Call Detail Records Driven Anomaly Detection and Traffic Prediction in Mobile Cellular Networks

TL;DR

This paper leverages call detail records and machine learning techniques to detect network anomalies and improve traffic prediction in mobile cellular networks, enhancing network management and planning.

Contribution

It introduces a novel approach combining unsupervised clustering, neural networks, and ARIMA models for anomaly detection and traffic forecasting using CDR data.

Findings

Anomaly detection with k-means effectively identifies network issues.

Anomaly-free data improves neural network training and prediction accuracy.

ARIMA models perform better on cleaned, anomaly-free data.

Abstract

Mobile networks possess information about the users as well as the network. Such information is useful for making the network end-to-end visible and intelligent. Big data analytics can efficiently analyze user and network information, unearth meaningful insights with the help of machine learning tools. Utilizing big data analytics and machine learning, this work contributes in three ways. First, we utilize the call detail records (CDR) data to detect anomalies in the network. For authentication and verification of anomalies, we use k-means clustering, an unsupervised machine learning algorithm. Through effective detection of anomalies, we can proceed to suitable design for resource distribution as well as fault detection and avoidance. Second, we prepare anomaly-free data by removing anomalous activities and train a neural network model. By passing anomaly and anomaly-free data through this model, we observe the effect of anomalous activities in training of the model and also observe mean square error of anomaly and anomaly free data. Lastly, we use an autoregressive integrated moving average (ARIMA) model to predict future traffic for a user. Through simple visualization, we show that anomaly free data better generalizes the learning models and performs better on prediction task.