Huawei applies machine learning to network control

Huawei has developed a prototype technology involving using machine learning to achieve intelligent, automated network traffic control.

The vendor’s Noah’s Ark Laboratory has announced results of tests into Network Mind, a prototype technology designed to enable automatic detection and accurate prediction of traffic changes on a network, applying optimizations based on service changes.

Huawei said Network Mind can facilitate the management of millions of network elements with millisecond response time.

It uses cutting edge machine learning technologies such as online deep reinforcement learning and real-time big data mining

The technology is being designed for operators and enterprises maintaining ultra-large networks. The prototype was first developed in December last year, and is being tested in collaboration with operators.

Tests indicate that Network Mind is is up to 500% more efficient in realizing KPIs such as task completion or policy generation compared to existing template or heuristic algorithm-based optimization methods.

Network Mind is also over 50 times more efficient when analyzing paths of large optical networks, which has the potential to reduce the time it takes to analyze use cases such as optical network failure prevention from 5 hours to as little as 6 minutes.