LEOSTP: A Spatio-Temporal Traffic Prediction Framework for LEO Satellite Networks

2026-06-29

AI Summary

This work addresses the challenging problem of spatiotemporal traffic forecasting in low Earth orbit (LEO) satellite networks, where complex dynamics arise from satellite mobility, multi-satellite coordination, and heterogeneous geographical environments. To tackle this issue, the authors propose LEOSTP, a novel end-to-end framework that introduces diffusion models to this domain for the first time. Built upon a Transformer architecture, LEOSTP jointly models temporal traffic dynamics and geographical semantics—such as population density, points of interest (POIs), and local time—through a unified traffic feature extractor and an external condition encoder. Evaluated on large-scale simulated LEO constellation data, LEOSTP significantly outperforms established baselines including ARIMA, SVR, LSTM, and standard Transformer models, achieving substantial improvements in prediction accuracy.

Abstract

With the evolution of next-generation mobile communication networks and the commercial boom of Low Earth Orbit (LEO) satellites, globally covered satellite networks are gradually becoming a crucial infrastructure for massive user access and seamless connectivity. Accurate traffic prediction is crucial for maintaining the quality of service (QoS) and resource allocation efficiency in satellite networks. However, existing methods struggle to effectively address the three major challenges of LEO networks: highly complex temporal dynamics caused by satellite cross-regional movement, multivariate dependencies in multi-satellite collaboration, and strong spatial heterogeneity driven by user distribution, human activity intensity, and local geographic environments. In this article, we propose a LEO Satellite Traffic Predictor (LEOSTP) framework, a diffusion model-based end-to-end model that forecasts future satellite traffic by jointly leveraging historical traffic patterns and contextual characteristics of the corresponding service regions. The framework consists of two core modules: 1) The general traffic feature extractor module combines the diffusion process with a Transformer architecture to model the multi-scale temporal features of the traffic itself. 2) The external condition encoder module integrates geographic semantic information such as population distribution, point-of-interest (POI) distribution, and local time into the prediction process through a Transformer-based encoder. In this way, the model captures the deep correlation between the external environment and traffic dynamics. Experimental results based on large-scale simulated constellation data show that LEOSTP significantly outperforms traditional statistical models such as ARIMA and SVR, and classical sequence models including LSTM and Transformer, in prediction accuracy.

Problem

• LEO satellite networks
• traffic prediction
• spatio-temporal dynamics
• spatial heterogeneity
• multi-satellite collaboration

Innovation

• diffusion model
• Transformer architecture
• spatio-temporal traffic prediction
• LEO satellite networks
• external condition encoding