Edge-Enabled Two-Stage Scheduling Based on Deep Reinforcement Learning for Internet of Everything

被引:68
作者
Zhou, Xiaokang [1 ]
Liang, Wei [2 ]
Yan, Ke [3 ]
Li, Weimin [4 ]
Wang, Kevin I-Kai [5 ]
Ma, Jianhua [6 ]
Jin, Qun [7 ]
机构
[1] Shiga Univ, Fac Data Sci, Hikone 5228522, Japan
[2] Hunan Univ Technol & Business, Base Int Sci & Technol Innovat & Cooperat Big Data, Changsha 410205, Peoples R China
[3] Natl Univ Singapore, Coll Design & Engn, Singapore 117566, Singapore
[4] Shanghai Univ, Sch Comp Engn & Sci, Shanghai 200444, Peoples R China
[5] Univ Auckland, Dept Elect Comp & Software Engn, Auckland 1010, New Zealand
[6] Hosei Univ, Fac Comp & Informat Sci, Tokyo 1028160, Japan
[7] Waseda Univ, Fac Human Sci, Tokorozawa 3591192, Japan
基金
中国国家自然科学基金;
关键词
Task analysis; Internet of Things; Processor scheduling; Reinforcement learning; Scheduling; Job shop scheduling; Optimal scheduling; Deep reinforcement learning; edge computing; Internet of Everything (IoE); makespan; two-stage scheduling; IOT;
D O I
10.1109/JIOT.2022.3179231
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Nowadays, the concept of Internet of Everything (IoE) is becoming a hotly discussed topic, which is playing an increasingly indispensable role in modern intelligent applications. These applications are known for their real-time requirements under limited network and computing resources, thus it becomes a highly demanding task to transform and compute tremendous amount of raw data in a cloud center. The edge-cloud computing infrastructure allows a large amount of data to be processed on nearby edge nodes and then only the extracted and encrypted key features are transmitted to the data center. This offers the potential to achieve an end-edge-cloud-based big data intelligence for IoE in a typical two-stage data processing scheme, while satisfying a data security constraint. In this study, a deep-reinforcement-learning-enhanced two-stage scheduling (DRL-TSS) model is proposed to address the NP-hard problem in terms of operation complexity in end-edge-cloud Internet of Things systems, which is able to allocate computing resources within an edge-enabled infrastructure to ensure computing task to be completed with minimum cost. A presorting scheme based on Johnson's rule is developed and applied to preprocess the two-stage tasks on multiple executors, and a DRL mechanism is developed to minimize the overall makespan based on a newly designed instant reward that takes into account the maximal utilization of each executor in edge-enabled two-stage scheduling. The performance of our method is evaluated and compared with three existing scheduling techniques, and experimental results demonstrate the ability of our proposed algorithm in achieving better learning efficiency and scheduling performance with a 1.1-approximation to the targeted optimal IoE applications.
引用
收藏
页码:3295 / 3304
页数:10
相关论文
共 31 条
  • [1] Parallel Reinforcement Learning With Minimal Communication Overhead for IoT Environments
    Camelo, Miguel
    Claeys, Maxim
    Latre, Steven
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2020, 7 (02) : 1387 - 1400
  • [2] Chen K., 2018, J. Hardw. Syst. Secur., V2, P97, DOI [DOI 10.1007/S41635-017-0029-7, 10.1007/s41635-017-0029-7]
  • [3] Edge-Aided Computing and Transmission Scheduling for LTE-U-Enabled IoT
    He, Hongli
    Shan, Hangguan
    Huang, Aiping
    Ye, Qiang
    Zhuang, Weihua
    [J]. IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2020, 19 (12) : 7881 - 7896
  • [4] Green Resource Allocation Based on Deep Reinforcement Learning in Content-Centric IoT
    He, Xiaoming
    Wang, Kun
    Huang, Huawei
    Miyazaki, Toshiaki
    Wang, Yixuan
    Guo, Song
    [J]. IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING, 2020, 8 (03) : 781 - 796
  • [5] Hoogeveen JA, 1996, EUR J OPER RES, V89, P172, DOI 10.1016/S0377-2217(96)90070-3
  • [6] Adaptive Wireless Network Management with Multi-Agent Reinforcement Learning
    Ivoghlian, Ameer
    Salcic, Zoran
    Wang, Kevin I-Kai
    [J]. SENSORS, 2022, 22 (03)
  • [7] Reinforcement Learning for Real-Time Optimization in NB-IoT Networks
    Jiang, Nan
    Deng, Yansha
    Nallanathan, Arumugam
    Chambers, Jonathon A.
    [J]. IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2019, 37 (06) : 1424 - 1440
  • [8] Johnson SM, 1954, NAV RES LOG, V1, P61, DOI [DOI 10.1002/NAV.3800010110, 10.1002/nav.3800010110]
  • [9] Kim Y., 2020, IEEE ACCESS
  • [10] Intelligent IoT Connectivity: Deep Reinforcement Learning Approach
    Kwon, Minhae
    Lee, Juhyeon
    Park, Hyunggon
    [J]. IEEE SENSORS JOURNAL, 2020, 20 (05) : 2782 - 2791