Deep Reinforcement Learning-Based Task Offloading and Resource Allocation for Mobile Edge Computing

Liang Huang; Xu Feng; Liping Qian; Yuan Wu

Machine Learning and Intelligent Communications. Third International Conference, MLICOM 2018, Hangzhou, China, July 6-8, 2018, Proceedings

Research Article

Deep Reinforcement Learning-Based Task Offloading and Resource Allocation for Mobile Edge Computing

Download

298 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-030-00557-3_4,
    author={Liang Huang and Xu Feng and Liping Qian and Yuan Wu},
    title={Deep Reinforcement Learning-Based Task Offloading and Resource Allocation for Mobile Edge Computing},
    proceedings={Machine Learning and Intelligent Communications. Third International Conference, MLICOM 2018, Hangzhou, China, July 6-8, 2018, Proceedings},
    proceedings_a={MLICOM},
    year={2018},
    month={10},
    keywords={Mobile edge computing Deep reinforcement learning Task offloading Resource allocation Deep Q-learning},
    doi={10.1007/978-3-030-00557-3_4}
}

Liang Huang
Xu Feng
Liping Qian
Yuan Wu
Year: 2018
Deep Reinforcement Learning-Based Task Offloading and Resource Allocation for Mobile Edge Computing
MLICOM
Springer
DOI: 10.1007/978-3-030-00557-3_4

Liang Huang¹^,*, Xu Feng¹^,*, Liping Qian¹^,*, Yuan Wu¹^,*

1: Zhejiang University of Technology

*Contact email: lianghuang@zjut.edu.cn, xfeng_zjut@163.com, lpqian@zjut.edu.cn, iewuy@zjut.edu.cn

Abstract

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.

Keywords: Mobile edge computing Deep reinforcement learning Task offloading Resource allocation Deep Q-learning

Published: 2018-10-12
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-030-00557-3_4