages by utilizing a quadtree-based point cloud compression mechanism. Simulation results show the ability of the RL agents to efficiently learn the vehicles’ association, RB allocation and message content selection that maximizes the fulfillment of the vehicles in terms of the received sensory information.

This article deals with the problem of distributed machine learning, in which agents update their models based on their local datasets, and aggregate the updated models collaboratively and in a fully decentralized manner. In this paper, we tackle the problem of information heterogeneity arising in multi-agent networks where the placement of informative agents plays a crucial role in the learning dynamics. Specifically, we propose BayGo, a novel fully decentralized joint Bayesian learning and graph optimization framework with proven fast convergence over a sparse graph. Under our framework, agents are able to learn and communicate with the most informative agent to their own learning. Unlike prior works, our framework assumes no prior knowledge of the data distribution across agents nor does it assume any knowledge of the true parameter of the system. The proposed alternating minimization based framework ensures global connectivity in a fully decentralized way while minimizing the number of communication links. We theoretically show that by optimizing the proposed objective function, the estimation error of the posterior probability distribution decreases exponentially at each iteration. Via extensive simulations, we show that our framework achieves faster convergence and higher accuracy compared to fully-connected and star topology graphs.

Remote state monitoring over wireless is envisaged to play a pivotal role in enabling beyond 5G applications ranging from remote drone control to remote surgery. One key challenge is to identify the system dynamics that is non-linear with a large dimensional state. To obviate this issue, in this article we propose to train an autoencoder whose encoder and decoder are split and stored at a state sensor and its remote observer, respectively. This autoencoder not only decreases the remote monitoring payload size by reducing the state representation dimension but also learns the system dynamics by lifting it via a Koopman operator, thereby allowing the observer to locally predict future states after training convergence. Numerical results under a non-linear cart-pole environment demonstrate that the proposed split learning of a Koopman autoencoder can locally predict future states, and the prediction accuracy increases with the representation dimension and transmission power.

This work studies a real-time environment monitoring scenario in the industrial Internet of things, where wireless sensors proactively collect environmental data and transmit it to the controller. We adopt the notion of risk-sensitivity in financial mathematics as the objective to jointly minimize the mean, variance, and other higher-order statistics of the network energy consumption subject to the constraints on the age of information (AoI) threshold violation probability and the AoI exceedances over a pre-defined threshold. We characterize the extreme AoI staleness using results in extreme value theory and propose a distributed power allocation approach by weaving in together principles of Lyapunov optimization and federated learning (FL). Simulation results demonstrate that the proposed FL-based distributed solution is on par with the centralized baseline while consuming 28.50% less system energy and outperforms the other baselines.

Today’s intelligent applications can achieve high performance accuracy using machine learning (ML) techniques, such as deep neural networks (DNNs). Traditionally, in a remote DNN inference problem, an edge device transmits raw data to a remote node that performs the inference task. However, this may incur high transmission energy costs and puts data privacy at risk. In this paper, we propose a technique to reduce the total energy bill at the edge device by utilizing model compression and time-varying model split between the edge and remote nodes. The time-varying representation accounts for time-varying channels and can significantly reduce the total energy at the edge device while maintaining high accuracy (low loss). We implement our approach in an image classification task using the MNIST dataset, and the system environment is simulated as a trajectory navigation scenario to emulate different channel conditions. Numerical simulations show that our proposed solution results in minimal energy consumption and CO2emission compared to the considered baselines while exhibiting robust performance across different channel conditions and bandwidth regime choices.

Recent advances in distributed learning raise environmental concerns due to the large energy needed to train and move data to/from data centers. Novel paradigms, such as federated learning (FL), are suitable for decentralized model training across devices or silos that simultaneously act as both data producers and learners. Unlike centralized learning (CL) techniques, relying on big-data fusion and analytics located in energy hungry data centers, in FL scenarios devices collaboratively train their models without sharing their private data. This article breaks down and analyzes the main factors that influence the environmental footprint of FL policies compared with classical CL/Big-Data algorithms running in data centers. The proposed analytical framework takes into account both learning and communication energy costs, as well as the incurred greenhouse gas, or carbon equivalent, emissions. The framework is evaluated in an industrial setting assuming a real-world robotized workplace. Results show that FL allows remarkable end-to-end energy savings (30%÷40%) in low-rate/power IoT communications (with limited energy efficiency). On the other hand, FL is slower to converge when local data are unevenly distributed (often 2x slower than CL).

While information delivery in industrial Internet of things demands reliability and latency guarantees, the freshness of the controller’s available information, measured by the age of information (AoI), is paramount for high-performing industrial automation. The problem in this work is cast as a sensor’s transmit power minimization subject to the peak-Aol requirement and a probabilistic constraint on queuing latency. We further characterize the tail behavior of the latency by a generalized Pareto distribution (GPD) for solving the power allocation problem through Lyapunov optimization. As each sensor utilizes its own data to locally train the GPD model, we incorporate federated learning and propose a local-model selection approach which accounts for correlation among the sensor’s training data. Numerical results show the tradeoff between the transmit power, peak AoI, and delay’s tail distribution. Furthermore, we verify the superiority of the proposed correlation-aware approach for selecting the local models in federated learning over an existing baseline.

Nonorthogonal multiple access (NOMA) is seen as an important technology for tomorrow's Internet-of-Things (IoT) systems. In uplink power-domain NOMA (PD-NOMA), allocating the uplink transmit power of the IoT devices is important to maximize both the sum rate and the reliability of devices. However, it is challenging to optimize the uplink transmit power when the received signal power is affected by a random fading channel. Hence, in this article, the problem of uplink transmit power assignment is studied for a wireless network with PD-NOMA that serves uplink IoT services. This is posed as a problem of determining the target received signal power at the base station (BS) so that the reliability and upper bound of sum rate of the users are jointly maximized, where the received signal power at the BS is unknown to the devices due to Nakagami- m fading channel. To find an optimal allocation of the lower and higher target received power values for the devices using PD-NOMA, the reliability and upper bound of sum rate are derived in terms of target received power values and power difference threshold. For a special case of Nakagami- m fading channel, the theoretical analysis shows that the highest reliability and the highest upper bound of sum rate are achieved, when the target received power values are highest. For a general Nakagami- m fading channel, simulation results show that there is a tradeoff between reliability and sum-rate upper bound and, thus, allocation of lower and higher target received power values is necessary to satisfy the communication requirements of IoT devices. Moreover, for a special case of Nakagami- m fading channel, simulation results show that the derived optimal transmit power achieves the optimal sum-rate upper bound and reliability, and the target received power values of two devices must be highest for the maximum upper bound of sum rate and reliability. Furthermore, in simulation results, increasing the lower and higher target received power values increases both the upper bound of sum rate and reliability.

Designing distributed, fast, and reliable wireless consensus protocols is instrumental in enabling mission-critical decentralized systems, such as robotic networks in the Industrial Internet of Things (IIoT), drone swarms in rescue missions, and so forth. However, chasing both low-latency and reliability of consensus protocols is a challenging task. The problem is aggravated under wireless connectivity that may be slower and less reliable, compared to wired connections. To tackle this issue, we investigate fundamental relationships between consensus latency and reliability through the lens of wireless connectivity, and co-design communication and consensus protocols for low-latency and reliable decentralized systems. Specifically, we propose a novel communication-efficient distributed consensus protocol, termed random representative consensus (R2C), and show its effectiveness under gossip and broadcast communication protocols. To this end, we derive a closed-form end-to-end (E2E) latency expression of the R2C that guarantees target reliability, and compare it with a baseline consensus protocol, referred to as referendum consensus (RC). The result shows that the R2C is faster compared to the RC and more reliable compared when co-designed with the broadcast protocol compared to that with the gossip protocol.

Analyzing massive amounts of data using complex machine learning models requires significant computational resources. The conventional approach to such problems involves centralizing training data and inference processes in the cloud, i.e., in data centers. However, with the proliferation of mobile devices and increasing application of the Internet-of-Things (IoT) paradigm, very large amounts of data are collected at the edges of wireless networks, and due to privacy constraints and limited communication resources, it is undesirable or impractical to upload this data from mobile devices to the cloud for centralized learning. This problem can be solved by distributed learning at the network edge, by which edge devices collaboratively train a shared learning model using real-time mobile data. The avoidance of raw-data uploading not only helps to preserve privacy but may also alleviate network-traffic congestion and minimize latency. With that said, distributed training still requires a substantial amount of information exchange between devices and edge servers over wireless links. In the process, wireless impairments such as noise, interference, and imperfect knowledge of channel states can significantly slow down distributed learning (e.g., convergence speed) and degrades its performance (e.g., learning accuracy). This makes it crucial to optimize wireless network performance so as to support the efficient deployment of distributed learning algorithms. On the other hand, distributed learning algorithms provide a powerful tool-set for solving complex problems in wireless communication and networking. One important framework, called federated learning (FL), enables users to collaboratively learn a shared model while helping to preserve local data privacy. The application of FL can endow edge devices with capabilities of user behavior prediction, user identification, and wireless environment analysis. As another example, distributed reinforcement learning is capable of leveraging distributed computation power and data to solve complex optimization and control problems that arise in various use cases, such as network control, user clustering, resource management, and interference alignment. To cover this paradigm of distributed learning over wireless networks, this two-part Special Issue features papers dealing with two main research challenges: a) optimization of wireless network performance for efficient implementation of distributed learning in wireless networks, and b) distributed learning for solving communication problems and optimizing network performance.

The next-generation of wireless networks will enable many machine learning (ML) tools and applications to efficiently analyze various types of data collected by edge devices for inference, autonomy, and decision making purposes. However, due to resource constraints, delay limitations, and privacy challenges, edge devices cannot offload their entire collected datasets to a cloud server for centrally training their ML models or inference purposes. To overcome these challenges, distributed learning and inference techniques have been proposed as a means to enable edge devices to collaboratively train ML models without raw data exchanges, thus reducing the communication overhead and latency as well as improving data privacy. However, deploying distributed learning over wireless networks faces several challenges including the uncertain wireless environment (e.g., dynamic channel and interference), limited wireless resources (e.g., transmit power and radio spectrum), and hardware resources (e.g., computational power). This paper provides a comprehensive study of how distributed learning can be efficiently and effectively deployed over wireless edge networks. We present a detailed overview of several emerging distributed learning paradigms, including federated learning, federated distillation, distributed inference, and multi-agent reinforcement learning. For each learning framework, we first introduce the motivation for deploying it over wireless networks. Then, we present a detailed literature review on the use of communication techniques for its efficient deployment. We then introduce an illustrative example to show how to optimize wireless networks to improve its performance. Finally, we introduce future research opportunities. In a nutshell, this paper provides a holistic set of guidelines on how to deploy a broad range of distributed learning frameworks over real-world wireless communication networks.

Next-generation wireless networks are witnessing an increasing number of clustering applications, and produce a large amount of non-linear and unlabeled data. In some degree, single kernel methods face the challenging problem of kernel choice. To overcome this problem for non-linear data clustering, multiple kernel graph-based clustering (MKGC) has attracted intense attention in recent years. However, existing MKGC methods suffer from two common problems: (1) they mainly aim to learn a consensus kernel from multiple candidate kernels, slight affinity graph learning, such that cannot fully exploit the underlying graph structure of non-linear data; (2) they disregard the high-order correlations between all base kernels, which cannot fully capture the consistent and complementary information of all kernels. In this paper, we propose a novel non-negative matrix factorization (NMF) tailored graph tensor MKGC method for non-linear data clustering, namely TMKGC. Specifically, TMKGC integrates NMF and graph learning together in kernel space so as to learn multiple candidate affinity graphs. Afterwards, the high-order structure information of all candidate graphs is captured in a 3-order tensor kernel space by introducing tensor singular value decomposition based tensor nuclear norm, such that an optimal affinity graph can be obtained subsequently. Based on the alternating direction method of multipliers, the effective local and distributed solvers are elaborated to solve the proposed objective function. Extensive experiments have demonstrated the superiority of TMKGC compared to the state-of-the-art MKGC methods.

Machine learning (ML) is a promising enabler for the fifth-generation (5G) communication systems and beyond. By imbuing intelligence into the network edge, edge nodes can proactively carry out decision-making and, thereby, react to local environmental changes and disturbances while experiencing zero communication latency. To achieve this goal, it is essential to cater for high ML inference accuracy at scale under the time-varying channel and network dynamics, by continuously exchanging fresh data and ML model updates in a distributed way. Taming this new kind of data traffic boils down to improving the communication efficiency of distributed learning by optimizing communication payload types, transmission techniques, and scheduling, as well as ML architectures, algorithms, and data processing methods. To this end, this article aims to provide a holistic overview of relevant communication and ML principles and, thereby, present communication-efficient and distributed learning frameworks with selected use cases.

In this article, we propose a communication-efficient decentralized machine learning (ML) algorithm, coined quantized group ADMM (Q-GADMM). To reduce the number of communication links, every worker in Q-GADMM communicates only with two neighbors, while updating its model via the group alternating direction method of multipliers (GADMM). Moreover, each worker transmits the quantized difference between its current model and its previously quantized model, thereby decreasing the communication payload size. However, due to the lack of centralized entity in decentralized ML, the spatial sparsity and payload compression may incur error propagation, hindering model training convergence. To overcome this, we develop a novel stochastic quantization method to adaptively adjust model quantization levels and their probabilities, while proving the convergence of Q-GADMM for convex objective functions. Furthermore, to demonstrate the feasibility of Q-GADMM for non-convex and stochastic problems, we propose quantized stochastic GADMM (Q-SGADMM) that incorporates deep neural network architectures and stochastic sampling. Simulation results corroborate that Q-GADMM significantly outperforms GADMM in terms of communication efficiency while achieving the same accuracy and convergence speed for a linear regression task. Similarly, for an image classification task using DNN, Q-SGADMM achieves significantly less total communication cost with identical accuracy and convergence speed compared to its counterpart without quantization, i.e., stochastic GADMM (SGADMM).

Wireless connectivity is instrumental in enabling scalable federated learning (FL), yet wireless channels bring challenges for model training, in which channel randomness perturbs each worker’s model update while multiple workers’ updates incur significant interference under limited bandwidth. To address these challenges, in this work we formulate a novel constrained optimization problem, and propose an FL framework harnessing wireless channel perturbations and interference for improving privacy, bandwidth-efficiency, and scalability. The resultant algorithm is coinedanalog federated ADMM (A-FADMM)based on analog transmissions and the alternating direction method of multipliers (ADMM). In A-FADMM, all workers upload their model updates to the parameter server (PS) using a single channel via analog transmissions, during which all models are perturbed and aggregated over-the-air. This not only saves communication bandwidth, but also hides each worker’s exact model update trajectory from any eavesdropper including the honest-but-curious PS, thereby preserving data privacy against model inversion attacks. We formally prove the convergence and privacy guarantees of A-FADMM for convex functions under time-varying channels, and numerically show the effectiveness of A-FADMM under noisy channels and stochastic non-convex functions, in terms of convergence speed and scalability, as well as communication bandwidth and energy efficiency.

This article studies the joint problem of uplink-downlink scheduling and power allocation for controlling a large number of control systems that upload their states to remote controllers and download control actions over wireless links. To overcome the lack of wireless resources, we propose a machine learning-based solution, where only one control system is controlled, while the rest of the control systems are actuated by locally predicting the missing state and/or action information using the previous uplink and/or downlink receptions via a Gaussian process regression (GPR). This GPR prediction credibility is determined using the age-of-information (AoI) of the latest reception. Moreover, the successful reception is affected by the transmission power, mandating a co-design of the communication and control operations. To this end, we formulate a network-wide minimization problem of the average AoI and transmission power under communication reliability and control stability constraints. To solve the problem, we propose a dynamic control algorithm using the Lyapunov drift-plus-penalty optimization framework. Numerical results corroborate that the proposed algorithm can stably control$2\times$more number of actuators compared to an event-triggered scheduling baseline with Kalman filtering and frequency division multiple access, which is$18\times$larger than a round-robin scheduling baseline.

In this paper, a novel framework for guaranteeing ultra-reliable millimeter wave (mmW) communications using multiple artificial intelligence (AI)-enabled reconfigurable intelligent surfaces (RISs) is proposed. The use of multiple AI-powered RISs allows changing the propagation direction of the signals transmitted from a mmW access point (AP) thereby improving coverage particularly for non-line-of-sight (NLoS) areas. However, due to the possibility of highly stochastic blockage over mmW links, designing an intelligent controller to jointly optimize the mmW AP beam and RIS phase shifts is a daunting task. In this regard, first, a parametric risk-sensitive episodic return is proposed to maximize the expected bitrate and mitigate the risk of mmW link blockage. Then, a closed-form approximation of the policy gradient of the risk-sensitive episodic return is analytically derived. Next, the problem of joint beamforming for mmW AP and phase shift control for mmW RISs is modeled as an identical payoff stochastic game within a cooperative multi-agent environment, in which the agents are the mmW AP and the RISs. Two centralized and distributed controllers are proposed to control the policies of the mmW AP and RISs. Todirectlyfind a near optimal solution, the parametric functional-form policies for the controllers are modeled using deep recurrent neural networks (RNNs). The deep RNN-based controllers are then trained based on the derived closed-form gradient of the risk-sensitive episodic return. It is proved that the gradient update algorithm converges to the same locally optimal parameters as the deep RNN-based centralized and distributed controllers. Simulation results show that the error between the policies of the optimal and the RNN-based controllers is less than 1.5%. Moreover, the variance of the achievable rates resulting from the deep RNN-based controllers is 60% less than the variance of the risk-averse baseline.

The performance of federated learning (FL) over wireless networks depend on the reliability of the client-server connectivity and clients' local computation capabilities. In this article we investigate the problem of client scheduling and resource block (RB) allocation to enhance the performance of model training using FL, over a pre-defined training duration under imperfect channel state information (CSI) and limited local computing resources. First, we analytically derive the gap between the training losses of FL with clients scheduling and a centralized training method for a given training duration. Then, we formulate the gap of the training loss minimization over client scheduling and RB allocation as a stochastic optimization problem and solve it using Lyapunov optimization. A Gaussian process regression-based channel prediction method is leveraged to learn and track the wireless channel, in which, the clients' CSI predictions and computing power are incorporated into the scheduling decision. Using an extensive set of simulations, we validate the robustness of the proposed method under both perfect and imperfect CSI over an array of diverse data distributions. Results show that the proposed method reduces the gap of the training accuracy loss by up to 40.7% compared to state-of-the-art client scheduling and RB allocation methods.

In this paper, we study the resource slicing problem in a dynamic multiplexing scenario of two distinct 5G services, namely Ultra-Reliable Low Latency Communications (URLLC) and enhanced Mobile BroadBand (eMBB). While eMBB services focus on high data rates, URLLC is very strict in terms of latency and reliability. In view of this, the resource slicing problem is formulated as an optimization problem that aims at maximizing the eMBB data rate subject to a URLLC reliability constraint, while considering the variance of the eMBB data rate to reduce the impact of immediately scheduled URLLC traffic on the eMBB reliability. To solve the formulated problem, an optimization-aided Deep Reinforcement Learning (DRL) based framework is proposed, including: 1) eMBB resource allocation phase, and 2) URLLC scheduling phase. In the first phase, the optimization problem is decomposed into three subproblems and then each subproblem is transformed into a convex form to obtain an approximate resource allocation solution. In the second phase, a DRL-based algorithm is proposed to intelligently distribute the incoming URLLC traffic among eMBB users. Simulation results show that our proposed approach can satisfy the stringent URLLC reliability while keeping the eMBB reliability higher than 90%.

In this paper, we considerpartitioned edge learning(PARTEL), which implements parameter-server training, a well known distributed learning method, in a wireless network. Thereby, PARTEL leverages distributed computation resources at edge devices to train a large-scaleartificial intelligence(AI) model by dynamically partitioning the model into parametric blocks for separated updating at devices. Targeting broadband channels, we consider the joint control of parameter allocation, sub-channel allocation, and transmission power to improve the performance of PARTEL. Specifically, the policies for joint SUbcarrier, Parameter, and POweR allocaTion (SUPPORT) are optimized under the criterion of minimum learning latency. Two cases are considered. First, for the case of decomposable models (e.g., logistic regression), the latency-minimization problem is a mixed-integer program and non-convex. Due to its intractability, we develop a practical solution by integer relaxation and transforming it into an equivalent convex problem of model size maximization under a latency constraint. Thereby, a low-complexity algorithm is designed to compute the SUPPORT policy. Second, consider the case ofdeep neural network(DNN) models which can be trained using PARTEL by introducing some auxiliary variables. This, however, introduces constraints on model partitioning reducing the granularity of parameter allocation. The preceding policy is extended to DNN models by applying the proposed techniques of load rounding and proportional adjustment to rein in latency expansion caused by the load granularity constraints.

In this paper, a novel framework is proposed to enable a predictive deployment of unmanned aerial vehicles (UAVs) as temporary base stations (BSs) to complement ground cellular systems in face of downlink traffic overload. First, a novel learning approach, based on the weighted expectation maximization (WEM) algorithm, is proposed to estimate the user distribution and the downlink traffic demand. Next, to guarantee a truthful information exchange between the BS and UAVs, using the framework of contract theory, an offload contract is developed, and the sufficient and necessary conditions for having a feasible contract are analytically derived. Subsequently, an optimization problem is formulated to deploy an optimal UAV onto the hotspot area in a way that the utility of the overloaded BS is maximized. Simulation results show that the proposed WEM approach yields a prediction error of around 10%. Compared with the expectation maximization and k-mean approaches, the WEM method shows a significant advantage on the prediction accuracy, as the traffic load in the cellular system becomes spatially uneven. Furthermore, compared with two event-driven deployment schemes based on the closest-distance and maximal-energy metrics, the proposed predictive approach enables UAV operators to provide efficient communication service for hotspot users in terms of the downlink capacity, energy consumption and service delay. Simulation results also show that the proposed method significantly improves the revenues of both the BS and UAV networks, compared with two baseline schemes.

This paper investigates the problem of age of information (AoI)-aware resource awareness in an unmanned aerial vehicle (UAV)-assisted mobile-edge computing (MEC) system, which is deployed by an infrastructure provider (InP). A service provider leases resources from the InP to serve the mobile users (MUs) with sporadic computation requests. Due to the limited number of channels and the finite shared I/O resource of the UAV, the MUs compete to schedule local and remote task computations in accordance with the observations of system dynamics. The aim of each MU is to selfishly maximize the expected long-term computation performance. We formulate the non-cooperative interactions among the MUs as a stochastic game. To approach the Nash equilibrium solutions, we propose a novel online deep reinforcement learning (DRL) scheme, which enables each MU to behave using its local conjectures only. The DRL scheme employs two separate deep Q-networks to approximate the Q-factor and the post-decision Q-factor for each MU. Numerical experiments show the potentials of the online DRL scheme in balancing the tradeoff between AoI and energy consumption.

A mega-constellation of low-earth orbit (LEO) satellites has the potential to enable long-range communication with low latency. Integrating this with burgeoning unmanned aerial vehicle (UAV) assisted non-terrestrial networks will be a disruptive solution for beyond 5G systems provisioning large-scale three-dimensional connectivity. In this article, we study the problem of forwarding packets between two faraway ground terminals, through an LEO satellite selected from an orbiting constellation and a mobile high-altitude platform (HAP) such as a fixed-wing UAV. To maximize the end-to-end data rate, the satellite association and HAP location should be optimized, which is challenging due to a huge number of orbiting satellites and the resulting time-varying network topology. We tackle this problem using deep reinforcement learning (DRL) with a novel action dimension reduction technique. Simulation results corroborate that our proposed method achieves up to 5.74x higher average data rate compared to a direct communication baseline without SAT and HAP.

In this paper, we consider the framework of partitioned edge learning for iteratively training a large-scale model using many resource-constrained devices (called workers). To this end, in each iteration, the model is dynamically partitioned into parametric blocks, which are downloaded to worker groups for updating using their local data. Then, the local updates are uploaded to and cascaded by the server for updating a global model. To reduce resource usage by minimizing the total learning-and-communication latency, this work focuses on the novel joint design of parameter (computation load) and bandwidth allocation (for downloading and uploading). Two design approaches are adopted. First, a practical sequential approach, called partially integrated parameter-and-bandwidth allocation (PABA), yields one scheme, namely parameter aware bandwidth allocation. It allocates the largest bandwidth to the slowest worker. Second, PABA are jointly optimized. Despite its being a nonconvex problem, an efficient and optimal solution algorithm is derived by intelligently nesting a bisection search and solving a convex problem. Experimental results using real data demonstrate that integrating PABA can substantially improve the performance of partitioned edge learning in terms of latency (by e.g., 46%) and accuracy (by e.g., 4%).

In this paper, a novel communication framework that uses an unmanned aerial vehicle (UAV)-carried intelligent reflector (IR) is proposed to enhance multi-user downlink transmissions over millimeter wave (mmWave) frequencies. In order to maximize the downlink sum-rate, the optimal precoding matrix (at the base station) and reflection coefficient (at the IR) are jointly derived. Next, to address the uncertainty of mmWave channels and maintain line-of-sight links in a realtime manner, a distributional reinforcement learning approach, based on quantile regression optimization, is proposed to learn the propagation environment of mmWave communications, and, then, optimize the location of the UAV-IR so as to maximize the long-term downlink communication capacity. Simulation results show that the proposed learning-based deployment of the UAV-IR yields a significant advantage, compared to a non-learning UAV-IR, a static IR, and a direct transmission schemes, in terms of the average data rate and the achievable line-of-sight probability of downlink mmWave communications.

In this paper, we propose a communication-efficient decen-tralized machine learning (ML) algorithm, coined quantized group ADMM (Q-GADMM). Every worker in Q-GADMM communicates only with two neighbors, and updates its model via the group alternating direct method of multiplier (GADMM), thereby ensuring fast convergence while reducing the number of communication rounds. Furthermore, each worker quantizes its model updates before transmissions, thereby decreasing the communication payload sizes. We prove that Q-GADMM converges to the optimal solution for convex loss functions, and numerically show that Q-GADMM yields 7x less communication cost while achieving almost the same accuracy and convergence speed compared to GADMM without quantization.

In this paper, the problem of associating reconfigurable intelligent surfaces (RISs) to virtual reality (VR) users is studied for a wireless VR network. In particular, this problem is considered within a cellular network that employs terahertz (THz) operated RISs acting as base stations. To provide a seamless VR experience, high data rates and reliable low latency need to be continuously guaranteed. To address these challenges, a novel risk-based framework based on the entropic value-at-risk is proposed for rate optimization and reliability performance. Furthermore, a Lyapunov optimization technique is used to reformulate the problem as a linear weighted function, while ensuring that higher order statistics of the queue length are maintained under a threshold. To address this problem, given the stochastic nature of the channel, a policy-based reinforcement learning (RL) algorithm is proposed. Since the state space is extremely large, the policy is learned through a deep-RL algorithm. In particular, a recurrent neural network (RNN) RL framework is proposed to capture the dynamic channel behavior and improve the speed of conventional RL policy-search algorithms. Simulation results demonstrate that the maximal queue length resulting from the proposed approach is only within 1% of the optimal solution. The results show a high accuracy and fast convergence for the RNN with a validation accuracy of 91.92%.

Ensuring high reliability is one of the major goals of 5G systems. This work investigates the problem of cooperative relaying and the optimal number of devices to be directly connected to the base station, in order to meet best uplink performance in terms of throughput and reliability. We first propose a D2D-relaying system where devices cooperate forming groups of cellular devices serving as relays to other groups of D2D transmitters. Second we adopt a Markov chain framework, where the states are defined as the numbers of D2D-relays present in the network. Based on that, we derive the average network throughput and reliability. Next, we show that there exists an optimal device distribution, that maximizes the overall reliability and throughput. This number is strongly related to the switching probabilities of the devices and the network parameters such as the orthogonality factor, the cooperation level of D2D-transmitter, the network density and the cluster's radius. Simulation results illustrate the optimal switching probabilities and the average number of D2D-relays that maximize the overall throughput and reliability.

When deployed as reflectors for existing wireless base stations (BSs), reconfigurable intelligent surfaces (RISs) can be a promising approach to achieve high spectrum and energy efficiency. However, due to the large number of RIS elements, the joint optimization of the BS and reflector RIS configuration is challenging. In essence, the BS transmit power and RIS's reflecting configuration must be optimized so as to improve users' data rates and reduce the BS power consumption. In this paper, the problem of energy efficiency optimization is studied in an RIS-assisted cellular network endowed with an RIS reflector powered via energy harvesting technologies. The goal of this proposed framework is to maximize the average energy efficiency by enabling a BS to determine the transmit power and RIS configuration, under uncertainty on the wireless channel and harvested energy of the RIS system. To solve this problem, a novel approach based on deep reinforcement learning is proposed, in which the BS receives the state information, consisting of the users' channel state information feedback and the available energy reported by the RIS. Then, the BS optimizes its action composed of the BS transmit power allocation and RIS phase shift configuration using a neural network. Due to the intractability of the formulated problem under uncertainty, a case study is conducted to analyze the performance of the studied RIS-assisted downlink system by asymptotically deriving the upper bound of the energy efficiency. Simulation results show that the proposed framework improves energy efficiency up to 77.3% when the number of RIS elements increases from 9 to 25.

In this paper, the content popularity prediction problem in fog radio access networks (F-RANs) is investigated. In order to obtain accurate prediction with low complexity, we propose a novel context-aware popularity prediction policy based on federated learning. Firstly, user preference learning is applied by considering that users prefer to request the contents they are interested in. Then, users' context information is utilized to cluster users efficiently by adaptive context space partitioning. After that, we formulate a popularity prediction optimization problem to learn the local model parameters using the stochastic variance reduced gradient (SVRG) algorithm. Finally, federated learning based model integration is proposed to construct the global popularity prediction model based on local models by combining the distributed approximate Newton (DANE) algorithm with SVRG. Our proposed popularity prediction policy not only predicts content popularity accurately, but also significantly reduces computational complexity. Simulation results show that our proposed policy increases the cache hit rate by up to 21.5 % compared to the traditional policies.

Unmanned aerial vehicle (UAV) swarms must exploit machine learning (ML) in order to execute various tasks ranging from coordinated trajectory planning to cooperative target recognition. However, due to the lack of continuous connections between the UAV swarm and ground base stations (BSs), using centralized ML will be challenging, particularly when dealing with a large volume of data. In this paper, a novel framework is proposed to implement distributed federated learning (FL) algorithms within a UAV swarm that consists of a leading UAV and several following UAVs. Each following UAV trains a local FL model based on its collected data and then sends this trained local model to the leading UAV who will aggregate the received models, generate a global FL model, and transmit it to followers over the intra-swarm network. To identify how wireless factors, like fading, transmission delay, and UAV antenna angle deviations resulting from wind and mechanical vibrations, impact the performance of FL, a rigorous convergence analysis for FL is performed. Then, a joint power allocation and scheduling design is proposed to optimize the convergence rate of FL while taking into account the energy consumption during convergence and the delay requirement imposed by the swarm's control system. Simulation results validate the effectiveness of the FL convergence analysis and show that the joint design strategy can reduce the number of communication rounds needed for convergence by as much as 35% compared with the baseline design.

Minimization of the expected value of age of information (AoI) is a risk-neutral approach, and it thus cannot capture rare, yet critical, events with potentially large AoI. In order to capture the effect of these events, in this paper, the notion of conditional value-at-risk (CVaR) is proposed as an effective coherent risk measure that is suitable for minimization of AoI for real-time IoT status updates. In the considered monitoring system, an IoT device monitors a physical process and sends the status updates to a remote receiver with an updating cost. The optimal status update process is designed to jointly minimize the AoI at the receiver, the CVaR of the AoI at the receiver, and the energy cost. This stochastic optimization problem is formulated as an infinite horizon discounted risk-aware Markov decision process (MDP), which is computationally intractable due to the time inconsistency of the CVaR. By exploiting the special properties of coherent risk measures, the risk-aware MDP is reduced to a standard MDP with an augmented state space, for which we derive the optimal stationary policy using dynamic programming. In particular, the optimal history-dependent policy of the risk-aware MDP is shown to depend on the history only through the augmented system states and can be readily constructed using the optimal stationary policy of the augmented MDP. The proposed solution is shown to be computationally tractable and able to minimize the AoI in real-time IoT monitoring systems in a risk-aware manner.

This paper investigates an unmanned aerial vehicle (UAV)-assisted mobile-edge computing (MEC) system, in which the UAV provides complementary computation resource to the terrestrial MEC system. The UAV processes the received computation tasks from the mobile users (MUs) by creating the corresponding virtual machines. Due to finite shared I/O resource of the UAV in the MEC system, each MU competes to schedule local as well as remote task computations across the decision epochs, aiming to maximize the expected long-term computation performance. The non-cooperative interactions among the MUs are modeled as a stochastic game, in which the decision makings of a MU depend on the global state statistics and the task scheduling policies of all MUs are coupled. To approximate the Nash equilibrium solutions, we propose a proactive scheme based on the long short-term memory and deep reinforcement learning (DRL) techniques. A digital twin of the MEC system is established to train the proactive DRL scheme offline. Using the proposed scheme, each MU makes task scheduling decisions only with its own information. Numerical experiments show a significant performance gain from the scheme in terms of average utility per MU across the decision epochs.

This article proposes a communication-efficient decentralized deep learning algorithm, coined layer-wise federated group ADMM (L-FGADMM). To minimize an empirical risk, every worker in L-FGADMM periodically communicates with two neighbors, in which the periods are separately adjusted for different layers of its deep neural network. A constrained optimization problem for this setting is formulated and solved using the stochastic version of GADMM proposed in our prior work. Numerical evaluations show that by less frequently exchanging the largest layer, L-FGADMM can significantly reduce the communication cost, without compromising the convergence speed. Surprisingly, despite less exchanged information and decentralized operations, intermittently skipping the largest layer consensus in L-FGADMM creates a regularizing effect, thereby achieving the test accuracy as high as federated learning (FL), a baseline method with the entire layer consensus by the aid of a central entity.

In this paper, we tackle the problem of remote monitoring (e.g., remote factory) in which a number of sensor nodes are transmitting time sensitive measurements to a remote monitoring site. We assume that packets generated by different sensors have different sizes. Moreover, different sensors have different Maximum Allowable Transfer Intervals (MATIs). We consider minimizing a metric that maintains a trade-off between minimizing the average MATI violation of all sensors, and minimizing the probability that the MATI violation of each sensor exceeds a predefined threshold. We formulate the problem as a stochastic optimization problem with integer constraints. In order to solve this problem, we first relax the original intractable formulation to a tractable problem. Then, we use the Lyapunov stochastic optimization framework to solve the relaxed problem. Simulation results show that the proposed algorithm outperforms the considered baselines in terms of minimizing the probability of the MATI violation for all sensors.

In this work, we propose a novel joint client scheduling and resource block (RB) allocation policy to minimize the loss of accuracy in federated learning (FL) over wireless compared to a centralized training-based solution, under imperfect channel state information (CSI). First, the problem is cast as a stochastic optimization problem over a predefined training duration and solved using the Lyapunov optimization framework. In order to learn and track the wireless channel, a Gaussian process regression (GPR)-based channel prediction method is leveraged and incorporated into the scheduling decision. The proposed scheduling policies are evaluated via numerical simulations, under both perfect and imperfect CSI. Results show that the proposed method reduces the loss of accuracy up to 25.8% compared to state-of-the-art client scheduling and RB allocation methods.

When the data is distributed across multiple servers, lowering the communication cost between the servers (or workers) while solving the distributed learning problem is an important problem and is the focus of this paper. In particular, we propose a fast, and communication-efficient decentralized framework to solve the distributed machine learning (DML) problem. The proposed algorithm, Group Alternating Direction Method of Multipliers (GADMM) is based on the Alternating Direction Method of Multipliers (ADMM) framework. The key novelty in GADMM is that it solves the problem in a decentralized topology where at most half of the workers are competing for the limited communication resources at any given time. Moreover, each worker exchanges the locally trained model only with two neighboring workers, thereby training a global model with a lower amount of communication overhead in each exchange. We prove that GADMM converges to the optimal solution for convex loss functions, and numerically show that it converges faster and more communication-efficient than the state-of-the-art communication-efficient algorithms such as the Lazily Aggregated Gradient (LAG) and dual averaging, in linear and logistic regression tasks on synthetic and real datasets. Furthermore, we propose Dynamic GADMM (D-GADMM), a variant of GADMM, and prove its convergence under the time-varying network topology of the workers.

While the notion of age of information (AoI) has recently been proposed for analyzing ultra-reliable low-latency communications (URLLC), most of the existing works have focused on the average AoI measure. Designing a wireless network based on average AoI will fail to characterize the performance of URLLC systems, as it cannot account for extreme AoI events, occurring with very low probabilities. In contrast, this paper goes beyond the average AoI to improve URLLC in a vehicular communication network by characterizing and controlling the AoI tail distribution. In particular, the transmission power minimization problem is studied under stringent URLLC constraints in terms of probabilistic AoI for both deterministic and Markovian traffic arrivals. Accordingly, an efficient novel mapping between AoI and queue-related distributions is proposed. Subsequently, extreme value theory (EVT) and Lyapunov optimization techniques are adopted to formulate and solve the problem considering both long and short packets transmissions. Simulation results show over a two-fold improvement, in shortening the AoI distribution tail, versus a baseline that models the maximum queue length distribution, in addition to a tradeoff between arrival rate and AoI.

Caching at mobile devices and leveraging device-to-device (D2D) communication are two promising approaches to support massive content delivery over wireless networks. The analysis of cache-enabled wireless networks is usually carried out by assuming that devices are uniformly distributed, however, in social networks, mobile devices are intrinsically grouped into disjoint clusters. In this regards, this paper proposes a spatiotemporal mathematical model that tracks the service requests arrivals and account for the clustered devices geometry. Two kinds of devices are assumed, particularly, content clients and content providers. Content providers are assumed to have a surplus memory which is exploited to proactively cache contents from a known library, following a random probabilistic caching scheme. Content clients can retrieve a requested content from the nearest content provider in their proximity (cluster), or, as a last resort, the base station (BS). The developed spatiotemporal model is leveraged to formulate a joint optimization problem of the content caching and spectrum partitioning in order to minimize the average service delay. Due to the high complexity of the optimization problem, the caching and spectrum partitioning problems are decoupled and solved iteratively using the block coordinate descent (BCD) optimization technique. To this end, an optimal and suboptimal solutions are obtained for the bandwidth partitioning and probabilistic caching subproblems, respectively. Numerical results highlight the superiority of the proposed scheme over conventional caching schemes under equal and optimized bandwidth allocations. Particularly, it is shown that the average service delay is reduced by nearly 100% and 350%, compared to the Zipf and uniform caching schemes under equal bandwidth allocations, respectively.

In this paper, the edge caching optimization problem in fog radio access networks (F-RANs) is investigated. Taking into account time-variant user requests and ultra-dense deployment of fog access points (F-APs), we propose a distributed edge caching scheme to jointly minimize the request service delay and fronthaul traffic load. Considering the interactive relationship among F-APs, we model the optimization problem as a stochastic differential game (SDG) which captures the dynamics of F-AP states. To address both the intractability problem of the SDG and the caching capacity constraint, we propose to solve the optimization problem in a distributive manner. Firstly, a mean field game (MFG) is converted from the original SDG by exploiting the ultra-dense property of F-RANs, and the states of all F-APs are characterized by a mean field distribution. Then, an iterative algorithm is developed that enables each F-AP to obtain the mean field equilibrium and caching control without extra information exchange with other F-APs. Secondly, a fractional knapsack problem is formulated based on the mean field equilibrium, and a greedy algorithm is developed that enables each F-AP to obtain the final caching policy subject to the caching capacity constraint. Simulation results show that the proposed scheme outperforms the baselines.

Immersive virtual reality (VR) applications require ultra-high data rate and low-latency for smooth operation. Hence in this paper, aiming to improve VR experience in multi-user VR wireless video streaming, a deep-learning aided scheme for maximizing the quality of the delivered video chunks with low-latency is proposed. Therein the correlations in the predicted field of view (FoV) and locations of viewers watching 360° HD VR videos are capitalized on to realize a proactive FoV-centric millimeter wave (mmWave) physical-layer multicast transmission. The problem is cast as a frame quality maximization problem subject to tight latency constraints and network stability. The problem is then decoupled into an HD frame request admission and scheduling subproblems and a matching theory game is formulated to solve the scheduling subproblem by associating requests from clusters of users to mmWave small cell base stations (SBSs) for their unicast/multicast transmission. Furthermore, for realistic modeling and simulation purposes, a real VR head-tracking dataset and a deep recurrent neural network (DRNN) based on gated recurrent units (GRUs) are leveraged. Extensive simulation results show how the content-reuse for clusters of users with highly overlapping FoVs brought in by multicasting reduces the VR frame delay in 12%. This reduction is further boosted by proactiveness that cuts by half the average delays of both reactive unicast and multicast baselines while preserving HD delivery rates above 98%. Finally, enforcing tight latency bounds shortens the delay-tail as evinced by 13% lower delays in the 99th percentile.

In this paper, the problem of joint power and resource allocation (JPRA) for ultra-reliable low-latency communication (URLLC) in vehicular networks is studied. Therein, the network-wide power consumption of vehicular users (VUEs) is minimized subject to high reliability in terms of probabilistic queuing delays. Using extreme value theory (EVT), a new reliability measure is defined to characterize extreme events pertaining to vehicles' queue lengths exceeding a predefined threshold. To learn these extreme events, assuming they are independently and identically distributed over VUEs, a novel distributed approach based on federated learning (FL) is proposed to estimate the tail distribution of the queue lengths. Considering the communication delays incurred by FL over wireless links, Lyapunov optimization is used to derive the JPRA policies enabling URLLC for each VUE in a distributed manner. The proposed solution is then validated via extensive simulations using a Manhattan mobility model. Simulation results show that FL enables the proposed method to estimate the tail distribution of queues with an accuracy that is close to a centralized solution with up to 79% reductions in the amount of exchanged data. Furthermore, the proposed method yields up to 60% reductions of VUEs with large queue lengths, while reducing the average power consumption by two folds, compared to an average queue-based baseline.

This paper investigates the control of a massive population of UAVs such as drones. The straightforward method of control of UAVs by considering the interactions among them to make a flock requires a huge inter-UAV communication which is impossible to implement in real-time applications. One method of control is to apply the mean field game (MFG) framework which substantially reduces communications among the UAVs. However, to realize this framework, powerful processors are required to obtain the control laws at different UAVs. This requirement limits the usage of the MFG framework for real-time applications such as massive UAV control. Thus, a function approximator based on neural networks (NN) is utilized to approximate the solutions of Hamilton-Jacobi-Bellman (HJB) and Fokker-Planck-Kolmogorov (FPK) equations. Nevertheless, using an approximate solution can violate the conditions for convergence of the MFG framework. Therefore, the federated learning (FL) approach which can share the model parameters of NNs at drones, is proposed with NN based MFG to satisfy the required conditions. The stability analysis of the NN based MFG approach is presented and the performance of the proposed FL-MFG is elaborated by the simulations.

In this paper, we investigate the problem of asynchronous coded caching in fog radio access networks (F-RANs). To minimize the fronthaul load, the encoding set collapsing rule and encoding set partition method are proposed to establish the relationship between the coded-multicasting contents for asynchronous and synchronous coded caching. Furthermore, a decentralized asynchronous coded caching scheme is proposed, which provides asynchronous and synchronous transmission methods for different delay requirements. The closed-form expression of the fronthaul load is established for the special case where the number of requests during each time slot is fixed, and the upper and lower bounds of the fronthaul load are given for the general case where the number of requests during each time slot is random. The simulation results show that our proposed scheme can create considerable coded-multicasting opportunities in asynchronous request scenarios.

In this paper, we investigate the problem of age of information (AoI)-aware radio resource management for expected long-term performance optimization in a Manhattan grid vehicle-to-vehicle network. With the observation of global network state at each scheduling slot, the roadside unit (RSU) allocates the frequency bands and schedules packet transmissions for all vehicle user equipment-pairs (VUE-pairs). We model the stochastic decision-making procedure as a discrete-time single-agent Markov decision process (MDP). The technical challenges in solving the optimal control policy originate from high spatial mobility and temporally varying traffic information arrivals of the VUE-pairs. To make the problem solving tractable, we first decompose the original MDP into a series of per-VUE-pair MDPs. Then we propose a proactive algorithm based on long short-term memory and deep reinforcement learning techniques to address the partial observability and the curse of high dimensionality in local network state space faced by each VUE-pair. With the proposed algorithm, the RSU makes the optimal frequency band allocation and packet scheduling decision at each scheduling slot in a decentralized way in accordance with the partial observations of the global network state at the VUE-pairs. Numerical experiments validate the theoretical analysis and demonstrate the significant performance improvements from the proposed algorithm.

Federated learning (FL) rests on the notion of training a global model in a decentralized manner. Under this setting, mobile devices perform computations on their local data before uploading the required updates to improve the global model. However, when the participating clients implement an uncoordinated computation strategy, the difficulty is to handle the communication efficiency (i.e., the number of communications per iteration) while exchanging the model parameters during aggregation. Therefore, a key challenge in FL is how users participate to build a high-quality global model with communication efficiency. We tackle this issue by formulating a utility maximization problem, and propose a novel crowdsourcing framework to leverage FL that considers the communication efficiency during parameters exchange. First, we show an incentive-based interaction between the crowdsourcing platform and the participating client's independent strategies for training a global learning model, where each side maximizes its own benefit. We formulate a two-stage Stackelberg game to analyze such scenario and find the game's equilibria. Second, we formalize an admission control scheme for participating clients to ensure a level of local accuracy. Simulated results demonstrate the efficacy of our proposed solution with up to 22% gain in the offered reward.

To leverage data and computation capabilities of mobile devices, machine learning algorithms are deployed at the network edge for training artificial intelligence (AI) models, resulting in the new paradigm of edge learning. In this paper, we consider the framework of partitioned edge learning for iteratively training a large-scale model using many resource-constrained devices (called workers). To this end, in each iteration, the model is dynamically partitioned into parametric blocks, which are downloaded to worker groups for updating using data subsets. Then, the local updates are uploaded to and cascaded by the server for updating a global model. To reduce resource usage by minimizing the total learning-and-communication latency, this work focuses on the novel joint design of parameter (computation load) allocation and bandwidth allocation (for downloading and uploading). Two design approaches are adopted. First, a practical sequential approach, called partially integrated parameter-and-bandwidth allocation (PABA), yields two schemes, namely bandwidth aware parameter allocation and parameter aware bandwidth allocation. The former minimizes the load for the slowest (in computing) of worker groups, each training a same parametric block. The latter allocates the largest bandwidth to the worker being the latency bottleneck. Second, PABA are jointly optimized. Despite it being a nonconvex problem, an efficient and optimal solution algorithm is derived by intelligently nesting a bisection search and solving a convex problem. Experimental results using real data demonstrate that integrating PABA can substantially improve the performance of partitioned edge learning in terms of latency (by e.g., 46%) and accuracy (by e.g., 4% given the latency of 100 seconds).

Network slicing is a proposing technology to support diverse services from mobile users (MUs) over a common physical network infrastructure. In this paper, we consider radio access network (RAN)-only slicing, where the physical RAN is tailored to accommodate both computation and communication functionalities. Multiple service providers (SPs, i.e., multiple tenants) compete with each other to bid for a limited number of channels across the scheduling slots, aiming to provide their subscribed MUs the opportunities to access the RAN slices. An eavesdropper overhears data transmissions from the MUs. We model the interactions among the non-cooperative SPs as a stochastic game, in which the objective of a SP is to optimize its own expected long-term payoff performance. To approximate the Nash equilibrium solutions, we first construct an abstract stochastic game using the channel auction outcomes. Then we linearly decompose the per-SP Markov decision process to simplify the decision- makings and derive a deep reinforcement learning based scheme to approach the optimal abstract control policies. TensorFlow-based experiments verify that the proposed scheme outperforms the three baselines and yields the best performance in average utility per MU per scheduling slot.

Federated learning (FL) rests on the notion of training a global model in a decentralized manner. Under this setting, mobile devices perform computations on their local data before uploading the required updates to the central aggregator for improving the global model. However, a key challenge is to maintain communication efficiency (i.e., the number of communications per iteration) when participating clients implement uncoordinated computation strategy during aggregation of model parameters. We formulate a utility maximization problem to tackle this difficulty, and propose a novel crowdsourcing framework, involving a number of participating clients with local training data to leverage FL. We show the incentive-based interaction between the crowdsourcing platform and the participating client's independent strategies for training a global learning model, where each side maximizes its own benefit. We formulate a two-stage Stackelberg game to analyze such scenario and find the game's equilibria. Further, we illustrate the efficacy of our proposed framework with simulation results. Results show that the proposed mechanism outperforms the heuristic approach with up to 22% gain in the offered reward to attain a level of target accuracy.

This paper investigates the autonomous control of massive unmanned aerial vehicles (UAVs) for mission-critical applications (e.g., dispatching many UAVs from a source to a destination for firefighting). Achieving their fast travel and low motion energy without inter-UAV collision under wind perturbation is a daunting control task, which incurs huge communication energy for exchanging UAV states in real time. We tackle this problem by exploiting a mean-field game (MFG) theoretic control method that requires the UAV state exchanges only once at the initial source. Afterwards, each UAV can control its acceleration by locally solving two partial differential equations (PDEs), known as the Hamilton-Jacobi- Bellman (HJB) and Fokker-Planck-Kolmogorov (FPK) equations. This approach, however, brings about huge computation energy for solving the PDEs, particularly under multi-dimensional UAV states. We address this issue by utilizing a machine learning (ML) method where two separate ML models approximate the solutions of the HJB and FPK equations. These ML models are trained and exploited using an online gradient descent method with low computational complexity. Numerical evaluations validate that the proposed ML aided MFG theoretic algorithm, referred to as \emph{MFG learning control}, is effective in collision avoidance with low communication energy and acceptable computation energy.

In this paper, a novel framework for guaranteeing ultra-reliable millimeter-wave (mmW) communications using a smart, artificial intelligence (AI)-powered mmW reflector is proposed. The use of an AI-powered reflector allows changing the propagation direction of mmW signals and, thus, improving coverage particularly for non-line-of-sight (LoS) areas. However, due to the possibility of stochastic blockage over mmW links, designing an intelligent phase shift-control policy for the mmW reflector to guarantee ultra-reliable mmW communications becomes very challenging. In this regard, first, based on the framework of risk-sensitive reinforcement learning, a parametric risk-sensitive episodic return is proposed to maximize the expected bit rate while mitigating the risk of non-LoS mmW link in the presence of future stochastic blockage over the mmW links. Then, a closed-form approximation for the gradient of the risk- sensitive episodic return is analytically derived. To \emph{directly} find the optimal policy for the proposed phase-shift controller, a parametric functional-form policy is implemented using a deep recurrent neural network (RNN). Then, based on the derived closed-form gradient of risk-sensitive episodic return, the deep RNN-based parametric functional-form policy is trained. The efficiency of the proposed AI-powered reflector is evaluated in an office environment. Simulation results show that the root-mean- square errors between the optimal and approximate phase shift-control policies of the proposed deep RNN is 1.35% in the worst case. Moreover, on average, the mean value and variance of the achievable rates resulting from the deep RNN-based policy are only 1% and 2% less than the optimal solution for different unknown mobile users' trajectories, respectively.

In this paper, the cooperative edge caching problem in fog radio access networks (F-RANs) is investigated to minimize the average download delay. Considering the non-linear and coupled multi-variable nature of the original optimizing problem, we transform it into an equivalent integer linear programming problem with decoupled variables. Then, we decomposed the transformed problem into two subproblems which can be solved separately by each fog access point (F-AP). Considering the non-deterministic polynomial hard (NP-hard) nature of the two decomposed subproblems, we propose an improved pigeon inspired optimization (PIO) based cooperative edge caching scheme, which utilizes Cauchy perturbation and self-adaptive factor to avoid pre-mature convergence and achieve a better search performance, respectively. Our proposed scheme not only allows F-APs to make cache decisions with low computational complexity, but also has very low message passing overhead. Simulation results show that our proposed scheme can greatly decrease the average download delay.

Vehicular networks will play an important role in enhancing road safety, improving transportation efficiency, and providing seamless Internet service for users on the road. Reaping the benefit of vehicular networks is contingent upon meeting stringent wireless communication performance requirements, particularly in terms of delay and reliability. In this paper, a dependence control mechanism is proposed to improve the overall reliability of vehicular networks. In particular, the dependence between the communication delays of different vehicle-to-vehicle (V2V) links is first modeled. Then, the concept of a concordance order, stemming from stochastic ordering theory, is introduced to show that a higher dependence can lead to a better reliability. Using this insight, a power allocation problem is formulated to maximize the concordance, thereby optimizing the overall communication reliability of the V2V system. To obtain an efficient solution to the power allocation problem, a dual update method is introduced. Simulation results verify the effectiveness of performing dependence control for reliability optimization in a vehicular network, and show that the proposed mechanism can achieve up to 25% reliability gain compared to a baseline system that uses a random power allocation.

In this paper, a novel approach that uses an unmanned aerial vehicle (UAV)-carried intelligent reflector (IR) is proposed to enhance the performance of millimeter wave (mmW) networks. In particular, the UAV-IR is used to intelligently reflect mmW beamforming signals from a base station towards a mobile outdoor user, while harvesting energy from mmW signals to power the IR. To maintain a line-of-sight (LOS) channel, a reinforcement learning (RL) approach, based on Q- learning and neural networks, is proposed to model the propagation environment, such that the location and reflection coefficient of the UAV-IR can be optimized to maximize the downlink transmission capacity. Simulation results show a significant advantage for using a UAV-IR over a static IR, in terms of the average data rate and the achievable downlink LOS probability. The results also show that the RL-based deployment of the UAV-IR further improves the network performance, relative to a scheme without learning.

This paper targets at the problem of radio resource management for expected long-term delay-power tradeoff in vehicular communications. At each decision epoch, the road side unit observes the global network state, allocates channels and schedules data packets for all vehicle user equipment-pairs (VUE-pairs). The decision-making procedure is modelled as a discrete-time Markov decision process (MDP). The technical challenges in solving an optimal control policy originate from highly spatial mobility of vehicles and temporal variations in data traffic. To simplify the decision-making process, we first decompose the MDP into a series of per-VUE-pair MDPs. We then propose an online long short-term memory based deep reinforcement learning algorithm to break the curse of high dimensionality in state space faced by each per-VUE-pair MDP. With the proposed algorithm, the optimal channel allocation and packet scheduling decision at each epoch can be made in a decentralized way in accordance with the partial observations of the global network state at the VUE-pairs. Numerical simulations validate the theoretical analysis and show the effectiveness of the proposed online learning algorithm.

One of the 5G promises is to provide Ultra Reliable Low Latency Communications (URLLC) which targets an end to end communication latency that is <; 1ms. The very low latency requirement of URLLC entails a lot of work in all networking layers. In this paper, we focus on the physical layer, and in particular, we propose a novel formulation of the massive MIMO uplink detection problem. We introduce an objective function that is a sum of strictly convex and separable functions based on decomposing the received vector into multiple vectors. Each vector represents the contribution of one of the transmitted symbols in the received vector. Proximal Jacobian Alternating Direction Method of Multipliers (PJADMM) is used to solve the new formulated problem in an iterative manner where at every iteration all variables are updated in parallel and in a closed form expression. The proposed algorithm provides a lower complexity and much faster processing time compared to the conventional MMSE detection technique and other iterative-based techniques, especially when the number of single antenna users is close to the number of base station (BS) antennas. This improvement is obtained without any matrix inversion. Simulation results demonstrate the efficacy of the proposed algorithm in reducing detection processing time in the multi-user uplink massive MIMO setting.

Connected and autonomous vehicles (CAVs) are able to improve on-road safety and provide convenience in our daily lives. To perform autonomous path tracking and navigation, CAVs can exploit vehicle-to-everything (V2X) communications to determine their vehicle dynamics parameters, such as location, heading angle, and curvature, which can be then used as inputs to their control system. However, the interference and uncertainty of the wireless channels can increase the transmission delay on the vehicle dynamics and, thus, impair the CAV's ability to track its target path. In this paper, the problem of joint communication network and control system design is studied to solve the path tracking problem for CAVs. In particular, a novel approach is proposed to maximize the number of reliable V2X transmitter-receiver pairs while jointly considering the stability of the controller and the state of the wireless network. Based on the joint design, the maximum transmission delay which can prevent instability in the controller is determined. Then, the reliable V2X links maximization problem is decomposed into two equivalent sub-problems. The first sub-problem is the control mechanism design in which a dual update method is used to determine the headway distance parameter for the control system. The second sub-problem uses the outcome of the first sub-problem to optimize the power allocation for the communication system. To solve this power allocation problem, a novel risk-based approach that uses the so-called conditional value at risk (CVaR) from financial engineering is proposed. Simulation results validate the theoretical results and show that the proposed joint design can improve the number of reliable V2X pairs by as much as 70% compared to a baseline scheme that optimizes the communication and control systems independently.

Age of Information (AoI) measures the freshness of the information at a remote location. AoI reflects the time that is elapsed since the generation of the packet by a transmitter. In this paper, we consider a remote monitoring problem (e.g., remote factory) in which a number of sensor nodes are transmitting time sensitive measurements to a remote monitoring site. We consider minimizing a metric that maintains a trade-off between minimizing the sum of the expected AoI of all sensors and minimizing an Ultra Reliable Low Latency Communication (URLLC) term. The URLLC term is considered to ensure that the probability the AoI of each sensor exceeds a predefined threshold is minimized. Moreover, we assume that sensors tolerate different threshold values and generate packets at different sizes. Motivated by the success of machine learning in solving large networking problems at low complexity, we develop a low complexity reinforcement learning based algorithm to solve the proposed formulation. We trained our algorithm using the state-of-the-art actor-critic algorithm over a set of public bandwidth traces. Simulation results show that the proposed algorithm outperforms the considered baselines in terms of minimizing the expected AoI and the threshold violation of each sensor.

In this paper, the distributed edge caching problem in fog radio access networks (F-RANs) is investigated. By considering the unknown spatio-temporal content popularity and user preference, a user request model based on hidden Markov process is proposed to characterize the fluctuant spatio-temporal traffic demands in F-RANs. Then, the Q-learning method based on the reinforcement learning (RL) framework is put forth to seek the optimal caching policy in a distributed manner, which enables fog access points (F-APs) to learn and track the potential dynamic process without extra communications cost. Furthermore, we propose a more efficient Q-learning method with value function approximation (Q-VFA-learning) to reduce complexity and accelerate convergence. Simulation results show that the performance of our proposed method is superior to those of the traditional methods.

In this study, cooperative caching is investigated in fog radio access networks. To maximise the offloaded traffic, a cooperative caching optimisation problem is formulated. By analysing the relationship between clustering and cooperation and utilising the solutions of the knapsack problems, the above challenging optimisation problem is transformed into a clustering subproblem and a content placement subproblem. To further reduce complexity, the authors propose an effective graph‐based approach to solve the two subproblems. In the graph‐based clustering approach, a node graph and a weighted graph are constructed. By setting the weights of the vertices of the weighted graph to be the incremental offloaded traffics of their corresponding complete subgraphs, the objective cluster sets can be readily obtained by using an effective greedy algorithm to search for the max‐weight independent subset. In the graph‐based content placement approach, a redundancy graph is constructed by removing the edges in the complete subgraphs of the node graph corresponding to the obtained cluster sets. Furthermore, they enhance the caching decisions to ensure each duplicate file is cached only once. Compared with traditional approximate solutions, their proposed graph‐based approach has lower complexity. Simulation results show remarkable improvements in terms of offloaded traffic by using the proposed approach.

To improve the quality of computation experience for mobile devices, mobile-edge computing (MEC) is a promising paradigm by providing computing capabilities in close proximity within a sliced radio access network (RAN), which supports both traditional communication and MEC services. Nevertheless, the design of computation offloading policies for a virtual MEC system remains challenging. Specifically, whether to execute a computation task at the mobile device or to offload it for MEC server execution should adapt to the time-varying network dynamics. This paper considers MEC for a representative mobile user in an ultradense sliced RAN, where multiple base stations (BSs) are available to be selected for computation offloading. The problem of solving an optimal computation offloading policy is modeled as a Markov decision process, where our objective is to maximize the long-term utility performance whereby an offloading decision is made based on the task queue state, the energy queue state as well as the channel qualities between mobile user and BSs. To break the curse of high dimensionality in state space, we first propose a double deep Q-network (DQN)-based strategic computation offloading algorithm to learn the optimal policy without knowing a priori knowledge of network dynamics. Then motivated by the additive structure of the utility function, a Q-function decomposition technique is combined with the double DQN, which leads to a novel learning algorithm for the solving of stochastic computation offloading. Numerical experiments show that our proposed learning algorithms achieve a significant improvement in computation offloading performance compared with the baseline policies.

With the cellular networks becoming increasingly agile, a major challenge lies in how to support diverse services for mobile users (MUs) over a common physical network infrastructure. Network slicing is a promising solution to tailor the network to match such service requests. This paper considers a system with radio access network (RAN)-only slicing, where the physical infrastructure is split into slices providing computation and communication functionalities. A limited number of channels are auctioned across scheduling slots to MUs of multiple service providers (SPs) (i.e., the tenants). Each SP behaves selfishly to maximize the expected long-term payoff from the competition with other SPs for the orchestration of channels, which provides its MUs with the opportunities to access the computation and communication slices. This problem is modelled as a stochastic game, in which the decision makings of a SP depend on the global network dynamics as well as the joint control policy of all SPs. To approximate the Nash equilibrium solutions, we first construct an abstract stochastic game with the local conjectures of channel auction among the SPs. We then linearly decompose the per-SP Markov decision process to simplify the decision makings at a SP and derive an online scheme based on deep reinforcement learning to approach the optimal abstract control policies. Numerical experiments show significant performance gains from our scheme.

Edge computing is an emerging concept based on distributed computing, storage, and control services closer to end network nodes. Edge computing lies at the heart of the fifth-generation (5G) wireless systems and beyond. While the current state-of-the-art networks communicate, compute, and process data in a centralized manner (at the cloud), for latency and compute-centric applications, both radio access and computational resources must be brought closer to the edge, harnessing the availability of computing and storage-enabled small cell base stations in proximity to the end devices. Furthermore, the network infrastructure must enable a distributed edge decision-making service that learns to adapt to the network dynamics with minimal latency and optimize network deployment and operation accordingly. This paper will provide a fresh look to the concept of edge computing by first discussing the applications that the network edge must provide, with a special emphasis on the ensuing challenges in enabling ultrareliable and low-latency edge computing services for mission-critical applications such as virtual reality (VR), vehicle-to-everything (V2X), edge artificial intelligence (AI), and so on. Furthermore, several case studies where the edge is key are explored followed by insights and prospect for future work.

Fueled by the availability of more data and computing power, recent breakthroughs in cloud-based machine learning (ML) have transformed every aspect of our lives from face recognition and medical diagnosis to natural language processing. However, classical ML exerts severe demands in terms of energy, memory, and computing resources, limiting their adoption for resource-constrained edge devices. The new breed of intelligent devices and high-stake applications (drones, augmented/virtual reality, autonomous systems, and so on) requires a novel paradigm change calling for distributed, low-latency and reliable ML at the wireless network edge (referred to as edge ML). In edge ML, training data are unevenly distributed over a large number of edge nodes, which have access to a tiny fraction of the data. Moreover, training and inference are carried out collectively over wireless links, where edge devices communicate and exchange their learned models (not their private data). In a first of its kind, this article explores the key building blocks of edge ML, different neural network architectural splits and their inherent tradeoffs, as well as theoretical and technical enablers stemming from a wide range of mathematical disciplines. Finally, several case studies pertaining to various high-stake applications are presented to demonstrate the effectiveness of edge ML in unlocking the full potential of 5G and beyond.

The month’s regular papers issue covers machine learning at the wireless network edge, soft-informationbased localization techniques, and Antenna-in-Package technology.

In this paper, the edge caching problem in fog radio access network (F-RAN) is investigated. By maximizing the overall cache hit rate, the edge caching optimization problem is formulated to find the optimal policy. Content popularity in terms of time and space is considered from the perspective of regional users. We propose an online content popularity prediction algorithm by leveraging the content features and user preferences, and an offline user preference learning algorithm by using the online gradient descent (OGD) method and the follow the (proximally) regularized leader (FTRL-Proximal) method. Our proposed edge caching policy not only can promptly predict the future content popularity in an online fashion with low complexity, but also can track the content popularity with spatial and temporal popularity dynamic in time without delay. Furthermore, we design two learning-based edge caching architectures. Moreover, we theoretically derive the upper bound of the popularity prediction error, the lower bound of the cache hit rate, and the regret bound of the overall cache hit rate of our proposed edge caching policy. Simulation results show that the overall cache hit rate of our proposed policy is superior to those of the traditional policies and asymptotically approaches the optimal performance.

To overcome devices' limitations in performing computation-intense applications, mobile edge computing (MEC) enables users to offload tasks to proximal MEC servers for faster task computation. However, the current MEC system design is based on average-based metrics, which fails to account for the ultra-reliable low-latency requirements in mission-critical applications. To tackle this, this paper proposes a new system design, where probabilistic and statistical constraints are imposed on task queue lengths, by applying extreme value theory. The aim is to minimize users' power consumption while trading off the allocated resources for local computation and task offloading. Due to wireless channel dynamics, users are reassociated to MEC servers in order to offload tasks using higher rates or accessing proximal servers. In this regard, a user-server association policy is proposed, taking into account the channel quality as well as the servers' computation capabilities and workloads. By marrying tools from Lyapunov optimization and matching theory, a two-timescale mechanism is proposed, where a user-server association is solved in the long timescale, while a dynamic task offloading and resource allocation policy are executed in the short timescale. The simulation results corroborate the effectiveness of the proposed approach by guaranteeing highly reliable task computation and lower delay performance, compared to several baselines.

In this paper, the effective use of multiple quadrotor drones as an aerial antenna array that provides wireless service to ground users is investigated. In particular, under the goal of minimizing the airborne service time needed for communicating with ground users, a novel framework for deploying and operating a drone-based antenna array system whose elements are single-antenna drones is proposed. In the considered model, the service time is minimized by minimizing the wireless transmission time as well as the control time that is needed for movement and stabilization of the drones. To minimize the transmission time, first, the antenna array gain is maximized by optimizing the drone spacing within the array. In this case, using perturbation techniques, the drone spacing optimization problem is addressed by solving successive, perturbed convex optimization problems. Then, according to the location of each ground user, the optimal locations of the drones around the array's center are derived such that the transmission time for the user is minimized. Given the determined optimal locations of drones, the drones must spend a control time to adjust their positions dynamically so as to serve multiple users. To minimize this control time of the quadrotor drones, the speed of rotors is optimally adjusted based on both the destinations of the drones and external forces (e.g., wind and gravity). In particular, using bang-bang control theory, the optimal rotors' speeds as well as the minimum control time are derived in closed-form. Simulation results show that the proposed approach can significantly reduce the service time to ground users compared with a fixed-array case in which the same number of drones form a fixed uniform antenna array. The results also show that, in comparison with the fixed-array case, the network's spectral efficiency can be improved by 32% while leveraging the drone antenna array system. Finally, the results reveal an inherent tradeoff between the control time and transmission time while varying the number of drones in the array.

Autonomous vehicular platoons will play an important role in improving on-road safety in tomorrow’s smart cities. Vehicles in an autonomous platoon can exploit vehicle-to-vehicle (V2V) communications to collect environmental information so as to maintain the target velocity and inter-vehicle distance. However, due to the uncertainty of the wireless channel, V2V communications within a platoon will experience a wireless system delay. Such system delay can impair the vehicles’ ability to stabilize their velocity and distances within their platoon. In this paper, the problem of integrated communication and control system is studied for wireless connected autonomous vehicular platoons. In particular, a novel framework is proposed for optimizing a platoon’s operation while jointly taking into account the delay of the wireless V2V network and the stability of the vehicle’s control system. First, stability analysis for the control system is performed and the maximum wireless system delay requirements which can prevent the instability of the control system are derived. Then, delay analysis is conducted to determine the end-to-end delay, including queuing, processing, and transmission delay for the V2V link in the wireless network. Subsequently, using the derived wireless delay, a lower bound and an approximated expression of the reliability for the wireless system, defined as the probability that the wireless system meets the control system’s delay needs, are derived. Then, the parameters of the control system are optimized in a way to maximize the derived wireless system reliability. Simulation results corroborate the analytical derivations and study the impact of parameters, such as the packet size and the platoon size, on the reliability performance of the vehicular platoon. More importantly, the simulation results shed light on the benefits of integrating control system and wireless network design while providing guidelines for designing an autonomous platoon so as to realize the required wireless network reliability and control system stability.

Fog computing is emerging as a promising paradigm to perform distributed, low-latency computation by jointly exploiting the radio and computing resources of end-user devices and cloud servers. However, the dynamic and distributed formation of local fog networks is highly challenging due to the unpredictable arrival and departure of neighboring fog nodes. Therefore, a given fog node must properly select a set of neighboring nodes and intelligently offload its computational tasks to this set of neighboring fog nodes and the cloud in order to achieve low-latency transmission and computation. In this paper, the problem of fog network formation and task distribution is jointly investigated while considering a hybrid fog-cloud architecture. The overarching goal is to minimize the maximum communication and computation latency by enabling a given fog node to form a suitable fog network and optimize the task distribution under uncertainty on the arrival process of neighboring fog nodes. To solve this problem, a novel online optimization framework is proposed, in which the neighboring nodes are selected by using a threshold-based online algorithm that uses a target competitive ratio, defined as the ratio between the latency of the online algorithm and the offline optimal latency. The proposed framework repeatedly updates its target competitive ratio and optimizes the distribution of the fog node's computational tasks in order to minimize latency. The simulation results show that, for specific settings, the proposed framework can successfully select a set of neighboring nodes while reducing latency by up to 19.25% compared with a baseline approach based on the well-known online secretary framework. The results also show how, using the proposed framework, the computational tasks can be properly offloaded between the fog network and a remote cloud server in different network settings.

In this paper, a novel concept of three-dimensional (3D) cellular networks, that integrate drone base stations (drone-BS) and cellular-connected drone users (drone-UEs), is introduced. For this new 3D cellular architecture, a novel framework for network planning for drone-BSs and latency-minimal cell association for drone-UEs is proposed. For network planning, a tractable method for drone-BSs' deployment based on the notion of truncated octahedron shapes is proposed, which ensures full coverage for a given space with a minimum number of drone-BSs. In addition, to characterize frequency planning in such 3D wireless networks, an analytical expression for the feasible integer frequency reuse factors is derived. Subsequently, an optimal 3D cell association scheme is developed for which the drone-UEs' latency, considering transmission, computation, and backhaul delays, is minimized. To this end, first, the spatial distribution of the drone-UEs is estimated using a kernel density estimation method, and the parameters of the estimator are obtained using a cross-validation method. Then, according to the spatial distribution of drone-UEs and the locations of drone-BSs, the latency-minimal 3D cell association for drone-UEs is derived by exploiting tools from an optimal transport theory. The simulation results show that the proposed approach reduces the latency of drone-UEs compared with the classical cell association approach that uses a signal-to-interference-plus-noise ratio (SINR) criterion. In particular, the proposed approach yields a reduction of up to 46% in the average latency compared with the SINR-based association. The results also show that the proposed latency-optimal cell association improves the spectral efficiency of a 3D wireless cellular network of drones.

Millimeter wave (mmW) communication is a promising solution for providing high-capacity wireless network access. However, the benefits of mmW are limited by the fact that the channel between a mmW access point and the user equipment can stochastically change due to severe blockage of mmW links by obstacles such as the human body. Thus, one main challenge of mmW network coverage is to enable directional line-of-sight links between access points and mobile devices. In this paper, a novel framework is proposed for optimizing mmW network coverage within hotspots and in-venue regions, while being cognizant of the body blockage of the network's users. In the studied model, the locations of potential access points and users are assumed as predefined parameters while the orientation of the users is assumed to be stochastic. Hence, a joint stochastic access point placement and beam steering problem subjected to stochastic users' body blockage is formulated, under desired network coverage constraints. Then, a greedy algorithm is introduced to find an approximation solution for the joint deployment and assignment problem using a new “size constrained weighted set cover” approach. A closed-form expression for the ratio between the optimal solution and approximate one (resulting from the greedy algorithm) is analytically derived. The proposed algorithm is simulated for three in-venue regions: the meeting room in the Alumni Assembly Hall of Virginia Tech, an airport gate, and one side of a stadium football. The simulation results show that, in order to guarantee network coverage for different in-venue regions, the greedy algorithm uses at most three more access points (APs) compared to the optimal solution. The results also show that, due to the use of the additional APs, the greedy algorithm will yield a network coverage up to 11.7% better than the optimal, AP-minimizing solution.

Owing to severe path loss and unreliable transmission over a long distance at higher frequency bands, this paper investigates the problem of path selection and rate allocation for multi-hop self-backhaul millimeter-wave (mm-wave) networks. Enabling multi-hop mm-wave transmissions raises a potential issue of increased latency, and thus, this paper aims at addressing the fundamental questions: how to select the best multi-hop paths and how to allocate rates over these paths subject to latency constraints? In this regard, a new system design, which exploits multiple antenna diversity, mm-wave bandwidth, and traffic splitting techniques, is proposed to improve the downlink transmission. The studied problem is cast to as a network utility maximization, subject to the upper delay bound constraint, network stability, and network dynamics. By leveraging stochastic optimization, the problem is decoupled into: 1) path selection and 2) rate allocation sub-problems, whereby a framework which selects the best paths is proposed using reinforcement learning techniques. Moreover, the rate allocation is a non-convex program, which is converted into a convex one by using the successive convex approximation method. Via mathematical analysis, the comprehensive performance analysis and convergence proof are provided for the proposed solution. The numerical results show that the proposed approach ensures reliable communication with a guaranteed probability of up to 99.9999% and reduces latency by 50.64% and 92.9% as compared to baseline models. Furthermore, the results showcase the key tradeoff between latency and network arrival rate.

In this paper, power control in the uplink for two-tier small-cell networks is investigated. We formulate the power control problem as a Stackelberg game, where the macrocell user equipment (MUE) acts as the leader and the small-cell user equipment (SUE) acts as the follower. To reduce the cross-tier and cotier interferences and the power consumption of both the MUE and SUE, we propose optimizing not only the transmit rate but also the transmit power. The corresponding optimization problems are solved through a two-layer iteration. In the inner iteration, the SUE items (SUEs) compete with each other, and their optimal transmit powers are obtained through iterative computations. In the outer iteration, the optimal transmit power of the MUE is obtained in a closed form based on the transmit powers of the SUEs through proper mathematical manipulations. We prove the convergence of the proposed power control scheme, and we also theoretically show the existence and uniqueness of the Stackelberg equilibrium (SE) in the formulated Stackelberg game. The simulation results show that the proposed power control scheme provides considerable improvements, particularly for the MUE.

While the notion of age of information (AoI) has recently emerged as an important concept for analyzing ultra-reliable low-latency communications (URLLC), the majority of the existing works have focused on the average AoI measure. However, an average AoI based design falls short in properly characterizing the performance of URLLC systems as it cannot account for extreme events that occur with very low probabilities. In contrast, in this paper, the main objective is to go beyond the traditional notion of average AoI by characterizing and optimizing a URLLC system while capturing the AoI tail distribution. In particular, the problem of vehicles' power minimization while ensuring stringent latency and reliability constraints in terms of probabilistic AoI is studied. To this end, a novel and efficient mapping between both AoI and queue length distributions is proposed. Subsequently, extreme value theory (EVT) and Lyapunov optimization techniques are adopted to formulate and solve the problem. Simulation results shows a nearly two-fold improvement in terms of shortening the tail of the AoI distribution compared to a baseline whose design is based on the maximum queue length among vehicles, when the number of vehicular user equipment (VUE) pairs is 80. The results also show that this performance gain increases significantly as the number of VUE pairs increases.

We formulate and solve the energy minimization problem for a clustered device-to-device (D2D) network with cache-enabled mobile devices. Devices are distributed according to a Poisson cluster process (PCP) and are assumed to have a surplus memory which is exploited to proactively cache files from a library. Devices can retrieve the requested files from their caches, from neighboring devices in their proximity (cluster), or from the base station as a last resort. We minimize the energy consumption of the proposed network under a random probabilistic caching scheme, where files are independently cached according to a specific probability distribution. A closed form expression for the D2D coverage probability is obtained. The energy consumption problem is then formulated as a function of the caching distribution, and the optimal probabilistic caching distribution is obtained. Results reveal that the proposed caching distribution reduces energy consumption up to 33% as compared to caching popular files scheme.

Offloading the network, minimizing the power consumption as well as reducing interference are important issues in wireless networks. These requirements mandates that future cellular networks need to use Device-to-Device communication as a key enabler. To harness this solution, we propose a two-device system that combines cellular and Device-to-Device (D2D) communication in an uplink communication. We model this system as a quitting game where devices choose simultaneously either to continue or to quit transmitting over the cellular network. The devices will strategically choose whether to compete or to cooperate through mobile relaying. We first calculate the throughput and the outage probability in a fading channel, then we find the Sub-game Perfect Equilibrium of this game by determining the pure and mixed Nash equilibrium of each subgame. Results show that the outage probability depends on the transmission power and the distance separating a device from its serving BS. The quitting decision of devices depends on the fraction of throughput they would get after quitting, on the quitting frame and on the quitting regret.

In this paper, the problem of unmanned aerial vehicle (UAV)-assisted fog computing in Industry 4.0 smart factories is studied. In particular, a novel online framework is proposed to enable a source UAV to offload computing tasks from ground sensors within a smart factory and allocate them to neighboring fog UAVs for distributed task computing, before the source UAV arrives at its destination. The online nature of the framework allows the UAVs to optimize their task allocation and decide on which neighbors to use for fog computing, even when the tasks are revealed to the source UAV in an online manner, and the information on future task arrivals is unknown. The proposed framework essentially maximizes the number of computed tasks by jointly considering the communication and computation latency. To solve the problem, an online greedy algorithm is designed and solved by using the primal-dual approach. Since the primal problem provides an upper bound of the original dual problem, the competitive ratio can be analytically derived as a function of the task sizes and the data rates of the UAVs. Simulation results show that the proposed online algorithm can achieve a near- optimal task allocation with an optimality gap that is no higher than 7.5% compared to the offline, optimal solution with complete knowledge of all tasks.

In this paper, a novel concept of three-dimensional (3D) cellular networks, that integrate drone base stations (drone-BS) and drone users (drone-UEs), is introduced. For this new 3D cellular network architecture, a novel framework for the deployment of drone-BSs and latency-minimal cell association for drone-UEs is proposed. For drone-BSs' deployment, a tractable method based on the notion of truncated octahedron shapes is proposed that ensures full coverage for a given space with minimum number of drone-BSs. Then, an optimal 3D cell association scheme is determined such that the drone-UEs' latency, considering transmission, computation, and backhaul latencies, is minimized. In particular, using optimal transport theory, the optimal 3D cell partitions are derived according to the spatial distribution of drone-UEs and the drone-BSs' locations. Simulation results show that the proposed approach reduces the latency of drone-UEs compared to the classical cell association approach that uses a signal-to-interference-plus-noise ratio (SINR) criterion. In particular, the proposed approach yields a reduction of up to 46% in average latency compared to the SINR-based association. Also, it is shown that the proposed latency-optimal cell association improves the spectral efficiency of a 3D wireless cellular network of drones.

Virtual reality (VR) enables mobile wireless users to experience multimodal perceptions in a virtual space. In this paper we investigate the problem of concurrent support of visual and haptic perceptions over wireless cellular networks, with a focus on the downlink transmission phase. While the visual perception requires moderate reliability and maximized rate, the haptic perception requires fixed rate and high reliability. Hence, the visuo-haptic VR traffic necessitates the use of two different network slices: enhanced mobile broadband (eMBB) for visual perception and ultra-reliable and low latency communication (URLLC) for haptic perception. We investigate two methods by which these two slices share the downlink resources orthogonally and non-orthogonally, respectively. We compare these methods in terms of the just-noticeable difference (JND), an established measure in psychophysics, and show that non- orthogonal slicing becomes preferable under a higher target integrated-perceptual resolution and/or a higher target rate for haptic perceptions.

In this paper, a novel joint transmit power and resource allocation approach for enabling ultra-reliable low-latency communication (URLLC) in vehicular networks is proposed. The objective is to minimize the network-wide power consumption of vehicular users (VUEs) while ensuring high reliability in terms of probabilistic queuing delays. In particular, a reliability measure is defined to characterize extreme events (i.e., when vehicles' queue lengths exceed a predefined threshold with non-negligible probability) using extreme value theory (EVT). Leveraging principles from federated learning (FL), the distribution of these extreme events corresponding to the tail distribution of queues is estimated by VUEs in a decentralized manner. Finally, Lyapunov optimization is used to find the joint transmit power and resource allocation policies for each VUE in a distributed manner. The proposed solution is validated via extensive simulations using a Manhattan mobility model. It is shown that FL enables the proposed distributed method to estimate the tail distribution of queues with an accuracy that is very close to a centralized solution with up to 79% reductions in the amount of data that need to be exchanged. Furthermore, the proposed method yields up to 60% reductions of VUEs with large queue lengths, without an additional power consumption, compared to an average queue-based baseline. Compared to systems with fixed power consumption and focusing on queue stability while minimizing average power consumption, the reductions in extreme events of the proposed method is about two orders of magnitude.

In this paper, a novel machine learning (ML) framework is proposed for enabling a predictive, efficient deployment of unmanned aerial vehicles (UAVs), acting as aerial base stations (BSs), to provide on-demand wireless service to cellular users. In order to have a comprehensive analysis of cellular traffic, an ML framework based on a Gaussian mixture model and a weighted expectation maximization algorithm is introduced to predict the potential network congestion. Then, the optimal deployment of UAVs is studied with the objective of minimizing the power needed for UAV transmission and mobility, given the predicted traffic. To this end, first, the optimal partition of service areas of each UAV is derived, based on a fairness principle. Next, the optimal location of each UAV that minimizes the total power consumption is derived. Simulation results show that the proposed ML approach can reduce power needed for downlink transmission and mobility by over 20% and 80%, respectively, compared with an optimal deployment of UAVs with no ML prediction.

In this paper, the effective use of multiple drones as an aerial antenna array that provides wireless service to ground users is investigated. In particular, under the goal of minimizing the service time needed for servicing ground users, a novel framework for deploying a drone- based antenna array system whose elements are single- antenna drones is proposed. To this end, first, the antenna array gain is maximized by optimizing the drone spacing within the array. In this case, using perturbation techniques, the drone spacing optimization problem is addressed by solving successive, perturbed convex optimization problems. In the second step, the optimal locations of the drones around the array''s center are derived such that the service time for each ground user is minimized. Simulation results show that the proposed approach can significantly reduce the service time to ground users compared to a single drone that uses the same amount of power as the array. The results also show that the network''s spectral efficiency can be improved by 78% while leveraging the drone antenna array system.

Vehicle platoons will play an important role in improving on-road safety in tomorrow's smart cities. Vehicles in a platoon can exploit vehicle- to-vehicle (V2V) communications to collect information, such as velocity and acceleration, from surrounding vehicles so as to coordinate their operations and maintain the target velocity and inter-vehicle distance required by the platoon. However, due to the interference and uncertainty of the wireless channel, V2V communications within a platoon will experience a wireless transmission delay which can impair the vehicles' ability to stabilize their speed and distances within their platoon. In this paper, the problem of integrated communication and control is studied for wireless-connected platoons. In particular, a novel approach is proposed for optimizing a platoon's stability while taking into account, jointly, the state of the wireless V2V network and the stability of the platoon's control system. Based on the proposed integrated communication and control strategy, the plant and string stability for the platoon are analyzed. The signal-to-interference-plus-noise-ratio (SINR) threshold, which will prevent the instability of the control system, is also determined. Moreover, the reliability of the wireless system, defined as the probability that the wireless system meets the control system's delay needs, is derived. Simulation results shed light on the benefits of the proposed approach and the synergies between the wireless network and the platoon's control system.

To improve the quality of computation experience for mobile devices, mobile-edge computing (MEC) is emerging as a promising paradigm by providing computing capabilities within radio access networks in close proximity. Nevertheless, the design of computation offloading policies for a MEC system remains challenging. Specifically, whether to execute an arriving computation task at local mobile device or to offload a task for cloud execution should adapt to the environmental dynamics in a smarter manner. In this paper, we consider MEC for a representative mobile user in an ultra dense network, where one of multiple base stations (BSs) can be selected for computation offloading. The problem of solving an optimal computation offloading policy is modelled as a Markov decision process, where our objective is to minimize the long-term cost and an offloading decision is made based on the channel qualities between the mobile user and the BSs, the energy queue state as well as the task queue state. To break the curse of high dimensionality in state space, we propose a deep Q-network-based strategic computation offloading algorithm to learn the optimal policy without having a priori knowledge of the dynamic statistics. Numerical experiments provided in this paper show that our proposed algorithm achieves a significant improvement in average cost compared with baseline policies.

In this paper, the edge caching problem in ultra-dense fog radio access networks (F-RAN) is investigated. Taking into account time-variant user requests and ultra-dense deployment of fog access points (F-APs), we propose a dynamic distributed edge caching scheme to jointly minimize the request service delay and fronthaul traffic load. Considering the interactive relationship among F-APs, we model the caching optimization problem as a stochastic differential game (SDG) which captures the temporal dynamics of F-AP states and incorporates user requests status. The SDG is further approximated as a mean field game (MFG) by exploiting the ultra-dense property of F-RAN. In the MFG, each F-AP can optimize its caching policy independently through iteratively solving the corresponding partial differential equations without any information exchange with other F-APs. The simulation results show that the proposed edge caching scheme outperforms the baseline schemes under both static and time-variant user requests.

In this paper, we investigate asynchronous coded caching in fog radio access networks (F-RAN). To minimize the fronthaul load, the encoding set collapsing rule and encoding set partition method are proposed to establish the relationship between the coded-multicasting contents in asynchronous and synchronous coded caching. Furthermore, a decentralized asynchronous coded caching scheme is proposed, which provides asynchronous and synchronous transmission methods for different delay requirements. The simulation results show that our proposed scheme creates considerable coded-multicasting opportunities in asynchronous request scenarios.

In this paper, a novel proactive computing and mmWave communication for ultra-reliable and low latency wireless virtual reality (VR is proposed. By leveraging information about users' poses, proactive computing and caching are used to pre-compute and store users' HD video frames to minimize the computing latency. Furthermore, multi-connectivity is exploited to ensure reliable mmWave links to deliver users' requested HD frames. The performance of the proposed approach is validated on a VR network serving an interactive gaming arcade, where dynamic and real-time rendering of HD video frames is needed and impulse actions of different players impact the content to be shown. Simulation results show significant gains of up to 30% reduction in end-to-end delay and 50% in the 90thpercentile communication delay.

We investigate the problem of multi-hop scheduling in self-backhauled millimeter wave (mmWave) networks. Owing to the high path loss and blockage of mmWave links, multi-hop paths/routes between the macro base station and the intended users via full-duplex small cells need to be carefully selected. This paper addresses the fundamental question: “how to select the best paths and how to allocate rates over these paths subject to latency constraints?” To answer this question, we propose a new system design, which factors in mmWave-specific channel variations and network dynamics. The problem is cast as a network utility maximization subject to a bounded delay constraint and network stability. The studied problem is decoupled into: (i) a path/route selection and (ii) rate allocation, whereby learning the best paths is done by means of a reinforcement learning algorithm, and the rate allocation is solved by applying the successive convex approximation method. Via numerical results, our approach ensures reliable communication with a guaranteed probability of 99.9999%, and reduces latency by 50.64% and 92.9% as compared to baselines.

Ensuring ultrareliable and low-latency communication (URLLC) for 5G wireless networks and beyond is of capital importance and is currently receiving tremendous attention in academia and industry. At its core, URLLC mandates a departure from expected utility-based network design approaches, in which relying on average quantities (e.g., average throughput, average delay, and average response time) is no longer an option but a necessity. Instead, a principled and scalable framework which takes into account delay, reliability, packet size, network architecture and topology (across access, edge, and core), and decision-making under uncertainty is sorely lacking. The overarching goal of this paper is a first step to filling this void. Towards this vision, after providing definitions of latency and reliability, we closely examine various enablers of URLLC and their inherent tradeoffs. Subsequently, we focus our attention on a wide variety of techniques and methodologies pertaining to the requirements of URLLC, as well as their applications through selected use cases. These results provide crisp insights for the design of low-latency and high-reliability wireless networks.

Provides an overview of the technical articles and features presented in this issue. Our regular papers this month focus on 5G related topics such as multipleinput– multipleoutput transmission using finite input signals, and achieving ultrareliable and low-latency wireless communication.

How to allocate the limited wireless resource in dense radio access networks (RANs) remains challenging. By leveraging a software-defined control plane, the independent base stations (BSs) are virtualized as a centralized network controller (CNC). Such virtualization decouples the CNC from the wireless service providers (WSPs). We investigate a virtualized RAN, where the CNC auctions channels at the beginning of scheduling slots to the mobile terminals (MTs) based on bids from their subscribing WSPs. Each WSP aims at maximizing the expected long-term payoff from bidding channels to satisfy the MTs for transmitting packets. We formulate the problem as a stochastic game, where the channel auction and packet scheduling decisions of a WSP depend on the state of network and the control policies of its competitors. To approach the equilibrium solution, an abstract stochastic game is proposed with bounded regret. The decision making process of each WSP is modeled as a Markov decision process (MDP). To address the signalling overhead and computational complexity issues, we decompose the MDP into a series of single-agent MDPs with reduced state spaces, and derive an online localized algorithm to learn the state value functions. Our results show significant performance improvements in terms of per-MT average utility.

Proactive wireless caching and device to device (D2D) communication have emerged as promising techniques for enhancing users' quality of service and network performance. In this paper, we propose a new architecture for D2D caching with inter-cluster cooperation. We study a cellular network in which users cache popular files and share them with other users either in their proximity via D2D communication or with remote users using cellular transmission. We characterize the network average delay per request from a queuing perspective. Specifically, we formulate the delay minimization problem and show that it is NP-hard. Furthermore, we prove that the delay minimization problem is equivalent to the minimization of a non-increasing monotone supermodular function subject to a uniform partition matroid constraint. A computationally efficient greedy algorithm is proposed which is proven to be locally optimal within a factor (1- e-1) ≈ 0.63 of the optimum. We analyze the average per request throughput for different caching schemes and conduct the scaling analysis for the average sum throughput. We show how throughput scaling depends on video content popularity when the number of files grows asymptotically large. Simulation results show a delay reduction of 45% to 80% compared to a D2D caching system without inter-cluster cooperation.

Software-defined networking (SDN) provides an agile and programmable way to optimize radio access networks via a control-data plane separation. Nevertheless, reaping the benefits of wireless SDN hinges on making optimal use of the limited wireless fronthaul capacity. In this paper, the problem of fronthaul-aware resource allocation and user scheduling is studied. To this end, a two-timescale fronthaul-aware SDN control mechanism is proposed in which the controller maximizes the time-averaged network throughput by enforcing a coarse correlated equilibrium in the long timescale. Subsequently, leveraging the controller's recommendations, each base station schedules its users using Lyapunov stochastic optimization in the short timescale, i.e., at each time slot. Simulation results show that significant network throughput enhancements and up to 40% latency reduction are achieved with the aid of the SDN controller. Moreover, the gains are more pronounced for denser network deployments.

One of the most promising approaches to overcoming the uncertainty of millimeter wave (mm-wave) communications is to deploy dual-mode small base stations (SBSs) that integrate both mm-wave and microwave (μW) frequencies. In this paper, a novel approach to analyzing and managing mobility in joint mmwave-μW networks is proposed. The proposed approach leverages device-level caching along with the capabilities of dual-mode SBSs to minimize handover failures and reduce inter-frequency measurement energy consumption. First, fundamental results on the caching capabilities are derived for the proposed dual-mode network scenario. Second, the impact of caching on the number of handovers (HOs), energy consumption, and the average handover failure (HOF) is analyzed. Then, the proposed cache-enabled mobility management problem is formulated as a dynamic matching game between mobile user equipments (MUEs) and SBSs. The goal of this game is to find a distributed HO mechanism that, under network constraints on HOFs and limited cache sizes, allows each MUE to choose between: 1) executing an HO to a target SBS; 2) being connected to the macrocell base station; or 3) perform a transparent HO by using the cached content. To solve this dynamic matching problem, a novel algorithm is proposed and its convergence to a two-sided dynamically stable HO policy for MUEs and target SBSs is proved. Numerical results corroborate the analytical derivations and show that the proposed solution will significantly reduce both the HOF and energy consumption of MUEs, resulting in an enhanced mobility management for heterogeneous wireless networks with mm-wave capabilities.

Proactive wireless caching and D2D communication have emerged as promising techniques for enhancing users' quality of service and network performance. In this paper, we propose a new architecture for D2D caching with inter- cluster cooperation. We study a cellular network in which users cache popular files and share them with other users either in their proximity via D2D communication or with remote users using cellular transmission. We characterize the network average delay per request from a queuing perspective. Specifically, we formulate the delay minimization problem and show that it is NP-hard. Furthermore, we prove that the delay minimization problem is equivalent to minimization of a non-increasing monotone supermodular function subject to a partition matroid constraint. A computationally efficient greedy algorithm is proposed which is proven to be locally optimal within a factor 2 of the optimum. Simulation results show more than 45% delay reduction compared to a D2D caching system without inter-cluster cooperation.

This paper addresses the problem of wireless resource scheduling in a vehicle-to-vehicle (V2V) communication network. The technical challenges lie in the fast changing network dynamics, namely, the channel quality and the data traffic variations. For a road segment covered by a road side unit (RSU), especially in a dense urban area, the vehicle density tends to be stable. The incoming service requests from the vehicle user equipment (VUE)-pairs compete with each other for the limited frequency resource in order to deliver data packets. Such competitions are regulated by the RSU via a sealed second-price auction at the beginning of scheduling slots. Each incumbent service request aims at maximizing the expected long-term payoff from bidding the frequency resource for packet transmissions. Markov perfect equilibrium (MPE) can be utilized to characterize the optimal competitive behaviors of the service requests. When the number of incumbent VUE-pairs becomes large, solving the MPE becomes infeasible. We adopt an oblivious equilibrium to approximate the MPE, which is theoretically proven to be error-bounded. The decision making process at each service request is hence transformed into a single-agent Markov decision process, for which we propose an on-line auction based learning scheme. Through simulation experiments, we show the potential performance gains from our proposed scheme, in terms of per-service request average utility.

In the commercial caching system, both Infrastructure Provider (InP), who owns the infrastructure and wireless network resource and Service Providers (SPs), who provide service to its users based on the virtual resource provided by the InP, are beneficial in leasing and renting the cache space. By partitioning the cache space at the BS into slices and leasing each partition to the SPs, the InP can receive a payment. Meanwhile, the SPs can serve their users with faster download service with local caching. However, both SPs and InP are selfish and want to maximize their own benefits. In addition, in practice, there is asymmetric information between SPs and InP. Thus, some SPs may declare inaccurate private information to get more cache space or less payment. To deal with these problems, in this paper, we propose an incentive mechanism based on contract theory, in which the InP, the employer, who designs and offers contracts to SPs, the employees. In particular, SPs are specified into types based on their valuation parameters and request rates. Different from the traditional contract model with two feasible contract conditions, we impose cache capacity constraints, which induces the interaction among SPs and makes the contract design more complicated. We propose an algorithm that achieves the optimal contract so that the InP can motivate SPs to participate into renting caching space while maximize its utility. Simulation results show that the proposed approach not only ensures no SP has incentive to select another contract but also outperforms the baseline allocation algorithm.

In this paper, the effective use of unmanned aerial vehicles (UAVs) as flying base stations that can provide wireless service to ground users is investigated. In particular, a novel framework for optimizing the performance of such UAV-based wireless systems, in terms of the average number of bits (data service) transmitted to users under flight time constraints, is proposed. In the considered model, UAVs are deployed over a given geographical area to serve ground users that are distributed within a given area based on an arbitrary spatial distribution function. In this case, based on the maximum possible flight times of the UAVs, the average data service delivered to the users is maximized by finding the optimal cell partitions associated to the UAVs, under a fair resource allocation scheme. To this end, using the powerful mathematical framework of optimal transport theory, a gradient-based algorithm is proposed for optimally partitioning the geographical area based on the users' distribution, flight times, and locations of the UAVs. Simulation results show that the proposed cell partitioning approach yields a significantly higher fairness among the users compared to the classical weighted Voronoi diagram. In particular, by using our approach, the Jain's fairness index is improved by a factor of 2.6.

Millimeter wave (mmW) communications at the 60 GHz unlicensed band is seen as a promising approach for boosting the capacity of wireless local area networks (WLANs). If properly integrated into legacy IEEE 802.11 standards, mmW communications can offer substantial gains by offloading traffic from congested sub-6 GHz unlicensed bands to the 60 GHz mmW frequency band. In this paper, a novel medium access control (MAC) is proposed to dynamically manage the WLAN traffic over the unlicensed mmW and sub-6 GHz bands. The proposed protocol leverages the capability of advanced multi-band wireless stations (STAs) to perform fast session transfers (FST) to the mmW band, while considering the intermittent channel at the 60 GHz band and the level of congestion observed over the sub-6 GHz bands. The performance of the proposed scheme is analytically studied via a new Markov chain model and the probability of transmissions over the mmW and sub-6 GHz bands, as well as the aggregated saturation throughput are derived. In addition, analytical results are validated by simulation results. Simulation results show that the proposed integrated mmW-sub 6 GHz MAC protocol yields significant performance gains, in terms of maximizing the saturation throughput and minimizing the delay experienced by the STAs. The results also shed light on the tradeoffs between the achievable gains and the overhead introduced by the FST procedure.

One of the most promising approaches to overcome the uncertainty and dynamic channel variations of millimeter wave (mmW) communications is to deploy dual-mode base stations that integrate both mmW and microwave (μW) frequencies. In particular, if properly designed, such dual-mode base stations can enhance mobility and handover in highly mobile wireless environments. In this paper, a novel approach for analyzing and managing mobility in joint μW-mmW networks is proposed. The proposed approach leverages device-level caching along with the capabilities of dual-mode base stations to minimize handover failures and provide seamless mobility. First, fundamental results on the caching capabilities, including caching probability and cache duration, are derived for the proposed dual-mode network scenario. Second, the average achievable rate of caching is derived for mobile users. Then, the impact of caching on the number of handovers (HOs) and the average handover failure (HOF) is analyzed. The derived analytical results suggest that content caching will reduce the HOF and enhance the mobility management in heterogeneous wireless networks with mmW capabilities. Numerical results corroborate the analytical derivations and show that the proposed solution provides significant reductions in the average HOF, reaching up to 45%, for mobile users moving with relatively high speeds.

In this paper, the use of multi-hop, device-to- device communications over millimeter wave (mmW) frequencies is studied for effective wearable communications. In particular, a problem of uplink communications is studied for a wearable network, in which each wearable device aims to form a multihop path over mmW to access a cellular base station, in order to overcome the high channel loss caused by mmW attenuation and blockage. To analyze the optimal selection of the uplink path, a network formation game is formulated between all wearable devices. In this game, each wearable device autonomously chooses the uplink path that maximizes its quality-of-service that captures the tradeoff between rate, delay, and privacy. To solve this game, a novel algorithm that combines best response dynamics with mixed-strategy techniques is proposed to find the mixed Nash network, which corresponds to a stable uplink structure at which no wearable device can improve its utility by changing its network formation decision. Simulation results show that the proposed game approach improves the average utility per wearable device of over 14% and 78%, respectively, compared with the direct transmission and the nearest next-hop schemes.

This paper investigates a cellular edge caching design under an extremely large number of small base stations (SBSs) and users. In this ultra-dense edge caching network (UDCN), SBS-user distances shrink, and each user can request a cached content from multiple SBSs. Unfortunately, the complexity of existing caching controls' mechanisms increases with the number of SBSs, making them inapphcable for solving the fundamental caching problem: How to maximize local caching gain while minimizing the replicated content caching? Furthermore, spatial dynamics of interference is no longer negligible in UDCNs due to the surge in interference. In addition, the caching control should consider temporal dynamics of user demands. To overcome such difficulties, we propose a novel caching algorithm weaving together notions of mean-field game theory and stochastic geometry. These enable our caching algorithm to become independent of the number of SBSs and users, while incorporating spatial interference dynamics as well as temporal dynamics of content popularity and storage constraints. Numerical evaluation validates the fact that the proposed algorithm reduces not only the long run average cost by at least 24% but also the number of replicated content by 56% compared to a popularity-based algorithm.

Fog computing is seen as a promising approach to perform distributed, low-latency computation for supporting Internet of Things applications. However, due to the unpredictable arrival of available neighboring fog nodes, the dynamic formation of a fog network can be challenging. In essence, a given fog node must smartly select the set of neighboring fog nodes that can provide low-latency computations. In this paper, this problem of fog network formation and task distribution is studied considering a hybrid cloud-fog architecture. The goal of the proposed framework is to minimize the maximum computational latency by enabling a given fog node to form a suitable fog network, under uncertainty on the arrival process of neighboring fog nodes. To solve this problem, a novel approach based on the online secretary framework is proposed. To find the desired set of neighboring fog nodes, an online algorithm is developed to enable a task initiating fog node to decide on which other nodes can be used as part of its fog network, to offload computational tasks, without knowing any prior information on the future arrivals of those other nodes. Simulation results show that the proposed online algorithm can successfully select an optimal set of neighboring fog nodes while achieving a latency that is as small as the one resulting from an ideal, offline scheme that has complete knowledge of the system. The results also show how, using the proposed approach, the computational tasks can be properly distributed between the fog network and a remote cloud server.

Machine-to-machine (M2M) communications consist of a large number of smart devices that communicate automatically without human intervention. The Third-Generation Partnership Project (3GPP) Long-Term Evolution (LTE) and LTE-Advanced (LTE-A), due to some features such as IP connectivity and scalability, are ready-to-use infrastructures for the M2M communications implementation. In the next generation of cellular networks with M2M devices, radio resource allocation is a major issue. In order to solve the issue, this paper addresses the efficient resource block (RB) allocation problem for different relay-aided cellular and M2M user equipments (UEs) to maximize the end-to-end data rate under different constraints of Single Carrier Frequency Division Multiple Access (SC-FDMA). The proposed solution also satisfies the maximum power budget, the minimum data rate and statistical QoS delay requirements for prioritizing different traffics under total power constraint. Numerical results demonstrate the effectiveness of the proposed scheme.

The proof-of-concept software-defined radio access network (RAN) is not flexible enough due to the inherent delay and the necessity of high-capacity fronthaul links. We are hence motivated to propose a hierarchical software-defined RAN architecture, over which the base stations (BSs) are abstracted into multiple virtual local controllers while these local controllers are administered by a high-level controller. Under such a hierarchical network architecture, we particularly investigate in this paper how to adapt the BS transmit power over a long term according to the network dynamics under the constraints of mobile user queue stability and limited fronthaul capacity. We first formulate an off-line stochastic power adaptation problem. Through developing the Lyapunov method, we transform the problem into an approximate on-line optimization task. However, the challenge arises from the introduced per-cluster fronthaul capacity constraint. To solve the task efficiently and avoid extensive information exchange between the high-level controller and the local controllers, we put forward a novel low-complexity algorithm by designing a non- cooperative power adaptation game among the local controllers. Simulations are provided to evaluate the efficacy of the proposed studies.

In this paper, the problem of uplink (UL) and downlink (DL) resource optimization, mode selection, and power allocation is studied for wireless cellular networks under the assumption of in-band full duplex base stations, non-orthogonal multiple access (NOMA) operation, and queue stability constraints. The problem is formulated as a network utility maximization problem for which a Lyapunov framework is used to decompose it into two disjoint subproblems of auxiliary variable selection and rate maximization. The latter is further decoupled into a user association and mode selection (UAMS) problem and a UL/DL power optimization (UDPO) problem that are solved concurrently. The UAMS problem is modeled as a many-to-one matching problem whose goal is to associate users to small cell base stations and select transmission mode (half-/full-duplex and orthogonal/NOMA). Then, an algorithm is proposed to solve the problem by finding a pairwise stable matching. Subsequently, the UDPO problem is formulated as a sequence of convex problems and is solved using the concave-convex procedure. Simulation results demonstrate that the proposed scheme is effective in allocating UL and DL power levels after dynamically selecting the operating mode and the served users, under different traffic intensity conditions, network density, and self-interference cancellation capability. The proposed scheme is shown to achieve up to 63% and 73% of gains in UL and DL packet throughput, and 21% and 17% in UL and DL cell edge throughput, respectively, compared with the existing baseline schemes.

Recently, millimeter-wave (mmWave) bands have been postulated as a means to accommodate the foreseen extreme bandwidth demands in vehicular communications, which result from the dissemination of sensory data to nearby vehicles for enhanced environmental awareness and improved safety level. However, the literature is particularly scarce in regards to principled resource allocation schemes that deal with the challenging radio conditions posed by the high mobility of vehicular scenarios. In this paper, we propose a novel framework that blends together matching theory and swarm intelligence to dynamically and efficiently pair vehicles and optimize both transmission and reception beamwidths. This is done by jointly considering channel state information and queue state information when establishing vehicle-to-vehicle (V2V) links. To validate the proposed framework, simulation results are presented and discussed, where the throughput performance as well as the latency/reliability tradeoffs of the proposed approach are assessed and compared with several baseline approaches recently proposed in the literature. The results obtained in this paper show performance gains of 25% in reliability and delay for ultra-dense vehicular scenarios with 50% more active V2V links than the baselines. These results shed light on the operational limits and practical feasibility of mmWave bands, as a viable radio access solution for future high-rate V2V communications.

Next-generation networks will be characterized by three key features:heterogeneity, in terms of technologies and services,dynamics, in terms of rapidly varying environments and uncertainty, andsize, in terms of the numbers of users, nodes, and services. The emergence of such large-scale and decentralized heterogeneous networks operating under dynamic and uncertain environments imposes new challenges in the design, analysis, and optimization of networks. The past decade has witnessed a confluence among the disciplines of networks, games, and economics, which has necessitated novel mathematical tools and designs that can truly remove the boundaries between these disciplines. In this context, advancing game-theoretic models and tailoring them towards the optimization and operation of future networked systems become pressing needs for our research community. The main goal of this IEEE JSAC Special Issue on “Game Theory for Networks” is to collect cutting-edge contributions that address and show the latest developments in game-theoretic models for emerging networking applications. The response of the community to the call has been overwhelming. We received a total of 120 submissions. We want to thank all the authors who submitted their works to this Special Issue. After a strict and selective review process, we accepted 40 papers and decided to publish two issues. Papers were selected based on their appropriateness for and relevance to the Special Issue as well as their technical merits. Unfortunately, a number of interesting papers did not make the cut because of the criteria set forth above and also due to the constraints on the total page count in a JSAC Special Issue. We hope that such interesting papers will find other venues for publication.

This is the second part of the IEEE JSAC Special Issue on “Game Theory for Networks.” The response of the community to the call has been overwhelming. We received a total of 120 submissions. We want to thank all the authors who submitted their works to this Special Issue. After a strict and selective review process, we accepted 40 papers and decided to publish two issues, each of 20 papers. The first one was published in February 2017. The papers of this second issue cover a wide selection of topics as follows.

We consider a multi-operator small cell network where mobile network operators are sharing a common pool of radio resources. The goal is to ensure long term fairness of spectrum sharing without coordination among small cell base stations. It is assumed that spectral allocation of the small cells is orthogonal to the macro network layer, and thus, only the small cell traffic is modeled. We develop a decentralized control mechanism for base stations using the Gibbs sampling based learning technique, which allocates a suitable amount of spectrum for each base station. Five algorithms are compared addressing co-primary multi-operator resource sharing under heterogeneous traffic requirements and the performance is assessed through extensive system-level simulations. The main performance metrics are user throughput and fairness between operators. The numerical results demonstrate that the proposed Gibbs sampling based learning algorithm provides about tenfold cell edge throughput gains compared to state-of-the-art algorithms, while ensuring fairness between operators.

The co-existence of small cell base stations (SBSs) with conventional macrocell base station is a promising approach to boost the capacity and coverage of cellular networks. However, densifying the network with a viral deployment of SBSs can significantly increase energy consumption. To reduce the reliance on unsustainable energy sources, one can adopt self-powered SBSs that rely solely on energy harvesting. Due to the uncertainty of energy arrival and the finite capacity of energy storage systems, self-powered SBSs must smartly optimize their ON and OFF schedule. In this paper, the problem of ON/OFF scheduling of self-powered SBSs is studied, in the presence of energy harvesting uncertainty with the goal of minimizing the operational costs consisting of energy consumption and transmission delay of a network. For the original problem, we show that an algorithm can solve the problem in the illustrative case. Then, to reduce the complexity of the original problem, an approximation is proposed. To solve the approximated problem, a novel approach based on the ski rental framework, a powerful online optimization tool, is proposed. Using this approach, each SBS can effectively decide on its ON/OFF schedule autonomously, without any prior information on future energy arrivals. By using competitive analysis, a deterministic online algorithm and a randomized online algorithm (ROA) are developed. The ROA is then shown to achieve the optimal competitive ratio in the approximation problem. Simulation results show that, compared with a baseline approach, the ROA can yield performance gains reaching up to 15.6% in terms of reduced total energy consumption of SBSs and up to 20.6% in terms of per-SBS network delay reduction. The results also shed light on the fundamental aspects that impact the ON time of SBSs while demonstrating that the proposed ROA can reduce up to 69.9% the total cost compared with a baseline approach.

In this paper, the efficient deployment and mobility of multiple unmanned aerial vehicles (UAVs), used as aerial base stations to collect data from ground Internet of Things (IoT) devices, are investigated. In particular, to enable reliable uplink communications for the IoT devices with a minimum total transmit power, a novel framework is proposed for jointly optimizing the 3D placement and the mobility of the UAVs, device-UAV association, and uplink power control. First, given the locations of active IoT devices at each time instant, the optimal UAVs' locations and associations are determined. Next, to dynamically serve the IoT devices in a time-varying network, the optimal mobility patterns of the UAVs are analyzed. To this end, based on the activation process of the IoT devices, the time instances at which the UAVs must update their locations are derived. Moreover, the optimal 3D trajectory of each UAV is obtained in a way that the total energy used for the mobility of the UAVs is minimized while serving the IoT devices. Simulation results show that, using the proposed approach, the total-transmit power of the IoT devices is reduced by 45% compared with a case, in which stationary aerial base stations are deployed. In addition, the proposed approach can yield a maximum of 28% enhanced system reliability compared with the stationary case. The results also reveal an inherent tradeoff between the number of update times, the mobility of the UAVs, and the transmit power of the IoT devices. In essence, a higher number of updates can lead to lower transmit powers for the IoT devices at the cost of an increased mobility for the UAVs.

In this paper, the effective use of flight-time constrained unmanned aerial vehicles (UAVs) as flying base stations that provide wireless service to ground users is investigated. In particular, a novel framework for optimizing the performance of such UAV-based wireless systems in terms of the average number of bits (data service) transmitted to users as well as the UAVs' hover duration (i.e. flight time) is proposed. In the considered model, UAVs hover over a given geographical area to serve ground users that are distributed within the area based on an arbitrary spatial distribution function. In this case, two practical scenarios are considered. In the first scenario, based on the maximum possible hover times of UAVs, the average data service delivered to the users under a fair resource allocation scheme is maximized by finding the optimal cell partitions associated to the UAVs. Using the powerful mathematical framework of optimal transport theory, this cell partitioning problem is proved to be equivalent to a convex optimization problem. Subsequently, a gradient-based algorithm is proposed for optimally partitioning the geographical area based on the users' distribution, hover times, and locations of the UAVs. In the second scenario, given the load requirements of ground users, the minimum average hover time that the UAVs need for completely servicing their ground users is derived. To this end, first, an optimal bandwidth allocation scheme for serving the users is proposed. Then, given this optimal bandwidth allocation, optimal cell partitions associated with the UAVs are derived by exploiting the optimal transport theory. Simulation results show that our proposed cell partitioning approach leads to a significantly higher fairness among the users compared with the classical weighted Voronoi diagram. Furthermore, the results demonstrate that the average hover time of the UAVs can be reduced by 64% by adopting the proposed optimal bandwidth allocation scheme as well as the optimal cell partitioning approach. In addition, our results reveal an inherent tradeoff between the hover time of UAVs and bandwidth efficiency while serving the ground users.

One of the many problems faced by current cellular network technology is the underutilization of the dedicated licensed spectrum of network operators. An emerging paradigm to solve this issue is to allow multiple operators to share some parts of each other's spectrum. Previous works on spectrum sharing have failed to integrate the theoretical insights provided by recent developments in stochastic geometrical approaches to cellular network analysis with the objectives of network resource allocation problems. In this paper, we study the non-orthogonal spectrum assignment with the goal of maximizing the social welfare of the network, defined as the expected weighted sum rate of the operators. We adopt the many-to-one stable matching game framework to tackle this problem. Moreover, using the stochastic geometrical approach, we show that its solution can be both stable as well as socially optimal. To obtain the maxima of social welfare, the computation of the game theoretical solution using the generic Markov Chain Monte Carlo method is proposed. We also investigate the role of power allocation schemes using Q-learning, and we numerically show that the effect of resource allocation scheme is much more significant than the effect of power allocation for the social welfare of the system.

The use of dual-mode base stations that can jointly exploit millimeter wave (mmW) and microwave (μW) resources is a promising solution for overcoming the uncertainty of the mmW environment. In this paper, a novel dual-mode scheduling framework is proposed that jointly performs user applications (UAs) selection and scheduling over μW and mmW bands. The proposed scheduling framework allows multiple UAs to run simultaneously on each user equipment (UE) and utilizes a set of context information, including the channel state information per UE, the delay tolerance and required load per UA, and the uncertainty of mmW channels, to maximize the quality-of-service (QoS) per UA. The dual-mode scheduling problem is then formulated as an optimization problem with minimum unsatisfied relations problem, which is shown to be challenging to solve. Consequently, a long-term scheduling framework, consisting of two stages, is proposed. Within this framework, first, the joint UA selection and scheduling over the μW band is formulated as a one-to-many matching game between the μW resources and UAs. To solve this problem, a novel scheduling algorithm is proposed and shown to yield a two-sided stable resource allocation. Second, over the mmW band, the joint contextaware UA selection and scheduling problem is formulated as a 0-1 Knapsack problem and a novel algorithm that builds on the Q-learning algorithm is proposed to find a suitable mmW scheduling policy while adaptively learning the UEs' line-of-sight probabilities. Furthermore, it is shown that the proposed scheduling framework can find an effective scheduling solution, over both μW and mmW, in polynomial time. Simulation results show that, compared with conventional scheduling schemes, the proposed approach significantly increases the number of satisfied UAs while improving the statistics of QoS violations and enhancing the overall users' quality-of-experience.

In this paper, a novel framework is proposed for optimizing the operation and performance of a large-scale multi-hop millimeter wave (mmW) backhaul within a wireless small cell network having multiple mobile network operators (MNOs). The proposed framework enables the small base stations to jointly decide on forming the multi-hop, mmW links over backhaul infrastructure that belongs to multiple, independent MNOs, while properly allocating resources across those links. In this regard, the problem is addressed using a novel framework based on matching theory composed of two, highly inter-related stages: a multi-hop network formation stage and a resource management stage. One unique feature of this framework is that it jointly accounts for both wireless channel characteristics and economic factors during both network formation and resource management. The multi-hop network formation stage is formulated as a one-to-many matching game, which is solved using a novel algorithm, that builds on the so-called deferred acceptance algorithm and is shown to yield a stable and Pareto optimal multi-hop mmW backhaul network. Then, a one-to-many matching game is formulated to enable proper resource allocation across the formed multi-hop network. This game is then shown to exhibit peer effects and, as such, a novel algorithm is developed to find a stable and optimal resource management solution that can properly cope with these peer effects. Simulation results show that, with manageable complexity, the proposed framework yields substantial gains, in terms of the average sum rate, reaching up to 27% and 54%, respectively, compared with a non-cooperative scheme in which inter-operator sharing is not allowed and a random allocation approach. The results also show that our framework improves the statistics of the backhaul sum rate and provides insights on how to manage pricing and the cost of the cooperative mmW backhaul network for the MNOs.

We study the problem of joint load balancing and interference mitigation in heterogeneous networks in which massive multiple-input multiple-output macro cell base station (BS) equipped with a large number of antennas, overlaid with wireless self-backhauled small cells (SCs), is assumed. Self-backhauled SC BSs with full-duplex communication employing regular antenna arrays serve both macro users and SC users by using the wireless backhaul from macro BS in the same frequency band. We formulate the joint load balancing and interference mitigation problem as a network utility maximization subject to wireless backhaul constraints. Subsequently, leveraging the framework of stochastic optimization, the problem is decoupled into dynamic scheduling of macro cell users, backhaul provisioning of SCs, and offloading macro cell users to SCs as a function of interference and backhaul links. Via numerical results, we show the performance gains of our proposed framework under the impact of SCs density, number of BS antennas, and transmit power levels at low and high frequency bands. It is shown that our proposed approach achieves a 5.6 times gain in terms of cell-edge performance as compared with the closed-access baseline in ultra-dense networks with 350 SC BSs per km2.

Broadband wireless communication is of critical importance during public safety scenarios as it facilitates situational awareness capabilities for first responders and victims. In this paper, the use of LTE-Unlicensed (LTE-U) technology for unmanned aerial base stations (UABSs) is investigated as an effective approach to enhance the achievable broadband throughput during emergency situations by utilizing the unlicensed spectrum. In particular, we develop a game theoretic framework for load balancing between LTE-U UABSs and WiFi access points (APs), based on the users' link qualities as well as the loads at the UABSs and the ground APs. To solve this game, we propose a regret-based learning (RBL) dynamic duty cycle selection (DDCS) method for configuring the transmission gaps in LTE-U UABSs, to ensure a satisfactory throughput for all users. Simulation results show that the proposed RBL-DDCS yields an improvement of 32% over fixed duty cycle LTE-U transmission, and an improvement of 10% over Q-learning based DDCS.

In this paper, the optimal trajectory and deployment of multiple unmanned aerial vehicles (UAVs), used as aerial base stations to collect data from ground Internet of Things (IoT) devices, is investigated. In particular, to enable reliable uplink communications for IoT devices with a minimum energy consumption, a new approach for optimal mobility of the UAVs is proposed. First, given a fixed ground IoT network, the total transmit power of the devices is minimized by properly clustering the IoT devices with each cluster being served by one UAV. Next, to maintain energy-efficient communications in time-varying mobile IoT networks, the optimal trajectories of the UAVs are determined by exploiting the framework of optimal transport theory. Simulation results show that by using the proposed approach, the total transmit power of IoT devices for reliable uplink communications can be reduced by 56% compared to the fixed Voronoi deployment method. Moreover, our results yield the optimal paths that will be used by UAVs to serve the mobile IoT devices with a minimum energy consumption.

This article investigates the mobility management of an ultra dense cellular network (UDN) from an energy-efficiency (EE) point of view. Many dormant base stations (BSs) in a UDN do not transmit signals, and thus a received power based handover (HO) approach as in traditional cellular networks is hardly applicable. In addition, the limited front/backhaul capacity compared to a huge number of BSs makes it difficult to implement a centralized HO and power control. For these reasons, a novel user-centric association rule is proposed, which jointly optimizes HO and power control for maximizing EE. The proposed mobility management is able to cope not only with the spatial randomness of user movement but also with temporally correlated wireless channels. The proposed approach is implemented over a HO time window and tractable power con- trol policy by exploiting mean-field game (MFG) and stochastic geometry (SG). Compared to a baseline with a fixed HO interval and transmit power, the proposed approach achieves the 1.2 times higher long-term average EE at a typical active BS.

This article investigates the performance of an ultra-dense network (UDN) from an energy-efficiency (EE) standpoint leveraging the interplay between stochastic geometry (SG) and mean-field game (MFG) theory. In this setting, base stations (BSs) (resp. users) are uniformly distributed over a two-dimensional plane as two independent homogeneous Poisson point processes (PPPs), where users associate to their nearest BSs. The goal of every BS is to maximize its own energy efficiency subject to channel uncertainty, random BS location, and interference levels. Due to the coupling in interference, the problem is solved in the mean-field (MF) regime where each BS interacts with the whole BS population via time- varying MF interference. As a main contribution, the asymptotic convergence of MF interference to zero is rigorously proved in a UDN with multiple transmit antennas. It allows us to derive a closed-form EE representation, yielding a tractable EE optimal power control policy. This proposed power control achieves more than 1.5 times higher EE compared to a fixed power baseline.

The integration of millimeter-wave base stations (mmW-BSs) with conventional microwave base stations (μW-BSs) is a promising solution for enhancing the quality-of-service (QoS) of emerging 5G networks. However, the significant differences in the signal propagation characteristics over the mmW and μW frequency bands will require novel cell association schemes cognizant of both mmW and μW systems. In this paper, a novel cell association framework is proposed that considers both the blockage probability and the achievable rate to assign user equipments (UEs) to mmW-BSs or μW-BSs. The problem is formulated as a one-to-many matching problem with minimum quota constraints for the BSs that provides an efficient way to balance the load over the mmW and μW frequency bands. To solve the problem, a distributed algorithm is proposed that is guaranteed to yield a Pareto optimal and two-sided stable solution. Simulation results show that the proposed matching with minimum quota (MMQ) algorithm outperforms the conventional max-RSSI and max-SINR cell association schemes. In addition, it is shown that the proposed MMQ algorithm can effectively balance the number of UEs associated with the μW-BSs and mmW-BSs and achieve further gains, in terms of the average sum rate.

In this paper, the problem of optimized beam alignment for wearable device-to-device (D2D) communications over millimeter wave (mmW) frequencies is studied. In particular, a noncooperative game is formulated between wearable communication pairs that engage in D2D communications. In this game, wearable devices acting as transmitters autonomously select the directions of their beams so as to maximize the data rate to their receivers. To solve the game, an algorithm based on best response dynamics is proposed that allows the transmitters to reach a Nash equilibrium in a distributed manner. To further improve the performance of mmW D2D communications, a novel quantum game model is formulated to enable the wearable devices to exploit new quantum directions during their beam alignment so as to further enhance their data rate. Simulation results show that the proposed game-theoretic approach improves the performance, in terms of data rate, of about 75% compared to a uniform beam alignment. The results also show that the quantum game model can further yield up to 20% improvement in data rates, relative to the classical game approach.

The viral and dense deployment of small cell base stations (SBSs) will lie at the heart of 5G cellular networks. However, such dense networks can consume a significant amount of energy. In order to reduce the network's reliance on unsustainable energy sources, one can deploy self-powered SBSs that rely solely on energy harvesting. Due to the uncertainty of energy arrival and the finite capacity of energy storage systems, self-powered SBSs must smartly schedule their ON and OFF operation. In this paper, the problem of ON/OFF scheduling of self-powered SBSs is studied in the presence of energy harvesting uncertainty with the goal of minimizing the tradeoff between power consumption and flow-level delay. To solve this problem, a novel approach based on the ski rental framework, a powerful online optimization tool, is proposed. To find the desired solution of the ski rental problem, a randomized online algorithm is developed to enable each SBS to autonomously decide on its ON/OFF schedule, without knowing any prior information on future energy arrivals. Simulation results show that the proposed algorithm can reduce power consumption and delay over a given time period compared to a baseline that turns SBSs ON by using an energy threshold. The results show that this performance gain can reach up to 12.7% reduction of the total cost. The results also show that the proposed algorithm can eliminate up to 72.5% of the ON/OFF switching overhead compared to the baseline approach.

In this paper, the optimal deployment of multiple unmanned aerial vehicles (UAVs) acting as flying base stations is investigated. Considering the downlink scenario, the goal is to minimize the total required transmit power of UAVs while satisfying the users' rate requirements. To this end, the optimal locations of UAVs as well as the cell boundaries of their coverage areas are determined. To find those optimal parameters, the problem is divided into two sub-problems that are solved iteratively. In the first sub-problem, given the cell boundaries corresponding to each UAV, the optimal locations of the UAVs are derived using the facility location framework. In the second sub-problem, the locations of UAVs are assumed to be fixed, and the optimal cell boundaries are obtained using tools from optimal transport theory. The analytical results show that the total required transmit power is significantly reduced by determining the optimal coverage areas for UAVs. These results also show that, moving the UAVs based on users' distribution, and adjusting their altitudes can lead to a minimum power consumption. Finally, it is shown that the proposed deployment approach, can improve the system's power efficiency by a factor of 20 χ compared to the classical Voronoi cell association technique with fixed UAVs locations.

Wireless caching has been used to improve network performance and reduce bandwidth and energy consumption. In this paper, we study the issue of joint admission control and content caching for wireless access points with energy harvesting capability. Given limited energy supply, the access points, in a competitive environment, aim to maximize their payoff defined in terms of revenue by optimizing their admission control and content caching policy. Moreover, the throughput of the content transmission by the access point has to be maintained above a certain threshold. Thus, we propose a constrained stochastic game to model this competitive caching scenario. The equilibrium policy, which is a mapping from the energy, cache, and demand states to the action, is obtained from the model. From the performance evaluation, the joint admission control and content caching policy can achieve significantly better performance than that of the baseline schemes, especially when the energy harvesting rate becomes constricted.

In this paper, we study a problem where multiple operators (OPs) need to share a common pool of spectrum with each other. Our objective is to maximize the social welfare, defined as the overall weighted sum rate of the OPs. The problem is decomposed into two parts: the first part is to allocate RBs to OPs, which we do so by extending the framework of many-to-one matching game with externalities. The second part is to allocate power of small cell base stations (SBSs) belonging to each OP, which is accomplished using reinforcement learning. Assuming that the SBSs associated with each OPs are spatially distributed according to Poisson point process (PPP), we show that pairwise stable matchings achieve local maximas of the social welfare function. We propose two algorithms to search for the stable matchings. Simulation results show that these algorithms are well behaved in terms of convergence and efficiency of the solutions.

One of the most promising approaches to overcome the drastic channel variations of millimeter wave (mmW) communications is to deploy dual-mode base stations that integrate both mmW and microwave (pW) frequencies. Reaping the benefits of a dual-mode operation requires scheduling mechanisms that can allocate resources efficiently and jointly at both frequency bands. In this paper, a novel resource allocation framework is proposed that exploits users' context, in terms of user application (UA) delay requirements, to maximize the quality-of-service (QoS) of a dual-mode base station. In particular, such a context-aware approach enables the network to dynamically schedule UAs, instead of users, thus providing more precise delay guarantees and a more efficient exploitation of the mmW resources. The scheduling of UAs is formulated as a one-to-many matching problem between UAs and resources and a novel algorithm is proposed to solve it. The proposed algorithm is shown to converge to a two-sided stable matching between UAs and network resources. Simulation results show that the proposed approach outperforms classical CSI-based scheduling in terms of the per UA QoS, yielding up to 36% improvement. The results also show that exploiting mmW resources provides significant traffic offloads reaching up to 43% from μW band.

The ever increasing video demands from mobile users have posed great challenges to cellular networks. To address this issue, video caching in radio access networks (RANs) has been recognized as one of the enabling technologies in future 5G mobile networks, which brings contents near the end-users, reducing the transmission cost of duplicate contents, meanwhile increasing the Quality-of-Experience (QoE) of users. Inspired by the emerging software-defined networking technology, recent proposals have employed centralized collaborative caching among cells to further increase the caching capacity of the RAN. In this paper, we explore a new dimension in video caching in software-defined RANs to expand its capacity. We enable the controller with the capability to adaptively select the bitrates of videos received by users, in order to maximize the number and quality of video requests that can be served, meanwhile minimizing the transmission cost. To achieve this, we further incorporate Scalable Video Coding (SVC), which enables caching and serving sliced video layers that can serve different bitrates. We formulate the problem of joint video caching and scheduling as a reward maximization (cost minimization) problem. Based on the formulation, we further propose a 2-stage rounding-based algorithm to address the problem efficiently. Simulation results show that using SVC with collaborative caching greatly improves the cache capacity and the QoE of users.

A two-tier heterogeneous cellular network (HCN) with intra-tier and inter-tier dependence is studied. The macro cell deployment follows a Poisson point process (PPP) and two different clustered point processes are used to model the cache-enabled small cells. Under this model, we derive approximate expressions in terms of finite integrals for the average delivery rate considering inter-tier and intra-tier dependence. On top of the fact that cache size drastically improves the performance of small cells in terms of average delivery rate, we show that rate splitting of limited-backhaul induces non-linear performance variations, and therefore has to be adjusted for rate fairness among users of different tiers.

In order to cope with the phenomenal growth of mobile data traffic, unlicensed spectrum can be utilized by the Long Term Evolution (LTE) cellular systems. However, ensuring fair coexistence with WiFi is a mandatory requirement. In one approach, periodically configurable transmission gaps can be used to facilitate a coexistence between WiFi and LTE. In this paper, a Multi-Armed Bandit (MAB) based dynamic duty cycle selection method is proposed for configuration of transmission gaps ensuring a better coexistence for both technologies. Then the concept is further strengthened with downlink power control mechanism using the same algorithm leading to a high energy efficiency and interference reduction. Performance results are given for different user equipment and WiFi station densities in which it is shown that significant improvements in overall throughput and energy efficiency can be achieved.

In this paper, a novel approach for joint power control and user scheduling is proposed for optimizing energy efficiency (EE), in terms of bits per unit energy, in ultra dense small cell networks (UDNs). Due to severe coupling in interference, this problem is formulated as a dynamic stochastic game (DSG) between small cell base stations (SBSs). This game enables capturing the dynamics of both the queues and channel states of the system. To solve this game, assuming a large homogeneous UDN deployment, the problem is cast as a mean-field game (MFG) in which the MFG equilibrium is analyzed with the aid of low-complexity tractable partial differential equations. Exploiting the stochastic nature of the problem, user scheduling is formulated as a stochastic optimization problem and solved using the drift plus penalty (DPP) approach in the framework of Lyapunov optimization. Remarkably, it is shown that by weaving notions from Lyapunov optimization and mean-field theory, the proposed solution yields an equilibrium control policy per SBS, which maximizes the network utility while ensuring users' quality-of-service. Simulation results show that the proposed approach achieves up to 70.7% gains in EE and 99.5% reductions in the network's outage probabilities compared to a baseline model, which focuses on improving EE while attempting to satisfy the users' instantaneous quality-of-service requirements.

In this paper, the deployment of an unmanned aerial vehicle (UAV) as a flying base station used to provide the fly wireless communications to a given geographical area is analyzed. In particular, the coexistence between the UAV, that is transmitting data in the downlink, and an underlaid device-to-device (D2D) communication network is considered. For this model, a tractable analytical framework for the coverage and rate analysis is derived. Two scenarios are considered: a static UAV and a mobile UAV. In the first scenario, the average coverage probability and the system sum-rate for the users in the area are derived as a function of the UAV altitude and the number of D2D users. In the second scenario, using the disk covering problem, the minimum number of stop points that the UAV needs to visit in order to completely cover the area is computed. Furthermore, considering multiple retransmissions for the UAV and D2D users, the overall outage probability of the D2D users is derived. Simulation and analytical results show that, depending on the density of D2D users, the optimal values for the UAV altitude, which lead to the maximum system sum-rate and coverage probability, exist. Moreover, our results also show that, by enabling the UAV to intelligently move over the target area, the total required transmit power of UAV while covering the entire area, can be minimized. Finally, in order to provide full coverage for the area of interest, the tradeoff between the coverage and delay, in terms of the number of stop points, is discussed.

In this paper, a novel cluster-based approach for maximizing the energy efficiency of wireless small cell networks is proposed. A dynamic mechanism is proposed to locally group coupled small cell base stations (SBSs) into clusters based on location and traffic load. Within each formed cluster, SBSs coordinate their transmission parameters to minimize a cost function, which captures the tradeoffs between energy efficiency and flow level performance, while satisfying their users' quality-of-service requirements. Due to the lack of intercluster communications, clusters compete with one another to improve the overall network's energy efficiency. This intercluster competition is formulated as a noncooperative game between clusters that seek to minimize their respective cost functions. To solve this game, a distributed learning algorithm is proposed using which clusters autonomously choose their optimal transmission strategies based on local information. It is shown that the proposed algorithm converges to a stationary mixed-strategy distribution, which constitutes an epsilon-coarse correlated equilibrium for the studied game. Simulation results show that the proposed approach yields significant performance gains reaching up to 36% of reduced energy expenditures and upto 41% of reduced fractional transfer time compared to conventional approaches.

Power consumption analysis is the first step in the process of dimensioning the cell size for any mobile network. Therefore, improving power utilization emerges as one of the major challenges to the 3rd Generation Partnership Project (3GPP) Long-Term Evolution (LTE) Release 12 coordinated multipoint (CoMP) transmission and reception scheme. This paper proposes new models for heterogeneous deployment of CoMP macrocells overlaid with the emerging neighborhood femtocell network in order to meet the power efficiency requirements. Two case studies are mathematically analyzed: Firstly, neighborhood femtocells are allocated at the macrocell edge line in order to reduce the ultimate range of CoMP transmission while coverage is extended using low power femtocell transmissions. Secondly, femtocells are deployed at selected CoMP intra-cell regions in order to improve neighborhood coverage; transmissions are coupled between femtocells and CoMP to provide the necessary converge across the cell area and transfer connections from macrocell to low power femtocells. A comparative study is performed to show the power efficiency obtained through scaling the network area at both cell-edge and sub-cell areas. The analysis show new strategies for deploying small cells under CoMP macrocell umbrella in order to minimize the power consumption figures compared to only macrocell based network.

The use of drone small cells (DSCs) which are aerial wireless base stations that can be mounted on flying devices such as unmanned aerial vehicles (UAVs), is emerging as an effective technique for providing wireless services to ground users in a variety of scenarios. The efficient deployment of such DSCs while optimizing the covered area is one of the key design challenges. In this paper, considering the low altitude platform (LAP), the downlink coverage performance of DSCs is investigated. The optimal DSC altitude which leads to a maximum ground coverage and minimum required transmit power for a single DSC is derived. Furthermore, the problem of providing a maximum coverage for a certain geographical area using two DSCs is investigated in two scenarios; interference free and full interference between DSCs. The impact of the distance between DSCs on the coverage area is studied and the optimal distance between DSCs resulting in maximum coverage is derived. Numerical results verify our analytical results on the existence of optimal DSCs altitude/separation distance and provide insights on the optimal deployment of DSCs to supplement wireless network coverage.

In this paper, a novel approach for joint power control and user scheduling is proposed for optimizing energy efficiency (EE), in terms of bits per unit power, in ultra dense small cell networks (UDNs). To address this problem, a dynamic stochastic game (DSG) is formulated between small cell base stations (SBSs). This game enables to capture the dynamics of both the queues and channel states of the system. To solve this game, assuming a large homogeneous UDN deployment, the problem is cast as a mean field game (MFG) in which the MFG equilibrium is analyzed with the aid of low-complexity tractable two partial differential equations. User scheduling is formulated as a stochastic optimization problem and solved using the drift plus penalty (DPP) approach in the framework of Lyapunov optimization. Remarkably, it is shown that by weaving notions from Lyapunov optimization and mean field theory, the proposed solution yields an equilibrium control policy per SBS which maximizes the network utility while ensuring users' quality-of-service. Simulation results show that the proposed approach achieves up to 18.1% gains in EE and 98.2% reductions in the network's outage probabilities compared to a baseline model.

Caching multimedia files at the network edge has been identified as a key technology for enhancing users' quality-of-service (QoS), while reducing redundant transmissions over capacity-constrained backhauls. Nevertheless, in small cell networks, the efficiency of a caching policy depends on the ability of small base stations (SBSs) to anticipate the requests from the user equipments (UEs). In this paper, we propose a collaborative filtering (CF) scheme for estimating the required backhaul usage at each SBS, by mining the cacheability of UEs' file requests. In the proposed approach, each SBS has a two-fold objective: update the bandwidth allocation based on the estimated backhaul utilization, and, given the current bandwidth availability, identify which UEs to service. We formulate the problem as a one-to many matching game between SBSs and UEs, and we propose a novel cache-aware user association algorithm that minimizes the backhaul usage at each SBS, subject to individual QoS requirements. Simulation results, based on real-world service request logs, have shown that the proposed CF-based solution can yield significant gains in terms of backhaul efficiency and cache hit-ratio, reaching up to 25%, with a maximum gap of 9% to an optimal cache-aware association technique.

Designing cost-effective and scalable backhaul solutions is one of the main challenges for emerging wireless small cell networks (SCNs). In this regard, millimeter wave (mmW) communication technologies have recently emerged as an attractive solution to realize the vision of a high-speed and reliable wireless small cell backhaul network (SCBN). In this paper, a novel approach is proposed for managing the spectral resources of a heterogeneous SCBN that can exploit simultaneously mmW and conventional frequency bands via carrier aggregation. In particular, a new SCBN model is proposed in which small cell base stations (SCBSs) equipped with broadband fiber backhaul allocate their frequency resources to SCBSs with wireless backhaul, by using aggregated bands. One unique feature of the studied model is that it jointly accounts for both wireless channel characteristics and economic factors during resource allocation. The problem is then formulated as a one-to-many matching game and a distributed algorithm is proposed to find a stable outcome of the game. The convergence of the algorithm is proven and the properties of the resulting matching are studied. Simulation results show that under the constraints of wireless backhauling, the proposed approach achieves substantial performance gains, reaching up to 30% compared to a conventional best-effort approach.

Mobile data offloading has been introduced to alleviate the congestion of cellular networks and to improve the quality of service for mobile end users. This paper presents a distributed mechanism for mobile data offloading in software defined network (SDN) at the network edge. In SDN, the data traffic of base stations (BSs) can be dynamically offloaded to access points (APs), which is enabled by the SDN controller. The SDN controller formulates a revenue maximization problem to optimize the data offloading decision, and solves the problem in a fully distributed fashion. The proposed mechanism is based on the proximal Jacobian multi-block alternating direction method of multipliers (ADMM). BSs and APs perform the offloading decision update concurrently, and are coordinated by the SDN controller through dual variables to reach a consensus on the offloading demand and supply. Numerical simulations validate the effectiveness of the proposed algorithm.

The use of small cell deployments in heterogeneous network (HetNet) environments is expected to be a key feature of 4G networks and beyond, and essential for providing higher user throughput and cell-edge coverage. However, due to different coverage sizes of macro and pico base stations (BSs), such a paradigm shift introduces additional requirements and challenges in dense networks. Among these challenges is the handover performance of user equipment (UEs), which will be impacted especially when high velocity UEs traverse picocells. In this paper, we propose a coordination-based and context-aware mobility management (MM) procedure for small cell networks using tools from reinforcement learning. Here, macro and pico BSs jointly learn their long-term traffic loads and optimal cell range expansion, and schedule their UEs based on their velocities and historical rates (exchanged among tiers). The proposed approach is shown to not only outperform the classical MM in terms of UE throughput, but also to enable better fairness. In average, a gain of up to 80% is achieved for UE throughput, while the handover failure probability is reduced up to a factor of three by the proposed learning based MM approaches.

Locally caching contents at the network edge constitutes one of the most disruptive approaches in 5G wireless networks. Reaping the benefits of edge caching hinges on solving a myriad of challenges such as how, what and when to strategically cache contents subject to storage constraints, traffic load, unknown spatio-temporal traffic demands and data sparsity. Motivated by this, we propose a novel transfer learning-based caching procedure carried out at each small cell base station. This is done by exploiting the rich contextual information (i.e., users' content viewing history, social ties, etc.) extracted from device-to-device (D2D) interactions, referred to as source domain. This prior information is incorporated in the so-called target domain where the goal is to optimally cache strategic contents at the small cells as a function of storage, estimated content popularity, traffic load and backhaul capacity. It is shown that the proposed approach overcomes the notorious data sparsity and cold-start problems, yielding significant gains in terms of users' quality-of-experience (QoE) and backhaul offloading, with gains reaching up to 22% in a setting consisting of four small cell base stations.

The articles in this special issue focus on recent advances in the field of heterogeneous cellular networking.

To tackle the challenge of providing higher data rates within limited spectral resources we consider the case of multiple operators sharing a common pool of radio resources. Four algorithms are proposed to address co-primary multi-operator radio resource sharing under heterogeneous traffic in both centralized and distributed scenarios. The performance of these algorithms is assessed through extensive system-level simulations for two indoor small cell layouts. It is assumed that the spectral allocations of the small cells are orthogonal to the macro network layer and thus, only the small cell traffic is modeled. The main performance metrics are user throughput and the relative amount of shared spectral resources. The numerical results demonstrate the importance of coordination among co-primary operators for an optimal resource sharing. Also, maximizing the spectrum sharing percentage generally improves the achievable throughput gains over non-sharing.

In this paper, a novel approach for optimizing resource allocation in wireless small cell networks (SCNs) with device-to-device (D2D) communication is proposed. The proposed approach allows jointly exploiting the wireless and social context of wireless users for optimizing the overall allocation of resources and improving the traffic offload in SCNs. This context-aware resource allocation problem is formulated as a matching game, in which user equipments (UEs) and resource blocks (RBs) rank one another, based on utility functions that capture both wireless and social metrics. Due to social interrelations, this game is shown to belong to a class of matching games with peer effects. To solve this game, a novel self-organizing algorithm is proposed, using which UEs and RBs can interact to decide on their desired allocation. The proposed algorithm is then proven to converge to a two-sided stable matching between UEs and RBs. The properties of the resulting stable outcome are then studied and assessed. Simulation results using real social data show that clustering of socially connected users allows offloading a substantially larger amount of traffic than the conventional context-unaware approach. These results show that exploiting social context has high practical relevance in saving resources on wireless links and in the backhaul.

Wi-Fi, small cells and macrocell networks serve users with different advantages and drawbacks. In this paper, we propose a multi-leader multi-follower Stackelberg game between these three types of networks and mobile users. In the multi-leader game, each network first sets the optimal price according to the behaviors of the other networks and the prediction of each mobile user's optimal strategies. Subsequently, mobile users choose their optimal network, accordingly. In the proposed game, there exists a Stackelberg equilibrium between the leader level and the follower level, and two Nash Equilibria within leaders and within followers, respectively. This fact differentiates the proposed work from most existing literature. Simulation results show that the proposed approach yields high social welfare at the equilibrium.

The deployment of small cells, overlaid on existing cellular infrastructure, is seen as a key feature in next-generation cellular systems. In this paper, the problem of user association in the downlink of small cell networks (SCNs) is considered. The problem is formulated as a many-to-one matching game in which the users and SCBSs rank one another based on utility functions that account for both the achievable performance, in terms of rate and fairness to cell edge users, as captured by newly proposed priorities. To solve this game, a novel distributed algorithm that can reach a stable matching is proposed. Simulation results show that the proposed approach yields an average utility gain of up to 65% compared to a common association algorithm that is based on received signal strength. Compared to the classical deferred acceptance algorithm, the results also show a 40% utility gain and a more fair utility distribution among the users.

The design of energy-efficient mechanisms is one of the key challenges in emerging wireless small cell networks. In this paper, a novel approach for opportunistically switching ON/OFF base stations to improve the energy efficiency in wireless small cell networks is proposed. The proposed approach enables the small cell base stations to optimize their downlink performance while balancing the load among each another, while satisfying their users' quality-of-service requirements. The problem is formulated as a noncooperative game among the base stations that seek to minimize a cost function which captures the tradeoff between energy expenditure and load. To solve this game, a distributed learning algorithm is proposed using which the base stations autonomously choose their optimal transmission strategies. Simulation results show that the proposed approach yields significant performance gains in terms of reduced energy expenditures up to 23% and reduced load up to 40% compared to conventional approaches.

Anticipating multimedia file requests via caching at the small cell base stations (SBSs) of a cellular network has emerged as a promising technique for optimizing the quality of service (QoS) of wireless user equipments (UEs). However, developing efficient caching strategies must properly account for specific small cell constraints, such as backhaul congestion and limited storage capacity. In this paper, we address the problem of devising a user-cell association, in which the SBSs exploit caching capabilities to overcome the backhaul capacity limitations and enhance the users' QoS. In the proposed approach, the SBSs individually decide on which UEs to service based on both content availability and on the data rates they can deliver, given the interference and backhaul capacity limitations. We formulate the problem as a one-to-many matching game between SBSs and UEs. To solve this game, we propose a distributed algorithm, based on the deferred acceptance scheme, that enables the players (i.e., UEs and SBSs) to self-organize into a stable matching, in a reasonable number of algorithm iterations. Simulation results show that the proposed cell association scheme yields significant gains, reaching up to 21% improvement compared to a traditional cell association techniques with no caching considerations.

The deployment of underlay small base stations (SBSs) is expected to significantly boost the spectrum efficiency and the coverage of next-generation cellular networks. However, the coexistence of SBSs underlaid to a macro-cellular network faces important challenges, notably in terms of spectrum sharing and interference management. In this paper, we propose a novel game-theoretic model that enables the SBSs to optimize their transmission rates by making decisions on the resource occupation jointly in the frequency and spatial domains. This procedure, known as interference draining, is performed among cooperative SBSs and allows to drastically reduce the interference experienced by both macro- and small cell users. At the macrocell side, we consider a modified water-filling policy for the power allocation that allows each macrocell user (MUE) to focus the transmissions on the degrees of freedom over which the MUE experiences the best channel and interference conditions. This approach not only represents an effective way to decrease the received interference at the MUEs but also grants the SBS tier additional transmission opportunities and allows for a more agile interference management. Simulation results show that the proposed approach yields significant gains at both macrocell and small cell tiers, in terms of average achievable rate per user, reaching up to 37%, relative to the non-cooperative case, for a network with 150 MUEs and 200 SBSs.

Despite its notable importance, backhauling has - thus far - been a largely overlooked issue. However, driven by the uptake of small cell networks, current dedicated backhaul solutions are no longer viable for mobile operators, calling for novel deployment and backhaul-aware access strategies. In this paper, following the market's latest developments in infrastructure sharing, we investigate the uplink performance improvement when using a spatially-close open access small cell over one operator's carrier and simultaneously a direct access over another carrier. An important constituent of our work is the optimization problem of joint access and in-band (over-the-air) backhaul for the small cell link. Given the large degree of parametric freedom, another important constituent is the use of cognitive self-organizing networking mechanisms in the form of reinforcement learning, to autonomously optimize the resources allocated to and within each carrier. Simulation results corroborate our findings, with reported performance improvements of 40% under completely autonomous operating conditions when compared to benchmark backhaul approaches.

As future small cell base stations (SCBSs) are set to be multi-mode capable (i.e., transmitting on both licensed and unlicensed bands), a cost-effective integration of both technologies coping with peak data demands is crucial. Using tools from reinforcement learning, a distributed cross-system traffic steering framework is proposed whereby SCBSs leverage WiFi, to autonomously optimize their long-term performance over the licensed spectrum band, as a function of the traffic load and users' heterogeneous Quality of Service (QoS) requirements. The proposed traffic steering solution is validated in a Long-Term Evolution (LTE) simulator augmented with WiFi hotspots. Remarkably, it is shown that the proposed cross-system learning-based approach outperforms several benchmark algorithms and traffic steering policies, with gains reaching up to 200% when using a traffic-aware scheduler as compared to the classical proportional fair (PF) scheduler.

This paper presents the derivation for per-tier outage probability of a randomly deployed femtocell network over an existing macrocell network. The channel characteristics of macro user and femto user are addressed by considering different propagation modeling for outdoor and indoor links. Location based outage probability analysis and capacity of the system with outage constraints are used to analyze the system performance. To obtain the simplified expressions, approximations of ratios of Rayleigh random variables (RVs), Rayleigh to log normal RVs and their weighted summations, are derived with the verifications using simulations.

The use of small cells serviced by low-power base stations such as femtocells is envisioned to improve the spectrum efficiency and the coverage of next-generation mobile wireless networks. However, one of the major challenges in femtocell deployments is managing interference. In this paper, we propose a novel cooperative solution that enables femtocells to improve their achievable data rates, by suppressing intratier interference using the concept of interference alignment (IA). We model this cooperative behavior among the femtocells as a coalitional game in partition form and we propose a distributed algorithm for the coalition formation. The proposed algorithm allows the femtocell base stations to independently decide on whether to cooperate or not, while maximizing a utility function capturing both the gains and costs from cooperation. Using the proposed algorithm, the femtocells can self-organize into a stable network partition composed of disjoint femtocell coalitions and which constitutes the recursive core of the game. Inside every coalition, cooperative femtocells use advanced IA techniques to improve their downlink transmission rate. Simulation results show that the proposed coalition formation algorithm yields significant gains, in terms of average payoff per femtocell, reaching up to 30 percent relative to the noncooperative case for a network of N=300 femtocells.

In this paper, a decentralized and self-organizing mechanism for small cell networks (such as micro-, femto- and picocells) is proposed. In particular, an application to the case in which small cell networks aim to mitigate the interference caused to the macrocell network, while maximizing their own spectral efficiencies, is presented. The proposed mechanism is based on new notions of reinforcement learning (RL) through which small cells jointly estimate their time-average performance and optimize their probability distributions with which they judiciously choose their transmit configurations. Here, a minimum signal to interference plus noise ratio (SINR) is guaranteed at the macrocell user equipment (UE), while the small cells maximize their individual performances. The proposed RL procedure is fully distributed as every small cell base station requires only an observation of its instantaneous performance which can be obtained from its UE. Furthermore, it is shown that the proposed mechanism always converges to an epsilon Nash equilibrium when all small cells share the same interest. In addition, this mechanism is shown to possess better convergence properties and incur less overhead than existing techniques such as best response dynamics, fictitious play or classical RL. Finally, numerical results are given to validate the theoretical findings, highlighting the inherent tradeoffs facing small cells, namely exploration/exploitation, myopic/foresighted behavior and complete/incomplete information.

In this paper, we apply the concepts of network multiple-input-multiple-output (MIMO) to small cell networks. To do so, the issue of imperfect channel state information (CSI) at the transmitter is considered when frequency-division duplexing is used, for which the feedback channel is limited. We first introduce a regret based learning approach to optimize the transmit beamforming parameters for the cases when the feedback channel is temporarily unavailable during deep fades. We then propose a coalition formation game model to cluster the small cell base stations so that they can perform cluster-wise joint beamforming. We take the \tit{recursive core} as the solution concept of the coalition formation game. To obtain the recursive core, we first consider a typical merge-split algorithm. However, we show that this algorithm can be unstable. Alternatively, we adopt the merge-only algorithm which guarantees the formation stability and show that its outcome belongs to the recursive core. Finally, we analyze the average number and the average size of coalitions that can form during such a coalition formation process. Numerical simulations are given to illustrate the behavior of the coalition formation among small cell base stations.

The design of distributed mechanisms for interference management is one of the key challenges in emerging wireless small cell networks whose backhaul is capacity limited and heterogeneous (wired, wireless and a mix thereof). In this paper, a novel, backhaul-aware approach to interference management in wireless small cell networks is proposed. The proposed approach enables macrocell user equipments (MUEs) to optimize their uplink performance, by exploiting the presence of neighboring small cell base stations. The problem is formulated as a noncooperative game among the MUEs that seek to optimize their delay-rate tradeoff, given the conditions of both the radio access network and the - possibly heterogeneous - backhaul. To solve this game, a novel, distributed learning algorithm is proposed using which the MUEs autonomously choose their optimal uplink transmission strategies, given a limited amount of available information. The convergence of the proposed algorithm is shown and its properties are studied. Simulation results show that, under various types of backhauls, the proposed approach yields significant performance gains, in terms of both average throughput and delay for the MUEs, when compared to existing benchmark algorithms.

In this paper, we investigate enhanced Inter-Cell Interference Coordination (e-ICIC) techniques for Heterogeneous Networks (HetNets), consisting of a mix of macro and picocells. We model this strategic coexistence as a multi-agent system in which decentralized interference management and cell association strategies inspired from Reinforcement Learning (RL) are devised. Specifically, we focus on time and frequency domain ICIC techniques in which picocells optimally learn their cell range bias and downlink transmit power allocation. In turn, the macrocell optimizes its transmission by serving its own users while adhering to the picocell interference constraint. To substantiate our theoretical findings, system level simulations are carried out in which our proposed solution is compared with a number of existing ICIC approaches, such as resource partitioning, fixed cell range expansion (CRE) and fixed Almost Blank Subframe (ABS). Interestingly, our proposed solution is shown to yield substantial gains of up to 125% compared to static ICIC approaches.

In this paper, we study the strategic coexistence between macro and femto cell tiers from a game theoretic learning perspective. A novel regret-based learning algorithm is proposed whereby cognitive femtocells mitigate their interference toward the macrocell tier, on the downlink. The proposed algorithm is fully decentralized relying only on the signal-to-interference-plus-noise ratio (SINR) feedback to the corresponding femtocell base stations. Based on these local observations, femto base stations learn the probability distribution of their transmission strategies (power levels and frequency band) by minimizing their regrets for using certain strategies, while adhering to the cross-tier interference constraint. The decentralized regret based learning algorithm is shown to converge to an ϵ-coarse correlated equilibrium (ϵ-CCE) which is a generalization of the classical Nash Equilibrium (NE). Finally, numerical results are shown to corroborate our findings where, quite remarkably, our learning algorithm achieves the same performance as the classical regret matching, but with substantially much less overhead.

The choice of a suitable backhaul constitutes one of the main performance bottlenecks in the emerging femtocell networks. In this paper, we study the impact of adopting a heterogenous backhaul (i.e., wired or over-the-air) with realistic quality-of-service requirements on coherent coordinated multipoint (CoMP) transmission in the downlink of femtocell networks. We formulate a cooperative game with continuum among the femtocell access points (FAPs) for performing CoMP in order to maximize the downlink rate while accounting for the constraints on the heterogeneous backhaul. In this respect, we propose a distributed algorithm that enables the FAPs to jointly decide on their cooperative partners as well as the choice of a backhaul strategy. In this respect, the proposed algorithm jointly addresses the problem of coalition formation as well as the optimization of the tradeoff between OTA and wired backhaul transmission modes, each of which is limited by a different factor such as delay or spectrum resources availability. We show that the proposed algorithm converges to a stable partition which constitutes the continuum core of the studied cooperative game. Simulation results show that our proposed scheme yields interesting gains in terms of the average downlink rate per FAP, reaching up to 26% relative to the classical of non-cooperative transmissions.

Autonomous interference management solutions for inter-cell interference coordination (ICIC) are of utmost importance. In this paper, the coexistence between macro and small cells is studied whereby different ICIC techniques pertaining to different deployment and information assumptions are evaluated. Inspired from Evolutionary Game Theory (EGT), decentralized strategies are devised, in which small cell Base Stations (BSs) exchange information through a central controller, and adapt their strategies based on instantaneous and average payoffs of the small cell population. In contrast, when distributed operation is aimed at, using tools from Reinforcement Learning (RL) small cells learn by interacting with their environment through trials and-errors, and autonomously optimize their strategies based on a mere feedback. In particular, we compare the performance of decentralized Q- learning, Fuzzy Q-learning, improved Q-learning and expertness-based Q-learning procedures. Finally, the overall performance of the network in terms of average peruser data throughput and convergence are carried out in an LTE-A system level simulator.

In this work we compare full-duplex (FD) and half-duplex (HD) relaying in terms of outage probability and throughput. We consider a practical FD relay model where the loop interference between transmitted and received signals is taken into account. We analyze two modes for FD transmission, block Markov encoding and multi-hop transmission without interference cancellation, and two different modes for HD transmission, which are based on selective and incremental decode-and-forward protocols. Results show that there is a tradeoff between SNR and information rate in which each scheme becomes more suitable.

The concept of femtocell access points underlaying existing communication infrastructure has recently emerged as a key technology that can significantly improve the coverage and performance of next-generation wireless networks. In this paper, we propose a framework for macrocell-femtocell cooperation under a closed access policy, in which a femtocell user may act as a relay for macrocell users. In return, each cooperative macrocell user grants the femtocell user a fraction of its superframe. We formulate a coalitional game with macrocell and femtocell users being the players, which can take individual and distributed decisions on whether to cooperate or not, while maximizing a utility function that captures the cooperative gains, in terms of throughput and delay. We show that the network can self-organize into a partition composed of disjoint coalitions which constitutes the recursive core of the game which is a key solution concept for coalition formation games in partition form. Simulation results show that the proposed coalition formation algorithm yields significant gains in terms of average rate per macrocell user, reaching up to 239%, relative to the non-cooperative case. Moreover, the proposed approach shows an improvement in terms of femtocell users' rate of up to 21% when compared to the traditional closed access policy.

We analyze the physical layer (PHY) security of a communication scheme consisting of a multiple antenna transmitter with a single radio frequency (RF) chain using transmit antenna selection (TAS) and a single antenna receiver, in the presence of a sophisticated multiple antenna eavesdropper. We develop closed-form expressions for the analysis of the secrecy outage probability, and we show that the PHY security can be considerably enhanced when multiple antennas are available at the legitimate transmitter. Moreover, a single RF chain multiple antenna transmitter reduces cost, complexity, size and power consumption at the expense of a slight loss in performance with respect to a multiple RF chain transmitter.

We propose and investigate distributed coordination mechanisms for controlling the co-channel interference generated by standalone femtocells in two-tier coexistence scenarios consisting of macrocells underlaid with short-range small cells. The rationale behind employing such mechanism is to opportunistically reuse resources without compromising ongoing transmissions on overlaid macrocells, while still guaranteeing Quality of Service in both tiers. Stochastic geometry is used to model network deployments, while higher-order statistics through the cumulants concept is utilized to characterize the probability distribution of the aggregate interference at the tagged receiver. To conduct our studies, we consider a shadowed fading channel model incorporating log-normal shadowing and Nakagami fading. In addition, various network algorithms, such as power control and frequency (re)allocation, are included in the analytical framework. To evaluate the performance of the proposed solutions, we also derive closed-form expressions for the outage probability and average spectral efficiency with respect to the tagged receiver. Results show that the analytical framework matches well with numerical results obtained from Monte Carlo simulations, and that the coordination mechanisms substantially improve the performance of overlaid macrocell networks, while also benefiting femtocells.

In this paper, the \emph{strategic} coexistence between macro and femtocell tiers is studied using tools from evolutionary game theory and reinforcement learning. In the first case, femto base stations (FBSs) exchange information through a central controller, and adapt their strategies based on their instantaneous payoffs and average payoffs of the femtocell population. A fictitious play formulation is also examined where FBSs maximize their payoffs given the empirical frequency of other femtocells' actions. In the second case, when information exchange among femtocells is no longer possible, each femtocell gradually learns by interacting with its local environment through trials-and-errors, and adapt its strategies. Variant of the evolutionary game approach (referred to as replication by imitation) is also investigated where femtocells probabilistically review their strategies and imitate other femtocells in the network. Finally, the overall performance of the network in terms of spectral efficiency and convergence is shown to be adamantly driven by the type of information available at femtocells.

We investigate coordination mechanisms for controlling the co-channel interference generated by stand-alone femtocells in two-tier coexistence scenarios. Stochastic geometry is used to model network deployment scenarios, while the cumulants concept is utilized to characterize the probability distribution of the aggregate interference at a tagged user. The rationale for using coordination mechanisms is to opportunistically reuse resources without compromising ongoing transmissions on overlay macrocells, while still guaranteeing Quality of Service in both tiers. Results have shown that the analytical framework matches fairly well with numerical results obtained with Monte Carlo simulations. Yet coordination mechanisms improve performance of overlay macrocell network by substantially diminishing co-channel interference.

Underlay femtocells have recently emerged as a key technology that can significantly improve the coverage and performance of next- generation wireless networks. In this paper, we propose a novel approach for interference management that enables a number of femtocells to cooperate and improve their downlink rate, by sharing spectral resources and suppressing intra-tier interference using interference alignment. We formulate a coalitional game in partition form among the femtocells and propose a distributed algorithm for coalition formation. Using our approach, the femtocell access points can make individual decisions on whether to cooperate or not, while maximizing a utility function that captures the cooperative gains and the costs in terms of transmit power for information exchange. We show that, using the proposed coalition formation algorithm, the femtocells can self-organize into a network partition composed of disjoint femtocell coalitions, which constitutes the recursive core of the game. Simulation results show significant gains in terms of average payoff per femtocell, reaching up to 30% relative to the non-cooperative scheme.

In this paper, recent results in game theory and stochastic approximation are brought together to mitigate the problem of femto-to-macrocell cross-tier interference. The main result of this paper is an algorithm which reduces the impact of interference of femtocells over the existing macrocells. Such algorithm relies on the observations of the signal to interference plus noise ratio (SINR) of all active communications in both macro and femtocells when they are fed back to the corresponding base stations. Based on such observations, femto base stations learn the probability distributions over the feasible transmit configurations (frequency band and power levels) such that a minimum time-average SINR can be guaranteed in the macrocells, at the equilibrium. In this paper, we introduce the concept of logit equilibrium (LE) and present its interpretation in terms of the trade-off faced by femtocells when experimenting several actions to discover the network, and taking the action to maximize their instantaneous performance. Finally, numerical results are given to validate our theoretical findings.

Femtocells are envisioned to be deployed in indoor environments in order to improve both radio coverage and spectrum efficiency. This paper focuses on the self-organization of indoor femtocells, which includes mechanisms of cooperation. In this context, we propose a solution to automatically form cooperating groups among severely interfered femtocells in order to avoid interference. A hybrid access policy is proposed and compared to the closed and open policies. Results show that, as stated in the Braess Paradox, pervasive cooperation may be detrimental, when available resources are highly contended. Conversely, in particular cases, a marginal selfish behavior of femtocells can be preferable.

Overlaying low-power, low-cost, femtocells, over existing wireless networks has recently emerged as a means to significantly improve the coverage and performance of next-generation wireless networks. While most existing literature focuses on spectrum sharing and interference management among non-cooperative femtocells, in this paper, we propose a novel cooperative model that enables the femtocells to improve their performance by sharing spectral resources, minimizing the number of collisions, and maximizing the spatial reuse. We model the femtocell spectrum sharing problem as a coalitional game in partition form and we propose a distributed algorithm for coalition formation. Using the proposed algorithm, the femtocells can take autonomous decisions to cooperate and self-organize into a network partition composed of disjoint femtocell coalitions and that constitutes a stable partition which lies in the recursive core of the considered game. Whenever a coalition forms, the femtocells inside this coalition can cooperatively pool the occupied spectral resources. Additionally, the members of any given coalition jointly schedule their transmissions in order to avoid collisions, in a distributed way. Simulation results show that the proposed coalition formation algorithm yields a performance advantage, in terms of the average payoff (rate) per femtocell reaching up to 380% relative to the non-cooperative case.

In this paper, we address the problem of spectrum sharing where wireless (competitive) operators coexist in the same frequency band. First, we model this problem as a strategic non-cooperative game where operators simultaneously share the spectrum according to the Nash equilibrium (N.E). Given a set of channel realizations, several Nash equilibria exist which render the outcome of the game unpredictable. Second, the inter-operator spectrum sharing problem is reformulated as a hierarchical power allocation game, where one of the operators (i.e., primary) poses as a leader and the other operator (i.e., secondary) as a follower. Using backward induction, the Stackelberg equilibrium (S.E) is reached where the best response of the secondary operator is taken into account upon maximizing the primary operator's payoff. It turns out that the Stackelberg approach yields better payoffs for operators compared to the classical greedy water-filling approach. Furthermore, to reach Pareto-efflcient boundaries, the spectrum sharing problem is formulated as a repeated game, where players interact over a longer period of time and learning from each other's strategies. Numerical results provide a comparison between the non-cooperative, hierarchical and centralized approach.

The IST 6thframework WINNER project defines spectrum sharing techniques for future wireless communication systems. This paper addresses spectrum sharing capabilities between different radio technologies. More particularly, spectrum sharing between WINNER system and the Fixed Satellite Service (FSS) community is at stake. The goal is to efficiently share the spectrum without causing harmful interference towards the primary system (i.e., FSS). A power assignment mechanism for the coexistence is proposed where different power levels are assigned in the cellular network in the areas surrounding the FSS system. Simulation results for the coexistence between both systems is carried out where the spectrum used by the WINNER system is punctured for the transmission of the primary FSS system. Finally, the results show that spectrum utilization is significantly improved.

Abstract This paper presents novel spectral resource management (SRM) functionalities of WINNER ‡ The WINNER project is a major European research activity to develop a flexible and scalable radio access interface for future wireless communication systems. project. The proposed SRM spectrum architecture uses more efficient resource allocation techniques where flexible spectrum access and usage leads to more capable and faster services with high quality‐of‐service (QoS) giving more user satisfaction than conventional networks. In this context, short‐term (ST) spectrum assignment is proposed where spectral resources are exchanged between WINNER radio access networks (RANs) on a fast basis, leading to a better utilization of the spectrum. Moreover, multi‐band scheduler (MBS) and base station (BS) to BS communications are presented as key enablers for efficient dynamic spectrum management. Performance gains of ST spectrum assignment are analyzed in a multi‐network, multi‐cell environment based on realistic traffic patterns while taking inter‐cell interference into account. The results confirm that spectrum availability and utilization can be considerably enhanced. Copyright © 2008 John Wiley & Sons, Ltd.

In this paper, we address the problem of non-cooperative operators trying to maximize their profits by offering extra spectral resources to other operators starving for spectrum. An oligopoly market is used to model this game-theoretical setting where several operators seek to maximize their profit while customers try to sustain or increase their quality-of-service (QoS). In addition, a Bertrand game model is used to maximize the payoff of operators where the Nash equilibrium is computed. Simulations validate the proposed game model.

In this paper, we investigate the optimum detection of MIMO signals in the presence of channel estimation errors. A maximum likelihood (ML)-based detection algorithm is proposed for optimal MIMO signal detection based on the modified ML criterion which takes into account channel estimation errors. Moreover, we evaluate for both the uncoded and coded case, the bit-error-rate (BER) performance of the hard decoded MIMO systems. The new algorithm, taking into account channel estimation errors, achieves improvement in terms of BER gain over the conventional MIMO detector algorithm ignoring channel estimation errors. Moreover, the optimal designed constellations taking channel estimation errors into account, show an increase in the capacity over conventional schemes.

With the progress of technology and the fast growing demand for ubiquitous high-speed wireless services, flexible resource sharing is widely seen to be an important feature for the deployment of beyond 3G systems. Therefore, a migration from fixed allocations to a more flexible spectrum management has to be taken into account. In this context, inter-operator resource sharing in a broadband network is considered in this paper. A packet-based cellular network is developed, emphasizing the shift in the telecommunications industry towards IP-based services. We show that we can improve the overall efficiency of the system by sharing different resources in the network between several operators. Moreover, big and small operators, in addition to customers are altogether satisfied. In this paper, we use the term "resource" to not only account for spectrum sharing but also towers, base stations and time slots sharing. In our framework, we will use a physical layer cellular model with idealistic resource management, where we quantify the achievable sharing gains. We compare the performances for the non sharing case, the case where the base stations decide to share the resources as a "last resort", and also when the mobile stations always connect to the best base station, regardless of the operator. Finally, We analyze these gains in terms of quality of service, number of operators and different service classes.