Computation offloading optimization for UAV-assisted mobile edge computing: a deep deterministic policy gradient approach

• Published in: Wireless networks Vol. 27; no. 4; pp. 2991 - 3006
• Main Authors: Wang, Yunpeng, Fang, Weiwei, Ding, Yi, Xiong, Naixue
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.05.2021; Springer Nature B.V
• Subjects: Airspeed; Algorithms; Communications Engineering; Computation offloading; Computer Communication Networks; Convexity; Edge computing; Electrical Engineering; Energy consumption; Engineering; IT in Business; Machine learning; Mobile computing; Networks; Optimization; Original Paper; Task scheduling; Unmanned aerial vehicles; Wireless networks; Deep deterministic policy gradient; Unmanned aerial vehicle; Computation offloading; Mobile edge computing
• ISSN: 1022-0038; 1572-8196
• DOI: 10.1007/s11276-021-02632-z

Unmanned Aerial Vehicle (UAV) can play an important role in wireless systems as it can be deployed flexibly to help improve coverage and quality of communication. In this paper, we consider a UAV-assisted Mobile Edge Computing (MEC) system, in which a UAV equipped with computing resources can provide offloading services to nearby user equipments (UEs). The UE offloads a portion of the computing tasks to the UAV, while the remaining tasks are locally executed at this UE. Subject to constraints on discrete variables and energy consumption, we aim to minimize the maximum processing delay by jointly optimizing user scheduling, task offloading ratio, UAV flight angle and flight speed. Considering the non-convexity of this problem, the high-dimensional state space and the continuous action space, we propose a computation offloading algorithm based on Deep Deterministic Policy Gradient (DDPG) in Reinforcement Learning (RL). With this algorithm, we can obtain the optimal computation offloading policy in an uncontrollable dynamic environment. Extensive experiments have been conducted, and the results show that the proposed DDPG-based algorithm can quickly converge to the optimum. Meanwhile, our algorithm can achieve a significant improvement in processing delay as compared with baseline algorithms, e.g., Deep Q Network (DQN).