Deep Reinforcement Learning Based Resource Allocation in Multi-UAV-Aided MEC Networks

Resource allocation for mobile edge computing (MEC) in unmanned aerial vehicle (UAV) networks has been a popular research issue. Different from existing works, this paper considers a multi-UAV-aided uplink communication scenario and investigates a resource allocation problem of minimizing the total system latency and the energy consumption, subject to constraints on transmit power of mobile users (MUs), system latency caused by transmission and computation. The problem is confirmed to be a challenging time-series mixed-integer non-convex programming problem, and we propose a joint UAV Movement control, MU Association and MU Power control (UMAP) algorithm to solve it effectively, where three sub-problems are optimized iteratively. Specifically, UAV movement and MU association are optimized utilizing deep reinforcement learning (DRL) to decrease the energy consumption and system latency. Next, a closed-form solution of the MU transmit power is derived. Finally, simulation results show that the UMAP algorithm can significantly decrease the system latency and energy consumption and increase the coverage rate compared with benchmark algorithms.

I. Introduction

In 5G and upcoming 6G communication networks, computing requirement increases rapidly with the amount of network edge devices rising sharply [1]. In traditional networks, the computing tasks need to be offloaded to the cloud center, which needs fast data processing capacity and high bandwidth for data transmission. However, it is not financially viable for future networks due to the shortage of spectrum resources. Meanwhile, in emerging 5G mobile networks, ultra-reliable and low latency communications (URLLC) is the core category of communication services [2]. Thus, zero-latency experience is an urgent requirement in 5G mobile networks. Mobile edge computing (MEC) [3] that can effectively meet low-latency communication and computing requirements by moving computing resources from clouds and data centers to the edge of the mobile network is a feasible and promising proposal to address the above issues [4]. Recently, there have been many works on traditional MEC to reduce latency or improve energy efficiency [5], [6], [7], [8], [9], [10], [11], [12].