In this article, the problem of vertical handover in software-defined network (SDN) based heterogeneous networks (HetNets) is studied. In the studied model, HetNets are required to offer diverse services for mobile users. Using an SDN controller, HetNets have the capability of managing users' access and mobility issues but still have the problems of ping-pong effect and service interruption during vertical handover. To solve these problems, a mobility-aware seamless handover method based on multipath transmission control protocol (MPTCP) is proposed. The proposed handover method is executed in the controller of the software-defined HetNets (SDHetNets) and consists of three steps: location prediction, network selection, and handover execution. In particular, the method first predicts the user's location in the next moment with an echo state network (ESN). Given the predicted location, the SDHetNet controller can determine the candidate network set for the handover to pre-allocate network wireless resources. Second, the target network is selected through fuzzy analytic hierarchical process (FAHP) algorithm, jointly considering user preferences, service requirements, network attributes, and user mobility patterns. Then, seamless handover is realized through the proposed MPTCP-based handover mechanism. Simulations using real-world user trajectory data from Korea Advanced Institute of Science & Technology show that the proposed method can reduce the handover times by 10.85% to 29.12% compared with traditional methods. The proposed method also maintains at least one MPTCP subflow connected during the handover process and achieves a seamless handover.

This paper studies an efficient multimodal data communication scheme for video conferencing. In our considered system, a speaker gives a talk to the audiences, with talking head video and audio being transmitted. Since the speaker does not frequently change posture and high-fidelity transmission of audio (speech and music) is required, redundant visual video data exists and can be removed by generating the video from the audio. To this end, we propose a wave-to-video (Wav2Vid) system, an efficient video transmission framework that reduces transmitted data by generating talking head video from audio. In particular, full-duration audio and short-duration video data are synchronously transmitted through a wireless channel, with neural networks (NNs) extracting and encoding audio and video semantics. The receiver then combines the decoded audio and video data, as well as uses a generative adversarial network (GAN) based model to generate the lip movement videos of the speaker. Simulation results show that the proposed Wav2Vid system can reduce the amount of transmitted data by up to 83% while maintaining the perceptual quality of the generated conferencing video.

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods.

As a crucial enabler for the wireless upgrade of the industrial Internet of Things (IIoT), the integration of fifth-generation (5G) wireless network and the wired time-sensitive networking (TSN), i.e., 5G-TSN, is expected to support the deterministic transmission of massive data flows in IIoT systems. Therefore, we focus on the design of a joint flow scheduling scheme for the uplink of 5G-TSN. Specifically, in the 5G part, we propose a novel multiple configured grant (MCG) subframe structure to efficiently exploit the available spectrum resources. Meanwhile, in the TSN part, the age of synchronization (AoS) indicator, which measures the freshness of each flow arriving at the transparent bridge connecting 5G and TSN, determines which flow should be injected into the TSN. Then, to support massive device access, we formulate an optimization problem to maximize the number of successfully transmitted flows while satisfying the quality of service requirements. To solve the non-stationary and non-convex problem, we propose a cooperative multi-agent proximal policy optimization (CMA-PPO) based flow scheduling scheme to determine the MCG configuration with cognitive information of flows. The scheme can improve the number of successfully transmitted flows within the deadline constraints. Extensive numerical simulations demonstrate that, compared with benchmarks, the proposed scheme improves the number of successfully transmitted flows by up to 24.02% and about two times compared with the benchmarks in the 5G-TSN network.

Unmanned Aerial Vehicle (UAV) networks have evolved tremendously to provide pervasive intelligence services, handle compute-intensive and latency-sensitive tasks, and free up more network resources. However, time-varying channel gains and dynamic UAV locations hinder better offloading performance and reduce quality of service. Therefore, we propose a UAV-based computation offloading model to maximize the throughput of terrestrial users while reducing the privacy overhead. Based on an on-board battery energy harvesting technologies, we propose a multi-agent proximal policy optimization method to optimize the CPU cycle frequency and offloading decisions that further extend the UAV execution time. Then present a federated learning-based privacy protection framework to generate the optimal block size. In addition, we demonstrate the long-term energy queue constraint through massive mathematical derivations. Finally, extensive simulation results show that the proposed algorithm has better performance gains in terms of throughput and privacy protection overhead compared to some advanced benchmarks.