Cooperative Task Offloading for Mobile Edge Computing Based on Multi-Agent Deep Reinforcement Learning

被引:29
作者
Yang, Jian [1 ]
Yuan, Qifeng [1 ]
Chen, Shuangwu [1 ,2 ]
He, Huasen [1 ]
Jiang, Xiaofeng [1 ]
Tan, Xiaobin [1 ]
机构
[1] Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230026, Peoples R China
[2] Hefei Comprehens Natl Sci Ctr, Inst Artificial Intelligence, Hefei 230027, Anhui, Peoples R China
来源
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT | 2023年 / 20卷 / 03期
基金
中国国家自然科学基金; 国家重点研发计划;
关键词
Mobile edge computing; multi-agent system; task offloading; cooperative edge computing; deep reinforcement learning; RESOURCE-ALLOCATION;
D O I
10.1109/TNSM.2023.3240415
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Driven by the prevalence of the computation-intensive and delay-intensive mobile applications, Mobile Edge Computing (MEC) is emerging as a promising solution. Traditional task offloading methods usually rely on centralized decision making, which inevitably involves a high computational complexity and a large state space. However, the MEC is a typical distributed system, where the edge servers are geographically separated, and independently perform the computing tasks. This fact inspires us to conceive a distributed cooperative task offloading system, where each edge server makes its own decision on how to allocate local computing resources and how to migrate tasks among the edge servers. To characterize diverse task requirements, we divide the arrival tasks into different priorities according to the tolerance time, which enables to dynamically schedule the local computing resources for reducing the task timeout. In order to coordinate the independent decision makings of geographically separate edge servers, we propose a priority driven cooperative task offloading algorithm based on multi-agent deep reinforcement learning, where the decision making of each edge server not only depends on its own state but also on the shared global information. We further develop a Variational Recurrent Neural Network (VRNN) based global state sharing model which significantly reduces the communication overhead among edge servers. The performance evaluation conducted on a movement trajectories dataset of mobile devices verifies that the proposed algorithm can reduce the task consumption time and improve the edge computing resources utilization.
引用
收藏
页码:3205 / 3219
页数:15
相关论文
共 50 条
[41]   Dependency-aware task offloading based on deep reinforcement learning in mobile edge computing networks [J].
Li, Junnan ;
Yang, Zhengyi ;
Chen, Kai ;
Ming, Zhao ;
Li, Xiuhua ;
Fan, Qilin ;
Hao, Jinlong ;
Cheng, Luxi .
WIRELESS NETWORKS, 2024, 30 (06) :5519-5531
[42]   Sequence-Based Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing: A Comparison Study [J].
Xiao, Xiang-Jie ;
Wang, Yong ;
Wang, Kezhi ;
Huang, Pei-Qiu .
BIO-INSPIRED COMPUTING: THEORIES AND APPLICATIONS, PT 2, BIC-TA 2023, 2024, 2062 :94-106
[43]   Multi-user Edge Computing Task offloading Scheduling and Resource Allocation Based on Deep Reinforcement Learning [J].
Kuang Z.-F. ;
Chen Q.-L. ;
Li L.-F. ;
Deng X.-H. ;
Chen Z.-G. .
Jisuanji Xuebao/Chinese Journal of Computers, 2022, 45 (04) :812-824
[44]   Cache-assisted task offloading strategy based on multi-agent deep reinforcement learning [J].
Xie, Mande ;
Li, Longchen ;
Ni, Xueping .
COMPUTER NETWORKS, 2025, 270
[45]   Deep Reinforcement Learning for Task Offloading in Edge Computing [J].
Xie, Bo ;
Cui, Haixia .
2024 4TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND INTELLIGENT SYSTEMS ENGINEERING, MLISE 2024, 2024, :250-254
[46]   Security-Aware Task Offloading Using Deep Reinforcement Learning in Mobile Edge Computing Systems [J].
Lu, Haodong ;
He, Xiaoming ;
Zhang, Dengyin .
ELECTRONICS, 2024, 13 (15)
[47]   Task offloading for multi-UAV asset edge computing with deep reinforcement learning [J].
Zakaryia, Samah A. ;
Mead, Mohamed A. ;
Nabil, Tamer ;
Hussein, Mohamed K. .
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2025, 28 (07)
[48]   Task offloading in hybrid-decision-based multi-cloud computing network: a cooperative multi-agent deep reinforcement learning [J].
Juan Chen ;
Peng Chen ;
Xianhua Niu ;
Zongling Wu ;
Ling Xiong ;
Canghong Shi .
Journal of Cloud Computing, 11
[49]   Task offloading in hybrid-decision-based multi-cloud computing network: a cooperative multi-agent deep reinforcement learning [J].
Chen, Juan ;
Chen, Peng ;
Niu, Xianhua ;
Wu, Zongling ;
Xiong, Ling ;
Shi, Canghong .
JOURNAL OF CLOUD COMPUTING-ADVANCES SYSTEMS AND APPLICATIONS, 2022, 11 (01)
[50]   Deep Reinforcement Learning-Based Task Assignment for Cooperative Mobile Edge Computing [J].
Hsieh, Li-Tse ;
Liu, Hang ;
Guo, Yang ;
Gazda, Robert .
IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (04) :3156-3171