Zobraziť v EDS

A structured distributed learning framework for irregular cellular spatial-temporal traffic prediction

Uložené v:
Podrobná bibliografia
Názov: A structured distributed learning framework for irregular cellular spatial-temporal traffic prediction
Autori: Xiangyu Chen, Kaisa Zhang, Gang Chuai, Weidong Gao, Xuewen Liu, Yibo Zhang, Yijian Hou
Zdroj: Digital Communications and Networks, Vol 11, Iss 5, Pp 1457-1468 (2025)
Informácie o vydavateľovi: KeAi Communications Co., Ltd., 2025.
Rok vydania: 2025
Zbierka: LCC:Information technology
Predmety: Network measurement and analysis, Distributed learning, Irregular time series, Cellular spatial-temporal traffic, Traffic prediction, Information technology, T58.5-58.64
Popis: Spatial-temporal traffic prediction technology is crucial for network planning, resource allocation optimizing, and user experience improving. With the development of virtual network operators, multi-operator collaborations, and edge computing, spatial-temporal traffic data has taken on a distributed nature. Consequently, non-centralized spatial-temporal traffic prediction solutions have emerged as a recent research focus. Currently, the majority of research typically adopts federated learning methods to train traffic prediction models distributed on each base station. This method reduces additional burden on communication systems. However, this method has a drawback: it cannot handle irregular traffic data. Due to unstable wireless network environments, device failures, insufficient storage resources, etc., data missing inevitably occurs during the process of collecting traffic data. This results in the irregular nature of distributed traffic data. Yet, commonly used traffic prediction models such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) typically assume that the data is complete and regular. To address the challenge of handling irregular traffic data, this paper transforms irregular traffic prediction into problems of estimating latent variables and generating future traffic. To solve the aforementioned problems, this paper introduces split learning to design a structured distributed learning framework. The framework comprises a Global-level Spatial structure mining Model (GSM) and several Node-level Generative Models (NGMs). NGM and GSM represent Seq2Seq models deployed on the base station and graph neural network models deployed on the cloud or central controller. Firstly, the time embedding layer in NGM establishes the mapping relationship between irregular traffic data and regular latent temporal feature variables. Secondly, GSM collects statistical feature parameters of latent temporal feature variables from various nodes and executes graph embedding for spatial-temporal traffic data. Finally, NGM generates future traffic based on latent temporal and spatial feature variables. The introduction of the time attention mechanism enhances the framework's capability to handle irregular traffic data. Graph attention network introduces spatially correlated base station traffic feature information into local traffic prediction, which compensates for missing information in local irregular traffic data. The proposed framework effectively addresses the distributed prediction issues of irregular traffic data. By testing on real world datasets, the proposed framework improves traffic prediction accuracy by 35% compared to other commonly used distributed traffic prediction methods.
Druh dokumentu: article
Popis súboru: electronic resource
Jazyk: English
ISSN: 2352-8648
Relation: http://www.sciencedirect.com/science/article/pii/S2352864825000410; https://doaj.org/toc/2352-8648
DOI: 10.1016/j.dcan.2025.04.003
Prístupová URL adresa: https://doaj.org/article/e2324e2bd8e14c20b67f5d6db490cffa
Prístupové číslo: edsdoj.2324e2bd8e14c20b67f5d6db490cffa
Databáza: Directory of Open Access Journals
Popis
Abstrakt:Spatial-temporal traffic prediction technology is crucial for network planning, resource allocation optimizing, and user experience improving. With the development of virtual network operators, multi-operator collaborations, and edge computing, spatial-temporal traffic data has taken on a distributed nature. Consequently, non-centralized spatial-temporal traffic prediction solutions have emerged as a recent research focus. Currently, the majority of research typically adopts federated learning methods to train traffic prediction models distributed on each base station. This method reduces additional burden on communication systems. However, this method has a drawback: it cannot handle irregular traffic data. Due to unstable wireless network environments, device failures, insufficient storage resources, etc., data missing inevitably occurs during the process of collecting traffic data. This results in the irregular nature of distributed traffic data. Yet, commonly used traffic prediction models such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) typically assume that the data is complete and regular. To address the challenge of handling irregular traffic data, this paper transforms irregular traffic prediction into problems of estimating latent variables and generating future traffic. To solve the aforementioned problems, this paper introduces split learning to design a structured distributed learning framework. The framework comprises a Global-level Spatial structure mining Model (GSM) and several Node-level Generative Models (NGMs). NGM and GSM represent Seq2Seq models deployed on the base station and graph neural network models deployed on the cloud or central controller. Firstly, the time embedding layer in NGM establishes the mapping relationship between irregular traffic data and regular latent temporal feature variables. Secondly, GSM collects statistical feature parameters of latent temporal feature variables from various nodes and executes graph embedding for spatial-temporal traffic data. Finally, NGM generates future traffic based on latent temporal and spatial feature variables. The introduction of the time attention mechanism enhances the framework's capability to handle irregular traffic data. Graph attention network introduces spatially correlated base station traffic feature information into local traffic prediction, which compensates for missing information in local irregular traffic data. The proposed framework effectively addresses the distributed prediction issues of irregular traffic data. By testing on real world datasets, the proposed framework improves traffic prediction accuracy by 35% compared to other commonly used distributed traffic prediction methods.
ISSN:23528648
DOI:10.1016/j.dcan.2025.04.003