Spatial-Temporal Traffic Prediction in LEO Satellite Networks via Hybrid GCN-Transformer
Authors:
- 12 September 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 825-830
Abstract
Low Earth Orbit (LEO) satellite networks are emerging as a critical component in future 6G networks, where accurate traffic prediction is essential for proactive scheduling, resource optimization and load balancing. However, such characteristics of satellite networks as dynamically changing topology, non-Euclidean structure, and significant spatial-temporal correlation pose severe challenges to traffic prediction. This paper proposes a GCN-Transformer scheme that integrates Graph Convolutional Network (GCN) with Transformer Encoding architecture. The GCN component captures local and global spatial dependencies, while the Transformer models long-range temporal dynamics via self-attention. This joint design is capable of processing highly coupled spatial-temporal data and maintaining stable performance under highly dynamic network topologies. Experiments on short-term and long-term prediction tasks (15-60 minutes) show that this scheme consistently outperforms other benchmark schemes in all metrics. The results demonstrate that GCN-Transformer achieves robust spatial-temporal modeling and stable prediction, offering substantial value for adaptive scheduling and resource optimization in satellite networks.Keywords
Funding Information
- Fundamental Research Funds for the Central Universities
This publication has 10 references indexed in Scilit:
- Dynamic Load-Balancing Routing Strategy for LEO Satellite Networks Based on Spatio-Temporal Traffic PredictionIEEE Transactions on Aerospace and Electronic Systems, 2025
- A Dynamic Spatio-Temporal Traffic Prediction Model Applicable to Low Earth Orbit Satellite ConstellationsElectronics, 2025
- Energy-Efficient Cooperative Secure Communications in mmWave Vehicular Networks Using Deep Recurrent Reinforcement LearningIEEE Transactions on Intelligent Transportation Systems, 2024
- NOMA-Assisted Secure Offloading for Vehicular Edge Computing Networks With Asynchronous Deep Reinforcement LearningIEEE Transactions on Intelligent Transportation Systems, 2023
- Satellite Network Traffic Prediction Based on LSTM and GAN2023
- RETRACTED ARTICLE: An EMD and ARMA-based network traffic prediction approach in SDN-based internet of vehiclesWireless Networks, 2021
- Research on GRU Neural Network Satellite Traffic Prediction Based on Transfer LearningWireless Personal Communications, 2021
- Traffic Flow Prediction Using Graph Convolution Neural Networks2020
- Traffic Prediction Based on Surrogate Model in Satellite Constellation Networks2019
- Traffic flow prediction using LSTM with feature enhancementNeurocomputing, 2019