Deep Reinforcement Learning-Based Task Offloading and Resource Allocation for Mobile Edge Computing
We consider a mobile edge computing system that every user has multiple tasks being offloaded to edge server via wireless networks. Our goal is to acquire a satisfactory task offloading and resource allocation decision for each user so as to minimize energy consumption and delay. In this paper, we propose a deep reinforcement learning-based approach to solve joint task offloading and resource allocation problems. Simulation results show that the proposed deep Q-learning-based algorithm can achieve near-optimal performance.
KeywordsMobile edge computing Deep reinforcement learning Task offloading Resource allocation Deep Q-learning
This work was supported in part by the National Natural Science Foundation of China under Grant 61572440 and Grant 61502428, in part by the Zhejiang Provincial Natural Science Foundation of China under Grants LR17F010002 and LR16F010003, in part by the Young Talent Cultivation Project of Zhejiang Association for Science and Technology under Grant 2016YCGC011.
- 6.Meskar, E., Todd, T., Zhao, D., Karakostas, G.: Energy efficient offloading for competing users on a shared communication channel. In: Proceedings of IEEE International Conference on Communications (ICC), pp. 3192–3197 (2015)Google Scholar
- 7.Chen, M.H., Liang, B., Dong, M.: Joint offloading decision and resource allocation for multi-user multi-task mobile cloud. In: 2016 IEEE International Conference on Communications (ICC), Kuala Lumpur, pp. 1–6 (2016)Google Scholar