Distributed Trajectory Planning and Resource Allocation for Dynamic Multi-UAV Collaborative Computing
A hierarchical joint optimization algorithm is developed within a multi-agent deep reinforcement learning (MADRL) framework to coordinate UAVs and MTs in a distributed manner and outperforms other benchmarks under varying network scales and capabilities by jointly optimizing UAV operations and resource utilization.
Tian-Kui Zhang, Wenlong Xu, Tian-Yi Shi et al.
· IEEE Internet of Things Jour... · 0 citations