With the development of the space-air-ground integration technology, the satellites are armed with a certain on-board computing resource. To fully offload communication tasks to each satellite, we investigate a multiuser multi-satellite cooperative communication system without a central processing unit (CPU), where the satellites are equipped with tunable load antennas leveraging the mutual coupling effect to reconfigure the wireless channel. First, we formulate the sum spectral efficiency (SE) maximization problem with respect to the beamforming and the tunable loads under the power constraint and the constraints of the tunable loads. Afterwards, we propose a cooperative algorithm with closed-form updates to obtain a stationary point based on parallel successive convex approximation (SCA). Furthermore, we propose an efficient information exchange strategy for the satellites based on the ring all-reduce method, which significantly reduces the information exchange overhead of each satellite. Lastly, numerical results verify the proposed design's notable gain over the baselines. As far as we know, this is the first work to study the multi-satellite cooperative communication system with tunable load antennas.

Federated edge learning (FEL) integrates federated learning (FL) into edge computing systems to improve communication efficiency and data privacy. We investigate a practical FEL system, where the computing and communication resources are dynamic and heterogeneous among workers, and the local data are non-independent and identically distributed (non-IID). We formulate a joint worker selection and FL algorithm parameter configuration problem to minimize the final test loss under time and energy constraints. The corresponding problem poses challenges of implicit objective, dimension-varying variables, and dynamic parameters. To tackle these issues, we transform the primal problem into a Markov decision process (MDP), using insights of FL algorithm convergence analysis, which enables the application of deep reinforcement learning (DRL) to capture system dynamics effectively. We propose a novel joint Knowledge/Model-Driven DRL (KMD-DRL) solution to address challenges arising from the MDP problem, including mixed discrete-continuous actions and large action space. Numerical results demonstrate the effectiveness and advantages of KMD-DRL in enhancing FEL efficiency.

The optimal implementation of federated learning (FL) in practical edge computing systems has been an outstanding problem. In this paper, we propose an optimization-based quantized FL algorithm, which can appropriately fit a general edge computing system with uniform or nonuniform computing and communication resources at the workers. Specifically, we first present a new random quantization scheme and analyze its properties. Then, we propose a general quantized FL algorithm, namely GQFedWAvg. Specifically, GQFedWAvg applies the proposed quantization scheme to quantize wisely chosen model update-related vectors and adopts a generalized mini-batch stochastic gradient descent (SGD) method with the weighted average local model updates in global model aggregation. Besides, GQFedWAvg has several adjustable algorithm parameters to flexibly adapt to the computing and communication resources at the server and workers. We also analyze the convergence of GQFedWAvg. Next, we optimize the algorithm parameters of GQFedWAvg to minimize the convergence error under the time and energy constraints. We successfully tackle the challenging non-convex problem using general inner approximation (GIA) and multiple delicate tricks. Finally, we interpret GQFedWAvg’s function principle and show its considerable gains over existing FL algorithms using numerical results.

This paper investigates optimal implementations of federated learning (FL) in practical edge computing systems with possibly distinct computing and communication resources at the server and workers. First, we present a new random quantization scheme and analyze its properties. Then, we propose a general quantized FL algorithm, namely HQFedWAvg, and analyze its convergence. HQFedWAvg adopts the proposed quantization scheme and a generalized mini-batch stochastic gradient descent (SGD) method and has several adjustable algorithm parameters to maximally adapt to the computing and communication resources at the server and workers. Next, we optimize the algorithm parameters of HQFedWAvg. The resulting challenging non-convex optimization problem is successfully tackled using several optimization techniques. Numerical results demonstrate HQFedWAvg's considerable performance gains over existing FL algorithms and interpret its function principle.

The optimal design of federated learning (FL) algorithms for solving general machine learning (ML) problems in practical edge computing systems with quantized message passing remains an open problem. This paper considers an edge computing system where the server and workers have possibly different computing and communication capabilities and employ quantization before transmitting messages. To explore the full potential of FL in such an edge computing system, we first present a general FL algorithm, namely GenQSGD, parameterized by the numbers of global and local iterations, mini-batch size, and step size sequence. Then, we analyze its convergence for an arbitrary step size sequence and specify the convergence results under three commonly adopted step size rules, namely the constant, exponential, and diminishing step size rules. Next, we optimize the algorithm parameters to minimize the energy cost under the time constraint and convergence error constraint, with the focus on the overall implementing process of FL. Specifically, for any given step size sequence under each considered step size rule, we optimize the numbers of global and local iterations and mini-batch size to optimally implement FL for applications with preset step size sequences. We also optimize the step size sequence along with these algorithm parameters to explore the full potential of FL. The resulting optimization problems are challenging non-convex problems with non-differentiable constraint functions. We propose iterative algorithms to obtain KKT points using general inner approximation (GIA) and tricks for solving complementary geometric programming (CGP). Finally, we numerically demonstrate the remarkable gains of GenQSGD with optimized algorithm parameters over existing FL algorithms and reveal the significance of optimally designing general FL algorithms.

Optimal algorithm design for federated learning (FL) remains an open problem. This paper explores the full potential of FL in practical edge computing systems where workers may have different computation and communication capabilities, and quantized intermediate model updates are sent between the server and workers. First, we present a general quantized parallel mini-batch stochastic gradient descent (SGD) algorithm for FL, namely GenQSGD, which is parameterized by the number of global iterations, the numbers of local iterations at all workers, and the mini-batch size. We also analyze its convergence error for any choice of the algorithm parameters. Then, we optimize the algorithm parameters to minimize the energy cost under the time constraint and convergence error constraint. The optimization problem is a challenging non-convex problem with non-differentiable constraint functions. We propose an iterative algorithm to obtain a KKT point using advanced optimization techniques. Numerical results demonstrate the significant gains of GenQSGD over existing FL algorithms and reveal the importance of optimally designing FL algorithms.