Joint Server Allocation and Path Selection in Wireless Multihop Networks With Edge Computing

With the rapid evolution towards Beyond 5G and future 6G networks, multi-access edge computing (MEC)-enabled wireless networks are expected to support massive device connectivity, ultra-low latency, and high network capacity. However, meeting these stringent requirements in multi-server wireless multihop networks essentially requires the joint orchestration of server selection, multihop routing, and interference management. This paper develops a novel three-stage optimization scheme named broad learning system with Q-learning (BLSQ), consisting of a broad learning system-based server allocation stage, a signal-to-interference-plus-noise ratio-driven Q-learning-based multihop path selection stage, and a consensus transmit power control stage for adaptive interference mitigation. Furthermore, a consensus transmit power control mechanism is incorporated to adaptively adjust the transmit power of user devices, aiming to balance interference mitigation and throughput enhancement. The proposed scheme is particularly suitable for various mission-critical and dynamic scenarios, such as emergency communication in disaster-stricken areas, multihop data exchange between rescue teams and command centers, and flexible network deployment in large-scale events using unmanned aerial vehicles. Extensive simulation results demonstrate that the proposed BLSQ schemes outperforms existing related approaches in terms of network capacity, task completion time, interference management, and quality of servers, validating the superiority and robustness of our design for future MEC-enabled wireless networks.