Nokia, in collaboration with Amazon Web Services (AWS), has just deployed the first advanced industrial network segmentation solution powered by agentic AI on an operational 5G connectivity network. The targeted 5G segmentation innovation combines Nokia’s advanced network management with AWS’s AI platform technologies to empower telecom providers to deliver premium services where and when they are needed. du and Orange are the first to explore this innovation in their respective networks.
Nokia’s innovative AI network segmentation solution, powered by AWS, uses agentic AI to analyze real-world internet data, including locations, events, traffic, incidents and maps, enabling telecom providers to offer adaptive network segmentation. This agentic AI-powered approach unlocks significant customer value across diverse applications and use cases by creating premium services that intelligently respond to dynamic conditions, ensuring optimal performance where and when customers need it.
Telecommunications providers may face challenges optimizing network performance during unpredictable events, such as traffic spikes, emergencies, or mass gatherings, which can result in suboptimal quality of service and inefficient resource utilization. Autonomous network segmentation intelligence dynamically adapts and manages even the most challenging traffic conditions in diverse geographic areas.
Pallavi Mahajan, Chief Technology and AI Officer at Nokia, commented: “This innovation marks an important milestone in the evolution of AI-native networks. By combining Nokia’s advanced network slicing capabilities with agentic AI, we are enabling operators to offer premium, goal-oriented services that dynamically adapt to real-world conditions. Nokia is driving connectivity by unlocking new sources of value for telecom providers and supporting next-generation applications and differentiated services for businesses, industries and consumers.”
Intelligent and aware network segmentation
“Network slicing has long promised to unlock new revenue streams for operators, but manual configuration and static policies have prevented end customers from accessing on-demand provisioning,” said Amir Rao, global director of GTM and Telco Solutions at AWS. “By integrating agentic AI capabilities through Amazon Bedrock with the Nokia app, operators can now deliver intelligent, context-aware network segmentation that dynamically responds to real-world conditions, from traffic spikes to emergency situations. This transforms network segmentation from a technical capability to a true business enabler, allowing operators to monetize their 5G investments through differentiated, premium services that automatically adapt to customer needs. “Agentic network slicing is the beginning of an era that will enable telecom providers to enable real-time, goal-oriented service provisioning to end customers.”
Agentic AI Segmentation
This 5G-Advanced network segmentation innovation powered by agentic AI can be used for different use cases, including:
• Target-driven enterprise and industrial segmentation measures real-time network KPIs, such as bitrate and latency, and autonomously adjusts RAN (Radio Access Network) policies to meet enterprise SLAs across campuses, business parks, and urban areas. The innovation enhances premium segmentation services for critical applications in manufacturing, IoT, drones, smart cities, hospitals, energy, transportation and ports.
• On-demand segmentation with agentic AI boosts network performance for select 5G base stations. When activated by external data, this service provides emergency services and public safety authorities with improved network connectivity during emergencies. On-demand network segmentation with agentic AI preserves quality of service for premium 5G+ and FWA customers using gaming, streaming, XR, and AI applications in response to large traffic spikes, weather conditions, and environmental changes.
• Agentic AI for mass events provides much higher capacity availability during times of high demand such as concerts and sporting events. AI analyzes network data, infers patterns, and sets segmentation policies for scheduled events, optimizing premium 5G segmentation for VIP spectators, paying apps, fan engagement, video streaming, and operational teams in stadiums, parks, and conference centers.
“We are excited to be one of the first to pilot this innovative solution on a live network. Agentic AI-powered segmentation will allow us to offer premium, highly responsive services to our customers, whether for critical business applications or enhanced consumer experiences,” said Saleem Alblooshi, Chief Technology Officer at du.
“Orange is committed to driving innovation in 5G, and this experimentation demonstrates how AI can transform network operations. With targeted segmentation, we can anticipate customer needs and offer personalized services that meet the demands of diverse use cases, from mission-critical applications to immersive entertainment,” said Atoosa Hatefi, Director of Radio and Environment Innovation at Orange.
5G-Advanced network segmentation powered by agentic AI can be used for different use cases
Nokia’s solution powered by agentic AI on AWS introduces goal-oriented network segmentation that continuously monitors network KPIs, infers real-world contextual data from multiple sources, and automatically adjusts RAN policies to meet service level agreements. Comprehensive innovation in advanced 5G network segmentation across the entire infrastructure, from spoke to core, primarily employs Nokia’s AirScale 5G base station, MantaRay SMO and agentic AI modules, which are seamlessly integrated with the Amazon Bedrock AI platform.
Agentic AI modules that interact
The integrated solution uses agentic AI to coordinate data analysis, inference and RAN policies. These AI agents leverage open internet data – including events, schedules, incidents, traffic, locations, maps and weather – for different network segmentation use cases. Agentic AI modules operate in multiple modes: chatbot, on-demand, scheduled, and autonomous. All modules interact with Amazon Bedrock through APIs. Additionally, applications and use cases powered by agentic AIs are enhanced with Nokia’s Edge Slicing solution, bringing cloud applications and workloads directly to users and mobile devices over high-capacity, secure and low-latency networks.
Amazon Bedrock enables intelligent network optimization by providing access to foundational models and the infrastructure to build specialized AI agents. These intelligent agents analyze RAN history and contextual data to improve the performance of the entire mobile network infrastructure. Using Amazon EKS hybrid nodes, telecom providers can deploy these network agents and workloads into their existing infrastructure while unifying Kubernetes management across cloud and edge environments, providing the flexibility and scalability needed for modern network operations.
