Computation Offloading for Energy and Delay Trade-Offs With Traffic Flow Prediction in Edge Computing-Enabled IoV

被引:19
作者
Xu, Xiaolong [1 ,2 ]
Yang, Chenyi [2 ]
Bilal, Muhammad [3 ]
Li, Weimin [4 ]
Wang, Huihui [5 ]
机构
[1] Nanjing Univ Informat Sci & Technol, Jiangsu Collaborat Innovat Ctr Atmospher Environm, Nanjing 210044, Peoples R China
[2] Nanjing Univ Informat Sci & Technol, Sch Software, Nanjing 210044, Peoples R China
[3] Hankuk Univ Foreign Studies, Dept Comp & Elect Syst Engn, Yongin 17035, Gyeonggi Do, South Korea
[4] Shanghai Univ, Sch Comp Engn & Sci, Shanghai 200444, Peoples R China
[5] St Bonaventure Univ, Cybersecur Program, St Bonaventure, NY 14778 USA
基金
中国国家自然科学基金;
关键词
Computation offloading; deep reinforcement learning; traffic flow prediction; graph neural network; edge computing; REINFORCEMENT; INTERNET; CLOUD;
D O I
10.1109/TITS.2022.3221975
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
An unprecedented prosperity in artificial intelligence promotes the development of Internet of Vehicles (IoV). Assisted by edge computing, vehicles enable to offload data to edge servers in close proximity to users for processing, thus making up for the shortage of local computing resources. However, due to the uneven space-time distribution of traffic flow, edge servers of a certain road segment may be overwhelmed by the surge of service requests. Furthermore, IoV system will incur significant additional energy consumption and time delay because of the absence of a proper computation offloading scheme between edge servers. To cope with above challenges, a computing offloading method for energy and delay trade-offs with traffic flow prediction in edge computing-enabled IoV is proposed. We first design the graph weighted convolution network (GWCN) that can fully excavate the connectivity and distance relation information between road segments to conduct traffic flow prediction. The short-term prediction results are utilized as the basis for adjusting the resource allocation of edge resources in different regions. Then, a computation offloading method driven by deep deterministic policy gradient (DDPG) is leveraged to obtain an optimal computation offloading scheme for edge servers. Finally, extensive comparative experiments demonstrate the low prediction error of GWCN and superior performance of DDPG-driven method in reducing total time delay and energy consumption.
引用
收藏
页码:15613 / 15623
页数:11
相关论文
共 29 条
  • [21] Energy-efficient computation offloading and resource allocation for delay-sensitive mobile edge computing
    Wang, Quyuan
    Guo, Songtao
    Liu, Jiadi
    Yan, Yuanyuan
    SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS, 2019, 21 : 154 - 164
  • [22] Energy-Efficient Computation Offloading in Delay-Constrained Massive MIMO Enabled Edge Network Using Data Partitioning
    Malik, Rafia
    Vu, Mai
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2020, 19 (10) : 6977 - 6991
  • [23] Delay-Aware and Energy-Efficient Computation Offloading in Mobile-Edge Computing Using Deep Reinforcement Learning
    Ale, Laha
    Zhang, Ning
    Fang, Xiaojie
    Chen, Xianfu
    Wu, Shaohua
    Li, Longzhuang
    IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2021, 7 (03) : 881 - 892
  • [24] Smart Edge-Enabled Traffic Light Control: Improving Reward-Communication Trade-offs with Federated Reinforcement Learning
    Hudson, Nathaniel
    Oza, Pratham
    Khamfroush, Hana
    Chantem, Thidapat
    2022 IEEE INTERNATIONAL CONFERENCE ON SMART COMPUTING (SMARTCOMP 2022), 2022, : 40 - 47
  • [25] FedSTN: Graph Representation Driven Federated Learning for Edge Computing Enabled Urban Traffic Flow Prediction
    Yuan, Xiaoming
    Chen, Jiahui
    Yang, Jiayu
    Zhang, Ning
    Yang, Tingting
    Han, Tao
    Taherkordi, Amir
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2023, 24 (08) : 8738 - 8748
  • [26] PREFER: A Pre-trained Model Recommendation Framework for Edge Computing Enabled Traffic Flow Prediction
    Cai, Qiqi
    Cao, Jian
    Chen, Yirong
    Qian, Shiyou
    Yuan, Liangxiao
    Wang, Jie
    ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2025, 19 (02)
  • [27] Energy-efficient optical memory architecture using phase change memory: Clock frequency trade-offs for edge computing
    Jahannia, Belal
    Ye, Jiachi
    Altaleb, Salem
    Cai, Qian
    Madadi-Kandjani, Ehsan
    Asadizanjani, Navid
    Patil, Chandraman
    Heidari, Elham
    Dalir, Hamed
    PHOTONIC COMPUTING: FROM MATERIALS AND DEVICES TO SYSTEMS AND APPLICATIONS, 2024, 13113
  • [28] Energy-Efficient Resource Allocation for Urban Traffic Flow Prediction in Edge-Cloud Computing
    Ali, Ahmad
    Ullah, Inam
    Singh, Sushil Kumar
    Sharafian, Amin
    Jiang, Weiwei
    Sherazi, Hammad I.
    Bai, Xiaoshan
    INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2025, 2025 (01)
  • [29] Edge Computing Enabled Large-Scale Traffic Flow Prediction With GPT in Intelligent Autonomous Transport System for 6G Network
    Rong, Yi
    Mao, Yingchi
    Cui, Huajun
    He, Xiaoming
    Chen, Mingkai
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024,