Google Cloud released a series of Mobile World Congress updates in a bid toward autonomous telecommunications networks, outlining tools for greater automation in carrier operations.

A key element of the update is expanded support for data platforms, reinforcing so-called level-four and level-five network autonomy, in which systems can identify, diagnose, and remediate faults independently.

In a blog post, Muninder Sambi, Google Cloud’s VP and GM of networking, and principal engineer Dave Weissman, explained: “To do this, the underlying data platform must be as dynamic as the network itself.

“Over the last year, we’ve evolved our Cloud Spanner Graph and Vertex AI to handle the ‘dual nature’ of telcos: the need for high-speed, real-time response for alarm correlation, combined with deep, historical pattern detection. Today, we’re refining our platform to support these autonomous operations," the duo wrote.

The company also described advances to its “network digital twin,” a software-based model designed to represent a carrier’s physical and logical infrastructure and allow analysis of current and past network conditions. The network digital twin evolved from a static map to a dynamic, temporal graph, capturing the network's live physical, logical, and real-time performance and fault states.

The duo also explained that by leveraging Spanner Graph for digital twins and federated graph analytics through BigQuery, telecom operators can interoperate between real-time updates and deep historical analysis without complex and slow extract, transform, and load processes.

Google Cloud announced that operators can now train graph neural networks (GNNs) on their network digital twin data in Vertex AI. They can then use the trained GNN models with Spanner’s ML.PREDICT capability and the real-time data in the network digital twin to move from monitoring to predicting, mathematically tracking how a failure might grow, and resolving it before it impacts subscribers.

“The agentic AI era is here. By embedding AI into the fabric of a telco’s network, we’re helping operators transform from connectivity utilities into intelligent service providers that continue to delight customers,” the duo outlined.

These announcements follow from the company’s Autonomous Network Operations framework, which it introduced last year and focus on software agents intended to detect network issues, analyze their causes, and initiate corrective actions with limited human involvement.

Nokia, One NZ, Deutsche Telekom, and Vodafone collaborations

Google Cloud unveiled its Nokia partnership in a bid to make networks fully programmable by turning complex technical code into AI agents that understand everyday language. This promises to see telecom operators simply asking the network to perform complex tasks – like prioritizing network resources for critical services like emergency response or remote health care – without any manual engineering.

In another collaboration, Google Cloud is working with New Zealand-owned operator One NZ on testing AI-based agents for tasks such as traffic rerouting and automated network adjustments. The company said the initiatives are aimed at reducing reliance on manual processes within legacy systems.

Google Cloud said that operators, including Deutsche Telekom and Vodafone, are already working with its platform to streamline operations.