TY - GEN
T1 - Cellular Traffic Prediction Based on Spatiotemporal Graph Feature Fusion
AU - Yang, Mengke
AU - Zhai, Daosen
AU - Zhang, Ruonan
AU - Li, Bin
AU - Du, Pengfei
AU - Cao, Haotong
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - ellular traffic prediction
KW - feature fusion
KW - spatial feature
KW - temporal feature
UR - http://www.scopus.com/inward/record.url?scp=105000735778&partnerID=8YFLogxK
U2 - 10.1109/CCPQT64497.2024.00042
DO - 10.1109/CCPQT64497.2024.00042
M3 - 会议稿件
AN - SCOPUS:105000735778
T3 - Proceedings - 2024 3rd International Conference on Computing, Communication, Perception and Quantum Technology, CCPQT 2024
SP - 185
EP - 189
BT - Proceedings - 2024 3rd International Conference on Computing, Communication, Perception and Quantum Technology, CCPQT 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd International Conference on Computing, Communication, Perception and Quantum Technology, CCPQT 2024
Y2 - 25 October 2024 through 27 October 2024
ER -