Cellular Traffic Prediction Based on Spatiotemporal Graph Feature Fusion

Mengke Yang, Daosen Zhai, Ruonan Zhang, Bin Li, Pengfei Du, Haotong Cao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With the rapid development of 4G and 5G networks, accurate BS traffic prediction has become a critical factor for efficient cellular network management. Traditional traffic prediction models, such as Long Short-Term Memory (LSTM) and (Convolutional Neural Network) CNN+Transformer, either neglect spatial information or fail to efficiently integrate temporal and spatial features, limiting their prediction accuracy. To address this issue, we propose a Multi-Temporal Spatial Graph Convolution Network (MTSGCN) model. This model introduces a novel mechanism of multi-length historical sequences and combines a Gated Linear Unit (GLU)-based temporal module with a Graph Convolution Layer (GCL)-based spatial module, capturing both temporal and spatial dependencies effectively. Extensive experiments on real-world datasets demonstrate that MTSGCN achieves superior convergence and predictive accuracy compared to the existing models.

Original languageEnglish
Title of host publicationProceedings - 2024 3rd International Conference on Computing, Communication, Perception and Quantum Technology, CCPQT 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages185-189
Number of pages5
ISBN (Electronic)9798331528386
DOIs
StatePublished - 2024
Event3rd International Conference on Computing, Communication, Perception and Quantum Technology, CCPQT 2024 - Zhuhai, China
Duration: 25 Oct 202427 Oct 2024

Publication series

NameProceedings - 2024 3rd International Conference on Computing, Communication, Perception and Quantum Technology, CCPQT 2024

Conference

Conference3rd International Conference on Computing, Communication, Perception and Quantum Technology, CCPQT 2024
Country/TerritoryChina
CityZhuhai
Period25/10/2427/10/24

Keywords

  • ellular traffic prediction
  • feature fusion
  • spatial feature
  • temporal feature

Fingerprint

Dive into the research topics of 'Cellular Traffic Prediction Based on Spatiotemporal Graph Feature Fusion'. Together they form a unique fingerprint.

Cite this