Welcome to the InfoSci Platform
Reference Hub2
Deep Reinforcement Learning for Task Offloading and Power Allocation in UAV-Assisted MEC System

Deep Reinforcement Learning for Task Offloading and Power Allocation in UAV-Assisted MEC System

Nan Zhao, Fan Ren, Wei Du, Zhiyang Ye
Copyright: © 2021 |Volume: 12 |Issue: 4 |Pages: 20
ISSN: 1937-9412|EISSN: 1937-9404|EISBN13: 9781799860112|DOI: 10.4018/IJMCMC.289163
Cite Article Cite Article

MLA

Zhao, Nan, et al. "Deep Reinforcement Learning for Task Offloading and Power Allocation in UAV-Assisted MEC System." IJMCMC vol.12, no.4 2021: pp.32-51. http://doi.org/10.4018/IJMCMC.289163

APA

Zhao, N., Ren, F., Du, W., & Ye, Z. (2021). Deep Reinforcement Learning for Task Offloading and Power Allocation in UAV-Assisted MEC System. International Journal of Mobile Computing and Multimedia Communications (IJMCMC), 12(4), 32-51. http://doi.org/10.4018/IJMCMC.289163

Chicago

Zhao, Nan, et al. "Deep Reinforcement Learning for Task Offloading and Power Allocation in UAV-Assisted MEC System," International Journal of Mobile Computing and Multimedia Communications (IJMCMC) 12, no.4: 32-51. http://doi.org/10.4018/IJMCMC.289163

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Mobile edge computing (MEC) can provide computing services for mobile users (MUs) by offloading computing tasks to edge clouds through wireless access networks. Unmanned aerial vehicles (UAVs) are deployed as supplementary edge clouds to provide effective MEC services for MUs with poor wireless communication condition. In this paper, a joint task offloading and power allocation (TOPA) optimization problem is investigated in UAV-assisted MEC system. Since the joint TOPA problem has a strong non-convex characteristic, a method based on deep reinforcement learning is proposed. Specifically, the joint TOPA problem is modeled as Markov decision process. Then, considering the large state space and continuous action space, a twin delayed deep deterministic policy gradient algorithm is proposed. Simulation results show that the proposed scheme has lower smoothing training cost than other optimization methods.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.