Predictive alarm models for improving radio access network robustness

With the widespread expansion of telecommunication networks, the increase in the number and complexity of base stations has led to an exponential growth in the volume of alarms. Traditional alarm prediction based on expert experience or rules has posed significant challenges due to the demand for engineers' expertise and workload. It has become imperative to enhance efficiency by employing data-driven approaches for network alarm prognosis. In this paper, a data-driven alarm prediction model is proposed to support the alarm prognosis in base stations. To improve model performance, the proposed approach utilises ensemble deep learning methods to address the heterogeneity and highly imbalanced alarm dataset. The model is trained and validated using a dataset provided by British Telecom (BT) group. The validation results demonstrate that the proposed method achieves a top-5 accuracy of up to 90% in predicting alarms across 170 categories on the validation set.