As telecom operators continue to explore smarter network management, Ericsson has introduced a new software subscription called AI in RAN, designed to bring artificial intelligence capabilities directly into 5G radio access networks.
The new software enables AI-powered functions to run within basebands and radios without requiring operators to install additional hardware. Ericsson said the first AI in RAN features will be available from Q2 2026, with further enhancements planned later in the year.
Built for Ericsson 5G Advanced across purpose-built RAN and Cloud RAN platforms, the software applies AI models to improve network performance, energy efficiency, automation, and operational intelligence. It uses Ericsson Silicon for AI inference in radios and the latest generation of RAN Compute infrastructure, while Cloud RAN software portability supports deployment across partner platforms.
The solution includes several AI-driven capabilities such as AI-native scheduling for link adaptation, AI-powered macro positioning, AI-managed beamforming, multi-layer coordination, performance management event schema files, and enhanced observability features.
According to Ericsson, the AI models are designed for microsecond-level inference, enabling real-time decision-making in low-latency network environments. The company said the models were developed using domain expertise and trained on high-quality datasets to adapt to changing network conditions.
The launch follows earlier collaboration between AT&T, Ericsson, and Intel, where AI-native link adaptation on a Cloud RAN platform powered by Intel Xeon 6 SoC demonstrated up to 20% higher throughput compared to traditional rule-based systems.
Ericsson reported more than 15 deployments and trials globally. The company stated that the technology delivered up to 20% higher downlink throughput, up to 10% better spectral efficiency, support for up to 2 times more high-traffic users, 90% to 95% coverage prediction accuracy, and up to 5 times greater user-positioning precision.
The company has also worked with operators including SoftBank, Bell, SK Telecom, Rogers, and Optus to test and deploy AI-powered network optimisation capabilities. Operators highlighted benefits related to spectrum efficiency, energy savings, low-latency services, and preparation for future AI-native 6G networks.
Ericsson has been integrating AI into its network portfolio since the 4G era. In February 2026, the company introduced Neural Network Accelerators in its Massive MIMO radios, which it said increased AI inference capability by 10 times.
Also read: Viksit Workforce for a Viksit Bharat
Do Follow: The Mainstream LinkedIn | The Mainstream Facebook | The Mainstream Youtube | The Mainstream Twitter
About us:
The Mainstream is a premier platform delivering the latest updates and informed perspectives across the technology business and cyber landscape. Built on research-driven, thought leadership and original intellectual property, The Mainstream also curates summits & conferences that convene decision makers to explore how technology reshapes industries and leadership. With a growing presence in India and globally across the Middle East, Africa, ASEAN, the USA, the UK and Australia, The Mainstream carries a vision to bring the latest happenings and insights to 8.2 billion people and to place technology at the centre of conversation for leaders navigating the future.