Company Demonstrates New Industry Standard with Unprecedented AI/ML Milestone Proven in Live Open RAN Deployments with South Asian Mobile Operators

RICHARDSON, Texas, Feb. 27, 2025 (GLOBE NEWSWIRE) -- Mavenir, the cloud-native network infrastructure provider building the future of networks, today announced a groundbreaking achievement with its full-stack AI framework, Network Intelligence as a Service (NIaaS). For the first time globally, deep reinforcement learning (RL)-based live AI Agents – an integral component of Mavenir’s NIaaS – are autonomously controlling and performing full-closed-loop optimization for operational 5G non-standalone (NSA) networks, delivering over 40% gains in key performance indicators (KPIs) related to mobility in radio access networks (RAN). The significant performance gains were also cost-effective, since NIaaS runs only on CPUs in the field rather than GPUs. Hosted in Mavenir’s RAN Intelligent Controller (RIC), NIaaS has proven these milestones in live Open RAN deployments with two Tier 1 5G NSA operators in South Asia, with each deployment corresponding to 25+ sites and 100+ LTE and New Radio (NR) cells.

Presenting the first-of-its-kind telco AI capability for large-scale Open RAN operations, Mavenir’s NIaaS has significantly reduced the rate of unstable handovers (including mobility ping-pongs, too-late handovers, too-early handovers, radio link failures and wrong-cell handovers) by 40% to 60% for the aggregate KPI and individual KPI components, thereby improving the mobility robustness of 4G/5G mobile subscribers in the live networks.

"We are thrilled to lead the industry with our innovative NIaaS that is revolutionizing telecom network operations," said BG Kumar, President, Access Networks, Platforms, and Digital Enablement at Mavenir. "While traditional SON systems are too functionality-centric, without any guarantees of tangible improvement of the target KPIs in the field, our AI-native NIaaS is KPI-centric, extracting deep-dive intelligence about the KPIs from cell-to-cell, site-to-site, market-to-market, and precisely optimizing those factors impacting the KPIs in the live network. This achievement underscores our commitment to leveraging cutting-edge technologies and our in-house skillset of inventing, innovating and designing state-of-the-art AI/ML models to drive tangible improvements in network performance and customer experience," added Kumar.

Looking ahead, Mavenir’s NIaaS will focus on consistently improving other operational Telco KPIs, such as connectivity, coverage, traffic management, accessibility, retainability, traffic quality, efficiency and CAPEX/OPEX. Though hosted in Mavenir RIC for the Open RAN deployments, NIaaS is also offered as a stand-alone telco intelligence capability for other domains (such as Packet Core, IMS, etc.). Moreover, NIaaS is not only confined to offering telco AI capabilities in markets with Mavenir network functions (NFs), but also to markets with third-party NFs as well.

Mavenir NIaaS thus represents a significant leap forward in live telco AIOps, providing operators with AI-native tools to enhance network efficiency, reduce operational costs, and deliver superior service quality to their customers. As the telecom industry continues to evolve, Mavenir remains at the forefront of innovation, dedicated to pushing the boundaries of what is possible with AI/ML technologies.

Mavenir’s NIaaS hosts state-of-the-art AI suite including Deep-RL AI Agents – developed by Mavenir – that are blended with transfer learning to autonomously control and optimize mobility offsets across LTE cells, reducing network-wide unstable handovers. These Deep-RL AI Agents for optimization are significantly aided by other agents & models in full-stack AI suite of NIaaS. For example, AI causation and explainability models help in identifying and quantifying the root causes of unstable handovers and mobility KPI degradations, and data clustering and classification models help in correlating radio frequency, mobility, traffic, and other observability patterns across cells and across time, towards evaluating the net effect. The Deep-RL AI Agents address these factors and account for the effect, optimizing the mobility thresholds autonomously in the field.

About Mavenir:

Mavenir is building the future of networks today with cloud-native, AI-enabled solutions which are green by design, empowering operators to realize the benefits of 5G and achieve intelligent, automated, programmable networks. As the pioneer of Open RAN and a proven industry disruptor, Mavenir’s award-winning solutions are delivering automation and monetization across mobile networks globally, accelerating software network transformation for 300+ Communications Service Providers in over 120 countries, which serve more than 50% of the world’s subscribers. For more information, please visit www.mavenir.com

Meet Mavenir at Mobile World Congress 2025, Barcelona, Mar 3-6, 2025.

To explore Mavenir’s latest innovations and learn more about how Mavenir is delivering the Future of Networks – Today, visit us in Hall 2 (Stand 2H60) at #MWC25.

Mavenir PR Contact:
Emmanuela Spiteri
PR@mavenir.com