Detecting and predicting outages in cellular networks
Modern cellular networks are complex systems offering a wide range of services and present challenges in detecting anomalous events when they do occur. The networks are engineered for high re- liability and, hence, the data from these networks is predominantly normal with a small proportion being anomalous. Froman operations perspective, it is impor- tant to detect these anomalies in a timely manner, and to correct vulnerabilities in the network and preclude the occurrence of major failure events. The objective of our work is anomaly detection in cellular networks in near real-time to improve network performance and reliability. The communications traffic on the network generates large amounts of metadata on a continuous basis across the various servers involved in the commu- nication session. We use performance data from a 4G LTE network to develop a methodology for anomaly detection in such networks. The models developed use non-parametric (Chi-Square tests) and parametric (Gaussian Mixture Models) approaches. These models are trained to detect differences between distributions to classify a target distribution as belonging to a normal period or abnormal period with high accuracy. We dis- cuss the merits between the approaches and show that both provide a more nuanced view of the network than simple thresholds of success/failure used by operators in production networks today.