Telstra has deployed a predictive analytics system that uses the company’s operational data to help identify network issues before they occur.
Hadoop is a software project developed in response to the “avalanche” of data now being generated via the internet. It is built to process large amounts of data from terabytes to petabytes and beyond.
Telstra Chief Technical Officer Vish Nandlall, describes the project as creating “one of the largest Hadoop infrastructures in Australia”.
According to Telstra, the aim is “to prevent incidents before they happen, and shorten response times when they do happen through automated response”.
Hadoop will store operational data which Telstra can use to create performance “baselines”. It then compares real-time network data against those baselines. Should network performance fall short, the analytics system triggers targeted warning messages and suggests potential responses.
“Conventional network problem solving generally only responds to events that have occurred,” a Telstra spokesperson said.
The CWU has long argued for a more proactive approach to maintenance at all levels of the Telstra network. It is interested, nevertheless, in the employment implications of this new system and will be pursuing this question with Telstra in the coming weeks.