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

2026-03-11

AI Summary

This study addresses the issue of training/test data leakage caused by spatial autocorrelation in 5G/6G network planning. To mitigate neighborhood data leakage and enhance spatial generalization, the authors propose a two-stage context-aware partitioning strategy that integrates context clustering based on heterogeneous geographic and socioeconomic features with a residual spatial error correction mechanism. The approach is validated on real-world crowdsourced cellular traffic data from five major Canadian cities. Compared to conventional location-based clustering methods, it significantly reduces mean absolute error (MAE) and improves the robustness of fine-grained cellular traffic prediction, thereby offering reliable support for precise bandwidth allocation and spectrum planning.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Machine Learning: Clustering

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

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.

Problem

• spatial traffic demand prediction
• neighborhood leakage
• spatial autocorrelation
• 5G/6G planning
• training/testing split

Innovation

• spatial autocorrelation
• context-aware clustering
• error correction
• traffic demand prediction
• 5G/6G planning