Adaptive Alarm Threshold Prediction in 4G Mobile Networks: A Percentile-Guided Deep Learning Framework with Interpretable Outputs

TL;DR

This paper introduces a deep learning framework for automatically predicting adaptive alarm thresholds in 4G networks, improving accuracy and interpretability over fixed thresholds and previous models.

Contribution

It proposes a novel percentile-guided label derivation strategy and a new PCTN model that outperforms existing methods with fewer parameters and provides interpretable outputs.

Findings

PCTN achieves the best performance on three of four targets.

It outperforms the state-of-the-art iTransformer while using 83% fewer parameters.

The framework enables daily retraining for adaptive threshold adjustment.

Abstract

In mobile telecommunications, alarms act as early warning signals. They are triggered when a cell, the basic unit of radio coverage, shuts down or behaves abnormally. This signals a degradation in service quality, which directly affects the customer experience. To fix the issue, operators rely on preset thresholds to decide when an engineer should be sent out. In practice, these thresholds are set manually and remain fixed regardless of the time of day, traffic levels, or overall network conditions. This often leads to serious faults slipping through during busy hours, while minor issues can cause unnecessary callouts when the network is quiet. This paper presents a machine learning framework that automatically predicts four alarm thresholds, audit window duration, inactive time limit, total fluctuation count, and per hour fluctuation limit, from live network behavior. Since no ground truth labels exist for thresholds, we introduce a percentile guided label derivation strategy and evaluate four models on an anonymized dataset of 10,648 cells across three vendors and nine regions from a real 4G network, comprising a Gradient Boosted Trees baseline, a CNN-BiLSTM with attention, the proposed PCTN, and an iTransformer. PCTN performs the best overall with respect to three of the four targets, outperforming a state-of-the-art iTransformer while using 83 percent fewer parameters. Its mixed output heads and dynamic alpha mechanism produce thresholds that are both accurate and interpretable, allowing operators to inspect and adjust the learned policy without retraining. All comparisons are statistically significant at p < 0.001. The framework undergoes daily retraining using new data, which enables the thresholds to constantly adjust to changes in the network.