Deep Reinforcement Learning-Based Resource Management for UAV-Assisted Mobile Edge Computing Against Jamming

In mobile edge computing (MEC) systems, multiple unmanned aerial vehicles (UAVs) can be utilized as aerial servers to provide computing, communication, and storage services for edge users, called UAV-assisted MEC, which has emerged as a promising technology to improve both the computing and communication performances. Unlike existing works without considering jamming attacks, we investigate a multi-UAV-assisted-MEC scenario under multiple malicious jammers and then propose a resource management approach with the objective of minimizing both the system energy consumption and latency. Due to the time-varying nature of communication environments, we design a multi-agent deep reinforcement learning (MADRL)-based resource management approach to dynamically adjust the CPU frequency, communication bandwidth, and channel access selection of UAVs to enhance the system performance against jamming attacks. On this basis, in order to enhance the algorithm learning efficiency, we propose a multi-agent twin-delayed deep deterministic policy algorithm in combination with the prioritized experience replay mechanism (PER-MATD3) to effectively search for the joint resource management strategy under high-dimensional state and action spaces, where the time-varying channel state information and imperfect attack behavior information are also effectively trained to improve the learning capacity and convergence speed. Simulation and experimental results verify that the proposed approach can significantly decrease the overall system latency (i.e., computing and communication latency) and energy consumption compared to other benchmark algorithms under different real-world settings.

I. Introduction

Unmanned aerial vehicles (UAVs) have gained increasing attention as they offer a variety of advantages over traditional ground-based systems [2]. UAVs are small, low-cost, and can be easily deployed in various communication environments, making them an attractive solution for numerous applications, such as search and rescue [3], data collection [4], and surveillance [5]. For example, UAVs can be used for data collection in wireless sensor networks (WSNs) by flying over the sensor nodes and collecting data from them [6]. UAVs can also serve as mobile relays for wireless communication systems, enhancing network coverage and capacity in areas with poor connectivity [7]. Furthermore, UAVs can be employed for extending the battery life of mobile devices by acting as mobile charging stations [8], while enabling devices to offload some of their tasks to the UAVs and to access more computing resources [9]. Overall, the application of UAVs has revolutionized many fields and has the potential to contribute to many more in the future.