Understanding university campus network reliability characteristics using a big data analytics tool

Understanding the health of a network via offline outage and failure analysis is important to assess the availability of the network and understand the pattern of failures and the root cause of them for the future network reliability improvement. In this paper, we perform a university campus network outage and failure analysis (UMKC access network) that has not been investigated well due to the lack of effective methodologies. We used Splunk, one of the big data analysis tools, to effectively handle the sheer amount of node outage and link failure log data and topology information. We investigate the network reliability characteristics via SNMP and syslog data, causes of failures, and their impact. Our study shows that the general characteristics of the different layers are very distinct from each other and the wireless network is less reliable compared to the wired network and is affected by the performance of the wired network.