A Generalized Transformer-based Radio Link Failure Prediction Framework in 5G RANs

TL;DR

The paper tackles radio link failure prediction in 5G RANs under weather effects by introducing GenTrap, a generalized framework that jointly learns spatial weather context and temporal KPI-weather dynamics. It combines a learnable GNN weather-aggregation module with a time-series transformer to encode both the spatial relationships between radio links and surrounding weather stations and the long-range temporal dependencies of KPIs and weather observations. Empirical results on urban and rural Turkcell datasets show GenTrap achieving superior F1-scores and strong generalization to unseen links, and demonstrate that applying the GNN aggregation to existing models further improves performance. The work highlights practical implications for predictive maintenance in 5G networks and provides a prototype implementation for broader adoption. The approach offers a scalable, topology-robust path to mitigate weather-induced RLFs in dense mmWave deployments and beyond.

Abstract

Radio link failure (RLF) prediction system in Radio Access Networks (RANs) is critical for ensuring seamless communication and meeting the stringent requirements of high data rates, low latency, and improved reliability in 5G networks. However, weather conditions such as precipitation, humidity, temperature, and wind impact these communication links. Usually, historical radio link Key Performance Indicators (KPIs) and their surrounding weather station observations are utilized for building learning-based RLF prediction models. However, such models must be capable of learning the spatial weather context in a dynamic RAN and effectively encoding time series KPIs with the weather observation data. Existing works fail to incorporate both of these essential design aspects of the prediction models. This paper fills the gap by proposing GenTrap, a novel RLF prediction framework that introduces a graph neural network (GNN)-based learnable weather effect aggregation module and employs state-of-the-art time series transformer as the temporal feature extractor for radio link failure prediction. The proposed aggregation method of GenTrap can be integrated into any existing prediction model to achieve better performance and generalizability. We evaluate GenTrap on two real-world datasets (rural and urban) with 2.6 million KPI data points and show that GenTrap offers a significantly higher F1-score (0.93 for rural and 0.79 for urban) compared to its counterparts while possessing generalization capability.

Figures (11)

• Figure 1: An example of 5G RAN deployment.
• Figure 2: Transformer module for time-series representation learning.
• Figure 3: Impact of precipitation on radio link failure.
• Figure 4: GenTrap architecture.
• Figure 5: LSTM+ architecture.