Task Offloading Based on LSTM Prediction and Deep Reinforcement Learning for Efficient Edge Computing in IoT

被引:37
作者
Tu, Youpeng [1 ]
Chen, Haiming [1 ,2 ]
Yan, Linjie [1 ]
Zhou, Xinyan [1 ]
机构
[1] Ningbo Univ, Fac Elect Engn & Comp Sci, Ningbo 315211, Peoples R China
[2] Ningbo Univ, Zhejiang Prov Key Lab Mobile Network Applicat Tec, Ningbo 315211, Peoples R China
来源
FUTURE INTERNET | 2022年 / 14卷 / 02期
基金
中国国家自然科学基金;
关键词
computational offloading; resource allocation; prediction; DRL; LSTM; FRAMEWORK; ALLOCATION; INTERNET;
D O I
10.3390/fi14020030
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In IoT (Internet of Things) edge computing, task offloading can lead to additional transmission delays and transmission energy consumption. To reduce the cost of resources required for task offloading and improve the utilization of server resources, in this paper, we model the task offloading problem as a joint decision making problem for cost minimization, which integrates the processing latency, processing energy consumption, and the task throw rate of latency-sensitive tasks. The Online Predictive Offloading (OPO) algorithm based on Deep Reinforcement Learning (DRL) and Long Short-Term Memory (LSTM) networks is proposed to solve the above task offloading decision problem. In the training phase of the model, this algorithm predicts the load of the edge server in real-time with the LSTM algorithm, which effectively improves the convergence accuracy and convergence speed of the DRL algorithm in the offloading process. In the testing phase, the LSTM network is used to predict the characteristics of the next task, and then the computational resources are allocated for the task in advance by the DRL decision model, thus further reducing the response delay of the task and enhancing the offloading performance of the system. The experimental evaluation shows that this algorithm can effectively reduce the average latency by 6.25%, the offloading cost by 25.6%, and the task throw rate by 31.7%.
引用
收藏
页数:19
相关论文
共 41 条
  • [1] Mobile Edge Computing: A Survey
    Abbas, Nasir
    Zhang, Yan
    Taherkordi, Amir
    Skeie, Tor
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2018, 5 (01): : 450 - 465
  • [2] IoT traffic prediction using multi-step ahead prediction with neural network
    Abdellah, Ali R.
    Mahmood, Omar Abdul Kareem
    Paramonov, Alexander
    Koucheryavy, Andrey
    [J]. 2019 11TH INTERNATIONAL CONGRESS ON ULTRA MODERN TELECOMMUNICATIONS AND CONTROL SYSTEMS AND WORKSHOPS (ICUMT), 2019,
  • [3] Reinforcement-Learning-Enabled Massive Internet of Things for 6G Wireless Communications
    Ali R.
    Ashraf I.
    Bashir A.K.
    Zikria Y.B.
    [J]. IEEE Communications Standards Magazine, 2021, 5 (02): : 126 - 131
  • [4] A Federated Reinforcement Learning Framework for Incumbent Technologies in Beyond 5G Networks
    Ali, Rashid
    Bin Zikria, Yousaf
    Garg, Sahil
    Bashir, Ali Kashif
    Obaidat, Mohammad S.
    Kim, Hyung Seok
    [J]. IEEE NETWORK, 2021, 35 (04): : 152 - 159
  • [5] DeepEdge: A New QoE-Based Resource Allocation Framework Using Deep Reinforcement Learning for Future Heterogeneous Edge-IoT Applications
    AlQerm, Ismail
    Pan, Jianli
    [J]. IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2021, 18 (04): : 3942 - 3954
  • [6] Towards Trust and Friendliness Approaches in the Social Internet of Things
    Amin, Farhan
    Ahmad, Awais
    Choi, Gyu Sang
    [J]. APPLIED SCIENCES-BASEL, 2019, 9 (01):
  • [7] Performance evaluation metrics for cloud, fog and edge computing: A review, taxonomy, benchmarks and standards for future research
    Aslanpour, Mohammad S.
    Gill, Sukhpal Singh
    Toosi, Adel N.
    [J]. INTERNET OF THINGS, 2020, 12
  • [8] An intelligent task offloading algorithm (iTOA) for UAV edge computing network
    Chen, Jienan
    Chen, Siyu
    Luo, Siyu
    Wang, Qi
    Cao, Bin
    Li, Xiaoqian
    [J]. DIGITAL COMMUNICATIONS AND NETWORKS, 2020, 6 (04) : 433 - 443
  • [9] iRAF: A Deep Reinforcement Learning Approach for Collaborative Mobile Edge Computing IoT Networks
    Chen, Jienan
    Chen, Siyu
    Wang, Qi
    Cao, Bin
    Feng, Gang
    Hu, Jianhao
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2019, 6 (04): : 7011 - 7024
  • [10] A DRL Agent for Jointly Optimizing Computation Offloading and Resource Allocation in MEC
    Chen, Juan
    Xing, Huanlai
    Xiao, Zhiwen
    Xu, Lexi
    Tao, Tao
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (24) : 17508 - 17524