Nokia adds more automation to its Self-Organizing Network software

Automated network operations are growing more critical now, to help communication service providers handle the complexity of 5G networks, Nokia says

Nokia on Tuesday rolled out enhancements to its Self-Organizing Network software, bringing more automation to network operations. The vendor-agnostic software should help communication service providers more easily manage complex 5G networks, Nokia says. 

ZDNet Recommends

Best 5G smartphones available from US carriers: Galaxy Z Fold 2, Note 20 Ultra, and more

It's become standard in 2020 for mid-range and flagship phones across all major US wireless carriers and most new phones incorporate 5G technology.

Read More

Prior versions of the software automated some time-consuming tasks for network operators, "but you still needed individuals to decide which part of the networks needed to be optimized," Brian McCann, Chief Product Officer for Nokia Software, said to ZDNet, "to identify a problem, to identify the right solution and verify that it fixed the problem and monitor the outcome."

Prior versions of the software automated some time-consuming tasks for network operators, "but you still needed individuals to decide which part of the networks needed to be optimized," Brian McCann, Chief Product Officer for Nokia Software, said to ZDNet, "to identify a problem, to identify the right solution and verify that it fixed the problem and monitor the outcome."

The latest release uses machine learning to detect network issues and self-correct any deviations based on a set of defined objectives, such as latency or throughput levels. It can also leverage insights to further improve the solution itself. 

That should help as 5G deployments increase, McCann said. 

"There's a lot of opportunity with 5G, but it's a much of a real-time environment, so the reduction and almost elimination of human interaction is really a requirement," he said. 

The software has a vendor-agnostic network slice management function to automate the radio slice life cycle and resource optimization. Its machine learning capabilities will allow it to optimize each slice separately to ensure better network availability and quality.