Ericsson NetCloud Targets Enterprise Data Requirements

Network equipment manufacturer Ericsson has integrated large language models (LLMs) into its NetCloud management platform, marking a shift in how enterprises manage their networks.
The Stockholm-based telecommunications company has developed its network management system to operate entirely within its infrastructure, rather than connecting to external AI services through application programming interfaces (APIs).
This development comes as data centre operators face increasing pressure to manage hybrid cloud environments and remote access infrastructure, whilst maintaining security across distributed networks.
Ericsson’s system, called ANA (AI-based NetCloud Assistant), processes network data alongside technical documentation to generate configuration recommendations.
It operates without exposing sensitive network information to third-party services - a key consideration for data centre security protocols.
Deploying internal language models to improve security
Network administrators can now receive configuration instructions based on established practices when deploying wide area network edge devices, a process that previously required manual review of technical documentation.
- Ericsson has integrated LLMs into its NetCloud platform for enterprise network management, hosting the models internally rather than using external APIs like ChatGPT
- The system, called ANA (AI-based NetCloud Assistant), combines network data with technical documentation to automate troubleshooting and configuration tasks
- The platform uses an "agentic architecture" where multiple AI agents work in parallel to solve complex network problems
- A new feature will translate plain English business requirements into technical network policies automatically
The platform includes software-defined wide area network (SD-WAN) support - a technology that enables enterprises to connect data centres and branch offices across geographic locations using multiple connection types.
Ericsson's system assists with troubleshooting connectivity issues across SD-WAN and security gateways, eliminating requirements for manual port scanning and speed testing procedures in data centre environments.
The network operations dashboard is available to customers using NetCloud SASE (Secure Access Service Edge) - a network architecture that combines security functions with WAN capabilities - and NetCloud Exchange services with appropriate licensing.
A new feature translates business requirements into network policies, interpreting plain language descriptions of business needs to generate corresponding traffic management rules for data centre networks.
This capability reduces the time network administrators spend correlating information from multiple sources when implementing new configurations or troubleshooting existing systems.
Monitoring business performance
Ericsson's operations dashboard establishes baseline measurements for network traffic patterns. The system monitors variations in network performance metrics including latency - the time taken for data to travel between points - and jitter, which measures consistency in data transmission.
The dashboard identifies anomalies by severity and pinpoints affected sites, users and applications before providing analysis of root causes such as application server performance issues or network congestion.
“These insights in cellular network performance and application quality of experience empowers IT teams to proactively address issues to ensure optimal network operations,” Ericsson states in its technical documentation.
The system incorporates what Ericsson terms an "agentic architecture" where multiple AI systems operate in parallel to manage complex network tasks. This architecture enables virtual experts to execute and verify multiple operations simultaneously across networking environments.
For each detected issue, the system calculates potential impact across network infrastructure and suggests remediation steps, providing network administrators with actionable responses to performance degradation.
The platform also monitors variations in network performance metrics and establishes baseline measurements for traffic patterns, enabling early detection of potential issues before they affect data centre operations.
Ericsson plans to release the dashboard for wireless WAN customers in the first half of 2025. The system currently identifies latency and jitter anomalies specific to each customer's network infrastructure, with packet loss detection planned for future releases.
“AI is part of an evolution. It will contribute in the future and we are seeing that contribution starting already today,” says Keijo Mononen, Head of Security Solutions at Ericsson.
“What Gen AI will bring is an evolution of security toward the future, where you can actually detect new things with AI.”
Explore the latest edition of Data Centre Magazine and be part of the conversation at our global conference series, Tech & AI LIVE and Data Centre LIVE.
Discover all our upcoming events and secure your tickets today.
Data Centre Magazine is a BizClik brand