Lightweight Federated-Learning-Driven Traffic Prediction for Heterogeneous IoT Networks

被引:0
作者
Wang, Ying [1 ]
Zhang, Qianqian [1 ]
Wei, Tongyan [1 ]
Cong, Lin [1 ]
Yu, Peng [1 ]
Guo, Shaoyong [1 ]
Qiu, Xuesong [1 ]
机构
[1] Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing 100876, Peoples R China
来源
IEEE INTERNET OF THINGS JOURNAL | 2024年 / 11卷 / 24期
基金
北京市自然科学基金; 中国国家自然科学基金;
关键词
Internet of Things; Federated learning; Predictive models; Training; Data models; Accuracy; Cloud computing; Gradient compression; horizontal federated learning; Internet of Things (IoT) traffic prediction; NEURAL-NETWORK; INTERNET; EDGE;
D O I
10.1109/JIOT.2024.3454064
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 rapid development of the Internet of Things (IoT), more and more IoT traffic is generated in the data network. Accurate perception of IoT traffic changes will facilitate traffic engineering decisions, thus ensuring the performance of IoT applications. However, current traffic prediction methods ignore the limitations of actual application environment. In this article, we propose an IoT traffic prediction method based on horizontal federated learning to predict traffic trends under the cooperation of the cloud and the edge side. In order to improve the accuracy of IoT traffic prediction, a traffic prediction model SMN3-CIFGA is proposed to predict IoT traffic based on traffic feature extraction in a limited hardware environment. In addition, in order to improve the communication efficiency in the distributed training process of the traffic prediction model, we propose a gradient compression algorithm based on dynamic threshold (GCADT). The experimental results demonstrate that compared with current methods, the average training time of the GCADT algorithm is reduced by about 6.21%, the transmission gradient size of the GCADT is reduced by about 66.71%, the average training time of the classification model SMN3 is reduced by about 40%, and the testing set prediction accuracy of SMN3-CIFGA can reach 97.61%.
引用
收藏
页码:40656 / 40669
页数:14
相关论文
共 45 条
[1]   Learned Gradient Compression for Distributed Deep Learning [J].
Abrahamyan, Lusine ;
Chen, Yiming ;
Bekoulis, Giannis ;
Deligiannis, Nikos .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (12) :7330-7344
[2]   INTERNET-OF-THINGS-BASED SMART ENVIRONMENTS: STATE OF THE ART, TAXONOMY, AND OPEN RESEARCH CHALLENGES [J].
Ahmed, Ejaz ;
Yaqoob, Ibrar ;
Gani, Abdullah ;
Imran, Muhammad ;
Guizani, Mohsen .
IEEE WIRELESS COMMUNICATIONS, 2016, 23 (05) :10-16
[3]  
[Anonymous], 2020, The Mobile Economy Asia Pacific 2020
[4]   The Client and the Cloud Democratizing Research Computing [J].
Barga, Roger ;
Gannon, Dennis ;
Reed, Daniel .
IEEE INTERNET COMPUTING, 2011, 15 (01) :72-75
[5]   Lightweight Machine Learning Classifiers of IoT Traffic Flows [J].
Bikmukhamedov, R. F. ;
Nadeev, A. F. .
2019 SYSTEMS OF SIGNAL SYNCHRONIZATION, GENERATING AND PROCESSING IN TELECOMMUNICATIONS (SYNCHROINFO), 2019,
[6]   Internet of Things (IoT): Research, Simulators, and Testbeds [J].
Chernyshev, Maxim ;
Baig, Zubair ;
Bello, Oladayo ;
Zeadally, Sherali .
IEEE INTERNET OF THINGS JOURNAL, 2018, 5 (03) :1637-1647
[7]   A lightweight model with spatial-temporal correlation for cellular traffic prediction in Internet of Things [J].
Chien, Wei-Che ;
Huang, Yueh-Min .
JOURNAL OF SUPERCOMPUTING, 2021, 77 (09) :10023-10039
[8]   Edge-Cloud Computing for Internet of Things Data Analytics: Embedding Intelligence in the Edge With Deep Learning [J].
Ghosh, Ananda Mohon ;
Grolinger, Katarina .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2021, 17 (03) :2191-2200
[9]  
Hu Jun, 2008, Journal of Computer Applications, V28, P586, DOI 10.3724/SP.J.1087.2008.00586
[10]   Deep Learning with Long Short-Term Memory for Time Series Prediction [J].
Hua, Yuxiu ;
Zhao, Zhifeng ;
Li, Rongpeng ;
Chen, Xianfu ;
Liu, Zhiming ;
Zhang, Honggang .
IEEE COMMUNICATIONS MAGAZINE, 2019, 57 (06) :114-119