AI-Enhanced Spatial Cellular Traffic Demand Prediction with Contextual Clustering and Error Correction for 5G/6G Planning

TL;DR

This paper introduces an AI framework for accurate spatial cellular traffic demand prediction that reduces data leakage and enhances generalization, aiding 5G/6G network planning.

Contribution

It proposes a novel two-stage data splitting and error correction method to improve spatial prediction accuracy and reliability in cellular traffic modeling.

Findings

Significant MAE reductions across five Canadian cities.

Enhanced spatial generalization over traditional clustering methods.

Supports more reliable network planning and spectrum sharing.

Abstract

Accurate spatial prediction of cellular traffic demand is essential for 5G NR capacity planning, network densification, and data-driven 6G planning. Although machine learning can fuse heterogeneous geospatial and socio-economic layers to estimate fine-grained demand maps, spatial autocorrelation can cause neighborhood leakage under naive train/test splits, inflating accuracy and weakening planning reliability. This paper presents an AI-driven framework that reduces leakage and improves spatial generalization via a context-aware two-stage splitting strategy with residual spatial error correction. Experiments using crowdsourced usage indicators across five major Canadian cities show consistent mean absolute error (MAE) reductions relative to location-only clustering, supporting more reliable bandwidth provisioning and evidence-based spectrum planning and sharing assessments.