Fujitsu launches the world's first AI application to prevent quality loss in 5G wireless networks: Fujitsu Global

Reduce operating costs, save electricity and ensure a smooth connection during high traffic times

Fujitsu Limited

Kawasaki, Japan, October 15, 2024

Fujitsu today announced the development of an application that uses AI technology to improve the communication quality of mobile networks while achieving energy savings and optimizing network operations. This development is part of the research and development project “Improved Infrastructures for Post-5G Information and Communication Systems” (hereinafter NEDO-led project). ⁽¹⁾ carried out by the New Energy and Industrial Technology Development Organization (NEDO). Fujitsu, which has a successful track record of introducing Radio Unit (RU) products to the global market, will integrate this technology into its O-RAN ⁽²⁾ Compliant Service Management and Orchestration (SMO) ⁽³⁾ System, FUJITSU Network Virtuora Service Management and Orchestration. Fujitsu will gradually introduce the technology to mobile network operators worldwide from November 2024, leveraging the presence it has already established in RU.

This application includes three key technologies:

• An AI-powered technology that can estimate the quality of experience (QoE) of smartphone users on their networks in real time.
• A technology that detects early signs of increased communication traffic and proactively prevents network quality degradation.
• A technology that detects network quality degradation and redefines the area covered by peripheral base stations to maintain optimal quality.

Fujitsu verified the effectiveness of these technologies in August 2024 using real commercial data from mobile network operators ⁽⁴⁾ under conditions very similar to actual operating environments.

This application ensures 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 increasing user comfort, satisfaction and security in critical situations. For mobile network operators, the application will reduce operating costs and save electricity through optimized operations.

background

As digital transformation (DX) accelerates globally, the adoption of 5G mobile networks as a key infrastructure component is rapidly increasing. Mobile network operators are expected to continue improving their capabilities, including ultra-low latency and concurrent connectivity, while ensuring network quality at the user and application levels. Additionally, the Radio Access Network (RAN) space is undergoing an open and virtualized transformation based on the O-RAN concept, resulting in expected reductions in total cost of ownership (TCO).

The three technologies in this application run on the RIC ⁽⁵⁾ Deployed within the O-RAN compatible SMO, contributing to intelligent automation and self-sufficiency of RAN.

Development successes

1. Real-time QoE estimation and quality assurance using AI

This technology estimates QoE in real time and automatically switches users to other base station network areas when QoE degradation is detected. This is a world first that enables the creation of AI models that can easily estimate QoE for individual applications by selecting feature values ​​from statistical data (KPIs) calculated from high-speed packet analysis for 100 Gbps RAN traffic . This approach allows flexible adaptation to different applications.

By accurately understanding each user's QoE and allocating the required resources, this technology ensures user comfort and satisfaction while suppressing excessive resource allocation. This results in a 19% increase in the number of users that can be accommodated per base station ⁽⁶⁾.

Figure 1: QoE estimation based on packet analysis

2. Proactive activation/deactivation of the base station for quality maintenance and energy savings

Fujitsu has developed technology that uses AI to anticipate increased communication traffic and proactively activate previously inactive base stations to prevent degradation in user communication quality.

Previously, energy savings were achieved by monitoring traffic in each area in real time and putting unnecessary base stations into sleep mode. This world-first technology goes one step further by detecting unusual increases in foot traffic, such as those associated with local events, and predicting subsequent traffic increases at the network level ⁽⁷⁾. This predictive technology has been proven to enable successful activation of base stations in advance 99.8% of the time during the verification period without compromising user quality.

This enables pinpoint activation and deactivation of base stations based on traffic conditions and, combined with the power saving application announced by Fujitsu in December 2023, achieves a balance between maintaining QoE and saving energy ⁽⁸⁾.

3. Detecting deterioration in service quality and redesigning the area to maintain service quality

Traditional single cell anomaly detection technologies ⁽⁹⁾ struggled to distinguish between simple load reductions and actual anomalies. Fujitsu's new technology addresses this problem by using AI to compare traffic trends in surrounding cells, achieving an error detection accuracy rate of over 92%. This technology supports both supervised learning with limited error data and unsupervised learning. By understanding service impacts, including cell overlap, it is possible to assess which areas should be restored first.

When this anomaly detection technology identifies areas at risk of significant service loss, it uses a radio propagation prediction model that takes path loss into account ⁽¹⁰⁾ in the real field, in addition to the direction and load conditions of the surrounding cells, to calculate the optimal tilt angle for the surrounding cells. This minimizes the impact on quality of service caused by faulty cells. This has reduced recovery time from anomalies such as device failure, which previously took 24 hours, to less than an hour, minimizing the impact on users.

Figure 2: Detection and recovery of service quality degradation

Future plans

Fujitsu will continue to contribute to the realization of a safer, more secure and sustainable society by providing O-RAN products with AI-centric technologies for networks that support cross-industry applications and services.

• (1)

• (2)

• (3)

• (4)

• (5)

• (6)

• (7)

• (8)

• (9)

• (10)

Press Contacts

All company or product names mentioned herein are trademarks or registered trademarks of their respective owners. The information provided in this press release is accurate as of the date of publication and is subject to change without notice.

Date: October 15, 2024

City: Kawasaki, Japan

Company: Fujitsu Limited