The escalating demand for network services has prompted the evolution of Service Function Chaining (SFC) within 6G networks to deliver sophisticated, customized services while ensuring robust cybersecurity. This paper introduces an efficient and secure framework for SFC in Mobile Edge Computing (MEC) environments, termed the Federated Learning-based SFC (FL-SFC), which integrates SFC, MEC, and Federated Learning (FL) to enhance service policy decision-making and safeguard user privacy. The FL-SFC framework enables dynamic updating of service policies and optimizes communication efficiency. We propose an anomaly detection model, CNN-GRU, which combines Convolutional Neural Networks (CNNs) and Gated Recurrent Units (GRUs) to significantly improve anomaly detection performance at the network edge. Additionally, to address the high communication costs associated with service policy models, we have designed a model compression mechanism leveraging sparsification and quantization techniques, which substantially reduces communication overhead during model training. Simulation experiments demonstrated the superiority of the FL-SFC framework and the CNN-GRU model in detection performance over existing methods. Results indicate that our model excels in accuracy, precision, recall, and F1-score while significantly reducing the number of communication bits, thereby validating the effectiveness of our approach.

The rapid growth of the mobile Internet has led to an increasing demand for reliable transmission of various data types, particularly images shared among multiple users over wireless networks. Traditional communication systems face challenges in managing large-scale image transmissions. Semantic communication, focusing on conveying meaning rather than raw bits, offers a promising solution. For semantic communication, reliability hinges on two key factors: successful transmission and successful understanding. Taking image semantic communication (ISC) systems as an example, successful transmission ensures the physical delivery of the image, while successful understanding refers to the correct interpretation of its semantics. To address these requirements, we design a semantic extraction and reconstruction module, called STC-based on Swin Transformer and convolutional neural network that enables parallel semantic processing and incorporates enhanced channel-aware attention mechanism, which is then integrated with residual blocks to form a joint source-channel coding (JSCC) model for semantic extraction, compression, and reconstruction. To optimize ISC reliability, we design a system utility function integrating the impacts of successful transmission and comprehension. We formulate a utility maximization problem for joint semantic compression rate (SCR) selection and resource allocation, solved by a carefully-designed joint SCR selection and resource allocation (JSSRA) algorithm based on the hierarchical soft actor-critic method. Simulation results demonstrate that our JSCC model significantly improves image quality compared to other learning-based methods while maintaining computational efficiency. Meanwhile, the JSSRA algorithm enhances system utility by 15%-50% compared to existing resource allocation methods. These results validate the effectiveness and superiority of our proposed methods in multi-user ISC systems.

Advancements in Augmented Intelligence of Things (AIoT) have made vehicle trajectory anomaly detection essential for road safety and traffic efficiency. However, the privacy-sensitive nature of trajectory data results in regional data silos, limiting model generalization. Federated learning (FL) enables collaborative training without data sharing, but still struggles with data heterogeneity and synchronous update inefficiencies in real-world scenarios. To address these challenges, we propose a personalized FL scheme for trajectory anomaly detection, namedpFedVTAD. It introduces a mutual-distillation module that uses a messenger model to bidirectionally transfer knowledge between the global and personalized models, producing area-aligned personalized models via adaptive local distillation. It also presents a privacy-preserving asynchronous aggregation that combines differential privacy, a model bank, and threshold-triggered merging to balance privacy and communication efficiency under partial participation and asynchronous arrivals. Experiments on a public trajectory dataset show that under asynchronous updates, pFedVTAD yields a well-generalized global model and area-tailored personalized models, demonstrating strong deployability in dynamic cross-area AIoT settings.

Unmanned aerial vehicle (UAV) networks face critical challenges in dynamic environments where conventional approaches treat trajectory optimization and resource allocation as separate problems, failing to capture their intricate interdependencies and leading to suboptimal performance, excessive energy consumption, and processing delays. This paper addresses these limitations through a novel hybrid methodology that uniquely integrates deep reinforcement learning with convex optimization for joint optimization. Our innovation lies in two interdependent algorithms: Deep Reinforcement Learning (DRL)-based relay UAV trajectory optimization algorithm (DRL-RUTOA), which leverages Model-Agnostic Meta-Learning for rapid environmental adaptation, and computation-aware multi-UAV trajectory optimization algorithm (CA-MUTOA), which employs a benefit-cost prioritization mechanism for selective computational offloading. Unlike previous approaches, we formulate a unified multi-objective optimization framework that simultaneously balances network throughput, energy efficiency, and computational task management. Simulation results demonstrate that our integrated approach significantly outperforms conventional methods, achieving a 35% improvement in network throughput, 28% reduction in processing delay, and 42% reduction in energy consumption. Additionally, our framework exhibits superior convergence efficiency, requiring only 15 iterations compared to 32-42 iterations for conventional methods, confirming its practical viability for resource-constrained UAV operations in complex mission environments.

Network slicing is a key technology that can provide service assurance for the heterogeneous application scenarios emerging in the next-generation networks. However, the heterogeneity and complexity of virtualized end-to-end network slicing environments pose challenges for network security operations and management. In this paper, we propose a knowledge-driven cross-domain collaborative anomaly detection scheme for end-to-end network slicing, namely HFL-TranWGAN. Specifically, we first design a hierarchical management framework that performs three-tier hierarchical intelligent management of end-to-end network slices, while introducing a knowledge plane to assist the management plane in making intelligent decisions. Then, we develop a knowledge-driven sub-slice anomaly detection model, the conditional TranWGAN model, in which an encoder, a generator, and multiple discriminators perform adversarial learning simultaneously. Finally, taking the sub-slice anomaly detection model as the basic training model, we utilize hierarchical federated learning to achieve inter-slice and intra-slice collaborative anomaly detection. We calculate the anomaly scores through the discrimination error and reconstruction error to obtain the anomaly detection results. Simulation results on two real-world datasets show that the proposed HFL-TranWGAN scheme performs better in anomaly detection performance such as F1 score and precision compared to the benchmark methods. Specifically, HFL-TranWGAN improved precision by up to 8.53% and F1 score by up to 1.88% compared to benchmarks.

Holographic video creates an immersive experience for users with lifelike scene reconstruction, yet it comes with the trade-off of managing massive data volumes. Therefore, to maintain a consistent quality of experience (QoE) in wireless networks with fluctuating channel conditions, it is necessary to develop efficient and adaptive holographic video streaming methods. This paper proposes a coordinated multicast streaming framework for holographic video that integrates coordinated multipoint transmission with transcoding-enabled multicasting techniques. Our framework supports the simultaneous transmission of holographic video tiles at various bitrates from multiple multi-antenna base stations to different multicast groups, significantly enhancing the overall viewing experience. We formulate an optimization problem with the goals of improving the average video quality experienced by all users while reducing the energy consumption for transcoding, which is NP-hard. By employing the proximal policy optimization, a leading-edge deep reinforcement learning algorithm, and convex optimization techniques, we develop a dynamic algorithm for joint bitrate selection and resource allocation. Simulations confirm the effectiveness of our algorithm, showing marked improvements in QoE over existing baselines.

This paper explores task offloading within load-imbalance vehicular multi-access edge computing (MEC) sys-tems. Addressing the uneven distribution of mobile vehicles causing road side unit (RSU) load imbalances, we leverage vehicle mobility and service pricing to redistribute task loads. RSUs strategically set service prices to alleviate congestion and enhance profitability. Meanwhile, vehicles assess these prices to determine task offloading to different RSU s while in motion, to maximize their individual utility. To achieve this, the Karush- Kuhn- Tucker (KKT) condition is applied to determine the optimal RSU ser-vice pricing. Furthermore, a multi-agent reinforcement learning algorithm, Nash Q-Iearning, is utilized to manage the vehicles' offloading decisions. Simulation results substantiate the efficacy of the Nash Q-Iearning-based task offloading scheme, enhancing the utility of mobile vehicles within competitive environments.

Abstract Deep learning has been widely applied in ship detection in synthetic aperture radar (SAR) imagery due to their powerful feature representation capabilities. However, YOLOv8 models treat all regions of the image equally during convolutional feature processing, resulting in less‐than‐ideal outcomes. To address this limitation, this study proposes a simple, parameter‐free attention module (SimAM) attention‐based YOLOv8 algorithm for ship detection in SAR images. The proposed algorithm first passes through a backbone network, which incorporates SimAM attention modules. The SimAM attention mechanism successfully allocates the convolutional neural network's 3D weights effectively using an energy function method, without introducing additional parameters. This mechanism enables the network to automatically emphasize key features in the image, enhancing its ability to represent target areas and suppress background interference. Subsequently, deep features are upsampled and fused with relatively shallow features to extract features at three different scales and achieve target detection, ultimately outputting classification and positional information of the targets. The effectiveness of the model on the SAR‐ship‐dataset is experimentally validated achieving an mAP50 value of 97.72% and an mAP50‐95 value of 68.99%, confirming the superiority of the proposed model.

In this paper, we propose a low‐complexity expectation propagation (EP) detector for orthogonal time frequency space (OTFS) system with practical rectangular waveforms. In the high‐mobility scenario, OTFS is becoming a potential scheme for the sixth‐generation (6G) wireless communication system. However, the large size of the effective delay‐Doppler (DD) domain channel matrix brings unbearable computational complexity to the signal detection algorithm based on the matrix inversion. We propose a low‐complexity EP detector based on the sparsity and the block circulant structure of the effective channel covariance matrix in the DD domain. The proposed algorithm only requires log‐linear complexity. In addition, simulation results show that the proposed algorithm not only has the advantage of low complexity but also has good performance, which achieves a tradeoff between performance and complexity.

Clustered Vehicular Federated Learning (CVFL) can be used to improve traffic safety, increase traffic efficiency, and reduce vehicle carbon emissions. Therefore, it is extremely promising in intelligent transportation systems. However, in practice, it is difficult to accurately cluster vehicular clients with mobility according to data distribution. In addition, vehicular clients may be reluctant to contribute their computation and communication resources to perform learning tasks if the CVFL server does not give them proper incentives. In this paper, we would like to address the above issues. Specifically, considering the mobility of vehicular clients, we first propose a clustering method to cluster vehicular clients into several clusters based on the cosine similarity between the model gradient of local vehicular clients and the K-means method. Then, we design a set of optimal contracts specifically for the clusters, aiming to motivate them to select the optimal number of intra-cluster iterations for model training and give the closed-form solution to the contracts under the constraints of individual rationality, incentive compatibility, and task accuracy. The proposed contract theory based incentive mechanism not only effectively motivates every cluster, but also overcomes the information asymmetry problem to maximize the utility of the CVFL server. Finally, simulation results validate the effectiveness of the proposed clustering method and the designed contract.

Block propagation is a critical step in the consensus process, which determines the fork rate and transaction throughput of public blockchain systems. To accelerate block propagation, existing block relay protocols reduce the block size using transaction hashes, which requires the receiver to reconstruct the block based on the transactions in its mempool. Hence, their performance is highly affected by the number of transactions missed by mempools, especially in the P2P network with frequent arrival and departure of nodes. In this paper, we introduce Presync, a transaction synchronization protocol that can reduce the difference of transactions between the block and the mempool with controllable bandwidth overhead. It allows mining pool servers to synchronize the transactions in candidate blocks before the propagation of a valid block. Low-bandwidth mode provides a lightweight synchronization by identifying the unsynchronized transactions, so that the missing transactions can be detected with a low redundancy. High-bandwidth mode conducts a full synchronization of the candidate block using short hashes, and the Merkle root is utilized to match the valid block. We study the performance of Presync through stochastic modeling and experimental evaluations. The results illustrate that low and high-bandwidth modes can respectively reduce the end-to-end delay of compact block by 60% and 78% with bandwidth usages 25KB and 63KB, in a network with 5 active pool servers and 2/3 online probability of full nodes.

Blokchain is a promising technology to enable distributed and reliable data sharing at the network edge. The high security in blockchain is undoubtedly a critical factor for the network to handle important data item. On the other hand, according to the dilemma in blockchain, an overemphasis on distributed security will lead to poor transaction-processing capability, which limits the application of blockchain in data sharing scenarios with high-throughput and low-latency requirements. To enable demand-oriented distributed services, this paper investigates the relationship between capability and security in blockchain from the perspective of block propagation and forking problem. First, a Markov chain is introduced to analyze the gossiping-based block propagation among edge servers, which aims to derive block propagation delay and forking probability. Then, we study the impact of forking on blockchain capability and security metrics, in terms of transaction throughput, confirmation delay, fault tolerance, and the probability of malicious modification. The analytical results show that with the adjustment of block generation time or block size, transaction throughput improves at the sacrifice of fault tolerance, and vice versa. Meanwhile, the decline in security can be offset by adjusting confirmation threshold, at the cost of increasing confirmation delay. The analysis of capability-security trade-off can provide a theoretical guideline to manage blockchain networks based on the requirements of data sharing scenarios.

On-demand and resource reservation pricing models, widely used in cloud computing, are currently used in Multi-Access Edge Computing (MEC). Nevertheless the edge's resources are distributed and each server has lower capacity. If too much resources were reserved in advance, on-demand users may not get their jobs served on time, jeopardizing MEC's latency benefits. Concurrently, reservation plan users may possess un-used quota. Therefore, we propose a sharing platform where reservation plan users can re-sell unused resource quota to on-demand users. To investigate the mobile network operator's (MNO‘s) incentive of allowing re-selling, we formulate a 3-stage non-cooperative Stackelberg Game and characterize the optimal strategies of buyers and re-sellers. We show that users’ actions give rise to 4 different outcomes at equilibrium, dependent on the prices and supply levels of the sharing and on-demand pools. Based on the 4 possible outcomes, we characterise the MNO's optimal prices for on-demand users. Numerical results show that having both pools gives the MNO an optimal revenue when the on-demand pool's supply is low, and unexpectedly, when the MNO's commission is low. We develop an interactive prototype, and show that users’ decision distributions in studies on our prototype are similar to that of our decision model.

5G/B5G networks are expected to deliver huge traffic and support various use cases with diverse requirements. With the increasing demand for network capacity, a cost-effective and flexible RAN is urgently needed to provide customized services for users. On this basis, advanced flexible RAN architectures with functional splits are introduced. In this paper, we study the slice-centric fine-grained functional split and resource allocation problem in flexible RAN. We first formulate a multi-objective problem to jointly optimize the functional split selection, processing, and transmission resource allocation for slices, aiming at maximizing the functional split gain while satisfying slices’ requirements. Since a multi-objective problem may have multiple Pareto optimal solutions and is difficult to solve, we mathematically analyze and transform the problem into an equivalent parametric convex problem. Then, we propose an upper bound algorithm and a dual based resource allocation algorithm to find the solution for the optimization problem. Theoretical analysis and simulation results show that the proposed algorithms can effectively solve the functional split gain maximization problem and obtain a trade-off between processing and transmission resource gain. In addition, the proposed algorithms also outperform other benchmark approaches in terms of resource saving and flexibility.

Considering the spectrum sharing system (SSS) coexisting with multiple primary networks, we have employed a well-designed reconfigurable intelligent surface (RIS) to control the radio environments of wireless channels and relieve the scarcity of the spectrum resource. Specifically, the enhancement of the spectral efficiency of the secondary user in the considered SSS is decomposed into two subproblems which are a second-order cone programming (SOCP) and a fractional programming of the convex quadratic form (CQFP), respectively, to optimize alternatively the beamforming vector at the secondary access point (S-AP) and the reflecting coefficients at the RIS. The SOCP subproblem is shown as a concave problem, which can be solved optimally using standard convex optimization tools. The CQFP subproblem can be solved by a low-complexity method of gradient-based linearization with domain (GLD), providing a sub-optimal solution for fast deployment. Taking the discrete phase control at the RIS into account, a nearest point searching with penalty (NPSP) method is also developed, realizing the discretization of the phase shifts of the RIS in practice. The simulation results indicate that both GLD and NPSP can achieve an excellent performance.

5G/B5G networks are expected to deliver a huge traffic and support various use cases with diverse requirements. With the increasing demand for network capacity, a cost-effective and flexible RAN is urgently needed to provide customized services for users. On this basis, the advanced flexible RAN architectures with functional splits are introduced. In this paper, we study the slice-centric fine-grained functional split and resource allocation problem in flexible RAN. We first formulate a multi-objective problem to jointly optimize the functional split selection, processing, and transmission resource allocation for slices, aiming at maximizing the functional split gain while satisfying slices’ requirements. Since a multi-objective problem may have multiple Pareto optimal solutions and is difficult to solve, we mathematically analyze and transform the problem into an equivalent parametric convex problem. Then, we propose an upper bound algorithm and a dual based resource allocation algorithm to find the solution for the optimization problem. Theoretical analysis and simulation results show that the proposed algorithms can effectively solve the functional split gain maximization problem and obtain a trade-off between processing and transmission resource gain. In addition, the proposed algorithms also outperform other benchmark approaches in terms of resource saving and flexibility.

Driven by the development of time-sensitive applications, short packet transmission (SPT) design has become the key point in the ultra-reliable and low-latency communications (URLLC) area. The primary challenge in it is that the delay caused by pilot overhead cannot be neglected. To deal with this issue, this paper presents a frame structure adopting partial-superimposed-pilot (PSP) scheme for SPT. The key of PSP scheme is that the number of data symbols is equal to the available blocklength, and the number of pilot symbols transmitted with data in the training stage needs to be optimized. Under the finite blocklength regime, we first derive a closed-form lower bound achievable rate of an uplink massive MIMO system with imperfect pilot removal for maximal-ratio-combining (MRC) receiver. Then, we formulate a weighted sum rate maximization problem by jointly optimizing the pilot length, pilot power, and data power. We derive a closed-form solution of optimal pilot length. Using the log-function and successive convex approximation (SCA) method, we develop an iterative optimization framework to find a locally optimal power solution. For comparison, the conventional frame structures based on complete-superimposed-pilot (CSP) and regular pilot (RP) schemes are also shown. Simulation results indicate that the proposed PSP scheme is superior to the existing CSP and RP schemes.

In a D2D-enabled MEC system, devices cooperate in task computation by relaying tasks to servers or providing computation capabilities for users. We investigate how nodes choose the roles to join in the offloading process in a dynamic environment, where mobile devices forming a tree-like multihop network can play relays and intermediate executors earning corresponding economic utility. By mathematically modeling the multihop computation offloading, we formulate the task-flow constrained network-wide utility maximization problem as a potential game. Based on the properties of the potential game, we prove the existence of Nash equilibrium and propose two learning-based algorithms, i.e., myopic best response (MBR-CO) and stochastic learning-based computation offloading (SL-CO), to find the equilibrium point in a distributed manner. Theoretical and simulation results show that MBR-CO is dominant in static scenarios, and SL-CO achieves a high utility and stable performance in dynamic scenarios.

Blokchain is a promising technology to enable distributed and reliable data sharing at the network edge. The high security in blockchain is undoubtedly a critical factor for the network to handle important data item. On the other hand, according to the trilemma in blockchain, an overemphasis on distributed security will lead to poor transaction-processing capability, which limits the application of blockchain in data sharing scenarios with high-throughput and low-latency requirements. To enable demand-oriented distributed services, this paper investigates the relationship between capability and security in blockchain from the perspective of block propagation and forking problem. First, a Markov chain is introduced to analyze the gossiping-based block propagation among edge servers, which aims to derive block propagation delay and forking probability. Then, we study the impact of forking on blockchain capability and security metrics, in terms of transaction throughput, confirmation delay, fault tolerance, and the probability of malicious modification. The analytical results show that with the adjustment of block generation rate, transaction throughput improves at the sacrifice of fault tolerance, and vice versa. Meanwhile, the decline in security can be offset by adjusting confirmation threshold, at the cost of increasing confirmation delay.

Hierarchical federated edge learning (H-FEEL) has been recently proposed to enhance the federated learning model. Such a system generally consists of three entities, i.e., the server, helpers, and clients. Each helper collects the trained gradients from users nearby, aggregates them, and sends the result to the server for model update. Due to limited communication resources, only a portion of helpers can upload their aggregated gradients to the server, thereby necessitating a well design for helper scheduling and communication resources allocation. In this paper, we develop a training algorithm for H-FEEL which involves local gradient computing, weighted gradient uploading, and model updating phases. By characterizing these phases mathematically and analyzing the one-round convergence bound of the training algorithm, we formulate a problem to achieve the scheduling and resource allocation scheme. To solve the problem, we first transform it into an equivalent problem and then decompose the transformed problem into two subproblems: bit and sub-channel allocation problem and helper scheduling problem. For the first subproblem, we obtain a low-complexity suboptimal solution by using a four-stage method. For the second subproblem, we obtain a stationary point by using the penalty convex-concave procedure. The efficacy of our scheme is demonstrated via simulations, and the analytical framework is shown to provide valuable insights for the design of practical H-FEEL system.

In this paper, we consider the dynamic content caching issue in the cache-enabled Internet of Things (IoT) systems. For real-time applications in cache-enabled IoT systems, it is imperative to design dynamic content caching schemes to reduce the energy consumption of sensors and improve the freshness of information at users. We first design a dynamic content caching procedure for a cache-enabled IoT system with limited cache capacity and express the evolution of the Age of Information (AoI) at both the edge caching node and each user. Then, we formulate the dynamic content caching problem as a Markov Decision Process to minimize the expectation of a long-term accumulative cost, which jointly considers the average AoI of users and the energy consumption of sensors. To solve this problem, we propose an actor-critic based caching algorithm without prior knowledge of users’ content demands. The numerical results show that the proposed algorithm can achieve lower average AoI and energy consumption than other baselines.

The concept of hierarchical federated edge learning (H-FEEL) has been recently proposed as an enhancement of federated learning model. Such a system generally consists of three entities, i.e., the server, helpers, and clients, in which each helper collects the trained gradients from clients nearby, aggregates them, and sends the result to the server for global model update. Due to limited communication resources, only a portion of helpers can be scheduled to upload their aggregated gradients in each round of the model training. And that necessitates a well-designed scheme for the joint helper scheduling and communication resources allocation. In this paper, we develop a training algorithm for the H-FEEL system which involves local gradient computing, weighted gradient uploading, and machine learning model updating phases. By characterizing these phases mathematically and analyzing one-round convergence bound of the training algorithm, we formulate an optimization problem to achieve the scheduling and resource allocation scheme. The problem simultaneously captures the uncertainty of the wireless channel and the importance of the weighted gradient. To solve the problem, we first transform it into an equivalent problem and then decompose the transformed problem into two subproblems:bit and sub-channel allocationandhelper scheduling, which are mixed integer nonlinear programming and continuous nonlinear problems, respectively. For the first subproblem, we obtain an optimal solution of exponential complexity and a suboptimal solution that has polynomial complexity. For the second subproblem, we obtain a closed-form optimal solution in a special case and a suboptimal solution in the general case. The efficacy of our scheme is amply demonstrated via simulations and the analytical framework is shown to provide valuable design insights for the practical implementation of the H-FEEL system.

In this paper, we consider a hierarchical federated learning system and formulate a joint problem of edge aggregation interval control and time allocation to minimize the weighted sum of training loss and training latency. To quantify the learning performance, an upper bound of the average global gradient deviation, in terms of the edge aggregation interval, the time allocated for training, and the number of successfully participating devices, is derived. Then an alternative problem is formulated, which can be decoupled into two sub-problems and solved with two steps. In the first step, given the time allocation strategy, a relaxation and rounding method is proposed to optimize the edge aggregation interval. In the second step, with the results of the obtained edge aggregation interval and based on the convex optimization theory, an optimal time allocation can be evaluated. Simulation results show that the proposed scheme, compared to the benchmarks, can achieve higher learning performance with lower training latency.

Content caching is recognized as a promising solution to release the heavy burden of backhaul links and decrease the content transmission latency in Fog radio access networks (Fog-RANs). However, the content caching design is still a challenging problem with considering the user request patterns, the content delivery strategies, and the limited caching capacity. Recommendation has the capability of reshaping users' content requests for further prompting caching gain. The joint recommendation, caching, beamforming holds the potential to improve the system performance of Fog-RANs. In this paper, a joint recommendation, caching, and beamforming scheme is proposed for multi-cell multi-antenna recommendation aware Fog-RANs. Aiming at minimizing the content transmission latency, we formulate a joint recommendation, caching, and beamforming optimization problem. The minimization problem is a very challenging two-timescale mixed integer nonlinear programming problem, which is hard to solve in general. By exploring structural properties of the problem, we propose an alternative optimization algorithm with low complexity through decomposing the original problem into three sub-problems. Extensive simulations show that our proposed method can significantly reduce the content transmission delay.

Edge side caching assisted device-to-device (D2D) communication has been acknowledged as a promising technique to alleviate the heavy burden of backhaul transmission link and to reduce the network latency. However, the effectiveness of caching strategies at the network edge is highly dependent on the distribution of individual user’s content preference. To fully attain the benefits of edge caching, some proactive mechanisms shall be considered. Among which, recommendation performs noticeably well due to its capability of reshaping the content request probabilities of different users, which in turn affects the cache decision significantly. In this work, we quantitatively investigate how recommendation can be applied to enhance the caching efficiency of D2D enabled wireless content caching networks. And for that, the cache hit ratio maximization problem for a generic network model is formulated taking into account the requirements of each user’s personalized recommendation quality, recommendation quantity and cache capacity. Then, we show that the optimal recommendation and caching policies which jointly maximize the cache efficiency is NP-hard to compute. Further, a time-efficient sub-optimal algorithm is designed, which works in an iterative manner and has provable convergence guarantee as well as polynomial time complexity. Monte-Carlo simulation results demonstrate the convergence performance of our proposed joint decision algorithm and its cache efficiency improvements compared to extensive benchmarks.

To maintain reliability of content-oriented wireless caching networks (CWCNs), repair mechanism is of necessity to be considered due to the natural that storage entities are individually unreliable and thus subject to failure on account of hardware error, network congestion or software updating. Meanwhile, recommendation is tunable for edge caching performance improvement. In this paper, we study the revenue maximization problem for CWCNs with both repair and recommendation considerations. The formulated problem is an integer non-convex and non-linear problem, and thus is difficult to be solved. The difficulties are intrinsically derived from the implicit weighted sum costs (WSCs) as regards storage and repair of each content and the coupling among the Boolean variables. For the sake of analytical tractability, a two-step methodology is developed. Specifically, we first explore the optimal storage and repair amount among the content providers to minimize the WSCs in terms of successfully fixing any occurred data corruption for the stored contents. Thereof, an explicit instance is provided to show how the contents can be coded, stored and then repaired in our network given that an error occurs. Based on the obtained storage and repair amount vectors, we solve the resultant joint caching and recommendation decision making problem (DMP). To be more specific, we decouple the DMP into a pair of subproblems, namely a cache placement and a recommendation optimization subproblems. For each subproblem, a globally optimal and a time-efficient suboptimal solutions are developed, respectively. Later, a versatile iterative paradigm is devised to do the decision making jointly. The convergence performance and the complexity analysis of the proposed algorithms are rigorously analyzed. Numerical results confirm the convergence performance of our iterative algorithms and illustrate their revenue improvements compared to various baseline schemes.

In this paper, we propose a novel secure random caching scheme for large-scale multi-antenna heterogeneous wireless networks, where the base stations (BSs) deliver randomly cached confidential contents to the legitimate users in the presence of passive eavesdroppers as well as active jammers. In order to safeguard the content delivery, we consider that the BSs transmits the artificial noise together with the useful signals. By using tools from stochastic geometry, we first analyze the average reliable transmission probability (RTP) and the average confidential transmission probability (CTP), which take both the impact of the eavesdroppers and the impact of the jammers into consideration. We further provide tight upper and lower bounds on the average RTP. These analytical results enable us to obtain rich insights into the behaviors of the average RTP and the average CTP with respect to key system parameters. Moreover, we optimize the caching distribution of the files to maximize the average RTP of the system, while satisfying the constraints on the caching size and the average CTP. Through numerical results, we show that our proposed secure random caching scheme can effectively boost the secrecy performance of the system compared to the existing solutions.

By exploiting the computing power and local data of distributed clients, federated learning (FL) features ubiquitous properties such as reduction of communication overhead and preserving data privacy. In each communication round of FL, the clients update local models based on their own data and upload their local updates via wireless channels. However, latency caused by hundreds to thousands of communication rounds remains a bottleneck in FL. To minimize the training latency, this work provides a multi-armed bandit-based framework for online client scheduling (CS) in FL without knowing wireless channel state information and statistical characteristics of clients. Firstly, we propose a CS algorithm based on the upper confidence bound policy (CS-UCB) for ideal scenarios where local datasets of clients are independent and identically distributed (i.i.d.) and balanced. An upper bound of the expected performance regret of the proposed CS-UCB algorithm is provided, which indicates that the regret grows logarithmically over communication rounds. Then, to address non-ideal scenarios with non-i.i.d. and unbalanced properties of local datasets and varying availability of clients, we further propose a CS algorithm based on the UCB policy and virtual queue technique (CS-UCB-Q). An upper bound is also derived, which shows that the expected performance regret of the proposed CS-UCB-Q algorithm can have a sub-linear growth over communication rounds under certain conditions. Besides, the convergence performance of FL training is also analyzed. Finally, simulation results validate the efficiency of the proposed algorithms.

In this paper, we investigate the optimal caching policy in a K-tier millimeter wave (mmWave) cache- enabled heterogeneous network. In order to mitigate interferences, we incorporate base station (BS) idling into our analysis. Under the random caching framework, we derive the association probability for each tier as well as the successful transmission probability (STP) by utilizing stochastic geometry and taking the blockage effect into account. In addition, we adopt the gradient projection method to obtain the locally optimal caching probabilities and propose a two-stage scheme to obtain the globally optimal caching probabilities under the special case where the LOS ranges for K tiers are sufficiently large. Numerical results demonstrate the superiority of the proposed method over the conventional caching strategies such as Most Popular Content (MPC) and Uniform Caching (UC) schemes.

In this paper, to make better use of file diversity provided by random caching and improve the successful transmission probability (STP) of a file, we consider retransmissions with random discontinuous transmission (DTX) in a large-scale cache-enabled heterogeneous wireless network (HetNet) employing random caching. We analyze the STP in two mobility scenarios, i.e., the high mobility scenario and the static scenario. In each scenario, by using tools from stochastic geometry and series expansion of some special functions, we obtain the closed-form expressions for the STP in the general and low signal-to-interference ratio (SIR) threshold regimes, respectively. It shows that a larger caching probability corresponds to a higher STP in both scenarios; random DTX can improve the STP in the static scenario and its benefit gradually diminishes when mobility increases. In addition, the asymptotic analysis shows that the diversity gain is jointly affected by random caching and random DTX in both scenarios.

Base station cooperation in heterogeneous wireless networks (HetNets) is a promising approach to improve the network performance, but it also imposes a significant challenge on backhaul. On the other hand, caching at small base stations (SBSs) is considered as an efficient way to reduce backhaul load in HetNets. In this paper, we jointly consider SBS caching and cooperation in a downlink large-scale HetNet. We propose two SBS cooperative transmission schemes under random caching at SBSs with the caching distribution as a design parameter. Using tools from stochastic geometry and adopting appropriate integral transformations, we first derive a tractable expression for the successful transmission probability under each scheme. Then, under each scheme, we consider the successful transmission probability maximization by optimizing the caching distribution, which is a challenging optimization problem with a non-convex objective function. By exploring optimality properties and using optimization techniques, under each scheme, we obtain a locally optimal solution in the general case and a globally optimal solution in some special cases. Compared with some existing caching designs in the literature, e.g., the most popular caching, the i.i.d. caching and the uniform caching, the optimal random caching under each scheme achieves a promising successful transmission probability. The analysis and optimization results provide valuable design insights for practical HetNets.

To make better use of file diversity provided by random caching and improve the successful transmission probability (STP) of a file, we consider retransmissions with random discontinuous transmission (DTX) in a large-scale cache-enabled heterogeneous wireless network employing random caching. We analyze and optimize the STP in two mobility scenarios, i.e., the high mobility scenario and the static scenario. First, in each scenario, by using tools from stochastic geometry, we obtain a closed-form expression for the STP in the general signal-to-interference ratio (SIR) threshold regime. The analysis shows that a larger caching probability corresponds to a higher STP in both scenarios; random DTX can improve the STP in the static scenario and its benefit gradually diminishes when mobility increases. In each scenario, we also derive a closed-form expression for the asymptotic outage probability in the low SIR threshold regime. The asymptotic analysis shows that the diversity gain is jointly affected by random caching and random DTX in both scenarios. Then, in each scenario, we consider the maximization of the STP with respect to the caching probability and the BS activity probability, which is a challenging non-convex optimization problem with a complex objective function. In particular, in the high mobility scenario, we obtain a globally optimal solution. In the static scenario, we develop a low-complexity iterative algorithm to obtain a stationary point. Finally, numerical results show that the proposed solutions achieve significant gains over existing baseline schemes and can well adapt to the changes of the system parameters to wisely utilize storage resources and transmission opportunities.

Base station cooperation in heterogeneous wireless networks (HetNets) is a promising approach to improve the network performance, but it also imposes a significant challenge on backhaul. On the other hand, caching at small base stations (SBSs) is considered as an efficient way to reduce backhaul load in HetNets. In this paper, we jointly consider SBS caching and cooperation in a downlink large-scale HetNet. We propose an SBS cooperative transmission scheme under random caching at SBSs with the caching distribution as a design parameter. Using tools from stochastic geometry, we first derive a tractable expression for the successful transmission probability. Then, we consider the successful transmission probability maximization by optimizing the caching distribution, which is a challenging optimization problem with a non-convex objective function. By exploring optimality properties and using optimization techniques, we obtain a local optimal solution in the general case and the global optimal solution in a special case. Compared with some existing caching designs in the literature, e.g., the most popular caching, the i.i.d. caching and the uniform caching, the optimal random caching achieves better successful transmission probability performance.