Multi-Agent Reinforcement Learning-Based UAV Path and Resource Allocation for Ground-to-air Communication Network

With the rapid expansion of the Internet of Things (IoT) and the increasing unmanned devices, data transmission and sharing between unmanned agents in the Internet of Unmanned Agents (IUA) face significant challenges. Mobile Edge Computing (MEC), which extends computing power from the cloud to the network edge, has become a key technology for enabling efficient, low-latency communication services. However, with the surge in the number of terminal devices and the diversification of service requirements, traditional MEC deployment methods face challenges such as inflexible resource allocation and limited service coverage. This paper mainly researches an unmanned aerial vehicle(UAV)-assisted ground-to-air communication and computing system, constructs a multi-UAV network communication model and a computing model, and proposes a joint optimization problem of system task processing delay and energy consumption based on the total system delay and the energy consumption of the UAV. For the path planning and resource allocation problems of the multi-UAV network, an improved double-delay deep deterministic policy gradient algorithm is proposed to jointly optimize the trajectory planning, user association and task offloading strategies of the multi-agent UAV. Finally, the performance of the proposed algorithm is verified and analyzed through simulation experiments.