An Optimal-Transport-Based Reinforcement Learning Approach for Computation Offloading

被引:2
作者
Li, Zhuo [1 ,2 ]
Zhou, Xu [1 ]
Li, Taixin [1 ]
Liu, Yang [3 ]
机构
[1] Chinese Acad Sci, Comp Network Informat Ctr, Beijing 100190, Peoples R China
[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[3] Beijing Normal Univ, Sch Math Sci, Beijing 100875, Peoples R China
来源
2021 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC) | 2021年
基金
中国国家自然科学基金; 国家重点研发计划;
关键词
computation offloading; reinforcement learning; optimal transport; cloud computing; edge computing;
D O I
10.1109/WCNC49053.2021.9417331
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
With the mass deployment of computing-intensive applications and delay-sensitive applications on end devices, only adequate computing resources can meet differentiated services' delay requirements. By offloading tasks to cloud servers or edge servers, computation offloading can alleviate computing and storage limitations and reduce delay and energy consumption. However, few of the existing offloading schemes take into consideration the cloud-edge collaboration and the constraint of energy consumption and task dependency. This paper builds a collaborative computation offloading model in cloud and edge computing and formulates a multi-objective optimization problem. Constructed by fusing optimal transport and Policy-Based RL, we propose an Optimal-Transport-Based RL approach to resolve the offloading problem and make the optimal offloading decision for minimizing the overall cost of delay and energy consumption. Simulation results show that the proposed approach can effectively reduce the cost and significantly outperforms existing optimization solutions.
引用
收藏
页数:6
相关论文
共 19 条
[1]  
Chen LQ, 2020, AAAI CONF ARTIF INTE, V34, P7512
[2]   Optimized Computation Offloading Performance in Virtual Edge Computing Systems via Deep Reinforcement Learning [J].
Chen, Xianfu ;
Zhang, Honggang ;
Wu, Celimuge ;
Mao, Shiwen ;
Ji, Yusheng ;
Bennis, Mehdi .
IEEE INTERNET OF THINGS JOURNAL, 2019, 6 (03) :4005-4018
[3]   Efficient Multi-User Computation Offloading for Mobile-Edge Cloud Computing [J].
Chen, Xu ;
Jiao, Lei ;
Li, Wenzhong ;
Fu, Xiaoming .
IEEE-ACM TRANSACTIONS ON NETWORKING, 2016, 24 (05) :2827-2840
[4]   A Primal-Dual Splitting Method for Convex Optimization Involving Lipschitzian, Proximable and Linear Composite Terms [J].
Condat, Laurent .
JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 2013, 158 (02) :460-479
[5]  
Cuturi M., 2013, ADV NEURAL INF PROCE, V26
[6]  
Guestrin Carlos., 2002, Proceedings of the International Conference on Machine Learning, P235
[7]  
Li J, 2018, IEEE WCNC, DOI 10.1109/WCNC.2018.8377343
[8]   Distributed Edge Computing Offloading Algorithm Based on Deep Reinforcement Learning [J].
Li, Yunzhao ;
Qi, Feng ;
Wang, Zhili ;
Yu, Xiuming ;
Shao, Sujie .
IEEE ACCESS, 2020, 8 :85204-85215
[9]   Task Scheduling with Dynamic Voltage and Frequency Scaling for Energy Minimization in the Mobile Cloud Computing Environment [J].
Lin, Xue ;
Wang, Yanzhi ;
Xie, Qing ;
Pedram, Massoud .
IEEE TRANSACTIONS ON SERVICES COMPUTING, 2015, 8 (02) :175-186
[10]   Mobile Edge Computing: A Survey on Architecture and Computation Offloading [J].
Mach, Pavel ;
Becvar, Zdenek .
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS, 2017, 19 (03) :1628-1656