Citywide Wireless Traffic Prediction Based on Personalized Federated Learning

被引：0
|
作者：
Lin S. [1 ]
Ma J. [2 ]
Li Y. [1 ]
Zhuang B. [1 ]
Li T. [1 ]
Li Z. [1 ]
Tian J. [2 ]
机构：
[1] Beijing Key Laboratory of Work Safety Intelligent Monitoring, Beijing University of Posts and Telecommunications Haidian, Beijing
[2] School of Network and Communication Engineering, Jinling Institute of Technology, Nanjing
来源：
Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China | 2023年 / 52卷 / 01期
关键词：
cloud-edge collaboration; coalitional game; federated learning; spatio-temporal dependence; wireless traffic prediction;
D O I：
10.12178/1001-0548.2022102
中图分类号：
学科分类号：
摘要：
Wireless communication network traffic prediction is of great significance to operators in network construction, base station wireless resource management and user experience improvement. However, the existing centralized algorithm models face the problems of complexity and timeliness, thus difficult to meet the traffic prediction of the whole city scale. A distributed urban global traffic prediction algorithm Fed-DenseNet is proposed in this paper. Each edge computing server of the algorithm performs collaborative training under the coordination of the central server, and the central server uses KL (Kullback-Leibler) divergence to select regional traffic models with similar traffic distribution and uses the federated average algorithm to fuse the parameters of these regional traffic models. In this way, the urban global traffic prediction can be realized with lower complexity and communication cost. In addition, the traffic in different areas within the city is highly differentiated, so how to improve the accuracy of model prediction is also facing challenges. Based on Fed-Densenet algorithm, a personalized federated learning algorithm p-Fed-DenseNet based on cooperative game is proposed. Each regional data feature in the region is taken as a participant of cooperative game, and local features are screened by the superadditivity criterion of cooperative game, so as to achieve the purpose of both improving the generalization of the model and maintaining the accurate description of local traffic. © 2023 Univ. of Electronic Science and Technology of China. All rights reserved.
引用
收藏
页码：67 / 73
页数：6
相关论文
共 11 条
  • [1] ZHANG J, BAI G W, SHA X L, Et al., Mobile traffic forecasting model based on spatio-temporal features, Computer Science, 46, 12, pp. 108-113, (2019)
  • [2] WANG K, MA C, QIAN Y, Et al., A hybrid deep learning model with 1DCNN-LSTM-Attention networks for short-term traffic flow prediction, Physica A: Statistical Mechanics and Its Applications, 583, 12, (2021)
  • [3] ZHANG J C, ZUO X Q, HUANG H, Et al., Application of prophet mixture model on long-term prediction of base station cell network traffic, Computer Engineering and Applications, 58, 14, pp. 80-88, (2022)
  • [4] ZHU J, PAN C S, KONG Z X, Et al., Network traffic prediction based on prophet fusion muti-grain feature extraction, Computer Simulation, 38, 7, pp. 475-480, (2021)
  • [5] KAIROUZ E, MCMAHAN H B., Advances and open problems in federated learning, Foundations and Trends in Machine Learning, 14, 1, pp. 1-210, (2021)
  • [6] BAO W, WU C, GULENG S, Et al., Edge computing-based joint client selection and networking scheme for federated learning in vehicular IoT, China Communications, 18, 6, pp. 39-52, (2021)
  • [7] KRABS W., A cooperative treatment of an n-person cost-goal-game, Mathematical Methods of Operations Research, 57, 2, pp. 309-319, (2003)
  • [8] SHIROKIKH V A, LEZHNINA E A., Coalition-Formation problem for cooperative inventory routing game, Automation and Remote Control, 80, 7, pp. 1358-1367, (2019)
  • [9] ZHENG Z, CHEN W, WU X, Et al., LSTM network: A deep learning approach for short-term traffic forecast, IET Intelligent Transport Systems, 11, 2, pp. 68-75, (2017)
  • [10] SHI X, CHEN Z, WANG H, Et al., Convolutional LSTM network: A machine learning approach for precipitation nowcasting, Proceedings of the 28th International Conference on Neural Information Processing Systems, pp. 802-810, (2015)
12