FLEXIBLE: Forecasting Cellular Traffic by Leveraging Explicit Inductive Graph-Based Learning

TL;DR

FLEXIBLE introduces an inductive graph-based learning model for cellular traffic forecasting that adapts to dynamic network changes and enables transfer learning, achieving significant accuracy improvements especially with limited training data.

Contribution

The paper presents a novel inductive GNN-based model for cellular traffic prediction that handles dynamic network topologies and supports transfer learning, addressing limitations of previous methods.

Findings

Achieves up to 9.8% performance improvement over state-of-the-art.

Effective in rare-data scenarios with less than 20% of training data.

Handles dynamic base station deployment and removal.

Abstract

From a telecommunication standpoint, the surge in users and services challenges next-generation networks with escalating traffic demands and limited resources. Accurate traffic prediction can offer network operators valuable insights into network conditions and suggest optimal allocation policies. Recently, spatio-temporal forecasting, employing Graph Neural Networks (GNNs), has emerged as a promising method for cellular traffic prediction. However, existing studies, inspired by road traffic forecasting formulations, overlook the dynamic deployment and removal of base stations, requiring the GNN-based forecaster to handle an evolving graph. This work introduces a novel inductive learning scheme and a generalizable GNN-based forecasting model that can process diverse graphs of cellular traffic with one-time training. We also demonstrate that this model can be easily leveraged by transfer learning with minimal effort, making it applicable to different areas. Experimental results show up to 9.8% performance improvement compared to the state-of-the-art, especially in rare-data settings with training data reduced to below 20%.