Multi-step Traffic Prediction Based on Causal Structure Learning and Improved Seq2Seq for LEO Satellite Networks
Authors:
- 7 August 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 827-832
Abstract
The rapid movement of low Earth orbit (LEO) satellites leads to dynamic changes in their ground access traffic. Multi-step traffic prediction can sense long-term changes in traffic, and accurate traffic prediction is essential for analyzing satellite traffic loads. In this paper, we propose a multi-step traffic prediction (MTP-CS) model based on causal structure learning and improved sequence-to-sequence (Seq2Seq) to improve traffic prediction accuracy by fully exploiting the spatio-temporal relationship of satellite traffic. Specifically, we introduce causal structure learning to model the spatial relationship between satellite traffic as a causal graph and utilize graph attention network (GAT) to aggregate spatial features. Then, we propose an improved Seq2Seq (Seq2Seq-DCCN) by constructing its encoder using a dilated causal convolutional network (DCCN), which can capture the long-term temporal relationships of traffic sequences. Experiments on real traffic datasets show that the proposed MTPCS model achieves 16.59% to 21.9% error reduction compared to the baseline model regarding root mean square error (RMSE) metric at different prediction steps.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 17 references indexed in Scilit:
- Robust Secure Transmission for Satellite CommunicationsIEEE Transactions on Aerospace and Electronic Systems, 2022
- Remaining Useful Life Prediction of Machinery: A New Multiscale Temporal Convolutional Network FrameworkIEEE Transactions on Instrumentation and Measurement, 2022
- Prediction for Dissolved Gas in Power Transformer Oil Based On TCN and GCNIEEE Transactions on Industry Applications, 2022
- Combined Approach for Short-Term Wind Power Forecasting Based on Wave Division and Seq2Seq Model Using Deep LearningIEEE Transactions on Industry Applications, 2022
- Multibranch Attentive Gated ResNet for Short-Term Spatio-Temporal Solar Irradiance ForecastingIEEE Transactions on Industry Applications, 2021
- ADGCN: An Asynchronous Dilation Graph Convolutional Network for Traffic Flow PredictionIEEE Internet of Things Journal, 2021
- Detecting direct causality in multivariate time series: A comparative studyCommunications in Nonlinear Science and Numerical Simulation, 2021
- A Missing Type-Aware Adaptive Interpolation Framework for Sensor DataIEEE Transactions on Instrumentation and Measurement, 2021
- Multivariate Long-Term State Forecasting in Cyber-Physical Systems: A Sequence to Sequence Approach2019
- Comparison of three artificial neural network approaches for estimating of slake durability indexEnvironmental Earth Sciences, 2012