Vodafone, in partnership with Nokia, has released a machine learning (ML) solution, operating on Google Cloud, to rapidly detect and eliminate network anomalies before they affect Vodafone’s end customers.
Built using Nokia Bell Labs technology, the Anomaly Detection Service automatically recognizes unusual behavior in a mobile cell area. Typically, this behavior, if unnoticed for a prolonged period of time, could affect the quality of service. The solution gives Vodafone engineers the ability to rapidly resolve issues such as congestion on mobile sites, interference, unexpected delays, difficulties in transferring calls between different cells and call setup failures.
Besides anomaly detection, the algorithm also pinpoints patterns of change that allow Vodafone to address performance issues before they affect the customer. The operator forecasts that the anomaly detection service will be able to automatically detect and resolve 80% of mobile network problems and capacity needs.
This new innovative solution is introduced as a part of Vodafone’s strategy to provide customers with the highest quality experience by introducing new, trustworthy and energy-efficient digital tools. The anomaly detection is offered As-a-service model and will be applied to Vodafone 5G and core networks.
Johan Wibergh, Chief Technology Officer at Vodafone, commented: “We are building an automated and programmable network that can respond quickly to our customers’ needs. As we extend 5G across Europe, it is important to match the speed and responsiveness of this new technology with a great service. With machine learning, we can ensure a consistently high-quality performance that is as smart as the technology behind it.”
As Nokia’s Anomaly Detection Service is deployed on Google Cloud, it gives engineers the ability to make quick and informed decisions based on secure and reliable data analysis and enables network data to be streamed to Vodafone’s data analysis platform while simultaneously analyzing data in multiple vendor environments.