AUTONOMAS FAULT DIAGNOSIS SYSTEM FOR CELLULAR NETWORKS BASED ON HIDDEN MARKOV MODEL

Automated diagnosis and Troubleshooting (TS) in Radio Access Networks (RAN) of cellularsystems are basic management tasks, which are required to guarantee efficient use of networkresources. In this paper, we investigate the usage of machine learning techniques: stochasticmethods and discriminant analysis for automating these TS tasks. Our proposed framework is basedon Hidden Markov Model (HMM), Principle Component Analysis (PCA) and Fisher LinearDiscriminant (FLD) techniques. In a learning phase, symptoms relating to faults in the network areextracted from a network management system (NMS). Then they are used to create a fault model.This model is used to identify the unknown faults using a nearest neighbor classifier. Reportedresults for the automated diagnosis using live RAN measurements illustrate the efficiency of theproposed TS framework and its importance to mobile network operators.