Mavenir claims that 40% operational efficiency can be reached using the new AI solution
Network infrastructure provider Mavenir developed an artificial intelligence “operations co-pilot” with Nvidia and Amazon Web Services, which it says shows that generative AI can be used to “effectively define a Service Assurance AI/Ops Platform” and increase operational efficiency for communications service providers.
The AI operations co-pilot for RAN service assurance relies on gen AI and large language models trained on the details of logs, traces, counters and other key performance indicators from network infrastructure, leveraging Mavenir’s Open RAN architecture to “provide accessibility into multiple open interfaces that can deliver the data needed to train and optimize domain-specific telecom LLMs,” the infrastructure provider said. Mavenir said that the new solution can increase operational efficiency for CSPs by as much as 40%. The vendor also added that it is working with Nvidia and AWS to offer a suite of related solutions for the AI co-pilot, for network operations automation.
The solution “significantly reduces manual debugging effort, development and maintenance lead times to enhance IT operations, service availability and delivery for increasingly complex mobile networks,” according to Mavenir.
“Our new Operations Co-Pilot framework has the potential to be a game-changer for operators, delivering a wealth of fault prediction and root cause analysis capabilities with AI-powered accuracy and speed,” said Mavenir’s Chief Technology and Strategy Officer Bejoy Pankajakshan. He added that there are three use cases to start: Core dump analysis, a log similarity search feature and log anomaly detection. “Combining information from these trained LLMs will provide broader and deeper coverage of all fault and anomaly scenarios, enabling very early prediction of potential problems in the network,” Pankajakshan continued. “Moreover, as these solutions evolve, the models have the ability to continuously learn and optimize based on user feedback and iterative training with further logs, KPIs and traces, promising even greater gains.”
