Enhancing Spatiotemporal Networks with xLSTM: A Scalar LSTM Approach for Cellular Traffic Forecasting

TL;DR

This paper introduces xLSTM, a scalar LSTM-based spatiotemporal network that improves cellular traffic forecasting accuracy, efficiency, and generalization by combining temporal and spatial modeling techniques.

Contribution

The paper proposes a lightweight dual-path spatiotemporal network utilizing scalar LSTM and Conv3D modules, enhancing gradient stability and forecast accuracy over existing methods.

Findings

23% MAE reduction compared to ConvLSTM

30% improvement in model generalization

Superior performance on real-world datasets

Abstract

Accurate spatiotemporal traffic forecasting is vital for intelligent resource management in 5G and beyond. However, conventional AI approaches often fail to capture the intricate spatial and temporal patterns that exist, due to e.g., the mobility of users. We introduce a lightweight, dual-path Spatiotemporal Network that leverages a Scalar LSTM (sLSTM) for efficient temporal modeling and a three-layer Conv3D module for spatial feature extraction. A fusion layer integrates both streams into a cohesive representation, enabling robust forecasting. Our design improves gradient stability and convergence speed while reducing prediction error. Evaluations on real-world datasets show superior forecast performance over ConvLSTM baselines and strong generalization to unseen regions, making it well-suited for large-scale, next-generation network deployments. Experimental evaluation shows a 23% MAE reduction over ConvLSTM, with a 30% improvement in model generalization.