Federated Learning in Mobile Networks: A Comprehensive Case Study on Traffic Forecasting

被引:0
作者
Pavlidis, Nikolaos [1 ]
Perifanis, Vasileios [1 ]
Yilmaz, Selim F. [2 ]
Wilhelmi, Francesc [3 ]
Miozzo, Marco [4 ]
Efraimidis, Pavlos S. [1 ]
Koutsiamanis, Remous-Aris [5 ]
Mulinka, Pavol
Dini, Paolo
机构
[1] Democritus Univ Thrace, Dept Elect & Comp Engn, Xanthi 69100, Greece
[2] Imperial Coll London, Dept Elect & Elect Engn, London SW7 2AZ, England
[3] Nokia Bell Labs, D-70469 Stuttgart, Germany
[4] Ctr Tecnol Telecomunicac Catalunya CTTC CERCA, Sustainable Artificial Intelligence, Barcelona 08860, Spain
[5] Inria, Dept Automat Prod & Comp Sci, IMT Atlantique, LS2N, F-44300 Nantes, France
来源
IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING | 2025年 / 10卷 / 03期
关键词
Forecasting; Data models; Time series analysis; Predictive models; Accuracy; Computational modeling; Training; Servers; Collaboration; Optimization; 5G; 6G; federated learning; machine learning; mobile networks; time series forecasting; traffic prediction; PREDICTION;
D O I
10.1109/TSUSC.2024.3504242
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
The increasing demand for efficient resource allocation in mobile networks has catalyzed the exploration of innovative solutions that could enhance the task of real-time cellular traffic prediction. Under these circumstances, federated learning (FL) stands out as a distributed and privacy-preserving solution to foster collaboration among different sites, thus enabling responsive near-the-edge solutions. In this paper, we comprehensively study the potential benefits of FL in telecommunications through a case study on federated traffic forecasting using real-world data from base stations (BSs) in Barcelona (Spain). Our study encompasses relevant aspects within the federated experience, including model aggregation techniques, outlier management, the impact of individual clients, personalized learning, and the integration of exogenous sources of data. The performed evaluation is based on both prediction accuracy and sustainability, thus showcasing the environmental impact of employed FL algorithms in various settings. The findings from our study highlight FL as a promising and robust solution for mobile traffic prediction, emphasizing its twin merits as a privacy-conscious and environmentally sustainable approach, while also demonstrating its capability to overcome data heterogeneity and ensure high-quality predictions, marking a significant stride towards its integration in mobile traffic management systems.
引用
收藏
页码:576 / 587
页数:12
相关论文
共 51 条
[1]   Estimating Energy Consumption of Cloud, Fog, and Edge Computing Infrastructures [J].
Ahvar, Ehsan ;
Orgerie, Anne-Cecile ;
Lebre, Adrien .
IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING, 2022, 7 (02) :277-288
[2]  
Andreoletti D, 2019, IEEE CONF COMPUT, P246, DOI [10.1109/infcomw.2019.8845132, 10.1109/INFCOMW.2019.8845132]
[3]  
[Anonymous], 2010, 3GPP TS 36213 V9.2.0
[4]   A multi-source dataset of urban life in the city of Milan and the Province of Trentino [J].
Barlacchi, Gianni ;
De Nadai, Marco ;
Larcher, Roberto ;
Casella, Antonio ;
Chitic, Cristiana ;
Torrisi, Giovanni ;
Antonelli, Fabrizio ;
Vespignani, Alessandro ;
Pentland, Alex ;
Lepri, Bruno .
SCIENTIFIC DATA, 2015, 2
[5]   A Review on Outlier/Anomaly Detection in Time Series Data [J].
Blazquez-Garcia, Ane ;
Conde, Angel ;
Mori, Usue ;
Lozano, Jose A. .
ACM COMPUTING SURVEYS, 2022, 54 (03)
[6]  
BOX GEP, 1976, TIME SERIES ANAL FOR
[7]  
Cho JH, 2016, Arxiv, DOI [arXiv:1511.06348, DOI 10.48550/ARXIV.1511.06348]
[8]   A deep-learning model for urban traffic flow prediction with traffic events mined from twitter [J].
Essien, Aniekan ;
Petrounias, Ilias ;
Sampaio, Pedro ;
Sampaio, Sandra .
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2021, 24 (04) :1345-1368
[9]  
Anthony LFW, 2020, Arxiv, DOI [arXiv:2007.03051, 10.48550/arXiv.2007.03051]
[10]   Building a Digital Twin for network optimization using Graph Neural Networks [J].
Ferriol-Galmes, Miquel ;
Suarez-Varela, Jose ;
Paillisse, Jordi ;
Shi, Xiang ;
Xiao, Shihan ;
Cheng, Xiangle ;
Barlet-Ros, Pere ;
Cabellos-Aparicio, Albert .
COMPUTER NETWORKS, 2022, 217