A Fault Management Preventive Maintenance Approach in Mobile Networks using Sequential Pattern Mining

Mobile networks' fault management can take advantage of Machine Learning (ML) algorithms making its maintenance more proactive and preventive. Currently, Network Operations Centers (NOCs) still operate in reactive mode, where the troubleshoot is only performed after the problem identification. The network evolution to a preventive maintenance enables the problem prevention or quick resolution, leading to a greater network and services availability, a better operational efficiency and, above all, ensures customer satisfaction. In this paper, different algorithms for Sequential Pattern Mining (SPM) and Association Rule Learning (ARL) are explored, to identify alarm patterns in a live Long Term Evolution (LTE) network, using Fault Management (FM) data. A comparative performance analysis between all the algorithms was carried out, having observed, in the best case scenario, a decrease of 3.31% in the total number of alarms and 70.45% in the number of alarms of a certain type. There was also a considerable reduction in the number of alarms per network node in a considered area, having identified 39 nodes that no longer had any unresolved alarm. These results demonstrate that the recognition of sequential alarm patterns allows taking the first steps in the direction of preventive maintenance in mobile networks.