Wireless federated learning (WFL) suffers from heterogeneity prevailing in the data distributions, computing powers, and channel conditions of participating devices. This paper presents a new Federated Learning with Adjusted leaRning ratE (FLARE) framework to mitigate the impact of the heterogeneity. The key idea is to allow the participating devices to adjust their individual learning rates and local training iterations, adapting to their instantaneous computing powers. The convergence upper bound of FLARE is established rigorously under a general setting with non-convex models in the presence of non-i.i.d. datasets and imbalanced computing powers. By minimizing the upper bound, we further optimize the scheduling of FLARE to exploit the channel heterogeneity. A nested problem structure is revealed to facilitate iteratively allocating the bandwidth with binary search and selecting devices with a new greedy method. A linear problem structure is also identified and a low-complexity linear programming scheduling policy is designed when training models have large Lipschitz constants. Experiments demonstrate that FLARE consistently outperforms the baselines in test accuracy, and converges much faster with the proposed scheduling policy.

Cloud native technology has revolutionized 5G beyond and 6G communication networks, offering unprecedented levels of operational automation, flexibility, and adaptability. However, the vast array of cloud native services and applications presents a new challenge in resource allocation for dynamic cloud computing environments. To tackle this challenge, we investigate a cloud native wireless architecture that employs container-based virtualization to enable flexible service deployment. We then study two representative use cases: network slicing and multi-access edge computing. To improve resource allocation and maximize utilization efficiency in these scenarios, we propose two deep reinforcement learning-based algorithms that enhance resource allocation efficiency and network resource utilization by leveraging comprehensive observational data to guide and refine the allocation policies. We validate the effectiveness of our algorithms in a testbed developed using Free5gc. Our findings demonstrate significant improvements in network efficiency, underscoring the potential of our proposed techniques in unlocking the full potential of cloud native wireless networks.

The Satellite-Terrestrial Integrated Network (STIN) enhances end-to-end transmission by simultaneously utilizing terrestrial and satellite networks, offering significant benefits in scenarios like emergency response and cross-continental communication. Low Earth Orbit (LEO) satellite networks offer reduced Round Trip Time (RTT) for long-distance data transmission and serve as a crucial backup during terrestrial network failures. Meanwhile, terrestrial networks are characterized by ample bandwidth resources and generally more stable link conditions. Therefore, integrating Multipath TCP (MPTCP) into STIN is vital for optimizing resource utilization and ensuring efficient data transfer by exploiting the complementary strengths of both networks. However, the inherent challenges of STIN, such as heterogeneity, instability, and handovers, pose difficulties for traditional multipath schedulers, which are typically designed for terrestrial networks. We propose a novel multipath data scheduling approach for STIN, the Adaptive Latency Compensation Scheduler (ALCS), to address these issues. ALCS refines transmission latency estimates by incorporating RTT, congestion window size, inflight and queuing packets, and satellite trajectory information. It further employs adaptive mechanisms for latency compensation and proactive handover management. Implemented in the MPTCP Linux Kernel and evaluated in a simulated STIN testbed, ALCS outperforms existing multipath schedulers, delivering faster data transmission and achieving throughput gains of 9.8% to 44.0% compared to benchmark algorithms.

Performance Enhancement Proxies (PEPs) are widely used to improve TCP performance in geostationary orbit (GEO) satellite networks, which experience long RTT (approximately 500 ms). As a split TCP-based solution, PEP divides the end-to-end connection into multiple sub-connections, each independently managing its own rate control, including both congestion and flow control. This independence naturally leads to rate imbalances, manifested as an abnormal on-off traffic pattern-a phenomenon confirmed by our experimental observations in real-world GEO satellite networks. Furthermore, we demonstrate that this on-off traffic pattern not only undermines fairness but also reduces throughput, particularly for small-sized flows. To address this problem, we propose PEP-Policer, an automatic rate limiter for PEP to limit the link with higher rate to the lower one. Unlike traditional rate limiting methods that require manual configuration of the target rate, PEP-Policer employs a finite state machine to automatically determine and enforce the appropriate target rate. Moreover, as an add-on, PEP-Policer is compatible with all PEP-based solutions and can be integrated without modifying existing systems. Extensive evaluations in an emulated GEO satellite network show that PEP-Policer improves TCP's fairness and increases goodput by up to 63.0% for Cubic, 49.6% for BBR, and 88.6% for Hybla.

Low Earth Orbit (LEO) satellites play a crucial role in the development of 6G mobile networks and space-air-ground integrated systems. Recent advancements in space technology have empowered LEO satellites with the capability to run Artificial Intelligence(AI) applications. However, centralized approaches, where ground stations (GSs) act as servers and satellites as clients, often encounter slow convergence and inefficiencies due to intermittent connectivity between satellites and GSs. In contrast, decentralized federated learning (DFL) offers a promising alternative by facilitating direct communication between satellites (clients) via inter-satellite links (ISLs). Nevertheless, inter-plane ISLs connecting satellites from different orbital planes remain dynamic due to Doppler shifts and pointing limitations. This could impact model propagation and lead to slower convergence. To mitigate these issues, we propose DFedSat, a fully decentralized federated learning framework tailored for LEO satellites. DFedSat accelerates the training process by employing two adaptive mechanisms for intra-plane and inter-plane model aggregation, respectively. Furthermore, a self-compensation mechanism is integrated to enhance the robustness of inter-plane ISLs against transmission failure. Additionally, we derive the sublinear convergence rate for the non-convex case of DFedSat. Extensive experimental results demonstrate DFedSat’s superiority over other DFL baselines regarding convergence rate, communication efficiency, and resilience to unreliable links.

Synchronous local stochastic gradient descent (local SGD) suffers from some workers being idle and random delays due to slow and straggling workers, as it waits for the workers to complete the same amount of local updates. To address this issue, a novel local SGD strategy called STSyn is proposed in this paper. The key point is to wait for the K fastest workers while keeping all the workers computing continually at each synchronization round, and making full use of any effective (completed) local update of each worker regardless of stragglers. To evaluate the performance of STSyn, an analysis of the average wall-clock time, average number of local updates, and average number of uploading workers per round is provided. The convergence of STSyn is also rigorously established even when the objective function is nonconvex for both homogeneous and heterogeneous data distributions. Experimental results highlight the superiority of STSyn over state-of-the-art schemes, thanks to its straggler-tolerant technique and the inclusion of additional effective local updates at each worker. Furthermore, the impact of system parameters is investigated. By waiting for faster workers and allowing heterogeneous synchronization with different numbers of local updates across workers, STSyn provides substantial improvements both in time and communication efficiency.

In the rapidly evolving landscape of distributed learning strategies, Federated Learning (FL) stands out for its features such as model training on resource-constrained edge devices and high data security. However, the growing complexity of neural network models produces two challenges such as communication bottleneck and resource under-utilization, especially in edge networks. To overcome these challenges, this paper introduces a novel framework by realizing the Parallel Communication-Computation Federated Learning Mode (P2CFed). Specifically, we design an adaptive layer-wise model segmentation strategy according to the wireless environments and computing capability of edge devices, which enables parallel training and transmission within different sub-models. In this way, parameter delivery takes place throughout the training process, thus considerably alleviating the communication overhead. Meanwhile, we also propose a joint optimization scheme with regard to the subchannel allocation, power control, and segmentation layer selection, which is then transformed into an iteration search process for obtaining optimal results. We have conducted extensive simulations to validate the effectiveness of P2CFed when compared with state-of-the-art benchmarks in terms of communication overhead and resource utilization. It also unveils that P2CFed brings a faster convergence rate and smaller training delay compared to traditional FL approaches.

A major bottleneck of distributed learning under parameter server (PS) framework is communication cost due to frequent bidirectional transmissions between the PS and workers. To address this issue, local stochastic gradient descent (SGD) and worker selection have been exploited by reducing the communication frequency and the number of participating workers at each round, respectively. However, partial participation can be detrimental to convergence rate, especially for heterogeneous local datasets. In this paper, to improve communication efficiency and speed up the training process, we develop a novel worker selection strategy named AgeSel. The key enabler of AgeSel is utilization of the ages of workers to balance their participation frequencies. The convergence of local SGD with the proposed age-based partial worker participation is rigorously established. Simulation results demonstrate that the proposed AgeSel strategy can significantly reduce the number of training rounds needed to achieve a targeted accuracy, as well as the communication cost. The influence of the algorithm hyper-parameter is also explored to manifest the benefit of age-based worker selection.

面向海洋感知网络对微弱信号高能效多址通信的重大需求，提出了光量子计数非正交多址通信理论及最大化光子信息效率的资源优化分配方法，实现了可达和速率紧密渐进闭式表达及功率优化分配方法，显著提升了系统光子信息效率，为海洋工程提供了技术支撑

面对浅海大背景光干扰，设计了波分多址可行域划分最优功率分配方法，明显提高了光量子计数正交多址系统容量

The increasing demand for computational resources poses substantial challenges for task offloading in terahertz (THz)-enabled Space–Terrestrial Integrated Networks (STINs), particularly in multi-user to multi-satellite scenarios. Achieving efficient task allocation and offloading is crucial for optimizing overall system performance, reducing latency, and improving overall network throughput. However, traditional centralized approaches suffer from excessive communication overhead and heightened privacy risks in STINs. To overcome these limitations, this paper proposes a novel framework based on Federated Learning-Assisted Multi-Agent Deep Deterministic Policy Gradient (FL-MADDPG). The THz-connected user–satellite network is modeled as a multi-agent system, enabling distributed decisionmaking while avoiding raw data sharing. Within this framework, federated learning preserves user privacy, and multi-agent reinforcement learning allows the system to dynamically adapt to complex THz channel variations and fluctuating resource availability. Experimental results demonstrate the effectiveness of FL-MADDPG in improving the overall performance of the network.

In recent years, the rapid development of Low Earth Orbit (LEO) satellite networks has highlighted the need for enhanced data processing capabilities. However, the limited computational capacity and inherent heterogeneity of LEO satellites pose significant challenges for efficient task computation, such as minimizing latency and energy consumption. To address these challenges, we propose QMIX-sat, a novel multi-agent reinforcement learning algorithm. We transform the optimization problem into a decentralized partially observable Markov decision process (Dec-POMDP) and solve it using an enhanced version of the QMIX algorithm. In the satellite scenario under study, we introduce attention modules and residual connections to generate accurate task segmentation and allocation decisions, effectively mitigating the issues caused by high-dimensional observation spaces, such as inter-satellite and satellite-ground link states. Additionally, given that QMIX is commonly used in discrete action spaces, this work extends QMIX to continuous action spaces, ensuring precise task segmentation and allocation. We construct a LEO satellite network model for experimental verification, and the results demonstrate that QMIX-sat significantly improves task allocation efficiency and overall performance within LEO satellite networks compared to existing algorithms.

Wireless federated learning (WFL) suffers from heterogeneity prevailing in data distributions, computing powers, and channel conditions of participating devices. This paper presents a new Federated Learning with Adjusted leaRning ratE (FLARE) framework to mitigate the impact of the heterogeneity. The key idea is to allow the participating devices to adjust their individual learning rates and local training iterations, adapting to their instantaneous computing powers. The convergence upper bound of FLARE is established rigorously under a generic setting with non-convex models, non-i.i.d. datasets and imbalanced computing powers. By minimizing the upper bound, we further optimize the scheduling strategy of FLARE to exploit the channel heterogeneity. A nested problem structure is uncovered to facilitate iterative bandwidth allocation with binary search and device selection with a new greedy method. Experiments demonstrate that FLARE consistently outperforms the baselines in test accuracy, and converges much faster with the proposed scheduling policy.

Satellite federated learning (SFL) allows satellites to collaboratively train models without sharing raw data, enhancing privacy and reducing communication costs. Traditional SFL requires a ground station (GS) to upload models to satellites, under the premise of adequate ground-satellite uplink (GSUL) resources. However, this assumption does not hold in dense LEO constellations, where frequent command interaction or parameter delivery make the bandwidth-constrained uplink a bottleneck. This work proposes satellite federated learning with uplink scheduling and model pruning (FedLSMP). The key idea behind this is jointly optimizing the GSUL bandwidth allocation plan and model compression ratio to maximize the approximated loss reduction, adhering to bandwidth constraints. Finally, numerical results demonstrate that FedLSMP improves convergence rates while reducing GSUL bandwidth usage, achieving higher overall effectiveness compared with conventional SFL approaches.

LEO satellite networks are essential for providing global communication coverage, especially in areas where traditional terrestrial networks are unavailable. However, LEO satellite networks face several challenges compared to terrestrial networks, including rapid bandwidth fluctuation, long Round-Trip Time (RTT), and high Bit Error Rate (BER), which can significantly impact communication quality and reliability. To address these issues and optimize network performance, we propose the OnlineAEPC algorithm. This algorithm adaptively adjusts the congestion window size based on real-time environmental conditions, thereby reducing transmission time and packet loss. Extensive simulations validate the performance of our algorithm under various challenging conditions characterized by rapid bandwidth fluctuation, long RTT, and high BER. Our comparisons with baseline algorithms demonstrate that OnlineAEPC offers significant improvements in transmission time and packet loss reduction.

The construction of Low Earth Orbit (LEO) satellite constellations has recently spurred tremendous attention from academia and industry. 5G and 6G standards have specified LEO satellite network as a key component of 5G and 6G networks. However, ground terminals experience frequent, high-latency handover incurred by satellites’ fast travelling speed, which deteriorates the performance of latency-sensitive applications. To address this challenge, we propose a novel handover flowchart for mobile satellite networks, which can considerably reduce the handover latency. The innovation behind this scheme is to mitigate the interaction between the access and core networks that occupy the majority of time overhead by leveraging the predictable travelling trajectory and spatial distribution inherent in mobile satellite networks. Specifically, we design a fine-grained synchronized algorithm to address the synchronization problem due to the lack of control signalling delivery between the access and core networks. Moreover, we minimize the computational complexity of the core network using information such as the satellite access strategy and unique spatial distribution, which is caused by frequent prediction operations. We have built a prototype for a mobile satellite network using modified Open5GS and UERANSIM, which is driven by actual LEO satellite constellations such as Starlink and Kuiper. We have conducted extensive experiments, and the results demonstrate that our proposed handover scheme can considerably reduce the handover latency compared to the 3GPP Non-terrestrial Networks (NTN) and two other existing handover schemes.

The widespread adoption of edge computing has emerged as a prominent trend for alleviating task processing delays and reducing energy consumption. However, the dynamic nature of network conditions and the varying computation capacities of edge servers (ESs) can introduce disparities between computation loads and available computing resources in edge computing networks, potentially leading to inadequate service quality. To address this challenge, this paper investigates a practical scenario characterized by dynamic task offloading. Initially, we examine traditional multi-armed bandit (MAB) algorithms, namely the ε-greedy algorithm and the UCB1-based algorithm. However, both algorithms exhibit certain weaknesses in effectively addressing the tidal data traffic patterns. Consequently, based on MAB, we propose an adaptive task offloading algorithm (ATOA) that overcomes these limitations. By conducting extensive simulations, we demonstrate the superiority of our ATOA solution in reducing task processing latency compared to conventional MAB methods. This substantiates the effectiveness of our approach in enhancing the performance of edge computing networks and improving overall service quality.

Machine learning is increasingly used in edge devices with limited computational resources for tasks such as face recognition, object detection, and voice recognition. Federated Learning (FL) is a promising approach to train models on multiple edge devices without requiring clients to upload their original data to the server. However, challenges such as redundant local parameters during synchronous aggregation and system heterogeneity can significantly impact training performance. To address these challenges, we propose LayerFED, a novel strategy that leverages model splitting and pipelined communication-computation mode. LayerFED enables partial and full updates by splitting the model, and mitigates communication channel congestion during server aggregation by selectively updating parameters during computation. This reduces the amount of information that needs to be communicated between edge devices and the server. We demonstrate through experiments on benchmark datasets that LayerFED improves training time efficiency and accuracy while maintaining model performance.

Recent advancements in space technology have equipped low Earth Orbit (LEO) satellites with the capability to perform complex functions and run AI applications. Federated Learning (FL) on LEO satellites enables collaborative training of a global ML model without the need for sharing large datasets. However, intermittent connectivity between satellites and ground stations can lead to stale gradients and unstable learning, thereby limiting learning performance. In this paper, we propose FedGSM, a novel asynchronous FL algorithm that introduces a compensation mechanism to mitigate gradient staleness. FedGSM leverages the deterministic and time-varying topology of the orbits to offset the negative effects of staleness. Our simulation results demonstrate that FedGSM outperforms state-of-the-art algorithms for both IID and non-IID datasets, underscoring its effectiveness and advantages. We also investigate the effect of system parameters.

Cell-Free (CF) massive multiple-input multiple-output (MIMO) technology is poised to revolutionize future wireless networks by significantly improving network capacity. However, the conventional centralized implementation of CF networks brings about computational complexities in the central processing unit (CPU) and imposes a heavy burden on fronthaul links due to extensive channel state information (CSI) exchange. In this paper, we propose a distributed computing architecture that employs the preconditioned conjugate gradient algorithm to achieve the performance level of centralized minimum mean square error (MMSE) combining. The proposed algorithm offers two key advantages: firstly, it offloads a significant portion of computations from the CPU to distributed access points, thereby alleviating the computational burden; secondly, it significantly reduces the transmission of instantaneous and historical data through fronthaul links. These benefits contribute to the overall efficiency and scalability of CF massive MIMO systems, as demonstrated in the simulation results.

In traditional designs of applying network coding in wireless two-way relay channels, network coding operates at upper layers above (including) the link layer and it requires the input packets to be correctly decoded at the physical layer. Different from that, this chapter investigates a physical layer wireless network coding scheme, which is referred to as soft network coding (SoftNC), where the relay nodes apply symbol-by-symbol soft decisions on the received signals from the two end nodes to come up with the network-coded information to be forwarded. We do not assume further channel coding on top of SoftNC at the relay node (channel coding is assumed at the end nodes). According to measures of the soft information adopted, two kinds of SoftNC are proposed: amplify-and-forward SoftNC (AFSoftNC) and soft-bit-forward SoftNC (SBF-SoftNC).