Multimodal Spatiotemporal-Frequency Fusion with Peak Enhancement for Cellular Traffic Forecasting

2026-07-08

AI Summary

Existing cellular traffic forecasting methods struggle to simultaneously capture endogenous bursty dynamics and exogenous disturbances caused by urban events, limiting prediction accuracy. This work proposes MSPF-Net, a novel framework that jointly models traffic burst behavior and contextual signals from news articles for the first time. By integrating a spatio-temporal-frequency encoder, a peak-enhancement module, and a multimodal dynamic fusion mechanism, MSPF-Net achieves high-precision forecasting. The approach overcomes the limitations of unimodal modeling and significantly outperforms state-of-the-art methods on the Milano, Trento, and LTE datasets, demonstrating the effectiveness and superiority of multimodal fusion for predicting bursty cellular traffic.

Abstract

Accurate forecasting of cellular network traffic is essential for network planning, resource allocation, and quality-of-service assurance in modern mobile communication systems. Real-world traffic often exhibits bursty endogenous dynamics and disturbances triggered by external urban events, which makes reliable prediction highly challenging. Most existing spatiotemporal traffic forecasting methods primarily focus on intrinsic traffic patterns or structural relationships within a single modality, and rarely model burst behavior together with exogenous contextual signals. To address this issue, we propose \textbf{MSPF-Net}, a multimodal cellular traffic forecasting framework that integrates external contextual information. Specifically, MSPF-Net consists of a Spatiotemporal-Frequency Traffic Encoder for capturing temporal, spatial, and spectral traffic patterns, a Peak Enhancement Module for extracting burst-aware representations of sudden spikes, a News Context Representation Module for encoding urban news streams into exogenous contextual embeddings, and a Dynamic Fusion Prediction Module for adaptively integrating these heterogeneous signals to generate forecasts. Experiments on the Milano, Trento, and LTE traffic datasets demonstrate that jointly modeling traffic dynamics, burst patterns, and news contextual signals can effectively improve forecasting performance.

Problem

• cellular traffic forecasting
• burst behavior
• exogenous contextual signals
• spatiotemporal prediction
• multimodal fusion

Innovation

• multimodal fusion
• spatiotemporal-frequency modeling
• peak enhancement
• exogenous context
• cellular traffic forecasting