An Explainable Failure Prediction Framework for Neural Networks in Radio Access Networks

TL;DR

This paper introduces an explainable framework for neural network-based radio link failure prediction in 5G networks, improving model transparency, reducing complexity, and enhancing performance by leveraging feature importance insights.

Contribution

It presents a novel explainability-guided model refinement framework that integrates with existing predictors, leading to lighter, more interpretable, and more accurate RLF prediction models.

Findings

Weather data has minimal impact on RLF prediction in real datasets.

The refined model achieves 50% fewer parameters and higher F1 scores.

Explainability insights guide effective feature pruning and model simplification.

Abstract

As 5G networks continue to evolve to deliver high speed, low latency, and reliable communications, ensuring uninterrupted service has become increasingly critical. While millimeter wave (mmWave) frequencies enable gigabit data rates, they are highly susceptible to environmental factors, often leading to radio link failures (RLF). Predictive models leveraging radio and weather data have been proposed to address this issue; however, many operate as black boxes, offering limited transparency for operational deployment. This work bridges that gap by introducing a framework that combines explainability based feature pruning with model refinement. Our framework can be integrated into state of the art predictors such as GNN Transformer and LSTM based architectures for RLF prediction, enabling the development of accurate and explainability guided models in 5G networks. It provides insights into the contribution of input features and the decision making logic of neural networks, leading to lighter and more scalable models. When applied to RLF prediction, our framework unveils that weather data contributes minimally to the forecast in extensive real world datasets, which informs the design of a leaner model with 50 percent fewer parameters and improved F1 scores with respect to the state of the art solution. Ultimately, this work empowers network providers to evaluate and refine their neural network based prediction models for better interpretability, scalability, and performance.