GraFSTNet: Graph-based Frequency SpatioTemporal Network for Cellular Traffic Prediction

2026-02-06

AI Summary

This work proposes a novel forecasting framework for cellular traffic that effectively integrates spatiotemporal attention with time–frequency analysis to jointly capture complex spatial dependencies, temporal dynamics, and periodic patterns. Unlike existing approaches that rely on predefined spatial topologies, the model employs a graph attention mechanism to adaptively learn spatial relationships in a data-driven manner. To explicitly enhance the representation of periodic behaviors, a dedicated frequency-domain branch is introduced. Furthermore, an adaptive-scale LogCosh loss function is designed to balance prediction errors across varying traffic intensities. Extensive experiments on three public datasets demonstrate that the proposed method significantly outperforms state-of-the-art models, achieving more accurate and robust cellular traffic predictions.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Web traffic and log analysis
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

With rapid expansion of cellular networks and the proliferation of mobile devices, cellular traffic data exhibits complex temporal dynamics and spatial correlations, posing challenges to accurate traffic prediction. Previous methods often focus predominantly on temporal modeling or depend on predefined spatial topologies, which limits their ability to jointly model spatio-temporal dependencies and effectively capture periodic patterns in cellular traffic. To address these issues, we propose a cellular traffic prediction framework that integrates spatio-temporal modeling with time-frequency analysis. First, we construct a spatial modeling branch to capture inter-cell dependencies through an attention mechanism, minimizing the reliance on predefined topological structures. Second, we build a time-frequency modeling branch to enhance the representation of periodic patterns. Furthermore, we introduce an adaptive-scale LogCosh loss function, which adjusts the error penalty based on traffic magnitude, preventing large errors from dominating the training process and helping the model maintain relatively stable prediction accuracy across different traffic intensities. Experiments on three open-sourced datasets demonstrate that the proposed method achieves prediction performance superior to state-of-the-art approaches.

Problem

• cellular traffic prediction
• spatio-temporal dependencies
• periodic patterns
• spatial correlations
• temporal dynamics

Innovation

• Graph-based modeling
• Time-frequency analysis
• Adaptive loss function
• Spatio-temporal prediction
• Cellular traffic forecasting