MegaFon reports successful AI trials to improve transport performance

MegaFon reports successful AI trials to improve transport performance

Russian operator MegaFon has reported the successful use of artificial intelligence to improve its transport network.

The company has given details of trials with NEC on using artificial intelligence (AI) to forecast demand and to schedule preventive maintenance.

“We have verified that significant improvements can be achieved for the planning and operation of transport networks, resulting in more effective use of resources and providing the highest quality services to millions of subscribers,” said Anton Sherbakov, technical director of MegaFon Ural.

The tests used an NEC AI platform called NEC the Wise. The vendor adopted this brand for all its AI services two years ago.

According to the results reported by MegaFon and NEC, the study had an accuracy of over 97% for traffic prediction against actual traffic. “This enables more efficient planning of transport network capacity expansion and helps to reduce expenses for unnecessary infrastructure, while also reducing losses from untimely procurement of equipment,” said the companies.

“The preventive maintenance feature accurately predicts packet loss figures several months in advance for each network device and identifies those that are likely to cause disruptions in services,” they added.

By using this service, MegaFon will be able to prioritise the maintenance of potentially faulty devices.

“Our partnership with NEC aligns with our goals of efficiently improving the planning and maintenance of networks, which is becoming increasingly complex,” said Sherbakov.

Hiroshi Kawada, managing director of St Petersburg-based NEC Neva Communications Systems, said: “We are very pleased to see our services streamline and optimize MegaFon’s network without the need to expend additional resources. We aim to enhance our partnership with MegaFon and to continue delivering the latest innovations to the entire operator network.”

Gift this article