Online model training is pivotal for enabling multiuser semantic communication systems to adapt to dynamic channel conditions. However, conventional frameworks suffer from prohibitive communication overhead and vulnerabilities to privacy attacks, hindering practical deployment. This paper proposes semantic information mixup (SIMix), a secure and efficient training framework that integrates Over-the-Air Mixup (OAM) with label-aware user grouping to jointly optimize spectral efficiency and semantic security. The OAM mixes semantic features of multiple users via wireless channels, inherently obfuscating sensitive data while reducing communication overhead. A closed-form Tx-Rx scaling optimization minimizes the mean square error (MSE) of over-the-air computation under channel noise, ensuring stable convergence in low-SNR regimes. Furthermore, an extended max-clique algorithm dynamically partitions users into groups with minimal intra-label similarity, reducing model inversion attack success rates. Experiments on CIFAR-10 and Tiny ImageNet demonstrate that the proposed approach is superior in terms of communication efficiency and security, reducing communication overhead by up to 25% and attaining 17.58 dB PSNR (20.98 dB reduction) under inversion attack and reducing 13.44% attack success rate under label inference attack, while achieving comparable transmission accuracy.

Adversarial examples are one critical security threat to various visual applications, where injected human-imperceptible perturbations confuse the output. Generating transferable adversarial examples in the black-box setting is crucial but challenging in practice. Existing input-diversity-based methods adopt different image transformations, but may be inefficient due to insufficient input diversity and an identical perturbation step size. Motivated by the fact that different image regions have distinctive weights in classification, this paper proposes a black-box adversarial generative framework by jointly designing enhanced input diversity and adaptive step sizes. We design local mixup to randomly mix a group of transformed adversarial images, strengthening the input diversity. For precise adversarial generation, we project the perturbation to relax the boundary constraint. Moreover, the step sizes of different regions can be dynamically adjusted by integrating a second-order momentum. Extensive experiments on ImageNet validate that our framework can achieve superior transferability compared to state-of-the-art baselines. Code is available at https://github.com/ZeroWalker10/IDAA.

We aim to provide a unified convergence analysis for permutation-based Stochastic Gradient Descent (SGD), where data examples are permuted before each epoch. By examining the relations among permutations, we categorize existing permutation-based SGD algorithms into three categories: Arbitrary Permutations, Independent Permutations (including Random Reshuffling and FlipFlop Rajput et al., 2022), Dependent Permutations (including GraBs Lu et al., 2022a; Cooper et al., 2023). Existing unified analyses failed to encompass the Dependent Permutations category due to the inter-epoch permutation dependency. In this work, we propose a generalized assumption that explicitly characterizes the dependence of permutations across epochs. Building upon this assumption, we develop a unified framework for permutation-based SGD with arbitrary permutations of examples, incorporating all the existing permutation-based SGD algorithms. Furthermore, we adapt our framework for Federated Learning (FL), developing a unified framework for regularized client participation FL with arbitrary permutations of clients.

Abstract With the growing demand for seamless connectivity and intelligent communication, the integration of artificial intelligence (AI) and sixth-generation (6G) communication networks has emerged as a transformative paradigm. By embedding AI capabilities across various network layers, this integration enables optimized resource allocation, improved efficiency, and enhanced system robust performance. This paper presents a comprehensive overview of AI and communication for 6G networks, with a focus on their foundational principles, inherent challenges, and future research opportunities. We first review the integration of AI and communications in the context of 6G, exploring the driving factors behind incorporating AI into wireless communications, as well as the vision for the convergence of AI and 6G. The discourse then transitions to a detailed exposition of the envisioned integration of AI within 6G networks, divided into three progressive stages. The first stage, AI for network, focuses on employing AI to augment network performance, optimize efficiency, and enhance user service experiences. The second stage, network for AI, highlights the role of the network in facilitating and buttressing AI operations and presents key enabling technologies. We compare wireless network large models with conventional large language models (LLMs), and identify key design principles and components for building wireless network architectures. In the final stage, AI as a service, it is anticipated that future 6G networks will innately provide AI functions as services, supporting application scenarios like immersive communication and intelligent industrial robots. Specifically, we define the quality of AI service, which refers to a framework for measuring AI services within the network. We further summarize the standardization process of AI for wireless networks, highlighting key milestones and ongoing efforts. In addition, we analyze the critical challenges faced by the integration of AI and communications in 6G. Finally, we outline promising future research opportunities that are expected to drive the development and refinement of AI and 6G communications.

With the proliferation of smart devices and the expansion of human production and living areas, low Earth orbit (LEO) satellite computing is needed to meet the computing demands over a wide area. Due to the limited resources that a single LEO satellite can carry, it is essential to realize intersatellite collaborative computing to achieve efficient onboard processing. However, the high spatiotemporal dynamics of satellite networks pose significant challenges to the establishment of connection and offloading decisions in collaborative computing. Facing these challenges, we propose a multilayer LEO satellite collaborative computing framework by integrating LEO satellites from different orbits. Considering the continuity of task generation, we establish a temporal model for on-board processing. On this basis, we optimize intersatellite offloading decisions to minimize the average system cost over a long-term timescale. To address the constantly changing environment information and the strict constraints on task completion time, we propose using the proximal policy optimization (PF-PPO) algorithm to solve the problem. Extensive simulation results illustrate the effectiveness of the proposed algorithm, which can achieve lower system costs compared with benchmark methods under different conditions. It is also proved that our algorithm has stable performance for the system over a long-term continuous timescale.

There are two paradigms in Federated Learning (FL): parallel FL (PFL), where models are trained in a parallel manner across clients, and sequential FL (SFL), where models are trained in a sequential manner across clients. Specifically, in PFL, clients perform local updates independently and send the updated model parameters to a global server for aggregation; in SFL, one client starts its local updates only after receiving the model parameters from the previous client in the sequence. In contrast to that of PFL, the convergence theory of SFL on heterogeneous data is still lacking. To resolve the theoretical dilemma of SFL, we establish sharp convergence guarantees for SFL on heterogeneous data with both upper and lower bounds. Specifically, we derive the upper bounds for the strongly convex, general convex and non-convex objective functions, and construct the matching lower bounds for the strongly convex and general convex objective functions. Then, we compare the upper bounds of SFL with those of PFL, showing that SFL outperforms PFL on heterogeneous data (at least, when the level of heterogeneity is relatively high). Experimental results validate the counterintuitive theoretical finding.

Accurate and fast beam alignment is non-trivial in millimeter-wave (mmWave) communication systems. Deep learning models hold great promise to yield accurate beams within these systems. However, in practice, deep learning-based approaches suffer from generalization issues that the model trained under a given environment may not effectively adapt to new environments. This motivates us to propose a novel meta-learning-based algorithm to provide a general model for beam alignment, which aims to adapt to the unknown environments quickly. Concretely, this paper first proposes a Meta-Predictive Beam Alignment (MPBA) algorithm to assist model convergence and improve the quality of predicted beams. The MPBA simplifies the data partitioning process and training process when comparing traditional meta-algorithm, which is more conducive for actual deployment. This simplified and effective mechanism aids in identifying more general initial model parameters and transferring to new scattering environments without the need of heavy beam collection. Numerical simulation results reveal that the proposed MPBA has robust performance under various conditions and has about 21% accuracy gain and 2.2 bits/s/Hz spectral efficiency gain over direct transfer learning, as well as showcasing superior generalization capabilities when we transfer it to unseen base station (BS) environments.

Vertical Federated Learning (VFL) enables collaborative multi-agent model training with distributed feature spaces. Compared to horizontal federated learning (HFL), poisoning attacks in VFL confront the challenges of partial/incomplete data and model information, i.e., the adversary only has its local input feature space and model structure without knowing the ground-truth labels or server-side model. Existing attacks are inefficient in terms of stability and scalability under different learning configurations. In this paper, we design the poisoning framework via embedding manipulation in the model-partitioning structure of VFL, and propose two efficient poisoning attacks, i.e., layer embedding manipulation (LMP) and perturbation embedding manipulation (PMP). Both LMP and PMP meticulously transform the benign embeddings into the poisoned ones to dominate the model prediction. In particular, LMP blends a malicious trigger layer to poison the embedding. PMP exploits the gradients to generate a universal perturbation, which can be injected into the benign embeddings for poisoning. We conduct extensive experiments for attack performance evaluation. PMP and LMP achieve an average attack success rate of more than 0.9, and keep stability and robustness under different learning configurations. We further conduct six different defense methods to evaluate the proposed attacks. The proposed attacks are still shown to succeed against these defenses, necessitating the advanced defenses for VFL in future work.

Input diversity is an effective technique for crafting transferable adversarial examples that can deceive unknown AI models. Existing input-diversity-based methods typically use single input transformation, limiting targeted transferability and defense robustness. Combining different transformation types is challenging, as keeping increasing types would degrade semantic information and targeted transferability. This paper proposes a quality-awaretransformationcombinationattack (TCA) that selects high-quality transformation combinations. The quality-aware selection enables expansion of transformation types, enhances input diversity, and hence improves targeted transferability and defense robustness. We first design a quality-evaluation framework to quantify the effectiveness of transformation combinations, which jointly considers convergence, transferability, and robustness. Only a small group (up to 10) of images are required for computation-efficient quality evaluation. Experiments validate TCA's superiority over state-of-the-art baselines in adversarial transferability and robustness. When defenses are secured, the average targeted success rate of TCA with four transformation types (i.e., TCA-t4) outperforms the best baseline by 26%$\sim$42% on ImageNet.

The efficient implementation of massive multiple-input-multiple-output (MIMO) transceivers is essential for the next-generation wireless networks. To reduce the high computational complexity of the massive MIMO transceiver, in this paper, we propose a new massive MIMO architecture using finite-precision arithmetic. First, we propose a mixed-precision architecture for massive MIMO systems based on blocked matrix computations. Then the corresponding analysis of rounding errors and computational costs is derived. Finally, simulation results underscore the superiority of the proposed mixed-precision architecture to the conventional structure.

Distributed learning is a promising paradigm for future UAV (unmanned aerial vehicle) networks networks and other emerging autonomous unmanned systems. Such distributed learning framework can suit the intrisic decentralized topology of UAV networks, where the UAVs can collaborate to train a global AI model by only exchanging the model parmeters via its peer-to-peer (i.e, inter-UAV) links in a distributed manner. However, with the ever-increasing AI model sizes, the challenges arise from the significant communication overhead for exchanging massive model weights via inter-UAV links in an ad-hoc manner: Previous communication-efficient techniques are mainly designed for conventional federated learning and not easily extendable to the decentralized counterpart. We propose selective link orchestration to minimize communication overhead while ensuring convergence of distributed learning, and prove that the convergence constraint is equivalent to the connectivity of the selected sub-graph. As such, we can reformulate the problem as a link selection problem in graph theory and develop a distributed optimization algorithm based on the modification of the Gallager, Humblet, and Spira’s algorithm. Experimental results on MNIST, Fashion-MNIST, and CIFAR-10 datasets demonstrate up to a $90 \%$ reduction in communication overhead without compromising model accuracy.

Split learning is a promising paradigm for privacy-preserving distributed learning. The learning model can be cut into multiple portions to be collaboratively trained at the participants by exchanging only the intermediate results at the cut layer. Understanding the security performance of split learning is critical for many privacy-sensitive applications. This paper shows that the exchanged intermediate results, including the smashed data (i.e., extracted features from the raw data) and gradients during training and inference of split learning, can already reveal the private labels. We mathematically analyze the potential label leakages and propose the cosine and Euclidean similarity measurements for gradients and smashed data, respectively. Then, the two similarity measurements are shown to be unified in Euclidean space. Based on the similarity metric, we design three label inference attacks to efficiently recover the private labels during both the training and inference phases. Experimental results validate that the proposed approaches can achieve close to 100% accuracy of label attacks. The proposed attack can still achieve accurate predictions against various state-of-the-art defense mechanisms, including DP-SGD, label differential privacy, gradient compression, and Marvell.

Federated learning is a popular distributed machine learning paradigm that enables collaborative model training at multiple entities via exchanging intermediate learning results. Security and communication efficiency are crucial for successful applications of federated learning in various privacy-sensitive services. However, existing work focused on gradient defense and communication efficiency separately, and also incurred additional computation, signaling, and accuracy overhead. A lightweight (in terms of time-complexity and signaling) technique that simultaneously achieves security and communication efficiency is critical for massive resource-constrained devices (e.g., Internet-of-Things generating the data), but has yet to be established. This paper proposes a secure and efficient federated learning framework with provable communication-accuracy-security performance guarantees. A low-complexity and signaling-free stochastic quantization module is added at the client side that quantizes the original local gradients to discrete values for communication-efficient global aggregation. The stochastic quantization module is shown to be interpreted as triangular or Gaussian-multiply-triangular noises under uniform or Gaussian distributions of local gradients, hence protecting data privacy. We prove that the proposed framework exhibits an {O(log21/δ),O(δ2),O(1/δ)}-tradeoff between the communication overhead, model accuracy, and data protection, where δ is an adjustable quantization interval. Experimental results validate the tradeoff and the superiority of the proposed stochastic quantization technique in terms of communication efficiency (only 14.1% of differential privacy and 0.2% of homomorphic encryption) and computation complexity (similar to differential privacy and only 0.03% of homomorphic encryption). Under the same data protection performance, the proposed approach also outperforms (in terms of accuracy) differential privacy in all the 9 comparison settings on CIFAR10 dataset.

Resource provisioning aims to efficiently allocate the infrastructure provider's communication, computation and caching resources to provide reliable (e.g., 99.999%) and responsive actions for massive delay-critical services. However, the challenges arise from the partial knowledge of uncertain traffic arrivals (even the distributions of estimation error may not be available) and computation complexity for massive numbers of emerging services. This paper aims to design efficient and robust resource provisioning for massive delay-critical services based on only partial knowledge on traffic uncertainty. We formulate the problem of robust resource provisioning to minimize the system cost with only partial (i.e., the first/second momentum) information of traffic estimation errors. We derive the robust approximation of the reliability constraint using the Bernstein approximation, which is proved to guarantee service reliability given the partial traffic knowledge. The problem is reformulated and solved via Lagrangian duality to obtain the closed-form expression for low-complexity solutions. Experimental results on both the simulation-based and trace-based datasets validate that the proposed approach can guarantee up to 99.999% service reliability with reduced time complexity.

Split learning is a promising paradigm for distributed learning at resource-constrained devices, where the learning model is split to be trained at the participants collaboratively. Unlike federated learning that shares the entire gradients among participants, split learning only exchanges the intermediate learning results (i.e., the extracted features/smashed data and gradients) at the cut layer between participants and server. This requires different/new attack designs to understand the security performance of various privacy-sensitive applications using split learning. This paper focuses on private labels and proposes three label inference attacks based on the similarities between exchanged gradients/smashed data and sample points. We mathematically analyze and unify these similarities (for retrieving accurate labels) as Euclidean distance, such that the attack can be conducted by finding the nearest sample point from target data in Euclidean space. We also show that transfer learning can help retrieve private labels directly from raw data. Experimental results demonstrate that our attacks can recover private labels against three state-of-the-art label protection methods.

End-to-end semantic communication (ESC) system is able to improve communication efficiency by only transmitting the semantics of the input rather than raw bits. Although promising, ESC has also been shown susceptible to the crafted physical layer adversarial perturbations due to the openness of wireless channels and the sensitivity of neural models. Previous works focus more on the physical layer white-box attacks, while the challenging black-box ones, as more practical adversaries in real-world cases, are still largely under-explored. To this end, we present SemBLK, a novel method that can learn to generate destructive physical layer semantic attacks for an ESC system under the black-box setting, where the adversaries are imperceptible to humans. Specifically, 1) we first introduce a surrogate semantic encoder and train its parameters by exploring a limited number of queries to an existing ESC system. 2) Equipped with such a surrogate encoder, we then propose a novel semantic perturbation generation method to learn to boost the physical layer attacks with semantic adversaries. Experiments on two public datasets show the effectiveness of our proposed SemBLK in attacking the ESC system under the black-box setting. Finally, we provide case studies to visually justify the superiority of our physical layer semantic perturbations.

There are two categories of methods in Federated Learning (FL) for joint training across multiple clients: i) parallel FL (PFL), where clients train models in a parallel manner; and ii) sequential FL (SFL), where clients train models in a sequential manner. In contrast to that of PFL, the convergence theory of SFL on heterogeneous data is still lacking. In this paper, we establish the convergence guarantees of SFL for strongly/general/non-convex objectives on heterogeneous data. The convergence guarantees of SFL are better than that of PFL on heterogeneous data with both full and partial client participation. Experimental results validate the counterintuitive analysis result that SFL outperforms PFL on extremely heterogeneous data in cross-device settings.

Split learning is an emerging distributed machine learning framework for enabling edge intelligence, especially for training sophisticated AI models at resource-constrained Internet-of-Things (IoT) devices. In split learning, the full AI model is partitioned to the client-side (e.g., input/privacy-sensitive layers) and server-side (e.g., computation-intensive layers) portions to be trained collaboratively at the devices and edge server. Only intermediate data at the split layer are exchanged during the training process for data privacy. However, the intermediate data may still cause security concerns to reconstruct the raw data from the partial gradients. This paper proposes the masking-enabled data protection approach for split learning without compromising the model accuracy. The devices are designed to perturb the reported results via masks, and the adversary can only retrieve the global information of all the devices (instead of individual devices). We mathematically prove that the masking-enabled perturbation mechanism would not compromise the learning accuracy. Experimental results validate the effectiveness of the proposed approach in terms of successful data protection and up to 10% model accuracy gain, compared to vanilla split learning and differential privacy.

The Internet of Vehicles (IoV) is a promising paradigm for autonomous driving, where the sensing data from the onboard sensors can be disseminated and processed cooperatively via vehicle-to-vehicle links. Autonomous vehicles can share their local views for cooperative, reliable, and robust driving decisions. However, the limited wireless resources may become the bottleneck with the increasing number of vehicles. The technical challenges also arise from the decentralized control, the spatial couplings of decisions, and the complexity of combinatorial optimization. This paper proposes a novel fully distributed graph-based approach to jointly optimize multicast link establishment with data dissemination and processing decisions by only exchanging partial information among neighboring vehicles. The mixed-integer programming problem aims to maximize system energy efficiency while achieving maximum data throughput. We prove that maximizing data processing throughput is submodular optimization to find the local optimum efficiently. The optimization of data dissemination and processing is reformulated to a minimum-cost maximum-flow problem in a three-layer graph, and efficiently solved by exploiting the graphical interdependence. Both simulation-generated and trace-based datasets are evaluated to validate the effectiveness of the proposed approach in terms of data throughput and energy efficiency.

By exploiting the superiority of nonorthogonal multiple access (NOMA), NOMA-aided mobile-edge computing (MEC) can provide scalable and low-latency computing services for the Internet of Things. However, given the prevalent stochasticity of wireless networks and sophisticated signal processing of NOMA, it is critical but challenging to design an efficient task offloading algorithm for NOMA-aided MEC, especially under a large number of devices. This article presents an online algorithm that jointly optimizes offloading decisions and resource allocation to maximize the long-term system utility (i.e., a measure of throughput and fairness). Since the optimization variables are temporary coupled, we first apply Lyapunov technique to decouple the long-term stochastic optimization into a series of per-slot deterministic subproblems, which does not require any prior knowledge of network dynamics. Second, we propose to transform the nonconvex per-slot subproblem of optimizing NOMA power allocation equivalently to a convex form by introducing a set of auxiliary variables, whereby the time-complexity is reduced from the exponential complexity to$\mathcal {O} (M^{3/2})$. The proposed algorithm is proved to be asymptotically optimal, even under partial knowledge of the device states at the base station. Simulation results validate the superiority of the proposed algorithm in terms of system utility, stability improvement, and the overhead reduction.

Cooperative caching can unify storage across edge clouds and provide efficient delivery of popular contents under effective content placement. However, the placement and delivery are non-trivial in cooperative caching due to the decentralized property of edge clouds, as well as the temporal and spatial correlation of the placement. We propose a new distributed online learning approach to jointly optimize content placement and delivery without the a-priori knowledge on file popularity and link availability. Content placement and delivery can be asymptotically optimized in real-time by running distributed online learning at individual edge servers by exploiting stochastic gradient descent (SGD). The proposed approach can allow operations at different timescales by integrating mini-batch learning for farsighted content placement. The optimality loss, stemming from the different timescales, can asymptotically reduce, as the SGD stepsize declines. Simulations confirm that the proposed approach outperforms existing techniques in terms of cache hit ratio and cost effectiveness. Insights are shed on the optimal placement of popular contents.

This paper aims to produce an effective online scheduling technique, where a base station (BS) schedules the transmissions of energy harvesting-powered Internet-of-Things (IoT) devices only based on the (differently outdated) in-band reports of the devices on their states. We establish a new primal-dual learning framework, which learns online the optimal proactive schedules to maximize the time-average throughput of all the devices. Batch gradient descent is designed to enable stochastic gradient descent (SGD)-based dual learning to learn the network dynamics from the outdated reports. Replay memory is deployed to allow online convex optimization (OCO)-based primal learning to predict channel conditions and prevent over-fitting. We also decentralize the online learning between the BS and devices, and speed up learning by leveraging the instantaneous knowledge of the devices on their states. We prove that the proposed framework asymptotically converges to the global optimum, and the impact of the outdated knowledge of the BS diminishes. Simulation results confirm that the proposed approach can increasingly outperform state of the art, as the number of devices grows.

Lyapunov optimization has shown to be effective for online optimization of fog computing, asymptotically approaching the optimality only achievable offline. However, it is not directly applicable to the Internet of Things, as inexpensive sensors have small buffers and cannot generate sufficient backlogs to activate the optimization. This article proposes an enabling technique for the Lyapunov optimization to operate under finite buffers without loss of asymptotic optimality. This is achieved by optimizing the biases (namely, “virtual placeholders”) of the buffers to create sufficient backlogs. The optimization of the placeholders is proved to be a new three-layer shortest path problem and solved in a distributed manner by extending the Bellman-Ford algorithm. The sizes of the virtual placeholders decline fastest along the shortest paths from the sensors to the data center, thereby preventing unnecessary detours and reducing end-to-end delays. Corroborated by simulations, the proposed approach is able to operate under the conditions the direct application of the Lyapunov optimization fails, and significantly increase the throughput and reduce the delays in other cases.

Edge computing allows an edge server to adaptively place virtual instances to serve different types of data. This article presents a new algorithm which jointly optimizes virtual service placement farsightedly and service data admission instantly to maximize the time-average service throughput of edge computing. The data admission is optimized, adapting to fast-changing data arrivals and wireless channels. The service placement is transformed into a two-dimensional knapsack problem by approximating future arrivals and channels with past observations, and solved over a slow timescale to allow services to be properly installed. Different from existing studies, our algorithm considers practical aspects of edge servers, such as finite memory size and bandwidth. We prove that the algorithm is asymptotically optimal and the optimality loss resulting from the approximation diminishes. Simulations show that our approach can improve the time-average throughput of existing alternatives by 16% for our considered simulation setup. The improvement becomes higher, as the memory size becomes increasingly tight. The number of services to be replaced is reduced without loss of throughput, after being placed farsightedly.

Processing data around the point of capture, fog computing can support computationally demanding Internet-of-Things (IoT) services. Distributed online optimization is important given the size of IoT, but challenging due to time variations of random traffic and nonuniform connectivity (or cardinality) of edge servers and IoT devices. This paper presents a distributed online learning approach to asymptotically minimizing the time-average cost of fog computing in the absence of the a-priori knowledge on traffic randomness, for light-weight, and delay-tolerant application scenarios. Stochastic gradient descent is exploited to decouple the optimizations between time slots. A graph matching problem is then formulated for every time slot by decoupling and unifying the nonuniform cardinalities, and solved in a distributed manner by developing a new linear (1/2)-approximation method. We prove that the optimality loss resulting from the distributed approximate graph matching method can be compensated and diminish by increasing the learning time. Corroborated by simulations, the proposed distributed online learning is asymptotically optimal and superior to the state of the art in terms of throughput and energy efficiency.

A spurt of progress in wireless power transfer (WPT) and mobile edge computing (MEC) provides a promising approach for Industrial Internet of Things (IIoT) to enhance the quality and productivity of manufacturing. Scheduling in such a scenario is challenging due to congested wireless channels, time-dependent energy constraints, complicated device heterogeneity, and prohibitive signaling overheads. In this article, we first propose an online algorithm, called energy-aware resource scheduling (ERS), to maximize the system utility comprising throughput and fairness, with consideration on both system sustainability and stability. Based on Lyapunov optimization and convex optimization techniques, the proposed algorithm achieves asymptotic optimality for heterogeneous IIoT systems without prior knowledge of network state information (NSI). Subsequently, we extend the ERS algorithm to a more realistic scenario where the overhead and delay of NSI feedbacks are non-negligible. The optimal scheduling decisions of the scenario are provided, and the optimality loss on system utility under outdated NSI is analyzed. The simulations verify our theoretical claims and demonstrate the gains of our proposed ERS algorithm over alternative benchmark schemes.

To enable machine learning at the edge of wireless networks (such as edge cloud), close to mobile users, is critical for future wireless networks, but challenging since the lower layers in edge cloud are substantially different from existing machine learning configurations in the cloud. In such geo-distributed computing environment, streaming data need to be evenly and cost-efficiently partitioned for different workers to produce an unbiased learning model with reduced parameter synchronization frequency. This paper presents a new online approach to optimally partitioning streaming data under time-varying network conditions. A new measure is proposed to quantify the evenness of data partitioning and restrain the optimization of data admission, partitioning, and processing. Stochastic gradient descent is applied to learn the optimal decisions online and asymptotically maximize the time-average utility of data partitioning. A new protocol is designed to further reduce the measurements of link costs, while preserving the asymptotic optimality, data evenness, and stability of the platform. Simulation results show that the proposed approach is superior to the state of the art in terms of throughput and cost efficiency, while only 24% of the links need to be measured to achieve the asymptotic optimality.

Cooperative caching can unify network storage to improve efficiency, but the effective placement and search of contents are challenging especially in distributed edge clouds with neither a-priori knowledge on content requests nor instantaneous global view. This paper establishes a new profitable cooperative region for every content request admitted at an edge server, within which the content, if cached, can be retrieved with guaranteed profit against a direct retrieval from the network backbone. This narrows down the search for the content. The caching density of the content can also be significantly reduced, e.g., to a cached copy per region. The regions are based on a novel distributed framework which allows individual servers to spontaneously admit/dispatch requests and deliver/forward contents, while asymptotically maximizing the time-average profit of caching. The cooperative region for content is erected at individual servers by comparing the upper and lower bounds for the backlogs of unsatisfied requests of the content. Simulations show the substantially improved profit of the proposed approach over existing solutions. The regions can help automate the placement of contents with reduced density and improved efficiency.

Fog computing enables resource-limited network devices to help each other with computationally demanding tasks, but has yet to be implemented in large scales due to sophisticated control and network inhomogeneity. This paper presents a new fully distributed online optimization to asymptotically minimize the time-average cost of fog computing, where tasks are selected to be offloaded and processed independently between different links and devices by measuring their cost effectiveness at each time slot. A key contribution is that we optimize the cost-effectiveness measures which achieve the asymptotic optimality over infinite time. Another contribution is that we optimize placeholders at the devices; which create collaborative computing regions of tasks in the vicinity of the point of capture, prevent tasks being offloaded beyond, preserve the asymptotic optimality and reduce delay. This is achieved in a distributed fashion by discovering the optimal substructure of the placeholders. Simulations show that the average size of collaborative regions is only 3.2 out of total 500 servers, and the system income increases by 43% as compared with existing techniques.

Decentralized orchestration of the control plane is critical to the scalability and reliability of software-defined network (SDN). However, existing orchestrations of SDN are either one-off or centralized, and would be inefficient the presence of temporal and spatial variations in traffic requests. In this paper, a fully distributed orchestration is proposed to minimize the time-average cost of SDN, adapting to the variations. This is achieved by stochastically optimizing the on-demand activation of controllers, adaptive association of controllers and switches, and real-time request processing and dispatching. The proposed approach is able to operate at multiple timescales for activation and association of controllers, and request processing and dispatching, thereby alleviating potential service interruptions caused by orchestration. A new analytic framework is developed to confirm the asymptotic optimality of the proposed approach in the presence of non-negligible signaling delays between controllers. Corroborated from extensive simulations, the proposed approach can save up to 73% the time-average operational cost of SDN, as compared to the existing static orchestration.

Task admission is critical to delay-sensitive applications in mobile edge computing, but is technically challenging due to its combinatorial mixed nature and consequently limited scalability. We propose an asymptotically optimal task admission approach which is able to guarantee task delays and achieve (1-ϵ)-approximation of the computationally prohibitive maximum energy saving at a time-complexity linearly scaling with devices. ϵ is linear to the quantization interval of energy. The key idea is to transform the mixed integer programming of task admission to an integer programming (IP) problem with the optimal substructure by pre-admitting resource-restrained devices. Another important aspect is a new quantized dynamic programming algorithm which we develop to exploit the optimal substructure and solve the IP. The quantization interval of energy is optimized to achieve an [O(ϵ), O(1/ϵ)]-tradeoff between the optimality loss and time complexity of the algorithm. Simulations show that our approach is able to dramatically enhance the scalability of task admission at a marginal cost of extra energy, as compared with the optimal branch and bound method, and can be efficiently implemented for online programming.

By performing fog computing, a device can offload delay-tolerant computationally demanding tasks to its peers for processing, and the results can be returned and aggregated. In distributed wireless networks, the challenges of fog computing include lack of central coordination, selfish behaviors of devices, and multi-hop signaling delays, which can result in outdated network knowledge and prevent effective cooperations beyond one hop. This paper presents a new approach to enable cooperations of N selfish devices over multiple hops, where selfish behaviors are discouraged by a tit-for-tat mechanism. The titfor-tat incentive of a device is designed to be the gap between the helps (in terms of energy) the device has received and offered; and indicates how much help the device can offer at the next time slot. The tit-for-tat incentives can be evaluated at every device by having all devices broadcast how much help they offered in the past time slot, and used by all devices to schedule task offloading and processing. The approach achieves asymptotic optimality in a fully distributed fashion with a timecomplexity of less than O(N2). The optimality loss resulting from multi-hop signaling delays and consequently outdated titfor-tat incentives is proved to asymptotically diminish. Simulation results show that our approach substantially reduces the timeaverage energy consumption of the state of the art by 50% and accommodates more tasks, by engaging devices hops away under multi-hop delays.

Mobile edge computing is of particular interest to Internet of Things (IoT), where inexpensive simple devices can get complex tasks offloaded to and processed at powerful infrastructure. Scheduling is challenging due to stochastic task arrivals and wireless channels, congested air interface, and more prominently, prohibitive feedbacks from thousands of devices. In this paper, we generate asymptotically optimal schedules tolerant to out-of-date network knowledge, thereby relieving stringent requirements on feedbacks. A perturbed Lyapunov function is designed to stochastically maximize a network utility balancing throughput and fairness. A knapsack problem is solved per slot for the optimal schedule, provided up-to-date knowledge on the data and energy backlogs of all devices. The knapsack problem is relaxed to accommodate out-of-date network states. Encapsulating the optimal schedule under up-to-date network knowledge, the solution under partial out-of-date knowledge preserves asymptotic optimality, and allows devices to self-nominate for feedback. Corroborated by simulations, our approach is able to dramatically reduce feedbacks at no cost of optimality. The number of devices that need to feed back is reduced to less than 60 out of a total of 5000 IoT devices.