A new NBN initiative will use a range of open source projects including Apache SPARK, Kafka, Flume, Cassandra and JanusGraph to help analyse and improve the end user experience on the National Broadband Network.
The government-owned company today announced it was launching a new ‘Tech Lab’, which it hopes will provide insights into pain points for customers on its network and help resolve faults sooner.
NBN said the lab will employ machine learning techniques and software including RStudio, H2O.ai and ArangoDB, and leverage Amazon’s public cloud services.
For example the lab will help determine whether a fault encountered by an end user on the network can be remedied remotely or whether a technician needs to be dispatched, cutting resolution times.
The end user experience on the NBN is currently being studied by the Australian Communications and Media Authority.
“Our Tech Lab sees us utilising existing capability to solve a complex problem and will help provide us with crucial insights about the way people are using the NBN network,” NBN’s chief systems engineering officer, John McInerney, said in a statement.
McInerney, NBN’s chief information officer, was appointed CSEO earlier this year, heading up the company’s new Systems Engineering and Operations team.
The Tech Lab will operate as a ‘virtual team’ based in Melbourne and Sydney.
“Developing these insights will help enrich the customer experience of services over the NBN access network and make our systems and processes more agile by synthesising massive data sets,” McInerney said.
“Once the investigation and implementation of the Tech Lab research is complete we could, for example, easily identify trends that occur in a failed activation in order to preempt problems before arriving at a house.
“Faults are an inevitable part of any technology network but minimising the disruption is key to improving the experience. We expect to see significant improvements as a result of early detection and quick resolution.”