Jing-Sheng Tan

Wireless federated learning (FL) is an emerging artificial intelligence (AI) technique capable of leveraging the data and computing capacity of networked wireless devices while ensuring their individual data privacy and security. However, in geographical areas with poor wireless signal coverage, implementing FL is challenging. Additionally, intensive computation and communication put significant strain on resource-limited wireless devices. To address these issues, firstly, we propose a user equipment (UE)-to-network relay aided FL (UNR-FL) architecture that facilitates a low-cost and flexible implementation of wireless FL, without densifying network equipment deployment. Secondly, we propose an adaptive network control scheme that jointly optimizes device scheduling, network topology construction, and multi-type resource allocation to achieve low latency and low energy consumption. The second contribution is threefold. 1) For solving the device scheduling problem, we propose a voting-based strategy to identify the most suitable wireless UEs as relays. 2) Regarding the network topology optimization problem, we derive the optimal solutions under certain conditions, and propose a tabu search based meta-heuristic algorithm to find feasible solutions under the other conditions. 3) For solving the multi-type resource allocation problem, we analyze its mathematical structure and propose an iterative algorithm that has significantly lower computational complexity than the traditional method. This algorithm is capable of jointly optimizing the usage of transmission time resource, computing capacity, and transmit power. Extensive experimental results demonstrate that the proposed UNR-FL architecture and the adaptive network control scheme are capable of substantially reducing the learning latency and the total energy consumption.

The distributed and collaborative beamforming (DCBF) technology has emerged as a promising enabler, which bears the potential for substantially improving both energy efficiency and communication range of low-power wireless networks, such as wireless sensor networks, millimeter-wave/terahertz communication networks, machine-to-machine communication networks, and UAV communication networks. However, since the distributed transmitters are naturally asynchronous, and both the transmitters and receivers are movable, achieving phase synchronization at the target receiver remains a critical challenge for practical implementations of DCBF. As a remedy, in this paper we propose a high-performance robust bi-directional phase synchronization algorithm for DCBF. Different from the previous works that primarily focus on optimizing adaptive phase perturbation sizes, the proposed algorithm further introduces a novel adaptive mechanism to leverage the directional information of the phase perturbation to jointly accelerate the convergence speed and improve the synchronization accuracy. Extensive simulation results are provided to validate the superior performance of the proposed phase synchronization scheme over existing state-of-the-art schemes.

Federated learning (FL) over wireless networks has become a key enabler for privacy-preserving distributed artificial intelligence (AI). However, high learning latency remains a critical bottleneck due to the presence of stragglers, limited wireless resources, and frequent model uploads. While model quantization can mitigate this issue by reducing communication overhead, its effectiveness is sensitive to device heterogeneity and time-varying channel conditions. To address this issue, we propose FedDamQu, a communication-efficient FL framework with doubly adaptive model quantization, which dynamically adjusts quantization bit widths across devices and communication rounds to balance latency and accuracy. Our objective is to maximize the model performance under learning latency constraints. The main contributions are summarized as follows: 1) convergence analysis under unreliable channels: we derive a novel convergence error upper bound for FedDamQu, which explicitly quantifies the impact of device selection, unreliable transmission, and quantization error on the global model performance, under both fixed and dynamic quantization gain (QG) settings; 2) joint optimization framework: Based on the knowledge from the proposed theoretical bound, we formulate a joint mixed-integer nonlinear programming (MINLP) problem that integrates device selection, quantization bit-width configuration, and bandwidth allocation to minimize the convergence error under latency constraints; and 3) efficient solution design: the MINLP problem is decomposed into three subproblems, where closed-form solutions for quantization bit-width configuration and bandwidth allocation subproblems are derived, and a lightweight yet effective iterative algorithm is developed to obtain a suboptimal solution for the device selection subproblem. The extensive experiment results validate the theoretical analysis and demonstrate that FedDamQu consistently outperforms existing methods in terms of convergence rate and model accuracy, while significantly reducing the overall learning latency.

Wi-Fi sensing has emerged as a promising paradigm for indoor intrusion detection, as it offers a robust and high-accuracy solution without the need for extra hardware deployment. However, existing schemes often compromise the inherent structure of channel state information (CSI) during feature extraction through lossy preprocessing, causing high false alarm rates and poor generalization. As a remedy, we propose a novel tensor-based framework for indoor intrusion detection, which enables reliable perception of fine-grained human activities through structured feature extraction, even in motion-ambiguous scenarios. Our approach integrates tensor-based feature extraction, multi-dimensional feature consolidation, and a modified deep learning (DL) network for accurate intrusion recognition. To validate our framework, we collected a comprehensive through-wall CSI dataset under the IEEE 802.11n standard, encompassing five common human activities in realistic scenarios. Extensive experimental results demonstrate the superior performance of our method compared to existing state-of-the-art schemes.

Flexible duplex (FD) techniques, including dynamic time-division duplex and dynamic frequency division duplex, are widely recognized as pivotal solutions to meeting the asymmetric and dynamic traffic demands in cellular systems. However, the coexistence of opposite transmission directions at the same time between neighboring cells inevitably results in cross-link interference (CLI), leading to significant degradation in network throughput. To tackle this issue, we exploit the trade-off between interference cancellation and spatial multiplexing capabilities in FD systems, and develop a hybrid channel state information (CSI) based hierarchical beamforming algorithm to mitigate the CLI. Compared with the existing state-of-the-art schemes, the proposed algorithm can substantially suppress the CLI with a much lower overhead of CSI acquisition between base stations. Simulation results demonstrate the superior performance of our proposed algorithm.

Wireless sensor network (WSN) underpinning the smart-grid Internet of Things (SG-IoT) has been a popular research topic in recent years due to its great potential for enabling a wide range of important applications. However, the energy consumption (EC) characteristic of sensor nodes is a key factor that affects the operational performance (e.g., lifetime of sensors) and the total cost of ownership of WSNs. In this paper, to find the modulation techniques suitable for WSNs, we investigate the EC characteristic of continuous phase modulation (CPM), which is an attractive modulation scheme candidate for WSNs because of its constant envelope property. We first develop an EC model for the sensor nodes of WSNs by considering the circuits and a typical communication protocol that relies on automatic repeat request (ARQ)-based retransmissions to ensure successful data delivery. Then, we use this model to analyze the EC characteristic of CPM under various configurations of modulation parameters. Furthermore, we compare the EC characteristic of CPM with that of other representative modulation schemes, such as offset quadrature phase-shift keying (OQPSK) and quadrature amplitude modulation (QAM), which are commonly used in communication protocols of WSNs. Our analysis and simulation results provide insights into the EC characteristics of multiple modulation schemes in the context of WSNs; thus, they are beneficial for designing energy-efficient SG-IoT in the beyond-5G (B5G) and the 6G era.

Containers are used by an increasing number of Internet service providers to deploy their applications in multi-access edge computing (MEC) systems. Although container-based virtualization technologies significantly increase application availability, they may suffer expensive communication overhead and resource use imbalances. However, so far there has been a scarcity of studies to conquer these difficulties. In this paper, we design a workflow-based mathematical model for applications built upon interdependent multitasking composition, formulate a multi-objective combinatorial optimization problem composed of two subproblems—graph partitioning and multi-choice vector bin packing, and propose several joint task-containerization-and -container-placement methods to reduce communication overhead and balance multi-type computing resource utilization. The performance superiority of the proposed algorithms is demonstrated by comparison with the state-of-the-art task and container scheduling schemes.

The flexible duplex (FD) technique, including dynamic time-division duplex (D-TDD) and dynamic frequency-division duplex (D-FDD), is regarded as a promising solution to achieving a more flexible uplink/downlink transmission in 5G-Advanced or 6G mobile communication systems. However, it may introduce serious cross-link interference (CLI). For better mitigating the impact of CLI, we first present a more realistic base station (BS)-to-BS channel model incorporating the radio frequency (RF) chain characteristics, which exhibit a hardware-dependent nonlinear property, and hence the accuracy of conventional channel modelling is inadequate for CLI cancellation. Then, we propose a channel parameter estimation based polynomial CLI canceller and two machine learning (ML) based CLI cancellers that use the lightweight feedforward neural network (FNN). Our simulation results and analysis show that the ML based CLI cancellers achieve notable performance improvement and dramatic reduction of computational complexity, in comparison with the polynomial CLI canceller.