Parameter Efficient Hybrid Transformer (PEHT) for Network Traffic Prediction via Dynamic Urban Congestion Integration

2026-06-26

AI Summary

This study addresses the challenges of urban cellular traffic prediction, which arise from complex mobility patterns, dynamically varying congestion, and heterogeneous user behaviors. To tackle these issues, the authors propose a Parameter-Efficient Hybrid Transformer (PEHT) model that decouples primary communication features from auxiliary mobility features and incorporates Low-Rank Adaptation (LoRA) into the encoder for efficient modeling. By innovatively integrating multimodal urban data—such as traffic congestion information—with the LoRA mechanism, PEHT significantly reduces the number of trainable parameters while enhancing prediction accuracy. Experimental results demonstrate that PEHT consistently outperforms state-of-the-art models across multiple metrics—including RMSE, MAE, and R²—on both the real-world Telecom Italia Milan dataset and various synthetic congestion scenarios.

Abstract

Accurate network traffic prediction is a critical element for efficient resource allocation in dynamic urban cellular networks. However, prediction remains challenging because network demand is influenced by complex mobility patterns, congestion dynamics, and heterogeneous user behavior. This paper introduces the Parameter-Efficient Hybrid Transformer (PEHT), a network traffic prediction framework that integrates urban mobility and congestion information into a Transformer-based architecture. PEHT separates primary network communication features from secondary urban mobility features and incorporates Low-Rank Adaptation (LoRA) into the Transformer encoder to reduce the number of trainable parameters while maintaining high predictive accuracy. A multimodal fusion strategy then injects external mobility and congestion features into the decoder to improve traffic forecasting. Experiments on the Telecom Italia Milan dataset and multiple synthetic congestion scenarios show that PEHT outperforms state-of-the-art baselines in terms of RMSE, MAE, and $R^2$. The implementation is available in the GitHub repository.

Problem

• network traffic prediction
• urban congestion
• mobility patterns
• heterogeneous user behavior
• dynamic cellular networks

Innovation

• Parameter-Efficient Transformer
• Low-Rank Adaptation
• Multimodal Fusion
• Urban Congestion Integration
• Network Traffic Prediction