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.

As softwares may be used by multiple users, caching popular softwares at the wireless edge has been considered to save computation and communications resources for mobile edge computing (MEC). However, fetching uncached softwares from the core network and multicasting popular softwares to users have so far been ignored. Thus, existing design is incomplete and less practical. In this paper, we propose a joint caching, computation and communications mechanism which involves software fetching, caching and multicasting, as well as task input data uploading, task executing (with non-negligible time dura- tion) and computation result downloading, and mathematically characterize it. Then, we optimize the joint caching, offloading and time allocation policy to minimize the weighted sum energy consumption subject to the caching and deadline constraints. The problem is a challenging two-timescale mixed integer nonlinear programming (MINLP) problem, and is NP-hard in general. We convert it into an equivalent convex MINLP problem by using some appropriate transformations and propose two low- complexity algorithms to obtain suboptimal solutions of the original non-convex MINLP problem. Specifically, the first sub- optimal solution is obtained by solving a relaxed convex problem using the consensus alternating direction method of multipliers (ADMM), and then rounding its optimal solution properly. The second suboptimal solution is proposed by obtaining a station- ary point of an equivalent difference of convex (DC) problem using the penalty convex-concave procedure (Penalty-CCP) and consensus ADMM. Finally, by numerical results, we show that the proposed solutions outperform existing schemes and reveal their advantages in efficiently utilizing storage, computation and communications resources.

Federated learning (FL) is promising in enabling large-scale model training by massive devices without exposing their local datasets. However, due to limited wireless resources, traditional cloud-based FL system suffers from the bottleneck of communication overhead in core network. Fueled by this issue, we consider a hierarchical FL system and formulate a joint problem of edge aggregation interval control and resource 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 training latency, and the number of successfully participating devices, is derived. Then an alternative problem is formulated, which can be decoupled into an edge aggregation interval control problem and a resource allocation problem, and solved by an iterative optimization algorithm. Specifically, given the resource allocation strategy, a relaxation and rounding method is proposed to optimize the edge aggregation interval. The problem of resource allocation including training time allocation and bandwidth allocation is solved separately based on the convex optimization theory. Simulation results show that the proposed algorithm, compared to the benchmarks, can achieve higher learning performance with lower training latency, and is capable of adaptively adjusting the edge aggregation interval and the resource allocation strategy according to the training process.

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 allocation and helper 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.

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.

Semantic communications, which aim to effectively convey the meaning of messages (such as text and images) rather than transmitting the exact messages themselves, have garnered widespread attention from industry and academia. A suitable joint source-channel coding (JSCC) scheme is crucial for semantic communication systems, as it can significantly improve system performance, such as communication reliability. Current research efforts primarily focus on employing various deep neural network (DNN) models, particularly the Transformer model, to design JSCC schemes. However, existing Transformer-based JSCC schemes usually exhibit a considerable number of model parameters and computational demands, limiting their real-world applicability. To address this challenge, we propose a novel DNN model based on DeLighT, a deep and lightweight variant of the standard Transformer, using a text semantic communication system (TSC) as an example. This proposed model enables a lightweight JSCC scheme for the TSC system. Through simulation results, we demonstrate that the proposed JSCC scheme achieves comparable or better communication reliability than the Transformer-based JSCC scheme while requiring significantly fewer parameters and smaller runtime.