The tool estimates a user’s quality of experience (QoE) in real time, intuitively detecting network issues and seamlessly switching to a more reliable connection.
Having verified the tool’s effectiveness using real commercial data from mobile network operators, Fujitsu plans to conduct a global rollout of the AI solution to mobile network operators starting in November 2024.
Subscribe today for free
“This application will ensure a seamless and reliable connection for mobile network users, not only during normal operations but also during emergencies and periods of increased network traffic, ultimately enhancing user convenience, satisfaction, and safety in critical situations,” Fujitsu said in a statement. “For mobile network operators, the application will reduce operational costs and save power through optimised operations.”
Fujitsu’s new AI wireless network tool covers three key areas.
The first enables it to estimate QoE and automatically switches users to other base station network areas when degradations are detected.
In what the company claims is a world-first, the AI-powered detection solution can estimate QoE for individual applications by analysing feature values from statistical data calculated from high-speed packet analysis for 100 Gbps RAN traffic.
By understanding the QoE for each user and subsequently reassigning resources, Fujitsu suggested the technology will maintain user satisfaction while simultaneously suppressing excessive resource allocation.
Tests of the solution showed a 19% increase in the number of users that can be accommodated per base station, according to Fujitsu.
The second area Fujitsu’s AI network tool covers is base station activations.
The solution’s AI system can anticipate increased communication traffic and proactively activate previously dormant base stations to prevent quality degradation.
The solution would enable operators to pinpoint the activation and deactivation of base stations based on traffic conditions, helping to reduce energy usage by placing unnecessary base stations into sleep mode.
Fujitsu suggested the predictive part of the AI solution can successfully activate base stations in advance without impacting user quality 99.8% of the time.
The final of three points Fujitsu’s new AI networking solution covers focuses on anomaly detection.
The AI tool can identify areas undergoing significant service impact by comparing traffic trends across surrounding cells.
The solution achieves a fault detection accuracy rate of over 92%, providing operators with improved views of service impacts, and enabling them to judge which areas should be recovered first.
Fujitsu plans to add the AI solution to its O-RAN products, including its Service Management and Orchestration (SMO) system and Network Virtuora Service Management and Orchestration offerings.
RELATED STORIES
How AI is transforming networks: The future of smart connectivity
Fujitsu and university ‘cut qubits needed for quantum computing’
