Vodafone, in partnership with Nokia, has introduced a new machine learning (ML) algorithm to its pan-European mobile networks to detect and correct anomalies before they impact customers, the U.K. carrier said in a release.
Based on Nokia Bell Labs technology, the Anomaly Detection Service autonomously detects if a mobile cell area is showing out of the ordinary behavior which, if allowed to go undetected for an extended period, could impact the quality of service to customers. This new technology allows Vodafone engineers to address issues faster such as congestion at a mobile site, interference, unexpected latency, difficulty in handing calls between different cells or call setup failures, Vodafone said.
In addition to detecting anomalies, the algorithm also identifies patterns of change to allow Vodafone’s operating companies to address issues before they impact the customer. Once active, Vodafone expects the new service to support its ambition to automatically detect and address 80% of all anomalous mobile network issues and capacity demands.
With support from Vodafone, Nokia’s Bell Labs algorithm has been tested on the live network to demonstrate its accuracy and to ensure that it works with equipment from all network vendors. Following the initial deployment in Italy on more than 60,000 4G cells, Vodafone aims to extend the service to all its European markets by early 2022.
Johan Wibergh, CTO at Vodafone, said: “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.”
Raghav Sahgal, Nokia’s President of Cloud and Network Services, said: “We are pleased to celebrate the first commercial deployment of our solution with Vodafone, running on the public cloud. By analyzing network data our machine-learning algorithms can detect anomalies impacting network operations and performance, helping Vodafone engineers to pre-empt and rapidly resolve issues.”
Vodafone noted that the new solution runs natively on the public cloud, streaming data to Vodafone’s analytics platform, enabling the analysis of aggregated and anonymised network data from various points across multi-vendor environments all at once, rather than processing single variables independently. The solution can extract temporal patterns from the analyzed system to categorize network behavior and find anomalies. Anomaly detection is offered “as-a-Service” as part of Nokia’s Cloud Support Services with plans to add support for core and 5G networks and near real-time monitoring capabilities for operations
The post Vodafone and Nokia develop ML system to detect network anomalies appeared first on RCR Wireless News.