Multi-Agent Reinforcement Learning (MARL) has proven to be effective in learning cooperative policies, where agents learn decentralized policies, sharing the same network parameters, through centralized training. However, this parameter sharing can lead to similar behaviors among agents, hindering effective exploration. Existing multi-agent diversity methods that rely on the variational inference methods to differentiate agents may suffer from significant overfitting, which in turn hinders the exploration of new trajectories. To encourage multi-agent diversity and efficient exploration, we propose Active Exploration with Agent-Identity (AEAI), a novel exploration method, which maximizes the entropy over trajectories of different agents to promote sufficient exploration. Moreover, we derive a novel lower bound for the mutual information objective based on the successor features to align the directions of trajectories and agent identities in order to learn agent identity-conditioned policies. We combine these two items and integrate our method with existing MARL methods. We evaluate our proposed AEAI on challenging multi-agent tasks across various MARL benchmarks. Experimental results show that our method consistently outperforms existing state-of-the-art methods, highlighting its effectiveness in fostering diversity and improving exploration.

Collaborative mobile edge computing (MEC) has emerged as a promising paradigm to enable low-capability edge nodes to cooperatively execute computation-intensive tasks. However, straggling edge nodes (stragglers) significantly degrade the performance of MEC systems by prolonging computation latency. While coded distributed computing (CDC) as an effective technique is widely adopted to mitigate straggler effects, existing CDC schemes exhibit two critical limitations: (i) They cannot successfully decode the final result unless the number of received results reaches a fixed recovery threshold, which seriously restricts their flexibility; (ii) They suffer from inherent poles in their encoding/decoding functions, leading to decoding inaccuracies and numerical instability in the computational results. To address these limitations, this paper proposes an approximated CDC scheme based on barycentric rational interpolation. The proposed CDC scheme offers several outstanding advantages. Firstly, it can decode the final result leveraging any returned results from workers. Secondly, it supports computations over both finite and real fields while ensuring numerical stability. Thirdly, its encoding/decoding functions are free of poles, which not only enhances approximation accuracy but also achieves flexible accuracy tuning. Fourthly, it integrates a novel BRI-based gradient coding algorithm accelerating the training process while providing robustness against stragglers. Finally, experimental results reveal that the proposed scheme is superior to existing CDC schemes in both waiting time and approximate accuracy.

Efficient collaboration among Unmanned Aerial Vehicles (UAVs) has significant performance improvement for UAV-based applications. Task offloading is the typical collaboration form for UAV system. However, it still be a challenging problem for UAV system due to task dependencies and the UAV mobility which makes the traditional offloading approaches inefficiency. In this paper, we model the offloading problem as the Sequential Task Offloading Problem (sTOP), which takes the task spatiotemporal dependencies into account. We propose a Graph-based Spatiotemporal Reinforcement Learning (GSTRL) framework, where the environment is modeled as a heterogeneous graph to capture the diverse relationships among system entities. A spatiotemporal state extraction module is designed, which integrates a Heterogeneous Graph Neural Network (HGNN) for spatial dependency modeling and a Long Short-Term Memory (LSTM) network for temporal dynamics. Based on the extracted representations, a masked Proximal Policy Optimization (mPPO) algorithm is proposed to make valid and efficient offloading decisions under multiple system constraints. Extensive experiments using real UAV trajectory and building distribution datasets validate that the proposed method improves the average reward by approximately 25% over state-of-the-art DRL-based and heuristic baselines, by increasing task success rate and operational effectiveness ratio (OER) to 30–50%, while reducing execution time by up to 40% in complex multi-UAV systems.

Semantic communication has emerged as a promising paradigm in next-generation communication systems, leveraging advanced artificial intelligence (AI) models to extract and transmit semantic representations for efficient information exchange. However, the reliability of received information is often compromised by unpredictable semantic noise, such as corruptions or distortions in the transmitted representations. Traditional methods typically rely on adversarial training with artificially injected noise to improve robustness. Yet, these approaches suffer from limited adaptability to varying noise conditions and incur considerable computational overhead during training. To address these challenges, this paper introduces Semantic communication with High-and-Low Frequency Decomposition (Se-HiLo), a novel noise-resilient scheme designed for image transmission. Se-HiLo integrates a Finite Scalar Quantization (FSQ) module that enhances robustness by constraining encoded representations within predefined discrete spaces, thereby eliminating the need for adversarial training. While FSQ strengthens resistance to noise, it inherently limits representational expressiveness. To mitigate this trade-off, Se-HiLo further incorporates a transformer-based high-and-low frequency decomposition module that separates image representations into distinct frequency components and encodes them into independent FSQ spaces, thus preserving semantic diversity and expressiveness. Extensive experiments validate that Se-HiLo significantly improves noise robustness and maintains accurate semantic communication across a wide range of noise environments.

Large-Scale multi-UAV systems have significant advantages in enhancing the coverage and reliability of communication networks due to their flexible deployment capabilities. However, existing strategies in UAV-assisted communications primarily optimize bit-level throughput and energy efficiency, making it difficult to ensure effective information transmission under low SINR or complex channel conditions. To address issue, we introduce a new paradigm by incorporating semantic communication into UAV networks, and formulate the 3D UAV-BSs deployment problem with the goal of enhancing semantic fidelity. Furthermore, to tackle the challenges of large-scale multi-agent collaborative decision-making, this paper proposes a novel method which improves the traditional mean-field multi-agent deep deterministic policy gradient (MF-MADDPG), by combining with kernel density estimation (KDE) to model the neighborhood action distribution, enhancing the stability of the policy in continuous action spaces. A semantic-aware reward function is designed based on a representative metric of semantic fidelity, which guides the UAVs toward regions of higher semantic significance. Simulation results show that the proposed method outperforms existing strategies in terms of semantic transmission quality and training stability, demonstrating its application potential in large-scale semantic communication environments.

Cooperative Multi-Agent Reinforcement Learning (MARL) has drawn increasing interest in recent works due to its significant achievements. However, there are still some challenges impeding the learning of optimal cooperative policies, such as insufficient exploration. Prior works typically adopt mutual information-based methods to encourage exploration. However, this category of methods does not necessarily encourage agents to fully explore the joint behavior space. To address this limitation, we propose a novel objective based on learning a representation function with a Lipschitz constraint to maximize the traveled distances in the joint behavior space, encouraging agents to learn joint behaviors with large variations and leading to sufficient exploration. We further implement our method on top of QMIX. We demonstrate the effectiveness of our method by conducting experiments on the LBF, SMAC, and SMACv2 benchmarks. Our method outperforms previous methods in terms of final performance and state-action space exploration.

The high flexibility and mobility enable unmanned aerial vehicles (UAVs) playing a pivotal role in gathering/relaying data in emergency communication. However, communication resources are scarce in emergency communication scenarios, while Semantic Communication (SC) holds promise for overcoming current communication bottlenecks by reducing data transmission volumes. In this paper, we investigate joint resource optimization and trajectory optimization in UAV-assisted emergency semantic communication networks to further enhance communication efficiency. Firstly, considering the importance of data freshness in emergency communication scenarios, we propose a semantic metric, termed semantic transmission efficiency, which integrates both semantic similarity and semantic Age of Information (AoI). Then, we jointly optimize user bandwidth, transmission power, and UAV flight trajectories with the objective of maximizing the long-term semantic transmission efficiency. To solve the joint optimization problem, we propose the Diffusion-Deep Deterministic Policy Gradient (Diffusion-DDPG) algorithm. By leveraging the capability of generative diffusion model to capture data distributions, the algorithm effectively identifies optimal solutions to complex optimization problems, thereby enhancing the exploration ability of agent. Comparative experiments demonstrate that Diffusion-DDPG effectively balances semantic similarity and semantic AoI within semantic transmission efficiency. Particularly in resource-constrained scenarios, it shows superior convergence speeds.

Collaborative edge-device inference is a promising way to empower resource-constrained mobile devices to execute deep neural network (DNN)-based applications with heavy computational workloads. In particular, a DNN model is partitioned into two parts that are executed on the mobile device and the edge server, respectively. However, offline model partitioning methods suffer from poor adaptability to real computing environments, while online methods have the problem of delayed feedback. In addition, model partitioning inevitably incurs large transmission overheads of DNN's intermediate data. To tackle these challenges, we propose a collaborative edge-device inference optimization algorithm (JPCA) with Joint DNN Partitioning, data Compression, and resource Allocation. Our goal is to maximize the inference accuracy of all tasks while satisfying inference latency and energy requirements in a dynamically changing environment. In JPCA, the joint selection of model partition point and data quantization bit-width is first extracted from the original problem and we propose an improved deep reinforcement learning (DRL)-based algorithm to learn joint decisions. Optimal schemes under different bandwidth conditions are recorded, enabling mobile devices to adjust joint decisions in response to significant bandwidth changes. Furthermore, we design a dynamic edge resource allocation algorithm that makes edge resource allocation decisions for tasks arriving in real time, thereby accelerating DNN inference. The results of the testbed experiments affirm the effectiveness of our proposed algorithms in terms of inference accuracy.

Recent works have increasingly focused on learning decentralized policies for agents as a solution to the scalability challenges in Multi-Agent Reinforcement Learning (MARL), where agents typically share the parameters of a policy network to make action decisions. However, this parameter sharing can impede efficient exploration, as it may lead to similar behaviors among agents. Different from previous mutual information-based methods that promote multi-agent diversity, we introduce a novel multi-agent exploration method called Trajectory Entropy Exploration (TEE). Our method employs a particle-based entropy estimator to maximize the entropy of different agents' trajectories in a contrastive trajectory representation space, resulting in diverse trajectories and efficient exploration. This entropy estimator avoids challenging density modeling and scales effectively in high-dimensional multi-agent settings. We integrate our method with MARL algorithms by deploying an intrinsic reward for each agent to encourage entropy maximization. To validate the effectiveness of our method, we test our method in challenging multi-agent tasks from several MARL benchmarks. The results demonstrate that our method consistently outperforms existing state-of-the-art methods.

Semantic Communication (SemCom), as a next-generation communication technology, promises to enhance message delivery efficiency while reducing network resource consumption. Despite progress in SemCom, research on SemCom security is still in its infancy. To bridge this gap, we propose a general covert SemCom framework for wireless networks, which introduces the application of covert communications aided by a friendly jammer, thereby reducing the risk of eavesdropping. Our approach transmits semantic information covertly, making it difficult for wardens to detect. Given the aim of maximizing covert SemCom performance, we formulate a power control problem in covert SemCom under energy constraints. Furthermore, we propose a learning-based approach based on the soft actor-critic algorithm, optimizing the power of the transmitter and the friendly jammer. Our numerical findings substantiate the efficacy of our proposed approach in bolstering covert SemCom performance.

With the increase in computing speed and network bandwidth in data centers, microsecond-level tail latency has become a key metric for internet-based online services. However, the tail latency of messages in data centers is mainly determined by queuing delay, which is usually much larger than pure message transmission time. Existing traffic scheduling mechanisms fail to effectively coordinate end-side and in-network resources, leading to head-of-line (HOL) blocking for microsecond-level messages at both ends and switches, which severely impacts the tail latency. To address this issue, this paper proposes a network-wide Global Priority based Multi-Path message scheduling mechanism GPMP. It assigns the highest priority to microsecond-level messages at both ends and swtiches to ensure such messages can quickly acquire resources and complete quickly. Furthermore, GPMP also optimizes the transmission of low-priority large messages by introducing a multi-path method, which effectively reduces transmission time and improves the bandwidth utilization. Extensive simulation results show that GPMP not only meets the strict latency requirements of microsecond-level messages, but also significantly reduces the completion time of long messages, leading to an overall improvement in bandwidth utilization.

In cooperative Multi-Agent Reinforcement Learning (MARL), agents that share policy network parameters often learn similar behaviors, which hinders effective exploration and can lead to suboptimal cooperative policies. Recent advances have attempted to promote multi-agent diversity by leveraging the Wasserstein distance to increase policy differences. However, these methods cannot effectively encourage diverse policies due to ineffective Wasserstein distance caused by the policy similarity. To address this limitation, we propose Wasserstein Contrastive Diversity (WCD) exploration, a novel approach that promotes multi-agent diversity by maximizing the Wasserstein distance between the trajectory distributions of different agents in a latent representation space. To make the Wasserstein distance meaningful, we propose a novel next-step prediction method based on Contrastive Predictive Coding (CPC) to learn distinguishable trajectory representations. Additionally, we introduce an optimized kernel-based method to compute the Wasserstein distance more efficiently. Since the Wasserstein distance is inherently defined for two distributions, we extend it to support multiple agents, enabling diverse policy learning. Empirical evaluations across a variety of challenging multi-agent tasks demonstrate that WCD outperforms existing state-of-the-art methods, delivering superior performance and enhanced exploration.

Deep neural networks (DNNs) have revolutionized multiple generations by harnessing the power of advanced GPUs and extensive datasets. In fields such as audio and video processing, DNN models are deployed on edge servers to achieve millisecond-level latency to meet stringent service-level objectives (SLOs). However, the dynamic and unpredictable nature of real-world applications, characterized by erratic surges in inference requests, poses significant challenges to existing edge systems. To address these challenges, this study presents a novel scheduling algorithm that utilizes deep reinforcement learning to maximize the minimum margins of all GPUs. This strategic approach significantly enhances the system’s capacity to manage unexpected high-demand tasks, thereby improving resilience and overall response capabilities under diverse fluctuating workloads. The experimental results confirm that the proposed algorithm consistently outperforms traditional algorithms, demonstrating superior performance in task completion rate, resource utilization efficiency, robustness, and responsiveness across different load conditions.

Orthogonal frequency division multiplexing (OFD-M) has been widely used in modern communication networks. Notice that OFDM typically relies on (inverse) Discrete Fourier Transform (DFT/IDFT) for processing its waveforms. In this context, we propose a deep learning-based OFDM receiver that uses a deep complex-valued convolutional neural network (DC-CNN) to recover the information bit stream from synchronized time-domain signals without relying on DFT/IDFT. Specifically, a learned linear transform is designed to utilize the cyclic prefix (CP) of OFDM waveforms instead of DFT/IDFT, which presents the ability of DCCNN for complex communication waveforms. To improve the convergence of the training model for the DCCNN-based receiver, a novel transfer learning scheme is developed to train channel equalization and demodulation in two phases. In addition, both the DCCNN equalizer and DCCNN demodulator are trained and tested at different SNRs for Rayleigh fading and noise, and a mixed multiple fading channel model with various delay spreads is utilized to smooth the training loss. Simulation results suggest that our developed DCCNN channel estimator outperforms conventional estimators such as least square (LS), linear minimum mean square error (LMMSE) and low-rank approximation of LMMSE (ALMMSE) in multipath Rayleigh fading models with varying Doppler spreads and delay spreads.

Semantic communication has gained significant attention for its potential to address the limitations of traditional communication systems. However, most current research focuses on architectural design, neglecting the critical issue of communication security. In this paper, we reveal the security vulnerabilities in existing semantic communication systems. First, we introduce a knowledge base-assisted task-oriented image semantic communication network. Next, we design two types of semantic viruses that target the knowledge base: a static adversarial semantic virus and a dynamic diffusion semantic virus. The adversarial semantic virus generates a fixed-strength attack, while the diffusion semantic virus attack follows a Gaussian distribution. Finally, for multi-task scenarios, we propose a unified multi-task diffusion semantic virus capable of switching between task-specific viruses using different task embeddings. Experiments on semantic segmentation and image recognition tasks demonstrate that the proposed method effectively degrades task performance at the receiver.

With the development of Industry 4.0, Distributed Mixed-Criticality Systems (DMCS) have been widely applied to handle various complex tasks in IoT and aerospace fields. To ensure the reliability and end-to-end Quality of Service (QoS) of high-criticality tasks in DMCS, Time-Sensitive Networking (TSN) with inherent determinism can be adopted to provide deterministic low-latency transmission service. However, in modern DMCS, the emergency burst high-criticality tasks and the event-triggered scheduling mechanism used on end systems (ESs) conflict significantly with the time-triggered scheduling mechanism adopted in TSN. In this paper, we modify the standard static scheduling constraints in TSN and introduce new constraints to enforce time-triggered scheduling behavior on ESs based on the original event-triggered scheduling mechanism. Additionally, we propose a Priority-based Dynamic Slot Extension (PDSE) method to handle the emergency high-criticality tasks generated in DMCS. The simulation results show that our proposed time-triggered constraint is compatible with the standard TSN scheduling, enabling time-triggered scheduling of periodic high-criticality tasks on even-triggered ESs. Moreover, the results of end-to-end delays and delay jitters indicate that compared to other methods, PDSE can better schedule emergency high-criticality tasks in DMCS while exerting a lower impact on other high-criticality tasks.

Semantic communication has recently garnered substantial attention due to its potential to alleviate bandwidth constraints and improve network capacity. Nonetheless, existing studies primarily concentrate on network architecture and overlook the communication performance analysis. Therefore, this paper seeks to derive semantic-oriented error probability. Specifically, we develop a novel text semantic communication framework that comprises distinct semantic and physical layers. In the semantic layer, we employ latent Dirichlet allocation (LDA) to extract text topics and evaluate the topic distribution. Given an expected transmission accuracy, we propose a dichotomy to determine the minimal number of topics. These acquired topics, along with their respective distributions, are defined as the text semantic features. In the physical layer, the semantic features are encoded into a binary sequence and modulated with conventional methods. The relationship between the semantic and physical layers is uncover by associating coding of the semantic features with the symbol error probability (SEP). Considering a scenario wherein base stations (BSs) following a specific Poisson point process (PPP), we derive the approximate SEP and semantic inference error probability (SIEP) for multiple coding strategies. Simulation results show that the proposed text semantic communication network enables effective text transmission and the derived error probability accurately reflect the performance of an actual communication system.

In edge computing, end devices (EDs) containerize tasks with the necessary resources and offload subsets to a nearby high-capacity edge server (ES) to improve efficiency. Most existing research focuses on inseparable task offloading to minimize response times or resource allocation to reduce energy consumption. However, task execution can be speeded up with excessive computing and network resources, it will increase energy consumption and incur unnecessarily high costs. Besides, complex applications like autonomous driving often partition sequential tasks to improve performance, necessitating a joint optimization of sequential task offloading and multi-resource allocation. In this paper, we introduce a Stackelberg game-based framework to model the interplay between these elements.EDs, acting as leaders, determine the offloading breakpoints of sequential tasks and the locality for processing. TheES, as the follower, uses the Karush-Kuhn-Tucker (KKT) conditions and a Boundary-constrained quasi-Particle Swarm Optimization (Bc-qPSO) algorithm to refine computing and network resource allocation, aiming to reduce system costs effectively. Our simulations show that the proposed algorithms reduce cost by approximately 10%-20% compared to traditional methods, highlighting their potential for improving the efficiency of edge computing systems.

This work studies the problem of block validation in a blockchain network where a block manager acting as a task publisher sends a task (block validation) to all the workers (miners) within the network. The latter carries out the block validation and finally returns the final results to the former. The goal of this work is to maximize the block manager’s profit by jointly optimizing the latency of the block verification process and the reward offered by the manager to miners. Note that the latency and reward are closely coupled. Therefore, in this case, if it is solved directly, they are offered separately, and their dependency is not well considered, leading to overall poor performance. This work formalizes it as an optimization problem considering both delay and reward, and proposes an evolutionary approach, namely, the reborn dandelion algorithm (RDA), to solve it. Specifically, in the proposed algorithm, each individual contains both delays and rewards for different types of miners. A reborn strategy is designed to reborn an individual to replace the worst one in the current population, with the aim of enhancing its exploration ability. A greedy selection strategy is proposed to enhance its exploitation ability. The experimental results on CEC2013 functions and blockchain network instances indicate that our proposed approach is significantly superior to other evolutionary-based ones.

Unmanned aerial vehicles (UAVs) equipped with sensors, computing units, and communication modules, together with ground devices, constitute a ubiquitous integrated low-altitude network, which can provide users with sustainable computing and communication services in areas where terrestrial infrastructure has been compromised or rendered inoperable. Federated learning-enabled UAV (FL-UAV) wireless networks fully utilize the computational and communication capabilities of UAVs to protect user data privacy by exchanging model updates with ground devices. However, facing the challenges of low energy utilization efficiency and high training latency caused by UAV deployment, resource allocation, and communication overhead in FL-UAV. Existing solutions do not achieve efficient communication and resource scheduling to solve the energy and delay optimization issues in FL-UAV wireless networks. In this paper, we propose an air-to-ground integrated federated distillation (AirFD) framework for UAV-assisted mobile computing and communication networks, which significantly reduces communication overhead between UAV and ground devices by introducing knowledge distillation to transmit average logits instead of model parameters. Furthermore, we formulate cross-layer resource scheduling in AirFD as a non-convex optimization problem to achieve a trade-off between energy consumption and delay. To solve this nonlinear coupling and NP-complete problem, we use successive convex approximation and greedy algorithm to obtain the local optimal solution. Simulation evaluation and field experiments confirm the effectiveness of our proposed method in reducing communication costs and training delays by nearly 40%, and increasing energy utilization by about 50%.

As necessary information about whether cooperation can be reached, rewards should be determined in advance in Vertical Federated Learning (VFL). To determine reasonable rewards, participant contributions should be estimated precisely. We propose a Vertically Federated Contribution Estimation (VF-CE) method. VF-CE calculates Mutual Information (MI) between distributed features and the label using a neural network trained via VFL itself. Note that compensation for CE is low as it only covers computation costs, and reward for real VFL training is high as it needs to cover training costs as well as participants' contributions to model performance and the resulting business benefits. Because MI presents a strong positive correlation with the final model performance, contributions to model performance can be estimated based on contributions to MI. We integrate a scalar-level attention mechanism in MI neural network. The attention weights of participants are treated as their contributions. We find that attention weights can effectively measure contribution redundancy, as its Spearman correlation coefficient with Shapley value is as high as 0.963. We demonstrate that VF-CE also satisfies properties of balance, zero element, and symmetry concerning fairness, which are hallmark properties of Shapley value. Compared with existing work, we consider contribution redundancy precisely, efficiently output approximated Shapley values through one MI calculation instead of 2 n where n is the number of participants, and introduce no extra privacy risk except the inherent risk in VFL, i.e., gradient transmission.

Policy network parameter sharing is a commonly used technique in advanced deep multi-agent reinforcement learning (MARL) algorithms to improve learning efficiency by reducing the number of policy parameters and sharing experiences among agents. Nevertheless, agents that share the policy parameters tend to learn similar behaviors. To encourage multi-agent diversity, prior works typically maximize the mutual information between trajectories and agent identities using variational inference. However, this category of methods easily leads to inefficient exploration due to limited trajectory visitations. To resolve this limitation, inspired by the learning of pre-trained models, in this paper, we propose a novel Contrastive Trajectory Representation (CTR) method based on learning distinguishable trajectory representations to encourage multi-agent diversity. Specifically, CTR maps the trajectory of an agent into a latent trajectory representation space by an encoder and an autoregressive model. To achieve the distinguishability among trajectory representations of different agents, we introduce contrastive learning to maximize the mutual information between the trajectory representations and learnable identity representations of different agents. We implement CTR on top of QMIX and evaluate its performance in various cooperative multi-agent tasks. The empirical results demonstrate that our proposed CTR yields significant performance improvement over the state-of-the-art methods.

Existing deep neural network (DNN) pruning methods can be classified into two main categories: structured pruning and weight pruning. Structured pruning is a representative model compression technology of DNN to reduce the storage and computation requirements and accelerate inference, which mainly includes filter pruning and channel pruning. However, they both belong to coarse-grained methods, which can only decide whether to prune a whole filter or channel or not and provide limited decision space. On the other hand, structured stripe-wise pruning has finer granularity than filter pruning, and shape-wise pruning also has finer granularity than channel pruning. These two fine-grained methods are related to two dimensions: rows and columns from the general matrix multiplication (GEMM) perspective of convolution operations. Considering that combining pruning decisions in finer granularity from multiple dimensions will produce a larger solution space, in this paper we propose a joint multi-dimensional fine-grained pruning scheme (JFP) for DNN compression, which simultaneously prune elements in filters and channels. Extensive experiments on the CIFAR-10 dataset demonstrate that: (1) JFP achieves stabler pruning ratios compared to stripe-wise pruning (2) JFP effectively compresses DNN parameters and reduces calculation amount while maintaining the accuracy compared with counterparts.

Nowadays, Federated learning (FL) is popular as it achieves distributed model training while allowing data to stay locally. It trains a global model by aggregating a selected set of local models from participants' local data. However, the global model may not perform well for all participants, especially when participants' data distributions are non-IID. Participants actually care more about the Personal Model Performance (PMP), i.e., the model performance on their own data distribution, instead of the model performance on all data. In this paper, we design a model selection method to assign a personalized set of models for each participant to maximize PMP. We first propose a model selection metric, that is model similarity. We prove theoretically that selecting models similar to a participant's own local model can make the aggregated model closer to the ideal one. Then we design a DRL-based model selection method to maximize PMP for each participant. By careful design and dimension reduction of actions and states, our TD3-based model selection method achieves the highest PMP compared with baselines. Moreover, it has a transfer ability, which means a model selection agent trained on a dataset, e.g., MNIST, works well on another similar dataset, e.g., FMNIST.

With the recent development of deep learning (DL), DL-based autoencoder techniques provide a novel paradigm for end-to-end physical layer optimization. In this paper, we address the dynamic interference in an end-to-end communication system with a multiuser Gaussian interference channel. In this context, the standard constellation is not optimal under high interference conditions. To address this issue, we propose an adaptive learning algorithm for learning and predicting dynamic interference. Note that existing DL-based autoencoders are unable to train end-to-end learning systems by deep learning without a known channel. Thus, we propose a generative adversarial network (GAN)-based training scheme to imitate the real channel. Simulation results show that compared with traditional PSK and QAM modulation schemes, our proposed adaptive learning-based auto encoder can achieve significantly lower block error rate (BLER) in presence of interference. Besides, the BLER performance of our proposed GAN-based training scheme is close to that of the optimal training scheme with known channel on different channel models.

In this paper, the energy-efficient unmanned aerial vehicle (UAV) swarm assisted mobile edge computing (MEC) with dynamic clustering and scheduling is studied. In the considered system model, UAVs are divided into multiple swarms, with each swarm consisting of a leader UAV and several follower UAVs to provide computing services to end-users. Unlike existing work, we allow UAVs to dynamically cluster into different swarms, i.e., each follower UAV can change its leader based on the time-varying spatial positions, updated application placement, etc. in a dynamic manner. Meanwhile, UAVs are required to dynamically schedule their energy replenishment, application placement, trajectory planning and task delegation. With the aim of maximizing the long-term energy efficiency of the UAV swarm assisted MEC system, a joint optimization problem of dynamic clustering and scheduling is formulated. Taking into account the underlying cooperation and competition among intelligent UAVs, we further reformulate this optimization problem as a combination of a series of strongly coupled multi-agent stochastic games, and then propose a novel reinforcement learning-based UAV swarm dynamic coordination (RLDC) algorithm for obtaining the equilibrium. Simulations are conducted to evaluate the performance of the RLDC algorithm and demonstrate its superiority over counterparts.

With the rapid development of UAV technology, optimizing task allocation is a promising approach to improving the efficiency and application breadth of multi-UAV systems. A major bottleneck in task allocation for multi-UAV systems is how to optimize multiple targets simultaneously. This paper considers the problem of maximizing the number of task assignments in a distributed multi-UAV system under strict time constraints while minimizing the waiting time for tasks. The proposed method is based on the well-known PI-MaxAss algorithm and improves it with the full-shuffle task sequence allocation (FSTSA) strategy. The basic idea is that if an unassigned task can replace the assigned task of a certain UAV, the unassigned task will be reassigned locally together with the tasks in the UAV's task sequence. Another serious issue is that the UAV may fall into an infinite loop for task allocation, which hinders task performance and significantly prolongs overall completed time. We address the deadlock problem by introducing a deletion record table and a flag for new task inclusion. Numerical simulations show that the proposed method can achieve more task allocation while reducing the average waiting time. Especially compared with PI-MaxAss in large-scale complex scenarios, its advantages are more obvious.

Semantic communication powered by artificial in-telligence is carried out vigorously to further improve communication efficiency. The knowledge base (KB), as a critical component of semantic communication systems, guides devices to do semantic coding/encoding. However, mismatched KBs hinder semantic alignment between the transceiver and the receiver, which brings severe semantic error. In this work, we design a semantic knowledge base synchronization (SKBS) framework based on federated knowledge distillation for KB establishment and dynamic evolution. In the SKBS, we use the mutual distil-lation mechanism to learn knowledge from heterogeneous local KBs. Meanwhile, the global KB is compressed to improve the synchronization efficiency. Moreover, a filtering method for KB parameters with noise is applied to mitigate the effects of noise for KB synchronization. The experiment results demonstrate that our proposed approach can assist in establishing a universal global KB and improve the accuracy of multi-user semantic communication while reducing the communication cost during KB synchronization.

Emerging wireless technologies such as 6G and satellite communications need thorough testing and validation before deployment. While NFV (Network Function Virtualization) effectively supports network analysis, evaluation, and testing, it lacks the ability to facilitate research in wireless communication and the convergence of wired and wireless networks. In this paper, we aim to enhance the capabilities of NFV by integrating the ns-3 network simulator with the NFV system. Moreover, we utilize the rich wireless modules in ns-3 to expand wireless communication emulation functions for NFV. Firstly, we discuss the operational principles of integrating the ns-3 emulated wireless network with the NFV network, which implemented by utilizing the communication interface between ns-3 and Linux. Next, we discuss the technical details of expanding the wireless communication emulation function within the NFV system. Furthermore, we provide a case study on the convergence between the NFV-based wired network and the ns-3 emulated MANET (Mobile Ad-hoc NETwork). The experimental results demonstrate that the proposed method has extended the availability of NFV in wireless communication emulation.

Mobile crowdsensing (MCS) has been applied for signal map construction in smart city. MCS leverages the mobility of users and the sensors embedded in mobile phones to collect and transfer sensing data. However, it is still costly for MCS to cover large-scale regions. Accordingly, data recovery algorithms are proposed, which allow participants to collect only few signal data and infer the rest by leveraging spatial-temporal correlation of signals. However, existing work only considered the temporal and 2-D spatial correlation in the plane, while the altitude dimension is not exploited. In this paper, we give an attempt to exploit the 3-D spatial-temporal correlation of signals to infer missing data and reconstruct ground signal map, where UAVs can be used to collect signals from the air. Two UAV-assisted ground signal map construction schemes are proposed based on propagation loss (PL) and convolution neural network (CNN). To further reduce the number of aerial samples required and reduce the cost incurred by UAV, a random-active sampling strategy is proposed to select more valuable signals in our work. Extensive simulations are performed which show that the proposed framework and schemes perform well under extremely high missing rate situations and outperform pure ground-based data recovery schemes. In addition, experiments for both indoor and outdoor are conducted to further verify the effectiveness of the proposed schemes.

In recent years, UAV-assisted mobile edge computing (MEC) has attracted significant attention. However, it is still challenging to dispatch a UAV to accompany ground vehicles and provide both communication and computation support in a highly dynamic environment with various constraints on mobility, coverage, and resources. This study delves into a novel, low-complexity, long-term UAV-assisted vehicular cooperative computation problem, examining the reciprocal impact of vehicles’ flight/driving trajectories and the complementary relationship among different offloading options. Specifically, we formulate a joint optimization problem that considers flying trajectory and offloading decision, aiming to minimize both service delay and energy consumption from a long-term perspective. Due to the time coupling of variables, we employ the Lyapunov optimization framework to decompose the original problem into manageable subproblems for each time slot. Furthermore, we introduce a low-complexity Greedy Bats Algorithm (GBA) to solve the NP-hard two-dimensional generalized assignment problem (TDGAP), optimizing the upper bound of the Lyapunov drift-plus-penalty function to minimize service delay in each time slot. Additionally, we utilize the Successive convex approximation (SCA) algorithm to convert the UAV’s trajectory optimization problem into a convex problem for further low-complexity solution. Simulation results demonstrate that our proposed scheme outperforms other comparative algorithms in terms of computation delay, complexity and energy consumption.

The Industrial Metaverse is driving a new revolution wave for smart manufacturing domain by reproducing the real industrial environment in a virtual space. Real-time synchronization and rendering of all industrial factors result in numerous time-sensitive and computation-intensive tasks, especially matrix multiplication. Distributed edge computing (DEC) can be exploited to handle these tasks due to its low-latency and powerful computing. In this paper, we propose an efficient and reliable coded DEC framework to compute large-scale matrix multiplication tasks. However, an existence of stragglers causes high computation latency that seriously limits the application of DEC in the Industrial Metaverse. To mitigate the impact of stragglers, we design a secure and flexible PolyDot (SFPD) code, which enables information theoretic security (ITS) protection. Several improvements can be achieved with the proposed SFPD. First, it can achieve a smaller recovery threshold than that of the existing codes in almost all settings. And compared with the original PolyDot codes, our SFPD code considers the extra workers required to add ITS protection. It also provides a flexible tradeoff between recovery threshold and communication & computation loads by simply adjusting two given storage parameters$p$and$t$. Furthermore, as an important application scenario, the SFPD code is employed to secure model training in machine learning, which can alleviate the straggler effects and protect ITS of raw data. The experiments demonstrate that the SFPD code can significantly speed up the training process while providing ITS of data. Finally, we provide comprehensive performance analysis which shows the superiority of the SFPD code.

Unmanned Air Vehicle (UAV) has been widely used as the flying edge server to support ground vehicles’ Onboard-Unit (OBU) applications. In this work, we address the challenges of training an adaptive learning model which can be deployed on distributed energy-limited UAVs for making highly-reliable low-latency vehicle-to-UAV (V2U) computation offloading. Firstly, we formulate a two-objective mixed integer programming (MIP) problem for optimizing the energy consumption and offloading utility under the robust reliability constraints. The generalized Chebyshev inequality is applied to transform the chance constraints, and then, the minimum transmission power which satisfies the reliability threshold under the worst case is derived. Then, we decompose the primal problem into the IP subproblem while guaranteeing the Pareto optimality. An adaptive Q-value adjustment based deep reinforcement learning (ADRL) model is proposed, which calculates the expected return in theoretic via the heuristic algorithm, and uses it to replace the Q-value from the target network. The replacement is conducted at an adaptive frequency for saving training time and improving learning results. Comprehensive studies demonstrate the advantages of the proposed ADRL in improving the offloading utility, energy efficiency and convergence rate, when comparing with other classical DRL models and optimization algorithms.

This work investigates how multiple unmanned aerial vehicles (UAVs) assist the large-scale IoT devices (its count$\geq$100) in the edge computing system in accomplishing their tasks. The UAVs serve the latter as edge servers, and fly to footholds to collect task data from the latter, execute tasks locally and return results to the latter. The goal of this work is to minimize overall energy consumption by jointly optimizing the association between each UAV and ground-based IoT devices, deployments of UAVs, and their flight trajectories. To achieve this, this work proposes a joint optimization approach (JOA). It has three parts: 1) an improved k-means method is designed to handle the association between each UAV and ground-based IoT devices, where the number of clusters is equal to that of UAVs, which means that each UAV is responsible for the IoT devices within a cluster; 2) for the deployments of UAVs, an improved fireworks algorithm (IFWA) with variable-length encoding strategy and population size update strategy is proposed to optimize the number and locations of footholds of each UAV, where each member of the population symbolizes a UAV foothold, and each firework and its offspring are considered as the deployment of UAV. Also, the population size update strategy is employed to dynamically change the number of footholds; and 3) regarding UAV flight trajectory, a pre-computed greedy algorithm based on the footholds of UAVs obtained by IFWA is proposed to minimize the total UAV distance. The proposed approach is verified on ten large-scale instances, and the results demonstrate its effectiveness in achieving minimal energy consumption when compared to other state-of-the-art methods.

In unmanned aerial vehicles (UAVs) assisted cellular networks, user association plays an important role in interference control and spectrum efficiency. In this paper, we study the performance of uplink-downlink decoupled (UDDe) user association in a multi-UAV assisted network in which each user can associate with different UAVs or the macro base station (MBS) for uplink (UL) and downlink (DL) transmissions. Since some popular data may be requested by multiple users, grouping these users and applying multicasting can significantly improve spectral efficiency. Unlike traditional linear precoding that treats interference entirely as noise, we propose a rate-splitting multiple access (RSMA) policy that employs rate splitting at the transmitter and successive interference cancellation (SIC) at the receiver. To be specific, the transmitted signal is split into a common part and a private part, and the interference is partially decoded and partially treated as noise. In this context, we formulate a joint optimization problem of UL-DL association and beamforming for maximizing the sum-rate of users in UL and that of multicast groups in DL under the constraints of UAV backhaul capacity and power budget. Since the formulated problem is non-convex with intricate states and an individual UAV may not know the rewards of other UAVs, we convert it into a robust partially observable Markov decision process (POMDP). Then we resort to multi-agent deep reinforcement learning (MADRL) that enables each UAV to learn and optimize its policy in a distributed manner. To achieve an optimal policy, we further propose an improved clip and count-based proximal policy optimization (PPO) algorithm to train actor and critic networks. Simulation results demonstrate the superiority of the proposed decoupled association strategy with RSMA and the MADRL learning algorithm.

In this article, we propose a novel scheduling scheme to guarantee per-packet delay in single-hop wireless networks for delay-critical applications. We consider several classes of packets with different delay requirements, where high-class packets yield high utility after successful transmission. Considering the correla-tionship of delays among competing packets, we apply a delay-laxity concept and introduce a new output gain function for scheduling decisions. Particularly, the selection of a packet takes into account not only its output gain but also the delay-laxity of other packets. In this context, we formulate a multi-objective optimization problem aiming to minimize the average queue length while maximizing the average output gain under the constraint of guaranteeing per-packet delay. However, due to the uncertainty in the environment (e.g., time-varying channel conditions and random packet arrivals), it is difficult and often impractical to solve this problem using traditional optimization techniques. We develop a deep reinforcement learning (DRL)-based framework to solve it. Specifically, we decompose the original optimization problem into a set of scalar optimization subproblems and model each of them as a partially observable Markov Decision Process (POMDP). We then resort to a Double Deep Q Network (DDQN)-based algorithm to learn an optimal scheduling policy for each subproblem, which can overcome the large-scale state space and reduce Q-value overestimation. Simulation results show that our proposed DDQN-based algorithm outperforms the conventional Q-learning algorithm in terms of reward and learning speed. In addition, our proposed scheduling scheme can achieve significant reductions in average delay and delay outage drop rate compared to other benchmark schemes.

The Metaverse is recognized as the next-generation Internet that provides immersive interaction experiences for users. Convolutional neural networks (CNNs) play a crucial role in providing strong immersive experiences in the Metaverse. However, the Metaverse faces challenges in meeting the escalating demands for computing and storage resources due to the explosive growth of convolution tasks, resulting in severe performance degradation. To tackle these issues, coded distributed computing (CDC) is commonly employed. In this paper, we first propose an efficient and reliable mobile-assisted CDC framework to perform large-scale CNN training tasks for the Metaverse. In this framework, the various mobile devices act as workers contributing their resources to collaborate with each other to complete convolution operation tasks. Furthermore, we design a novel resilient, secure, and private coded convolution (RSPCC) scheme for the proposed framework. The RSPCC scheme achieves several significant performances. First, it substantially reduces computation latency compared to conventional convolution. Second, it efficiently mitigates an adverse impact of straggling workers returning results exceedingly slow. Third, we integrate a verifiable computing approach into the encoding/decoding process to check the correctness of the final computation results. Fourth, the PSPCC scheme considers the existence of colluding workers, providing information-theoretic privacy protection for input data. Finally, experimental results demonstrate that our proposed RSPCC scheme can significantly reduce execution time while ensuring the correctness of computation results within the CDC-based Metaverse framework.

Intelligent terminal devices (TDs) usually request delay-sensitive and resource-demanding jobs, which are consisted of many sequential tasks. Mobile edge computing (MEC) offloads tasks to edge networks closer to TDs, making up for the lack of long delay response in the cloud, but it has a limited energy supply. Thanks to low-energy TDs also having processing capacity, it is a critical and challenging issue to offload sequential tasks for sustainable computing and reducing carbon emission in aterminal-edge-cloud(TEC) architecture. Existing research on offloading is limited to MEC orcloud-edgecoordination environment, and ignores the impact of sequential task (S-Task) constraint and service constraint. To bridge the gap, our paper first formulates the jointly optimalS-Taskoffloading and service deployment (JOTOSD) problems objected to maximize the energy utility related to response delay, which is NP-hard and is divided into deployment and offloading sub-problems. Then, we propose a comprehensive offloading and deployment (COD) method, including the Break-Point (BP) algorithm and the convex programming-based edge offloading (CVEO) algorithm under a service deployment strategy provided by an iterative service deployment (ISD) algorithm. Simulate results prove that the proposed method can improve by about 20% of energy utility by compared with other heuristic algorithms.

In this paper, a novel hierarchical game framework for physical layer security (PLS) aware wireless communications with dynamic trilateral coalitions is studied. In the considered system, legitimate users (LUs) aim to transmit secret data to associated base stations (BSs) via uplink communications under the threat of eavesdroppers (EVs), while there also exists jammers (JAs) which may choose to form coalitions with either LUs for increasing their secrecy transmission rates or EVs for increasing their eavesdropping rates in exchange for potential rewards. Different from the existing work, we explore such complicated while dynamic coalition relationships under uncertainties of wireless systems (e.g., time-varying channel conditions), and formulate a hierarchical game integrated with a dynamic trilateral coalition formation game to model strategic interactions among LUs, JAs and EVs. Particularly, we first analyze stability conditions of the trilateral coalitions and propose a hedonic coalition selection and formation algorithm for reaching the stable coalition partition in each time slot. On top of this, we propose a deep reinforcement learning (DRL) based solution, which can achieve the equilibrium with long-term performance guarantees for the hierarchical game running over multiple time slots with dynamic evolutions. Simulations evaluate the proposed solution and show its superiority over counterparts.

To meet the surging wireless traffic demand, underlaying cellular networks with device-to-device (D2D) communication to reuse the cellular spectrum has been envisioned as a promising solution. In this paper, we aim to secure the D2D communication of the D2D-underlaid cellular network by leveraging covert communication to hide its presence from the vigilant adversary. In particular, there are adversaries aiming to detect D2D communications according to their received signal powers. To avoid being detected, the legitimate entity, i.e., D2D-underlaid cellular network, performs power control aiming to hide the D2D communication. We model the conflict between the adversaries and the legitimate entity as a two-stage Stackelberg game. Therein, the adversaries are the followers intending to detect D2D communication at the lower stage while the legitimate entity is the leader and aims to maximize its utility constrained by the D2D communication covertness and the cellular quality of service (QoS) at the upper stage. Different from the conventional works, the study of the combat is conducted from the system-level perspective, where the scenario that a large-scale D2D-underlaid cellular network threatened by massive spatially distributed adversaries is considered and modeled by stochastic geometry. We obtain the adversary’s optimal strategy as the best response from the lower stage and also both analytically and numerically verify its optimality. Taking into consideration the best response from the lower stage and based on the successive convex approximation (SCA) method, we devise a bi-level algorithm to find the optimal strategy of the legitimate entity, which together with the best response from the lower stage constitute the Stackelberg equilibrium. Numerical results are presented to evaluate the network performance and reveal practical insights that instead of improving the legitimate utility by strengthening the D2D link reliability, increasing D2D transmission power will degrade it due to the security concern.

In this paper, an energy efficient scheduling problem for multiple unmanned aerial vehicle (UAV) assisted mobile edge computing is studied. In the considered model, UAVs act as mobile edge servers to provide computing services to end-users with task offloading requests. Unlike existing works, we allow UAVs to determine not only their trajectories but also decisions of whether returning to the depot for replenishing energies and updating application placements (due to limited batteries and storage capacities). Aiming to maximize the long-term energy efficiency of all UAVs, i.e., total amount of offloaded tasks computed by all UAVs over their total energy consumption, a joint optimization of UAVs, trajectory planning, energy renewal and application placement is formulated. Taking into account the underlying cooperation and competition among intelligent UAVs, we reformulate such problem as three coupled multi-agent stochastic games, and then propose a novel triple learner based reinforcement learning approach, integrating a trajectory learner, an energy learner and an application learner, for reaching equilibriums. Simulations evaluate the performance of the proposed solution, and demonstrate its superiority over counterparts.

In this paper, a novel hierarchical game framework for physical layer security (PLS) with dynamic trilateral coalitions is studied. In the considered system, legitimate users (LUs) aim to transmit secret data to associated base stations (BSs) via uplink communications under the threat of eavesdroppers (EVs), while there also exists jammers (JAs) which may choose to form coalitions with either LUs for increasing their secrecy transmission rates or EVs for increasing their eavesdropping rates in exchange for potential rewards. Different from the existing work, we explore such complicated while dynamic coalition relationships under the uncertainties of wireless systems (e.g., time-varying channel conditions), and formulate a hierarchical game integrated with a dynamic trilateral coalition formation game to model the strategic interactions among all three parties, i.e., LUs, JAs and EVs, in PLS. Particularly, we first analyze stability conditions of the trilateral coalitions. On top of this, we further propose a deep reinforcement learning (DRL) based approach for reaching the equilibrium with long-term performance guarantees for the hierarchical game. Simulations evaluate the proposed solution and show its superiority over counterparts.

With the vigorous increase in live video traffic today, more and more live users require low-latency high-quality video streaming. To this end, there have been many Adaptive Bitrate Streaming (ABR) algorithms to adapt video bitrate to network conditions, and most of them are implemented in the client side. Such algorithms typically can only optimize the quality of experience (QoE) for a single user, but are agnostic to the comprehensive video streaming performance of multiple users. The client-based ABR algorithms also cannot provide sufficient utilization of network resources due to the lack of multi-user perspective. Mobile edge computing (MEC) can achieve lower response latency and can obtain network states of multiple users at edge servers, which is a most applicable technology for mobile live streaming. In this paper, we propose a collaborative caching and scheduling (CCS) mechanism for live streaming services in the MEC environment, aiming to improve the overall viewing QoE for multiple users. CCS provides integrated segment scheduling and allocation of bandwidth and cache resources in the edge network to improve the utilization of resources. At the same time, CCS further explores the larger optimization space provided by scalable video coding (SVC) for enhancing the quality of caching and scheduling solutions. According to our simulation results, CCS can provide a better comprehensive QoE for users compared with counterparts.

In this paper, we study the performance of uplink-downlink decoupled (UDDe) user association in unmanned aerial vehicles (UAVs)-assisted cellular networks in which each user can associate with different UAVs or the macro base station (MBS) for uplink (UL) and downlink (DL) transmissions. Since some popular data may be requested by multiple users, grouping these users and applying multicast can significantly improve spectral efficiency. Unlike traditional linear precoding that treats interference entirely as noise, we develop a rate-splitting multiple access (RSMA) policy that employs rate splitting at the transmitter and successive interference cancellation at the receiver. In this context, we formulate a joint optimization problem of UL-DL association and beamforming for maximizing the sum-rate of users in UL and that of multicast groups in DL. Since the resultant problem is non-convex with complex states, we resort to multi-agent deep reinforcement learning (MADRL) that enables each UAV to learn and optimize its policy in a distributed manner. Simulation results show the superiority of the proposed decoupled association policy with RSMA and the MADRL learning algorithm.

With the widespread application of deep learning (DL) technology in the modern Internet of Things (IoT) areas such as autonomous driving, smart cities and homes, embedded real-time systems are increasingly used at the edge of the network to complete various hybrid DNN tasks. Although embedded real-time systems are equipped with heterogeneous CPU and GPU cores to reduce the response time of inference jobs, the computing resources of heterogeneous devices are not fully utilized, and there is still plenty of room for schedulability to be improved. In this paper, we propose a layer-based hybrid deep neural network (DNN) tasks scheduling algorithm in embedded real-time systems (LHTS) that maps DNN layers to CPU and GPU devices and regulates their start time to avoid confliction. We evaluate LHTS through extensive simulations. The experimental results show that LHTS can achieve more sufficient use of heterogeneous CPU and GPU resources in embedded real-time systems, reduce the worst-case execution time and enhance the schedulability performance of hybrid DNN tasks.

Leveraging mobile edge computing (MEC) for task offloading is an effective strategy to address the computational limitations of mobile devices. However, current offloading strategies largely cater to user-centric objectives, neglecting the motives of service providers, unintentionally diminishing their profits. In this work, we propose a novel allocation strategy to improve resource utilization efficiency based on a parallel edge computing system. Specifically, we jointly consider incentives and cross-server resource allocation in parallel-driven MEC. This approach facilitates the distribution of user workloads across multiple edge servers, enhancing system performance and efficiency. In our approach, we leverage the deep deterministic policy gradient (DDPG) algorithm to support task offloading decisions, maximizing the overall profits of service providers. Simulation results show that our approach, compared to non-parallel edge systems, efficiently boosts resource utilization by an average of 13.37%.

Metaverse, also known as the Internet of 3-D worlds, has recently attracted much attention from both academia and industry. Each virtual subworld, operated by a virtual service provider (VSP), provides a type of virtual service. Digital twins (DTs), namely, digital replicas of physical objects, are key enablers. Generally, a DT belongs to the party that develops it and establishes the communication link between the two worlds. However, in an interoperable metaverse, data-like DTs can be “shared” within the platform. Therefore, one set of DTs can be leveraged by multiple VSPs. As the quality of the shared DTs may not always be satisfying, in this article, we propose an agile solution, i.e., a dynamic hierarchical framework, in which a group of Internet of Things devices in the lower level are incentivized to collectively sense physical objects’ status information and VSPs in the upper level determine synchronization intensities to maximize their payoffs. We adopt an evolutionary game approach to model the devices VSP selections and a simultaneous differential game to model the optimal synchronization intensity control problem. We further extend it as a Stackelberg differential game by considering some VSPs to be first movers. We provide open-loop solutions based on the control theory for both formulations. We theoretically and experimentally show the existence, uniqueness, and stability of the equilibrium to the lower level game and further provide a sensitivity analysis for various system parameters. Experiments show that the proposed dynamic hierarchical game outperforms the baseline.

In this article, an energy-efficient scheduling problem for multiple unmanned aerial vehicle (UAV)-assisted mobile-edge computing (MEC) is studied. In the considered model, UAVs act as mobile edge servers to provide computing services to end-users with task offloading requests. Unlike existing works, we allow UAVs to determine not only their trajectories but also the decisions of whether returning to the depot for replenishing energies and updating application placements (due to their limited batteries and storage capacities). With the aim of maximizing the long-term energy efficiency of all UAVs, i.e., the total amount of offloaded tasks computed by all UAVs over their total energy consumption, a joint optimization of UAVs’ trajectory planning, energy renewal, and application placement is formulated. Taking into account the underlying cooperation and competition among intelligent UAVs, we reformulate such optimization problem as three coupled multiagent stochastic games. Since the prior environment information is unavailable to UAVs, we propose a novel triple-learner-based reinforcement learning (TLRL) approach, integrating a trajectory learner, an energy learner, and an application learner, for reaching equilibriums. Moreover, we analyze the convergence and the complexity of the proposed solution. Simulations are conducted to evaluate the performance of the proposed TLRL approach, and demonstrate its superiority over counterparts.

For future Internet of Things (IoT) systems, data-driven and dynamic spectrum-sharing schemes can significantly improve the spectrum utilization and efficiency. However, conventional centralized architecture of such dynamic IoT spectrum-sharing systems is often considered to be nontransparent, costly, and vulnerable to potential attacks and single-point failures. To address the aforementioned issues, a blockchain-based dynamic spectrum-sharing scheme has been proposed and investigated in this work, which aims at enhancing the system by providing desirable features, such as decentralization, transparency, immutability, and auditability. By considering the privacy and transaction dynamics issues when blockchain is integrated into spectrum-sharing systems, a privacy-preserving double auction mechanism based on differential privacy is developed for incentivizing spectrum sharing, where the time-varying valuations of the spectrum resources are also taken into consideration. In the proposed auction, a winner determination problem (WDP) is formulated to decide the winning bidders and spectrum allocation. A deep reinforcement learning (DRL)-based method is then proposed for efficiently solving the WDP. The proposed auction mechanism can be integrated with smart contracts on blockchain platforms. Furthermore, the computation of the DRL-based method for solving the WDP is designed as part of the consensus mechanism in the blockchain. Theoretical analysis show that the proposed privacy-aware double auction mechanism satisfies the properties of differential privacy, individual rationality, and truthfulness. Finally, simulation results are provided to validate the performance of the spectrum-sharing approach.

In recent years, joint radar and communication (JRC) has gained substantial attention due to its high spectrum efficiency and equipment utilization. In this paper, we consider a JRC-enabled multi-UAV cooperative detection scenario, in which each UAV equipped with a JRC unit simultaneously performs the detection function to sense multiple targets and the communication function to transmit the detected data to a fusion center. To strike a trade-off between radar sensory and communication performance for all UAVs, we optimize the transmit power, resource allocation and navigation for each UAV to maximize their sensing scores and the geographical fairness of the targets on the condition of the quality requirements of communication and radar sensing. This problem is a mixed integer non-convex optimization that is challenging to be solved in practice. Considering the complexity of the optimization and dynamics of the UAV environment, we design alearning basedtrajectoryplanning andresourceallocation (LTPRA) algorithm that leverages multiple learning agents to find effective policies from experiences while guaranteeing communication and sensing performance. To improve the environmental exploration of agents, we design an incentive mechanism for their detection behavior and introduce a policy regularization method to mitigate policy overfitting in multi-agent cooperation. Numerical results reveal the convergence performance of the proposed algorithm and show the improvement on detection and communication performance in JRC-enabled multi-UAV detection systems compared with state-of-the-art approaches.

As a novel neural network-based learning framework, a broad learning system (BLS) has attracted much attention due to its excellent performance on regression and balanced classification problems. However, it is found to be unsuitable for imbalanced data classification problems because it treats each class in an imbalanced dataset equally. To address this issue, this work proposes a weighted BLS (WBLS) in which the weight assigned to each class depends on the number of samples in it. In order to further boost its classification performance, an improved differential evolution algorithm is proposed to automatically optimize its parameters, including the ones in BLS and newly generated weights. We first optimize the parameters with a training dataset, and then apply them to WBLS on a test dataset. The experiments on 20 imbalanced classification problems have shown that our proposed method can achieve higher classification accuracy than the other methods in terms of several widely used performance metrics. Finally, it is applied to fault diagnosis in self-organizing cellular networks to further show its applicability to industrial application problems.

Feature selection can be used to solve imbalanced classification problems encountered in big data projects. There often exist multiple feature subsets achieving the same accuracy. These subsets tend to exhibit different acquisition difficulty and reliability, thus offering decision-makers with multiple choices if they can be well-identified. This work formulates feature selection as a Multimodal Multiobjective Problem (MMOP), where a point on Pareto front in objective space has multiple equivalent feature subsets in decision space. To seek more equivalent feature subsets, this work proposes a new multiobjective fireworks algorithm. It extends a latest single-objective fireworks algorithm to a multiobjective version such that it becomes suitable for solving MMOP. An adaptive strategy and special archive guidance are newly designed to improve its performance. A weighted extreme learning machine is chosen to classify datasets and return classification accuracy due to its fast learning speed. Experimental results show that the proposed algorithm outperforms its compared ones on 15 imbalanced classification datasets including 5 low-dimensional, 5 high-dimensional feature selection problems and 5 large-scale problems with larger imbalanced ratio, and its runtime is the least among them. Also, fault diagnosis in self-organizing cellular networks, as an important imbalance classification problem, is performed by the proposed algorithm and the results show that it can perform fault diagnosis well.

In multi-UAV networks, the downlink (DL) and uplink (UL) associations between a UAV and a user equipment (UE) is typically coupled, which restricts each UE to associate to the same UAV for both DL and UL. However, this mode may not be efficient since UAV networks can be heterogeneous (e.g., multi-tier UAV networks) and can experience high link uncertainty due to the mobility of UAVs. The introduction of full-duplex communication in a multi-UAV network further complicates the UE-UAV association. For this reason, the idea of DL-UL decoupling (DUDe) is introduced in this work, with which each UE is allowed to associate with separate UAVs for UL and DL transmissions. Besides, the UE-UAV association depends on the flight trajectory of the UAVs, which makes the DUDe design challenging. In this article, we study the joint decoupled UL-DL association and trajectory design problem for full-duplex multi-UAV networks. A joint optimization problem is formulated with the objective of maximizing the UEs’ sum-rate in both UL and DL. Since the problem is non-convex with sophisticated states and an individual UAV may not know the reward functions of other UAVs, a robust partially observable Markov decision process (POMDP) model is proposed to characterize the model uncertainty. A multi-agent deep reinforcement learning (MADRL) approach is proposed which enables each UAV to select its policy in a distributed manner. To train the actor-critic neural networks in the MADRL approach, an improved clip and count-based proximal policy optimization (PPO) algorithm is developed. In particular, a modified clip distribution is designed to deal with the hard restrictions between current and old policies, and an intrinsic reward is introduced to enhance the exploration capability. Simulation results illustrate the superiority of our proposed schemes when compared to the benchmarks. The codes are made publicly available in GitHub (https://github.com/isdai/MADRL-PPO).

In this article, we investigate the content transmission in a heavy-crowded multiple access cellular network, whose data traffic is offloaded through the combination of edge caching and unmanned aerial vehicle (UAV) communication. In this context, we formulate a novel optimization problem, which minimizes the sum content acquisition delay of users by optimizing the multiuser association and cache placement jointly with UAV trajectory and transmission power over a given flight duration. However, due to the uncertainty of the environment (e.g., random content requests and dynamic UAV positions), it is often difficult and impractical to solve the formulated problem using conventional optimization methods. To this end, we model our problem as a partially observable stochastic game where the macro base station (MBS) and UAVs act as agents to collectively interact with the environment to receive distinctive observations. Moreover, we take advantage of the Proximal Policy Optimization (PPO) learning strategy and propose a novel Dual-Clip PPO-based algorithm to solve the converted problem. To guide agent exploration, a new exploration criterion is proposed in which each UAV agent can obtain an intrinsic reward when it explores beyond the boundary of explored regions (BeBold). Note that the MBS agent has the extrinsic reward given by the environment only. Numerical results reveal that the proposed algorithm outperforms the standard PPO-based deep reinforcement learning algorithm. Moreover, the proposed joint design scheme can achieve a dramatic reduction of content acquisition delay compared with the benchmark schemes.

In this paper, a long-term workload management problem for multi-server edge computing with server collaboration is studied. In the considered model, mobile users’ computation-intensive tasks are generated dynamically over the time and offloaded to associated edge servers according to pre-determined subscription agreements. Upon receiving the subscribed workload, each edge server can then decide to whether participate in server collaboration for enabling workload re-allocation (i.e., workload exchange) with other heterogeneously configured edge servers. Unlike most of the existing work, this paper takes into account both competitions and collaborations among strategic edge servers in sharing their computing capacities. To achieve the equilibrium for each edge server in minimizing its expected cost (including energy consumption, delay, transmission, configuration and pricing costs), a joint optimization is formulated for determining i) its amount of workload to undertake, ii) compensation price charged from peers, and iii) computing speed to adopt. To efficiently solve this problem, we propose a novel cooperative queueing game approach, which integrates a convex optimization, a core cost sharing scheme and a mapping rule. Theoretical analyses and extensive simulations are conducted to evaluate the performance of the proposed solution, and demonstrate its superiority over counterparts.

With the dawn of 5G network, a new set of requirements for site spectrum monitoring, location-based services (LBS), network construction, and cellular planning are emerging, all of which are relying on fine-grained signal map. Although with significant importance, the traditional signal map construction, e.g., through full site survey, could be time-consuming and labor-intensive as the signal varies frequently over time and the accuracy requirement grows rapidly with the emergence of new applications. The state-of-the arts usually employ crowdsourcing scheme and matrix completion algorithm to solve the dilemma. However, the crowdsourcing scheme usually suffers from uneven distributed and inadequate participants, while the matrix completion methods do not take the specific signal map features into account, thus suffering from sub-optimal recovery results. To this end, in this paper, we study how to effectively reconstruct and update the signal map in the case of partially measured signal maps with smaller cost and propose a GAN-based active signal map reconstruction method (GSMAC). Our method is mainly innovative in two parts: GSMC, GAN-based signal map construction, and ACS, an active crowdsourcing scheme. Specifically, GSMC can effectively update the signal map with only a small number of observations while also fully using the incomplete historical signals to effectively update the signal map online. Meanwhile, ACS consists of a reinforce learning-based active query mechanism which quantitatively evaluates the most valuable measurement site for reconstruction, which further reduces the measurement cost to minimum. The simulation results and real implemented data driven experiments demonstrate the advantages and effectiveness of our approach in both accuracy and cost.

Grouping vehicles into platoons is a promising cooperative driving scenario to enhance the traffic safety and capacity of future vehicular networks. However, fast changing channel conditions in multi-platoon vehicular networks cause tremendous uncertainty for resource allocation. In addition, the unprecedented proliferation of various emerging vehicle-to-infrastructure (V2I) applications may result in some service demands with conflicting quality of experience. In this paper, we formulate a multi-objective resource allocation problem, which maximizes the transmission success ratio of intra-platoon communications and the mean opinion score (MOS) of V2I communication links. To efficiently solve this multi-objective optimization problem, we resort to a deep reinforcement learning (DRL) framework. Specifically, we divide it into a set of scalar optimization subproblems based on the weighted sum approach and model each one as a partially observable stochastic game (P-OSG), where each platoon acts as an agent and the actions taken by all platoons correspond to the resource allocation solution. We further propose a contribution-based dual-clip proximal policy optimization (CD-PPO) algorithm to deal with each subproblem, which is a DRL algorithm based on the actor-critic framework. The network parameters of all subproblems are then optimized collaboratively by using the proposed training algorithm and the neighborhood parameter transfer strategy. The desired Pareto front is obtained when all subproblems are solved. Simulation results reveal that the proposed algorithm can outperform other algorithms in terms of the MOS and transmission success ratio.

Over-the-air federated learning (AirFL) has developed as a communication-efficient solution to enable distributed machine learning over edge devices by integrating computation and communication into a joint design. However, the aggregation error caused by noise and wireless channel fading may lead to a compromised learning performance in an AirFL system. Potential malicious participants can also cause this compromise such that decoding the individual uploaded model updates at the server side to perform security examination is still imperative for AirFL. In this paper, we investigate a novel multi-objective resource allocation problem to combat against such aggregation error and improve the information transmission efficiency of uplink by jointly optimizing the device selection, power allocation and receive scalar control. The objective of the multi-objective optimization problem (MOP) is to minimize the average mean squared error (MSE) of the over-the-air aggregation for different communication rounds and maximize the long-term energy efficiency (EE) of the system. Considering the complexity and dynamic environment, we present a deep reinforcement learning (DRL) based framework to solve the MOP. The MOP is firstly decomposed into multiple subproblems. Each subproblem is modelled as a neural network, which can be addressed by the proposed learning-based resource allocation (LRA) algorithm. The numerical results illustrate that our proposed approach can effectively tackle the MOP and outperform the benchmark approaches with appropriate training mechanism and reward design.

As conservative intersection management, signalized intersection has a significant bottleneck in improving traffic efficiency when it comes to connected autonomous vehicles (CAVs). In this paper, to make the intersection management more fine-grained, a decentralized conflict-free coordination scheme is tailed for CAVs at intersections without traffic signals. First, the problem of multiple vehicles navigation through an unsignaled intersection is formulated as a Partially Observable Stochastic Game (POSG). Second, we propose a cooperative multi-agent proximal optimization algorithm (CMAPPO) to make driving-decision for each CAV agent and achieve collaboration in a distributed manner. Finally, simulations are carried out on SUMO to evaluate the proposed method. The results show that the CMAPPO has significant effectiveness in solving the multi-vehicle coordination at intersections.

In this paper, a joint optimization of sensor activation and mobile charging scheduling for industrial wireless rechargeable sensor networks (IWRSNs) is studied. In the considered model, an optimal sensor set is selected to collaboratively execute a bundle of heterogeneous tasks of production-line monitoring, meeting the quality-of-monitoring (QoM) of each individual task. There is a mobile charger vehicle (MCV) which is scheduled for recharging sensors before their charging deadlines (i.e., the time instant of running out of their energy). Our goal is to jointly optimize the sensor activation and MCV scheduling for minimizing the energy consumption of the entire IWRSN, subjected to tasks’ QoM requirements, sensor charging deadlines and the energy capacity of the MCV. Unfortunately, solving this problem is non-trivial, because it involves solving two tightly coupled NP-hard problems. To address this issue, we design an efficient algorithm integrating deep reinforcement learning and marginal product based approximation algorithm. Simulations are conducted to evaluate the performance of the proposed solution and demonstrate its superiority over counterparts.

Nowadays, diverse cloud services generate a mix of deadline and non-deadline data flows that constitute the mix-flow environment in data center networks. Deadline flows are mainly generated by user-interactive services and must be completed within deadlines, while non-deadline flows are usually produced by data-parallel services and desire a shorter completion time. To satisfy their performance requirements simultaneously, most existing mix-flow scheduling algorithms are dedicated to balancing the resource contention between these two types of flows. However, routing should also be considered in conjunction with scheduling because inappropriate routing tends to prevent scheduling from playing a valid role. In this paper, we propose ORSM, an online routing and scheduling mechanism for mix-flow transport. We formalize the mix-flow routing and scheduling problem as a mixed integer programming problem. ORSM then solves this problem in a distributed manner by leveraging the intrinsic feedback mechanism to determine the path and transmission rate for each flow. Extensive simulation results show that ORSM can effectively reduce the deadline miss ratio of deadline flows by up to 35.7% as well as the average flow completion time of non-deadline flows by up to 38.6% compared to state-of-art mechanisms.

Coded distributed computing(CDC) has shown great potentials to solve the unexpected delay caused by stragglers and communication load in distributed computing. We propose a novel learning auction to allocate computing resource efficiently in a CDC scenario. The user demand types are usually het-erogeneous according to different variation trends of the value with finish time and workload, which can be modeled by deep learning. As the goal of social welfare maximizationthe platform would allocate computing resources according to inferred value functions of users. Due to the uncertain finish time and nonlinear structures of deep learning models, the considered optimization problem is non-convex. We then reformulate the non-convex optimization problem into a mixed integer program(MIP). After analyzing the inference error caused by deep learning, a payment rule referred to VCG is designed to achieve incentive alignment and individual rationality. Besides, experiments have been performed to show the superiority of our mechanism.

In this paper, a multi-layer edge computing frame-work for the virtual machine (VM) placement and computation offloading in industrial Internet of Things (IIoT) is proposed. Unlike most existing works, we focus on addressing the temporal dependency among tasks in an IIoT task flow, and consider that there is a stringent requirement on its completion time (including the transmission time, computation time and waiting time). For striking a balance between the system completion time and the energy consumption while satisfying the storage capacity of edge servers (ESs), completion deadline of time-sequential task flows, and placement requirements of VMs, we design a many-to-one matching game (MGVDA) to jointly determine the optimal VM placement and task offloading decisions. Finally, we prove that the resulted matching game solution is effective and stable. Simulation results examine the efficiency of the proposed MGVDA and show its superiority over the counterparts.

We study the joint decoupled uplink (UL)-downlink (DL) association and trajectory design problem for full-duplex multi-UAV networks. A joint optimization problem is formulated aiming to maximize the sum-rate of user equipments (UEs) in both UL and DL. Since the formulated problem is non-convex and with sophisticated states, a multi-agent deep reinforcement learning (MADRL) approach is employed for enabling each agent (i.e., UAV) to select policy in a distributed manner. Moreover, in order to obtain the optimal policy, a clip-and-count based proximal policy optimization (PPO) algorithm is proposed to train actor-critic neural networks. In particular, a modified clip distribution is designed to deal with the hard restrictions between current and old policies, and an intrinsic reward is introduced to enhance the exploration capability. Simulation results demonstrate the significant performance improvement of our proposed schemes when compared to the benchmarks.

This paper investigates the content distribution in a hotspot area in which multiple cache-enabled unmarried aerial vehicles (UAVs) are deployed to offload part of the data traffic in a heavy-crowded cellular network. We formulate an optimization problem which minimizes the sum content acquisition delay of all users by designing the multiuser association and cache placement jointly with UAV transmission power and trajectory over a given flight duration. The non-convexity of the formulated problem and the uncertainty of the dynamic environment make it difficult and impractical to solve using traditional optimization methods. Thus we model our problem as a partially observable stochastic game where the macro base station (MBS) and UAVs act as agents and interact with the environment to receive distinctive observations. To guide exploration, we propose a new exploration criterion that gives each UAV agent an intrinsic reward when it explores beyond the boundary of explored regions (BeBold). Then we propose a Dual-Clip Proximal Policy Optimization (DC-PPO) algorithm to solve our problem. Extensive numerical results demonstrate that the proposed algorithm is superior than the PPO-based algorithm and the DC-PPO-based algorithm without exploration criterion.

Edge–cloud collaboration is critical in the Industrial Internet of Things (IIoT) for serving computation-intensive tasks (e.g., bearing fault monitoring) that require low-response delay, low energy consumption, and high processing accuracy. In this article, an energy-efficient resource management framework for IIoT with closed-loop control on end devices, edge servers, and cloud center is studied. In the considered model, each edge server aggregates the data collected by industrial sensors (i.e., end devices) and forms computation tasks for corresponding data analysis. In order to minimize the system-wide energy consumption, while maintaining a guaranteed service delay and a satisfied data processing accuracy for each IIoT application, a joint optimization of: 1) sensors’ sampling rate adaption; 2) edge servers’ preprocessing mode selection; and 3) edge–cloud communication and computing resource allocation is formulated. Further taking into account the time-varying channel conditions and randomness of data arrivals, we propose a low-complexity online algorithm, which solves the problem in a dynamic manner. Particularly, the Lyapunov optimization method is first utilized to decompose the long-term problem into a series of instant ones [mixed-integer nonlinear programming (MINLP) problems], and then a Markov approximation algorithm is applied to solve such instant problems to near optimum with the consideration of future impacts. Performance analyses and simulation results show that the proposed algorithm is feasible under long-term service satisfaction constraints, and its energy consumption and service delay are approximately 20% and 28% lower than those of the benchmark schemes, respectively.

Coded distributed computing(CDC) has shown great potentials to solve the unexpected delay caused by stragglers in distributed computing. In this paper, we focus on the auction design for efficient resource allocation in CDC. Specifically, we aim to design a learning auction mechanism to handle heterogeneous user demands and also to free users from the complexity of specifying valuations for resource combinations, which increases exponentially with the resource dimensions. The user demand type is heterogeneous according to different variation trends of the value with finish time and workload, which is modeled by deep learning. The platform would allocate resources according to the user value function. Then users do not need to consider the complex relationship between uncertain finish time and resource configuration in CDC. Due to the inference error of the learning model and the complexity of calculating uncertain finish time, the considered social welfare optimization problem is a non-linear and non-convex integer problem. Even worse, the typical VCG-based payment scheme cannot guarantee truthfulness with the inference error. In response to these difficulties, we transform the social welfare optimization problem into a mixed integer programming problem which already has efficient solutions. The social welfare gap caused by the inference error is analyzed theoretically. The relationship between the utility regret of reporting truthfully and the inference error is also analyzed. We prove that our mechanism satisfies incentive alignment and individual rationality. Extensive experiments show the superiority of our mechanism compared with existing ones.

This work investigates an unmanned aerial vehicle (UAV) assisted IoT system, where a UAV flies to each foothold to collect data from IoT devices, and then return to its start point. For such a system, we aim to minimize the energy consumption by jointly optimizing the deployment and flight trajectory of UAV. It is a mixed-integer non-convex and NP-hard problem. In order to address it, a bilevel optimization approach is proposed, where an upper-level method aims to optimize the deployment of UAV and a lower-level one aims to plan UAV flight trajectory. Specifically, the former optimizes the number and locations of footholds of UAV. This work proposes an improved dandelion algorithm with a novel encoding strategy, in which each dandelion represents a foothold of UAV and the entire dandelion population is seen as an entire deployment. Then, two mutation strategies are designed to adjust the number and locations of footholds. Based on the footholds of the UAV provided by the former, the latter transforms flight trajectory planning into a traveling salesman problem (TSP). This work proposes an iterated greedy algorithm to solve it efficiently. The effectiveness of the proposed bilevel optimization approach is verified on ten instances, and the experimental results show that it significantly outperforms other benchmark approaches.

In Internet of Electric Vehicles (IoEV), mobile charging stations (MCSs) can be deployed to complement fixed charging stations. Currently, the strategy of MCSs is to move towards the EVs with insufficient energy (IEVs) only after being requested, which is not efficient. However, similar to online car-hailing services, more IEVs could be charged and the charging expenses could be reduced if idle MCSs can actively move towards the potential charging positions. In this paper, the problem of placements of idle MCSs in an IoEV is investigated in order to enhance the proportion of charged IEVs and reduce the charging expenses of IEVs. To this end, we propose a Federated Learning based Placement Decision Method of Idle MCSs (FL-PDMIM) to help the idle MCSs to predict the future charging positions, by exploiting the historical routes of MCSs which contain rich information regarding the charging demand of IEVs. In the proposed framework, the historical routes are trained locally by each MCS, and then the local model parameters and charging records are periodically uploaded to an edge server for a global parameter aggregation. Then, idle MCSs decide their placements according to the predicted charging positions (potential charging positions). The training time can be largely shortened, because the distributed learning on each MCS is executed in parallel. Extensive simulations and comparisons demonstrate the performance superiority of FL-PDMIM. Specifically, with the proposed federated learning-based predictions, the waiting time of IEVs to be served can be significantly shortened, and FL-PDMIM enhances the proportion of charged IEVs and reduces the charging expenses of IEVs effectively.

In this paper, the computation resource configuration for vehicular edge computing is investigated in this study. Dissimilar to a large portion of the current literature, we center around the problem of determining the optimal edge computing resource allocation to vehicles with computation offloading requests for maximizing the long-term management profit of the network operator (i.e., the road-side unit of the vehicular network) under the randomness of vehicular traffics and task processing. A multi-type management framework is used to characterize the heterogeneities among different vehicles in terms of their edge computing quality-of-service (QoS) requirements. A novel fluid model is proposed that facilitates the formulation of the corresponding resource optimization problem by taking into account the system’s steady state characteristics with dynamic evolutions. In addition, rather than considering fixed QoS requirements in long-run, we explore the impact of the resulted service quality on the QoS requirements determined by vehicles. The QoS requirements of each vehicle is allowed to change adaptively according to the service quality fed back by the system. Based on this, we propose a simple but efficient approach, called threshold-based computation resource configuration scheme (TCRCS). The proposed solution’s performance is assessed by theoretical analysis and simulations, which show that it outperforms competitors.

User association is a crucial aspect which greatly affects the performance of wireless networks. In this work, we investigate the user association problem in full-duplex cellular networks, wherein base stations (BSs) are densely deployed with highly variable transmit powers and topologies (e.g., heterogeneous networks). To enhance the system performance, decoupled UL-DL (DUDe) association is considered, which enables each user equipment (UE) to associate with different BSs in uplink (UL) and downlink (DL), respectively. Considering the challenges raised by asymmetric information (e.g., channel gains and intercell interferences) between UEs and BSs, we propose a contract-theory based distributed user association approach. Specifically, the association process is modeled as a labor market, where the BSs act as employers and offer two-dimensional contracts to employees (i.e., UEs) for maximizing the utility of the BS. Theoretical proof for contract feasibility is presented by providing sufficient and necessary conditions. To reach the optimality, a contract-theoretic decoupled user association algorithm is developed, in which a BS broadcasts the drafted contracts, and each UE self-selects the optimal contract by considering her own demands. Numerical results are presented to demonstrate the performance of the proposed approach in terms of node utilities and social surplus. Impacts of system settings on the network performance are also investigated.

In this paper, a novel management framework for fog computing with strategic computing speed control at fog nodes (FNs) is studied. In the considered model, mobile users declare requests of offloading resource-hungry computation tasks that are dynamically collected at a dedicated edge server (ES). Upon receiving these requests, the ES can decide to either self-process or delegate some workloads to third-party FNs for maximizing the overall management profit. Unlike the existing work, this paper takes into account strategic behaviors of FNs in computing speed control, i.e., each FN can strategically allocate its computing resource to maximize its utility, which consists of the benefit gained from executing offloaded tasks and the cost incurred by dissatisfied (delayed) service to its own subscribed tasks. To jointly address the long-term system performance and FNs’ strategic interactions, a scheduling mechanism integrating a noncooperative game and a queueing model is formulated. We then investigate two delegation reward settings, i.e., constant and utility-dependent delegation prices, and propose efficient adaptive algorithms to determine the optimal workload distribution at the ES and the computing speed equilibrium among FNs. Both theoretical analyses and simulations are conducted to evaluate the performance of the proposed solutions and demonstrate their superiorities over counterparts.

Wireless virtualization has become a key concept in future cellular networks which can provide multiple virtualized wireless networks for different mobile virtual network operators (MVNOs) over the same physical infrastructure. Resource allocation is a main challenging issue in wireless virtualization for which auction approaches have been widely used. However, for most existing auction-based allocation schemes, the objective is to maximize the social welfare (i.e., the sum of all valuations of winning bidders) due to its simplicity. While in reality, MVNOs are more interested in maximizing their own revenues (i.e., received payments from auction winners). However, the revenue-optimal auction problem is much more complex since the payment price is unknown before calculation. In this paper, we aim to design a revenue-optimal auction mechanism for resource allocation in wireless virtualization. Considering the complexity, deep learning techniques are applied. Specifically, we construct a multi-layer feed-forward neural network based on the analysis of optimal auction design. The neural network adopts users’ bids as the input and the allocation rule and conditional payment rule for the users as the output. The proposed auction mechanism possesses several desirable properties, e.g., individual rationality, incentive compatibility and budget constraint. Finally, simulation results demonstrate the effectiveness of the proposed scheme. Comparing with second-price auction and optimization-based schemes, the proposed scheme can increase the revenue by 10 and 30 percent on average, for single MVNO and multi-MVNO cases, respectively.

A Dandelion algorithm (DA) inspired by the seed dispersal process of dandelions has been proposed as a newly intelligent optimization algorithm. For improving its exploration ability as well as reducing the probability of its falling into a local optimum, this work proposes to add a novel competition mechanism with historical information feedback to current DA. Specifically, the fitness value of each dandelion in the next generation, which is calculated by linear prediction, is compared with the current best dandelion, and the loser is replaced by a new offspring. Current DA generates new offsprings without considering historical information. This work improves its offspring generation process by exploiting historical information with an estimation-of-distribution algorithm. Three historical information models are designed. They are best, worst, and hybrid historical information feedback models. The experimental results show that the proposed algorithms outperform DA and its variants, and the proposed algorithms are superior or competitive to nine participating algorithms benchmarked on 28 functions from CEC2013. Finally, the proposed algorithms demonstrate the effectiveness on four real-world problems, and the results indicate that the proposed algorithms have better performance than its peers.

Feature selection has been considered as an effective method to solve imbalanced classification problems. It can be formulated as a multiobjective optimization problem (MOP) aiming to find a small feature subset while achieving a high classification accuracy. With traditional MOP, the focus is on deriving an optimal solution (i.e., a feature subset), while ignoring the diversity in solution space (e.g., there could exist multiple feature subsets achieving the same accuracy). Providing more options for feature selection would be beneficial since some features can be more difficult to obtain than others. In this work, we treat feature selection as a multimodal MOP (MMOP) whose goals are to find an excellent Pareto front in objective space and as many equivalent Pareto optimal solutions (feature subsets) as possible in feature space. Note that though several multimodal multiobjective evolutionary algorithms (MMEAs) have been proposed, their use of a convergence-first selection criterion could cause the loss of solution diversity in an objective and feature space. To address the issue, a novel competition-driven mechanism is designed to assist the existing multimodal MMEAs in locating more equivalent feature subsets and a desired Pareto front. The effectiveness of the proposed mechanism is first verified on all 22 MMOPs from CEC2019. Then, the proposed method is applied to feature selection in imbalanced classification problems and a real-world application, i.e., credit card fraud detection. Experimental results show that the proposed mechanism can not only provide more equivalent feature subsets but also improve classification accuracy.

We study the joint user association and resource allocation problem in both uplink (UL) and downlink (DL) for full-duplex heterogeneous cellular networks (HCNs), wherein base stations (BSs) are densely deployed with reusable subchannels and highly variable transmit powers. To reap the benefits of BS densification, decoupled multiple-association (DMA) is considered, which enables each user equipment (UE) to associate with multiple BSs for UL and DL in a decoupled manner. Furthermore, in order to provide the best service, appropriate holistic subchannel and power allocation are jointly studied and an optimization problem is formulated. However, it is challenging to solve the joint problem due to its combinatorial nature. To this end, we formulate a novel distributed four-sided matching game in which the UEs, BSs, subchannels, and power levels are ranked based on designed preference metrics for optimal matching. To obtain the solution, a low-complexity algorithm is developed. The convergence of the algorithm to a stable matching is proved and the worst-case complexity is analyzed. Numerical results are presented to demonstrate the performance of the proposed scheme in terms of the UEs’ sum-rate in UL and DL, respectively. The superiority of DMA is also investigated by comparisons.

In this paper, we address dynamic network selection problems of mobile users in an intelligent reflecting surface (IRS)-enabled wireless network. In particular, the users dynamically select different service providers (SPs) and network services over time. The network services are composed of adjustable resources of IRS and transmit power. To formulate the SP and network service selection, we adopt an evolutionary game in which the users are able to adapt their network selections depending on the utilities that they achieve. For this, the replicator dynamics is used to model the service selection adaptation of the users. To allow the users to take their past service experiences into account their decisions, we further adopt an enhanced version of the evolutionary game, namely fractional evolutionary game, to study the SP and network service selection. The fractional evolutionary game incorporates the memory effect that captures the users’ memory on their decisions. We theoretically prove that both the game approaches have a unique equilibrium. Finally, we provide numerical results to demonstrate the effectiveness of our proposed game approaches. In particular, we have reveal some important finding, for instance, with the memory effect, the users can achieve the utility higher than that without the memory effect.

Energy consumption accounts for a significant portion of OPEX in 5G networks, which will be further increased when millimeter-wave (mmWave) base stations are deployed. To reduce the cost, renewable energy has been introduced to provide complementary power supply. Nevertheless, how to cost-efficiently utilize radio resources and renewable energy remains a challenge. In this paper, we jointly investigate the beamwidth management and resource allocation in mmWave backhaul HetNets with hybrid energy supply aiming to maximize long-term cost efficiency. This requires solving a mixed stochastic combinatorial optimization problem, characterizing the causal property of renewable energy harvesting process, stochastic channel conditions, and imperfect antenna alignment. Considering the complexity and dynamic environment, a learning system is established instead of using traditional optimization methods which typically experience exponential worst-case complexity and require complete information. Specifically, we propose a Learning-based Cost-efficient Resource Allocation (LCRA) algorithm that employs deep neural network to learn policies from experiences to ensure system performance while achieving cost-efficiency. To enhance the sampling efficiency and stability of the conventional deep reinforcement learning methods for our problem, an improved proximal policy optimization method is proposed to reuse the history samples. Specifically, a modified clip function is designed to deal with the hard restrictions between current and old policies. Furthermore, random network distillation is introduced to enhance the exploration capability. Numerical results reveal the convergence performance of the LCRA and the superiority in improving the cost efficiency in a hybrid energy powered mmWave backhaul HetNet compared with state-of-the-arts

Scalable video coding (SVC) has received much attention for video transmission over wireless due to its flexibility. However, most previous work only considered SVC video streaming from a single base station (BS). At present, the densification of BSs enables a user equipment (UE) to connect to multiple BSs in ultra-dense networks (UDNs). In this paper, we consider the problem of SVC video streaming in a UDN, which allows different layers of a video block to be downloaded from different BSs. An optimization problem is formulated aiming to maximize the quality of experience (QoE) of users by selecting the optimal connection strategy and optimal number of video layers. Considering the complexity, to efficiently solve the problem in a distributed manner, the problem of choosing connection strategy is formulated as a multi-agent multi-armed bandit (MA-MAB) problem with only few information exchange. Each user can adapt its connection strategy in a distributed self-learning system. To obtain the optimal arm for the MA-MAB problem, we propose a multi-user arm decision algorithm. To avoid large computation and handover costs, we adopt the same connection strategy for the entire video sequence. Then for each video block, with the given connection strategy, the number of video layers is adjusted adaptively according to dynamic network conditions. Finally, based on the above designs, we provide the SVC-based video downloading scheme to obtain an approximate optimal solution to the original optimization problem. Extensive simulations and comparisons show the feasibility and superiority of the proposed scheme.

Mobile charging services (MCSs) have been developed as a supplement charging method for electric vehicles (EVs), wherein energy replenishment is provided by mobile charging vehicles (MCVs). An MCV has an internal storage system employed to replenish the energy of a certain number of EVs. Charging scheduling of MCV is one of the key issues on the Internet of EVs for providing efficient and convenient charging services, which requires determining the charging sequence and the amount of energy when serving multiple EVs by one MCV. In this paper, a multi-objective MCV scheduling problem is investigated. By optimizing the charging sequence and the actual amount of energy being charged, the proposed framework aims to minimize the EV waiting time while simultaneously to maximize the charging benefits of all EVs. To solve the multi-objective optimization problem (MOP), a deep reinforcement learning (DRL) based framework is further explored. The MOP is first decomposed into a set of subproblems. Each subproblem is modelled as a neural network, wherein an actor-critic algorithm and a modified pointer network are adopted to solve each subproblem. Pareto optimal solutions can be directly obtained through the trained models. The experimental results demonstrate that the proposed method can efficiently and effectively solve the MCV scheduling problem and outperform NSGA-II and MOEA/D in terms of solution convergence, solution diversity, and computing time. In addition, the trained model can be applied to newly encountered problems without retraining.

Radio environment monitoring is crucial for many network engineering applications. Integrated with mobile crowdsourcing (MCS), radio map can be updated by mobile users in a low-cost manner. However, the crowdsourced measurement data may get quite sparse, and contain noises and errors. Therefore, how to efficiently infer missing data under low-quality measurements is critical in crowdsourced radio map construction. Existing inference methods like matrix completion require certain strict conditions, e.g. missing at completely random (MACR), which is impractical in the city-scale sensing. To address these issues, we propose a deep learning scheme based on adversarial auto-encoder (AAE) to handle measurements with large missing regions and complicated loss patterns. Specifically, this scheme applies variational auto-encoder (VAE) to infer missing data, and further utilizes the adversarial nets to play a min-max game with the VAE to improve recovery quality. Comprehensive experiments on three real datasets show that the proposed scheme can outperform state-of-the-art methods under large missing rates and low-quality measurements.

Continuous and accurate respiratory volume monitoring is crucial in many healthcare-related applications. Traditional respiratory volume monitoring approaches involve obtrusive devices that are uncomfortable for long-term monitoring, while unobtrusive approaches mainly focus on sensing the respiratory rate, which is insufficient for many healthcare-related applications. In this article, we present radio-frequency respiratory volume monitoring (RF-RVM), an unobtrusive system to sense the respiratory volume based on commercial off-the-shelf (COTS) RFID devices. Specifically, RF-RVM continuously collects the temporal phase information from tags attached to the chest and abdomen to extract the chest displacement and abdomen displacement caused by respiration. Then, we assess the respiratory volume by training a backpropagation neural network model to correlate chest and abdomen displacements and respiratory volume. We use a reference tag attached under the user's neck to eliminate the noise caused by slight movements of the upper body during respiration. We implement and evaluate RF-RVM based on COTS RFID devices. The experimental results show that RF-RVM can continuously monitor user's respiratory volume with an average accuracy of 94.52% for leave-one-session-out cross-validation and 91.96% for leave-one-record-out cross-validation based on a data set sampled from 20 volunteers.

With the exponential growth of data traffic, the use of caching and device-to-device (D2D) communication has been recognized as an effective approach for mitigating the backhaul bottleneck in unmanned aerial vehicle (UAV)-assisted networks. In this article, we investigate the issue of secure transmission in a cache-enabled UAV-relaying network with D2D communications in the presence of an eavesdropper. Specifically, both UAVs and D2D users are equipped with cache memory, which can prestore some popular content to collaboratively serve users. Considering the fairness among users, we formulate an optimization problem to maximize the minimum secrecy rate among users, by jointly optimizing the user association and UAV scheduling, transmission power, and UAV trajectory over a finite period. The joint design problem is a nonconvex mixed-integer programming problem. To efficiently solve this problem, we propose an alternating iterative algorithm based on the block alternating descent and successive convex approximation methods. Specifically, the user association and UAV scheduling, UAV trajectory, and transmission power are optimized alternately in each iteration, and the convergence of the algorithm is proven. Extensive numerical results show that the proposed joint design scheme significantly outperforms other benchmark schemes in terms of the secrecy rate.

Unmanned aerial vehicles (UAVs) have been introduced into wireless communication systems to provide high-quality services and enhanced coverage due to their high mobility. In this article, we study a UAV-assisted mobile-edge computing (MEC) system in which a moving UAV equipped with computing resources is employed to help user devices (UDs) compute their tasks. The computing tasks of each UD can be divided into two parts: one portion is processed locally and the remaining portion is offloaded to the UAV for computing. Offloading is enabled by uplink and downlink communications between UDs and the UAV. On this basis, two types of access modes are considered, namely, nonorthogonal and orthogonal multiple access. For both access modes, we formulate new optimization problems to minimize the weighted-sum energy consumption of the UAV and UDs by jointly optimizing the UAV trajectory and computation resource allocation, under the constraint on the number of computation bits. These problems are nonconvex optimization problems that are difficult to solve directly. Accordingly, we develop alternating iterative algorithms to solve them based on the block alternating descent method. Specifically, the UAV trajectory and computation resource allocation are alteratively optimized in each iteration. Extensive simulation results demonstrate the significant energy savings of our proposed joint design over the benchmarks.

The ever-expanding applications of mobile crowdsensing have made scalable environment sensing possible by exploiting the power of ubiquitous smart devices. Nevertheless, the implementation of sensing applications in urban scale meets serious challenges in terms of sensing costs and quality. For example, data sparsity will arise due to sensing ability and cost, and the measurements could contain noise or errors. Therefore, missing data inference with low-quality measurements is critical. To tackle these challenges, we design a low-cost crowdsensing system by missing data inference incorporating with active sensing grids selection. Specifically, an adversarial autoencoder (AAE)-based scheme is proposed for missing data inference. This model applies VAE to learn latent variables and generates full data and further utilizes the adversarial nets to play a min-max game with the autoencoder. Furthermore, an active learning-based method is designed to iteratively select sensing grids to further reduce the cost. The proposed scheme can handle large missing rate, both random and block missing patterns, and is robust against measurement noise. Comprehensive experiments based on three data sets are conducted to evaluate the effectiveness of the proposed system.

Different from multiobjective optimization problems (MOPs), multimodal MOPs (MMOPs) focus on both decision and objective spaces rather than only objective one. Thus, finding a good Pareto front approximation and finding the maximal number of equivalent Pareto optimal solutions for each objective vector in the Pareto front are two core tasks for them. Although some multimodal multiobjective evolutionary algorithms have been proposed to handle them, they can quickly converge to the easy-to-find equivalent Pareto optimal solutions, thereby losing their ability to improve solution diversity in decision space and performance in objective space. To address the above issues, this work proposes a new information utilization method. Its core idea is to randomly extract a certain amount of decision variable information from the current optimal solutions to construct an information vector, which is, in turn, used to assist the generation of elite solutions. The proposed method can assist any available intelligent optimizers to improve their performance in solving MMOPs. This is confirmed by experimental results obtained from solving 22 such problems from CEC2019 and 12 scalable imbalanced distance minimization problems through a number of optimizers. Finally, we apply the proposed method to credit card fraud detection problems to show its practical significance.

Along with the exponentially increasing quantity of intelligent terminals connected to the Internet, the spectrum competition among users becomes more and more severe in wireless networks. The network have not the ability to satisfy all communication requirements due to the significantly increasing users and demanded rates. Energy-aware admission control has been proved to be an efficient way to tackle the infeasibility caused by the severe spectrum competition among users. However, the traditional admission control is limited by gradually removing chosen users, and pays less attention to the fairness. In this article, we elaborate the concept of the fairness in a max-min optimization problem with respect to the transmission rates, by leveraging the model of bit error rates with Q-function for general fading communications. Then, we make use of the max-min rate fairness to smartly determine the subset of users to be admitted in wireless networks. Meanwhile, the overall energy consumption is minimized and the network fairness is guaranteed. In particular, the algorithms can tackle more than one user at each iteration. Numerical evaluations show the effectiveness of the algorithms.

Heart rate (HR) estimation based on photoplethysmography (PPG) signals has been widely adopted in wrist-worn devices. However, the motion artifacts caused by the user’s physical activities make it difficult to get the accurate HR estimation from contaminated PPG signals. Although many signal processing methods have been proposed to address this challenge, they are often highly optimized for specific scenarios, making them impractical in real-world settings where a user may perform a wide range of physical activities. In this article, we propose DeepHeart, a new HR estimation approach that features deep-learning-based denoising and spectrum-analysis-based calibration. DeepHeart generates clean PPG signals from electrocardiogram signals based on a training data set. Then a set of denoising convolutional neural networks (DCNNs) are trained with the contaminated PPG signals and their corresponding clean PPG signals. Contaminated PPG signals are then denoised by an ensemble of DCNNs and a spectrum-analysis-based calibration is performed to estimate the final HR. We evaluate DeepHeart on the IEEE Signal Processing Cup training data set with 12 records collected during various physical activities. DeepHeart achieves an average absolute error of 1.61 beats per minute (bpm), outperforming a state-of-the-art deep learning approach (4 bpm) and a classical signal processing approach (2.34 bpm).

Improving energy efficiency has shown increasing importance in designing future cellular system. In this work, we consider the issue of energy efficiency in D2D-enabled heterogeneous cellular networks. Specifically, communication mode selection and resource allocation are jointly considered with the aim to maximize the energy efficiency in the long term. And an Markov decision process (MDP) problem is formulated, where each user can switch between traditional cellular mode and D2D mode dynamically. We employ deep deterministic policy gradient (DDPG), a model-free deep reinforcement learning algorithm, to solve the MDP problem in continuous state and action space. The architecture of proposed method consists of one actor network and one critic network. The actor network uses deterministic policy gradient scheme to generate deterministic actions for agent directly, and the critic network employs value function based Q networks to evaluate the performance of the actor network. Simulation results show the convergence property of proposed algorithm and the effectiveness in improving the energy efficiency in a D2D-enabled heterogeneous network.

Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) system is an appealing concept, where a fixed-wing UAV equipped with computing resources is used to help local resource-limited user devices (UDs) compute their tasks. In this paper, each UD has separable computing tasks to complete, which can be divided into two parts: one portion is processed locally and the other part is offloaded to the UAV. The UAV moves around above UDs and provides computing service in an orthogonal frequency division multiple access (OFDMA) manner. This paper aims to minimize the weighted sum energy consumption of the UAV and UDs by jointly optimizing resource allocation and UAV trajectory. The resulted optimization problem is nonconvex and challenging to solve directly. With that in mind, we develop an iterative algorithm for solving this problem based on the block coordinate descent method, which iteratively optimizes resource allocation variables and UAV trajectory variables till convergence. Simulation results show significant energy saving of our proposed solution compared to the benchmarks.

In social and economic fields, the peer effect and its influence gradually attract public attention. In this paper, we explore the interactions between a load-serving entity and a group of households in a smart grid community and put forward a peer effect-based demand response (PEDR) scheme applying dynamic pricing. A two-stage Stackelberg game based framework is established in which the electricity price and consumption decisions are derived adopting backward induction. We obtain the closed-form solution of the game (i.e., the equilibrium) in each stage and prove its existence and uniqueness. Simulation results indicate that the PEDR scheme shows superiority in energy consumption and peak to average ratio (PAR) compared with the baseline scheme without considering peer effects. Additionally, we study the impacts of social network structure of users and show that by setting the central node to be a frugal consumer in star topology structure, the performance of PEDR can be further improved. Such evaluations, as we believe, shall provide useful insights for energy providers to devise rational demand response policies.

Mobile crowdsensing (MCS) has been applied for signal map construction in smart city. However, it is still costly for MCS to cover large-scale regions. Accordingly some data recovery algorithms are proposed, which allow participants to collect only few signal data and infer the rest of missing data by leveraging spatial-temporal correlation of signals. However, existing work only considered the temporal and 2-D spatial correlation in the plane, while the altitude dimension is not exploited. In this paper, we give a first attempt to exploit the 3-D spatial-temporal correlation of signals to infer missing data in the ground and reconstruct ground signal map. An UAV-assisted ground signal map construction scheme is proposed based on matrix completion (MC). Specifically, UAVs can be used to collect signals in the air and aerial-ground signal mappings are performed to assist the ground signal inference. Extensive simulations are performed which show that the proposed scheme performs well under extremely high missing rate situations and outperform pure ground-based data recovery schemes.

With the increasing popularity of car sharing, a large amount of vehicle data has been generated which has great potential values for various applications (e.g., analyzing user habits for more economic benefits). These valuable data can be traded among owners and buyers on a data trading platform. Traditionally, data is traded in a centralized market which requires data exchange by trustworthy authorities. In this work, to address the potential unreliable issues (e.g., data loss and leakage), we design a consortium blockchain-based data trading framework to create a P2P trading market and enhance the security of data trading. We classify the data into five types to distinguish data with different values. Specifically, we investigate the pricing issue in the proposed car-sharing data market, which consists of data owner, service provider and data buyer. The data owner gives the pricing strategy of original data, and then the service provider processes the raw data and provides hierarchical quality of data with different data accuracy and privacy levels to the buyer who determines the data purchase strategy. Based on the interactions among these three parties, we formulate the problem as a three-layer Stackelberg game. Backward induction is applied to analyze the solution of the problem, and we conduct theoretical analysis to show the existence of Stackelberg game equilibrium. Numerical results evaluate the performance of our system under different settings.

With the exponential growth of data traffic, the use of caching and device-to-device (D2D) communications has been regarded as an efficient approach for alleviating the backhaul congestion in unmanned aerial vehicle (UAV) assisted networks. In this paper, we investigate the security issue of a cache-enabled UAV-relaying network with D2D communications in the presence of eavesdropper. Specifically, a UAV and multiple D2D users are equipped with cache memory, which can pre-store some popular contents to cooperatively provide content transfer services for users. To achieve secure and fair transmission, an optimization problem is formulated with the aim of maximizing the minimum secrecy rate among receivers, by jointly optimizing the cache placement and UAV flight trajectory in a finite flight period. The joint design problem is a non-convex mixed-integer programming problem. To facilitate solving this problem, we propose an alternating iterative algorithm based on the block alternating descend and successive convex approximation methods. Numerical results show that the joint design scheme significantly outperforms other benchmark schemes in terms of the secrecy rate.

In a PoW-based blockchain network, miners participate in a block-discovery racing game for financial incentives. As the total computing power becomes overwhelming, miners join in the mining pool which combines the scattered computing power to win a stable profit. Miners in the same mining pool work as a team and once they successfully mine a valid block, mining pool plays a role in distributing the payoff to miners according to its reward sharing mechanism. Specifically, two main reward sharing strategies: Pay-Per-Share (PPS) and Pay-Per-Last-NShare (PPLNS) are considered. In the mining system model, a miner can choose to join a pool and adapt the selection for improving the expected reward. And we formulate the dynamic pool selection problem as an evolutionary game. We consider the required hash rate, network delay and reward sharing strategy as the main factors which affect the choice of miners. Evolutionary stable equilibrium (ESS) is considered to be the solution, and we conduct theoretical analysis on the existence and stability of the ESS for a case of two mining pools. A low complexity distributed algorithm is proposed for miners to reach the equilibrium. Numerical results show the evolution of miners and demonstrate the theoretical findings of our study.

With the rise of privacy concerns in traditional centralized machine learning services, the federated learning, which incorporates multiple participants to train a global model across their localized training data, has lately received signifi-cant attention in both industry and academia. However, recent researches reveal the inherent vulnerabilities of the federated learning for the membership inference attacks that the adversary could infer whether a given data record belongs to the model’s training set. Although the state-of-the-art techniques could successfully deduce the membership information from the centralized machine learning models, it is still challenging to infer the membership to a more confined level, user-level. In this paper, We propose a novel user-level inference attack mechanism in federated learning. Specifically, we first give a comprehensive analysis of active and targeted membership inference attacks in the context of the federated learning. Then, by considering a more complicated scenario that the adversary can only passively observe the updating models from different iterations, we incorporate the generative adversarial networks into our method, which can enrich the training set for the final membership inference model. The extensive experimental results demonstrate the effectiveness of our proposed attacking approach in the case of single-label and multi-label.

In this paper, a novel computation offloading framework for edge computing is proposed. Unlike existing studies, this work considers that for offloading those computation-intensive tasks, mobile users are allowed to intentionally defer the declarations of their offloading requests and reserve some time for local pre-processing. By doing so, the offloading cost (including edge service charge and transmission cost) may be reduced because of less edge service demand, while the delay cost may increase due to later report. To strike the balance, each mobile user can strategically and selfishly determine a best timing of when to declare its offloading request (or the time-length of its local preprocessing). To characterize the resulted strategic interactions, a computation offloading game built upon a queueing model with strategic queue timing is formulated. Theoretical analyses and simulations evaluate the performance of the proposed equilibrium solution and demonstrate its superiority over counterparts.

With the exponential growth of data traffic, caching is regarded as a promising solution to combine with unmanned aerial vehicle (UAV)-assisted networks, which can offload cellular traffic and improve the system performance. Moreover, the cache capacity at user side can be leveraged, e.g., through local data storage or device-to-device (D2D) sharing. In this paper, we focus on the performance analysis and trajectory optimization of cache-enabled UAV-assisted networks with underlaid D2D communications. We consider both static and dynamic UAV deployments. For static UAV deployment, we first formulate an optimization problem to design the cache placement in order to maximize the cache hit probability. Then, the successful transfer probability (STP) and sum-rate are analyzed by using stochastic geometry, and their closed-form expressions are derived. For dynamic UAV deployment, the UAV moves over the cell and stops at several path points to serve users. To shorten the time required for the UAV to cover all users, a spiral algorithm is proposed to optimize the UAV trajectory, aiming at minimizing the number of UAV path points. Moreover, since at different locations, the UAV communication will incur different interference on D2D users, we derive the outage probability for the D2D users. Simulation results show the significant performance gain of our proposed probabilistic cache placement over existing strategies. For a given user density, we show that the optimal values for the UAV height which lead to the maximum UAV-STP and sum-rate exist.

It is well known that unmanned aerial vehicles (UAVs) can help terrestrial base stations (BSs) offload data traffic from crowded areas to improve coverage and boost throughput. However, the limited backhaul capacity cannot cope with the ever-increasing data demands, for which caching is introduced to relieve the backhaul bottleneck. In this paper, we focus on a multi-UAV assisted wireless network, and target to fully utilize the benefits of wireless caching and UAV mobility for multiuser content delivery. By taking into account the limited storage, our goal is to maximize the minimum throughput among UAV-served users by jointly optimizing cache placement, UAV trajectory, and transmission power in a finite period. The resultant problem is a mixed-integer non-convex optimization problem. To facilitate solving this problem, an alternating iterative algorithm is proposed by adopting the block alternating descent and successive convex approximation methods. Specifically, this problem is split into three subproblems, namely cache placement optimization, trajectory optimization, and power allocation optimization. Then these subproblems are solved alternately in an iterative manner. We show that the proposed algorithm can converge to the set of stationary solutions of this problem. Besides, we further analyze the computational complexity of this algorithm. Numerical results show that great throughput enhancement is achieved by applying our proposed joint design in comparison with other benchmarks without trajectory design and power control.

The mobile blockchain has been recognized as an emerging solution to address the security and privacy issues in a mobile application system. The mining process in mobile blockchain requires high computing resources which could overwhelm that which mobile devices can offer. In this case, mobile edge computing servers (MESs) can be involved to offer computing services to miners in mobile blockchain. Note that the resources of MESs are also limited; MESs could further request resources from the cloud computing server (CCS). Accordingly, the issue of hierarchical computing resource allocation arises. In this paper, we first consider a simple case with single-seller multiple buyers and a hierarchical single-seller multibuyer combinatorial auction model is proposed to solve this problem, based on which efficient and truthful frameworks are provided. We then extend the model to consider multiple CCSPs and propose a hierarchical multiple-seller multiple-buyer combinatorial auction model. For both models, the winner determination problems are formulated and computationally tractable algorithms are proposed. Also, pricing schemes are proposed to ensure the property of incentive compatibility and individual rationality. Finally, we evaluate the proposed schemes via simulations.

As a decentralized ledger to record all transaction information, blockchain can be applied to address the security and privacy issues in mobile application system. We term the blockchain applied to mobile applications as mobile blockchain. The mining process in mobile blockchain requires high computing capacity and energy which could overwhelm that mobile devices can offer. In this case, mobile edge computing servers (MESs) can be involved to offer computation services to miners in mobile blockchain. Note that the resources of MESs are also limited, MESs could further request resources from the cloud computing server (CCS). Accordingly, in this paper, both mobile edge computing and cloud computing are considered to support the mobile blockchain applications which makes the problem a hierarchical one. Naturally, the issue of hierarchical resource allocation arises. And a hierarchical combinatorial auction model is proposed to solve this problem, based on which an efficient and truthful framework is provided. Specifically, we formulate winner determination problems (WDPs) for mobile edge computing service providers and cloud computing service provider, and computationally tractable algorithms to address both problems are proposed. Finally, numerical analysis shows the effectiveness of the proposed scheme.

User association is indispensable for the operation of wireless network and has critical impacts on system performance. For most existing work, user associations are typically coupled, which require a user equipment (UE) to associate with the same base station (BS) in uplink (UL) and downlink (DL). However, wireless networks are becoming heterogeneous and densifying, which generates intrinsic distinctions (transmission power, data traffic and backhaul capacity etc.) between UL and DL. Accordingly, coupled association may no longer be optimal. In this work, we explore decoupled user association in full-duplex ultra-dense networks (UDNs), which allows a UE to associate with different BSs in UL and DL respectively. Furthermore, to fully exploit the benefits of UDNs, multiple association, referring to associating a UE with multiple BSs, is jointly adopted in UL and DL. Considering the dynamic and complicated association process, an evolutionary game (EG) is formulated, where UEs are players, and their strategies are association selections in UL/DL. Particularly, evolutionary equilibrium is viewed as the stable solution to the formulated problem. Moreover, an EG-based algorithm with low complexity is proposed for decoupled multiple association. Numerical results validate the convergence of the proposed algorithm for strategy adoption. Besides, the impacts of information exchange delay and learning rate are investigated for providing a better association decision.

Signal map is of great importance, especially in the dawn of 5G network, for site spectrum monitoring, location-based services (LBS), network construction, and cellular planning. Despite its significance, the traditional signal map construction, e.g., through full site survey, could be time-consuming and labor-intensive as the signal varies frequently over time and the accuracy requirement grows rapidly with the emergence of new applications. Even with crowdsourcing scheme, the participants tend to be unevenly distributed in space while the encouragement budgets for the participants could be far from enough to collect adequate high-quality measurements. Therefore, the signal map constructed by crowdsourcing is often sparse and incomplete. To this end, in this paper, we study how to effectively reconstruct and update the signal map in the case of partially measured signal maps with minimum cost and propose an auto-encoder-based active signal map reconstruction method (AER). Our method is mainly innovative in three parts. Firstly, AER can effectively update the signal map with only a small number of observations while also fully using the incomplete historical signals to effectively update the signal map online. Secondly, AER consists of an active query mechanism which quantitatively evaluates the most valuable measurement site for reconstruction, which further reduces the measurement cost to a large extent. Thirdly, to cope with the measurement dynamics, we give a new signal map model describing not only the signal strength but also the signal dynamics, based on which an advanced AER algorithm is proposed. The simulation results demonstrate the advantages and effectiveness of our approach in both accuracy and cost.

Wireless virtualization has become a key concept in future cellular networks which can provide multiple virtualized wireless networks for different mobile virtual network operators (MVNOs) over the same physical infrastructure. Resource allocation problem is a main challenge for wireless virtualization for which auction approaches have been widely used. However, for most existing auction-based allocation schemes, the objective is to maximize the social welfare (i.e., the sum of all valuations of winning bidders) due to its simplicity. While in reality, MVNOs are more interested in maximizing their own revenues. However, the revenue-maximization auction problem is much more complex since the price is unknown before calculation. In this paper, we give a first attempt for designing a revenueoptimal auction mechanism for resource allocation in wireless virtualization. Considering the complexity in revenue maximization, we apply the deep learning techniques. Specifically, we construct a multi-layer feed-forward neural network based on the analysis of optimal auction design. The neural network adopts users' bids as the input and the allocation rule and conditional payment rule for the users as the output. The training set of this neural network is the users' valuation profiles. The proposed auction mechanism possesses several satisfactory properties, e.g., individual rationality and incentive compatibility. Finally, simulation results demonstrate the effectiveness of the proposed scheme.

In recent years, unmanned aerial vehicles (UAVs) have attracted extensive interests from both academia and industry due to the potential wide applications with universal applicable nature of the deployment. However, currently the bottleneck for UAVs is the limited carried energy resources (e.g. oil box, battery), especially for electric-driven UAVs. For a system consisting of multiple UAVs using batteries, its stability depends on each UAV. Therefore, the lifetime of each UAV is expected to be extended. In this paper, we propose the concept of RF charging aerially for the UAV fleet. Specifically, in order to ensure the stability of the system, wireless charging is considered for enhancing the lifetime of each UAV. However, it may be unbalanced. Accordingly, the issue of charging scheduling arises. The problem is formulated as a Q-Learning problem in this paper. Agent constantly explores and optimizes its scheduling policy. Finally, it can adapt to different UAV distribution situations. We take the energy levels of UAVs as input, which is easy for implementation. We have compared with two other algorithms (RSA and LESA) and compared with the case of no-charging. The results show that comparing with no-charging, the stability of the system can be improved by up to 78%. Compared with RSA and LESA, system stability is increased by up to 30%-40%. In addition, our method is more flexible and applicable to fleet than other ways (such as return to base station, landing to power line, ground laser, etc) to supplement energy.

In this paper, we exploit the radio diversity gain in a multi-user hybrid radio network wirelessly powered by a power beacon station (PBS). Each user has a dual-mode radio that can switch between the passive and active modes, according to the channel and energy conditions. This provides extra degree of freedom to improve the overall network performance. As such, we propose a throughput maximization problem by jointly optimizing the PBS' energy beamforming and the radios' transmission scheduling strategies in two modes. We show that the throughput maximization is easily tractable by solving a semi-definite program. However, it becomes non-convex and intractable when we allow radios' cooperation in data transmissions. To this end, we propose a set of heuristic algorithms with different complexities for cooperative relay transmissions, which are shown to significantly improve the sum throughput compared to the non-cooperative case. The simulation results show that a simple adaptive scheme can achieve the maximum throughput according to the PBS' power supply.

User association is a crucial factor that affects the performance of wireless networks. In current cellular networks, user association is typically coupled, which means an user equipment (UE) must associate with the same base station (BS) in uplink (UL) and downlink (DL). For single-tier wireless networks, such mechanism is simple and effective. However, in heterogeneous ultra-dense networks (UDNs), there are distinct differences in transmission power, data traffic and channel quality etc., for which coupled association could restrict the performance of system. To cope with it, the concept of decoupled UL-DL (DUDe) association has been introduced recently, which enables a UE to associate with different BSs in UL and DL. In this paper, we investigate decoupled UL-DL user association in UDNs. Considering the existence of asymmetric information (i.e., channel gains and intercell interferences), which can be seen as the private information for UE, we propose a contract-theoretic user association approach. Particularly, we model the decoupled association process as a monopoly labor market, where BSs act as employers and offer contracts to employees (i.e., UEs). The contract items cover the available associated bandwidths, transmitted powers and corresponding prices. Then BS broadcasts these drafted contract information, and UE selects to sign the optimal contract by considering her own demands. Numerical results show significant superiorities of DUDe than coupled UL-DL association in perspective of nodes utilities and social surplus, and compared with the existing user association methods, contract-theoretic approach shows a certain improvement in performance.

In this paper, we consider wireless powered Internet of Things (IoT) by a power beacon station (PBS). Each IoT device can be a sensor node that has continuous data transmission using a dual-mode radio, which operates in either active radio frequency (RF) communications or passive backscatter communications. The flexibility in the radio mode switching provides an additional degree of freedom to improve the overall network performance. To exploit the radio's diversity gain, we formulate the sum throughput maximization by jointly optimizing the transmission strategy of each node, the time allocation, and beamforming strategies of the PBS. Besides, capitalizing the fact that two nodes in different modes can complement each other, we propose the passive relaying scheme to exploit the user's cooperation gain that leverages the passive radios to relay for active RF communications. Though the backscatter-aided throughput maximization is nonconvex due to the coupling among different nodes, we design the passive relaying game to balance energy harvesting and relay performance. The simulation results verify that it can significantly enhance the sum throughput of a hybrid radio network, along with the optimal time allocation and beamforming strategies at the PBS.

The new trends in network denisification, heterogeneity, and the introduction of new techniques (e.g., full-duplex) introduce new challenges for user association. For most existing user association schemes, the uplink (UL) and downlink (DL) access are coupled. That is, a user equipment (UE) is associated with the same BS for UL and DL transmissions. However, in ultra-dense heterogeneous networks (UDNs), due to the large disparities among base stations in different tiers and among uplink and downlink, the coupled UL-DL user association will limit the system performance. In this paper, we propose a novel concept of decoupled multiple association for user association in UDNs, which allows a UE to be associated with multiple base stations (BSs) for UL and DL in a decoupled manner. Furthermore, the context information of UEs is considered when making association decisions. Specifically, a decoupled multiple association matching game is formulated and a context-aware swap matching algorithm is proposed. The proposed scheme could attain higher data rates and could satisfy the quality of service (QoS) requirements of different UEs. Additionally, it could overcome the back-haul limitation of individual BSs. We compare the proposed scheme with three other association schemes, and the simulation results show significant performance gains of our proposed scheme in UDNs.

In this paper, we investigate the profit maximization problem for the mobile virtual network operator in cognitive radio networks considering the uncertain property of users' spectrum demand. In order to achieve more revenues while simultaneously satisfying the needs of users, the cognitive mobile virtual network operator chooses to dynamically sense the idle spectrum in the licensed band which is more economic, and at the same time leases the spectrum from the spectrum owner which guarantees more stable spectrum resources. However, the fluctuant spectrum demand of users imposes unprecedented challenges on the decision making process. To deal with the uncertain features of the users' demand, a flexible distribution uncertainty model is developed. Particularly, a reference distribution is introduced based on historical data and then a uncertainty set is defined to confine the spectrum demand. The uncertainty model developed allows the actual users' spectrum requirement to fluctuate around the reference distribution. Chance constraint approximations and robust optimization approaches are developed to transform and then solve the optimization problem. Simulation results based on the real-world traces evaluate the performance of the proposed scheme and investigate the parameter impacts on the system utilities. Our research may also help shed some insights on the investment policy making for the mobile virtual network operator.

Adapting the data rate is an important performance in mobile cloud networking, especially for the fast growth of intelligent terminals. We study a max-min fairness problem for the mobile cloud networking to guarantee the minimal transmit data rate, by leveraging the bit error rate (BER) with Q-function for modeling achievable data rates. We propose a distributed power control algorithm to obtain the optimal solution. Then, we address a total power minimization problem with the given rate requirement constraints. When there are plenty of users and excessive interferences, its feasibility issue is solved by making use of the max-min fairness of the networks. We propose a dynamic algorithm that adapts the rate requirements to minimize the total energy consumption and to simultaneously provide fairness guarantees. Numerical simulations show the efficient performance of the proposed algorithms.

Integrating ambient backscatter communications into RF-powered cognitive radio networks has been shown to be a promising method for achieving energy and spectrum efficient communications, which is very attractive for low-power or no-power communications. In such scenarios, a secondary user (SU) can operate in either transmission mode or backscatter mode. Specifically, an SU can directly transmit data if sufficient energy has been harvested (i.e., transmission mode). Or an SU can backscatter ambient signals to transmit data (i.e., backscatter mode). In this paper, for investigating the performance of such systems, we apply stochastic geometry to analyze coverage probability and achievable rates for both primary and secondary users considering both communication modes. Analytical tractable expressions are obtained. Extensive simulations are performed and the numerical results show the validity of our analysis. Furthermore, the results indicate that the performance of secondary systems can be improved with the integration of both communication modes with only limited impact on the performance of primary systems.

Caching popular contents at base stations (BSs) has been regarded as an effective approach to alleviate the backhaul load and to improve the quality of service. To meet the explosive data traffic demand and to save energy consumption, energy efficiency (EE) has become an extremely important performance index for the 5th generation (5G) cellular networks. In general, there are two ways for improving the EE for caching, that is, improving the cache‐hit rate and optimizing the cache size. In this work, we investigate the energy efficient caching problem in backhaul‐aware cellular networks jointly considering these two approaches. Note that most existing works are based on the assumption that the content catalog and popularity are static. However, in practice, content popularity is dynamic. To timely estimate the dynamic content popularity, we propose a method based on shot noise model (SNM). Then we propose a distributed caching policy to improve the cache‐hit rate in such a dynamic environment. Furthermore, we analyze the tradeoff between energy efficiency and cache capacity for which an optimization is formulated. We prove its convexity and derive a closed‐form optimal cache capacity for maximizing the EE. Simulation results validate the proposed scheme and show that EE can be improved with appropriate choice of cache capacity.

Integrating ambient backscatter communications into RF‐powered cognitive radio networks has been shown to be a promising method for achieving energy and spectrum efficient communications, which is very attractive for low‐power or no‐power communications. In such scenarios, a secondary user (SU) can operate in either transmission mode or backscatter mode. Specifically, an SU can directly transmit data if sufficient energy has been harvested (i.e., transmission mode). Or an SU can backscatter ambient signals to transmit data (i.e., backscatter mode). In this paper, we investigate the performance of such systems. Specifically, channel inversion power control and an energy store‐and‐reuse mechanism for secondary users are adopted for efficient use of harvested energy. We apply stochastic geometry to analyze coverage probability and achievable rates for both primary and secondary users considering both communication modes. Analytical tractable expressions are obtained. Extensive simulations are performed and the numerical results show the validity of our analysis. Furthermore, the results indicate that the performance of secondary systems can be improved with the integration of both communication modes with only limited impact on the performance of primary systems.

Self-organizing networks (SON) aim to offer high quality services while reducing both capital expenditure (CAPEX) and operational expenditure (OPEX). SON consists of three main functions: self- configuration, self-optimization, and self-healing. Comparing with self-configuration and self- optimization, there exits only few studies on self- healing. However, it plays an important role in maintaining network operation. Note that self- healing mainly includes fault detection, fault diagnosis, and fault compensation. In this paper, we focus on fault diagnosis and propose an ensemble learning based fault diagnosis system for a self- organizing cellular network. Specifically, in the proposed ensemble learning framework, the base learner is strengthened in each iteration and the final diagnosis result is obtained from the combination of all base classifications. Moreover, traditional classification algorithms are designed considering the premise of balanced data set. However, the classification accuracy of minority classes is not satisfactory. To deal with imbalanced training data sets, we applied the synthetic minority over- sampling technique (SMOTE) in the proposed system, which could also alleviate the difficulties caused by insufficient fault data. Simulation results show that the proposed system can achieve a high diagnosis accuracy, which can be further improved with the increase of training samples. In addition, the diagnosis accuracy of minority fault classes can be significantly improved with the application of SMOTE.

In this paper, a cost minimization problem is formulated to intelligently schedule energy generations for microgrids equipped with unstable renewable sources and energy storages. In such systems, the uncertain renewable energy will impose unprecedented scheduling challenges. To cope with the fluctuate nature of the renewable energy, an uncertainty model based on renewable energies' moment statistics is developed. Specifically, we obtain the mean vector and second-order moment matrix according to predictions and field measurements and then define uncertainty set to confine the renewable energy generation. The uncertainty model allows the renewable energy generation distributions to fluctuate within the uncertainty set. We develop chance constraint approximations and robust optimization approaches based on a Chebyshev inequality framework to firstly transform and then solve the scheduling problem. Numerical results based on real-world data traces evaluate the performance bounds of the proposed scheduling scheme. It is shown that the temporal-correlation information of the renewable energy within a proper time span can effectively reduce the conservativeness of the solution. Moreover, detailed studies on the impacts of different factors on the proposed scheme provide some interesting insights which shall be useful for the policy making for the future microgrids.

Wireless virtualization which enables resource sharing among different mobile virtual network operators (MVNOs) has become an important enabling technique in 5G cellular networks for increasing resource utilization and lowering the cost per bit. A main challenge for virtualization is efficient resource allocation while keeping isolation among different parties. In this paper, we consider a multi-dimensional resource market among multiple MVNOs and users. A combinatorial double auction (CDA) model is proposed, based on which a truthful and efficient resource allocation framework is provided. Specifically, for maximizing the social welfare, a winner determination problem (WDP) is formulated considering different QoS requirements of users, and a computationally tractable algorithm is proposed to solve the WDP. Also, a pricing scheme is designed such that several desirable properties (e.g., incentive compatibility, individual rationality, and budget balance) can be achieved in the proposed CDA framework. Numerical results show the effectiveness of the proposed scheme.

Virtualization has been seen as one of the main evolution trends in future cellular networks which enables the decoupling of infrastructure from the services it provides. In this case, the roles of infrastructure providers (InPs) and mobile virtual network operators (MVNOs) can be logically separated and the resources of a base station owned by an InP can be transparently shared by multiple MVNOs, while each MVNO virtually owns the entire BS. Naturally, the issue of resource allocation arises. Specifically, the InP is required to abstract the physical resources into isolated slices for each MVNO who then allocates the resources within the slice to its subscribed users. In this paper, we aim to address this two-level hierarchical resource allocation problem while satisfying the requirements of efficient resource allocation, strict inter-slice isolation, and the ability of intra-slice customization. To this end, we propose a hierarchical combinatorial auction model, based on which a truthful and efficient resource allocation framework is provided. And we show by an illustrative example how the proposed model can be applied for wireless virtualization. Specifically, winner determination problems (WDPs) are formulated for the InP and MVNOs, and computationally tractable algorithms are proposed for solving these WDPs. Also, pricing schemes are proposed for ensuring the incentive compatibility. Note that the proposed model can be generalized for the virtualization of resources with more dimensions (e.g., power, antennas, etc.).

Virtualization has been seen as one of the main evolution trends in the forthcoming fifth generation (5G) cellular networks which enables the decoupling of infrastructure from the services it provides. In this case, the roles of infrastructure providers (InPs) and mobile virtual network operators (MVNOs) can be logically separated and the resources (e.g., subchannels, power, and antennas) of a base station owned by an InP can be transparently shared by multiple MVNOs, while each MVNO virtually owns the entire BS. Naturally, the issue of resource allocation arises. In particular, the InP is required to abstract the physical resources into isolated slices for each MVNO who then allocates the resources within the slice to its subscribed users. In this paper, we aim to address this two-level hierarchical resource allocation problem while satisfying the requirements of efficient resource allocation, strict inter-slice isolation, and the ability of intra-slice customization. To this end, we design a hierarchical combinatorial auction mechanism, based on which a truthful and sub-efficient resource allocation framework is provided. Specifically, winner determination problems (WDPs) are formulated for the InP and MVNOs, and computationally tractable algorithms are proposed to solve these WDPs. Also, pricing schemes are designed to ensure incentive compatibility. The designed mechanism can achieve social efficiency in each level even if each party involved acts selfishly. Numerical results show the effectiveness of the proposed scheme.

In this work, a game theoretical approach for addressing the virtual network service providers (NSPs), small cell provider (SCP) and user interaction in heterogenous small cell networks is presented. In particular, we consider the users can select the services of different NSPs based on their prices. The NSPs have no dedicated hardware and need to rent from the SCP in term of radio resources, e.g., small cell base stations (SBSs) in order to provide satisfied services to the users. Due to the fact that the selfish parties involved aim at maximizing their own profits, a hierarchical dynamic game framework is presented to address interactive decision problem. In the lower-level, a Stackelberg game is formulated to model and analyze the adaptive service selection of non-atomic users. In the upper-level, the NSPs and SCP sequentially determine the leasing and pricing strategies, respectively, by taking into account the service selection in the lower-level game. Performance evaluation shows the effectiveness and advantages of the proposed game theoretic approaches.

We consider the problem of robust downlink power control in orthogonal frequency-division multiple access (OFDMA)-based heterogeneous wireless networks (HetNets) composed of macrocells and underlaying small cells. A non-cooperative setting is assumed where the macro base stations (MBSs) and small cell base stations (SBSs) compete with each other to maximize their own capacities considering imperfect channel state information. A robust Stackelberg game (RSG) is formulated to model this hierarchical competition where the MBSs and SBSs act as the leaders and the followers, respectively. The formulated RSG can be expressed as an equilibrium program with equilibrium constraints (EPEC). A comprehensive study of this RSG is provided considering various power constraints (e.g., total and spectral mask), various interference constraints (e.g., individual and global), and different uncertainty models (e.g., column-wise and ellipsoidal). We show how the different constraints and uncertainty models change the property of the game (e.g., Nash equilibrium problem (NEP) or generalized Nash equilibrium problem (GNEP)) and accordingly impact the choice of analysis method (e.g., game theory or variational inequality (VI)), solution (e.g., closed-form or numerical), and the design of algorithms and their distributive properties (e.g., totally distributed, semi-distributed, and centralized). A robust Stackelberg equilibrium (RSE) is considered to be the solution and its existence and uniqueness are investigated. Also, algorithms are proposed to arrive at the RSE. Numerical results show the effectiveness of robust solutions in an imperfect information environment.

We propose an evolutionary game theory (EGT)-based distributed resource allocation scheme for small cells underlaying a macro cellular network. EGT is a suitable tool to address the problem of resource allocation in self-organizing small cells since it allows the players with bounded-rationality to learn from the environment and take individual decisions for attaining the equilibrium with minimum information exchange. EGT-based resource allocation can also provide fairness among users. We show how EGT can be used for distributed subcarrier and power allocation in orthogonal frequency-division multiple access (OFDMA)-based small cell networks while limiting interference to the macrocell users below given thresholds. Two game models are considered, where the utility of each small cell depends on average achievable signal-to-interference-plus-noise ratio (SINR) and data rate, respectively. Forthe proposed distributed resource allocation method, the average SINR and data rate are obtained based on a stochastic geometry analysis. Replicator dynamics is used to model the strategy adaptation process of the small cell base stations and an evolutionary equilibrium is obtained as the solution. Based on the results obtained using stochastic geometry, the stability of the equilibrium is analyzed. We also extend the formulation by considering information exchange delay and investigate its impact on the convergence of the algorithm. Numerical results are presented to validate ourtheoretical findings and to show the effectiveness of the proposed scheme in comparison to a centralized resource allocation scheme.

Device-to-device (D2D) communication technology is a promising add-on component for future wireless networks to provide local area services with increased spectrum efficiency and improved user experience. Three modes (i.e., cellular mode, reuse mode, and dedicated mode) can be used for D2D communication. A potential D2D user equipment (UE) can select a communication mode and dynamically adapt the mode selection according to the performance and the cost. This is referred to as the user-controlled mode selection problem. Also, a base station (BS) needs to reserve a spectrum band for the dedicated mode of operation, which we refer to as spectrum partitioning. The optimal spectrum partitioning needs to consider the utility of the BS that depends on the distribution of the users' mode selection, which, in turn, is governed by the spectrum partitioning. To jointly address the problems of spectrum partitioning and user-controlled mode selection (which are cyclically dependent on each other), we propose a dynamic Stackelberg game framework in which the BS and the potential D2D UEs act as the leader and the followers, respectively. Specifically, the adaptive mode selection of potential D2D UEs is formulated as a follower evolutionary game, and an evolutionary stable strategy is considered to be the solution. The dynamic control of spectrum partitioning by the BS is formulated as a leader optimal control problem. We also extend the formulation by considering information delays in control and state. Numerical analysis is performed to evaluate the effectiveness of the proposed framework, which shows that although the mode selection is performed in a distributed and user-controlled manner, the dynamic spectrum partitioning can be viewed as an effective incentive mechanism to drive the user distribution close to the optimal one.

Small cells overlaid with macrocells can increase the capacity of two-tier cellular wireless networks by offloading traffic from macrocells. To motivate the small cell service providers (SSPs) to open portion of the access opportunities to macro users (i.e., to operate in a hybrid access mode), we design an incentive mechanism in which the macrocell service provider (MSP) could pay to the SSPs. According to the price offered by the MSP, the SSPs decide on the open access ratio, which is the ratio of shared radio resource for macro users and the total amount of radio resource in a small cell. The users in this two-tier network can make service selection decisions dynamically according to the performance satisfaction level and cost, which again depend on the pricing and spectrum sharing between the MSP and SSPs. To model this dynamic interactive decision problem, we propose a hierarchical dynamic game framework. In the lower level, we formulate an evolutionary game to model and analyze the adaptive service selection of users. An evolutionary stable strategy (ESS) is considered to be the solution of this game. In the upper level, the MSP and SSPs sequentially determine the pricing strategy and the open access ratio, respectively, taking into account the distribution of dynamic service selection at the lower-level evolutionary game. A Stackelberg differential game is formulated where the MSP and SSPs act as the leader and followers, respectively. An open-loop Stackelberg equilibrium is considered to be the solution of this game. We also extend the hierarchical dynamic game framework and investigate the impact of information delays on the equilibrium solutions. Numerical results show the effectiveness and advantages of dynamic control of the open access ratio and pricing.

Cooperative relay network will be supported in IEEE 802.16m to improve the coverage and performance of mobile broadband wireless access service. In this paper, we jointly consider the problem of dynamic service selection and bandwidth allocation in IEEE 802.16m mobile relay networks. Specifically, the advanced mobile stations (AMSs) perform the selection of advanced base station (ABS) and transmission mode (i.e., direct transmission or relay-cooperation transmission) for a better service quality. The ABSs allocate the bandwidth for different transmission modes to maintain the desired queue level at base stations and user distribution for satisfying performance requirements. This problem is challenging when the strategies of both ABSs and AMSs influence each other and the decisions are made dynamically. To address this problem, a two-level dynamic game framework based on an evolutionary game and a differential game is developed. Since the mobile stations can adapt their strategies according to the received service quality, the dynamic service selection is modeled as an evolutionary game at the lower level. At the upper level, a differential game is formulated for a dynamic bandwidth allocation of base stations and a closed-loop Nash equilibrium is obtained as the solution. Viewing the fluctuation of traffic flow rate as disturbance, the robust bandwidth allocation strategy design is performed. Both stochastic optimal control and H_∞ optimal control approaches are adopted for average performance and worst-case performance design, respectively.

We consider a problem of dynamic spectrum leasing in a spectrum secondary market of cognitive radio networks where secondary service providers lease spectrum from spectrum brokers to provide service to secondary users. The problem is challenging when the optimal decisions of both secondary providers and secondary users are made dynamically under competition. To address this problem, a two-level dynamic game framework is developed in this paper. Since the secondary users can adapt the service selection strategies according to the received service quality and price, the dynamic service selection is modeled as an evolutionary game at the lower level. The replicator dynamics is applied to model the service selection adaptation and the evolutionary equilibrium is considered to be the solution. With dynamic service selection, competitive secondary providers can dynamically lease spectrum to provide service to secondary users. A spectrum leasing differential game is formulated to model this competition at the upper level. Both simultaneous play model and asynchronous play model are considered. The service selection distribution of the underlying evolutionary game describes the state of the upper differential game. Both open-loop and closed-loop Nash equilibria are obtained as the solution of dynamic control of the differential game. Numerical comparison shows the advantages over static control in terms of profit and convergence speed.

In cloud computing, multiple cloud providers can cooperate to establish a resource pool to support internal users and to offer services to public cloud users. In this paper, we study the cooperative behavior of multiple cloud providers. The hierarchical cooperative game model is presented. First, given a group (i.e., coalition) of cloud providers, the resource and revenue sharing of a resource pool is presented. To obtain the solution, we develop the stochastic linear programming game model which takes the uncertainty of internal users from each provider into account. We show that the solution of the stochastic linear programming game is the core of cooperation. Second, we analyze the stability of the coalition formation among cloud providers based on coalitional game. The dynamic model of coalition formation is used to obtain stable coalitional structures. The resource and revenue sharing and coalition formation of cloud providers are intertwined in which the proposed hierarchical cooperative game model can be used to obtain the solution. An extensive performance evaluation is performed to investigate the decision making of cloud providers when cooperation can lead to the higher profit.

We consider the problem of dynamic bandwidth allocation among different service classes under uncertainty in cognitive radio networks. In such networks, the secondary users compete for bandwidth resources and the service providers compete for users access (e.g., subscription). To address this problem, a two-level dynamic game framework is developed. The underlying dynamic service selection of secondary users is modeled as an evolutionary game based on replicator dynamics. The randomly irrational churning behavior of secondary users is modeled as a stochastic disturbance to the service selection distribution evolution. At the upper level, a bandwidth allocation stochastic differential game is formulated to model the competition among different service providers. The service selection distribution of the underlying evolutionary game describes the state of the upper stochastic differential game and a Markov perfect Nash equilibrium is considered to be the solution. The decentralized nature of the framework makes the system flexible and simple for implementation.

Abstract Mobility management is one of the most challenging research issues for vehicular networks to support a variety of intelligent transportation system (ITS) applications. The traditional mobility management schemes for Internet and mobile ad hoc network (MANET) cannot meet the requirements of vehicular networks, and the performance degrades severely due to the unique characteristics of vehicular networks (e.g., high mobility). Therefore, mobility management solutions developed specifically for vehicular networks would be required. This paper presents a comprehensive survey on mobility management for vehicular networks. First, the requirements of mobility management for vehicular networks are identified. Then, classified based on two communication scenarios in vehicular networks, namely, vehicle‐to‐vehicle (V2V) and vehicle‐to‐infrastructure (V2I) communications, the existing mobility management schemes are reviewed. The differences between host‐based and network‐based mobility management are discussed. To this end, several open research issues in mobility management for vehicular networks are outlined. Copyright © 2009 John Wiley & Sons, Ltd.

Bandwidth allocation for different service classes in heterogeneous wireless networks is an important issue for service provider in terms of balancing service quality and profit. It is especially challenging when considering the dynamic competition both among service providers and among users. To address this problem, a two-level game framework is developed in this paper. The underlying dynamic service selection is modeled as an evolutionary game based on replicator dynamics. An upper bandwidth allocation differential game is formulated to model the competition among different service providers. The service selection distribution of the underlying evolutionary game describes the state of the upper differential game. An open-loop Nash equilibrium is considered to be the solution of this linear state differential game. The proposed framework can be implemented with minimum communication cost since no information broadcasting is required. Also, we observe that the selfish behavior of service providers can also maximize the social welfare.

Enabling users to connect to the best available network, dynamic network selection scheme is important for satisfying various quality of service (QoS) requirements, achieving seamless mobility and load balancing in heterogeneous wireless networks. In this paper, we formulate the network selection problem in heterogeneous wireless networks with incomplete information as a Bayesian game. In general, the preference (i.e., utility) of a mobile user is private information. Therefore, each user has to make the decision of network selection optimally given only the partial information of the preferences of other users. To study the dynamics of such network selection, the Bayesian best response dynamics and aggregate best response dynamics are applied. Bayesian Nash equilibrium is considered to be the solution of this game, and there is a one-to-one mapping between the Bayesian Nash equilibrium and the equilibrium distribution of the aggregate dynamics. The numerical results show the convergence of the aggregate best response dynamics for this Bayesian network selection game. This result ensures that even with incomplete information, the equilibrium of network selection decisions of mobile users can be reached.