Industry’s First Machine Learning-based RAN Application Boosts Spectral Efficiency by 15%
- Capgemini’s
Project Marconi on Intel Architecture delivers outstanding subscriber Quality
of Experience
- Machine
Learning inference enables real time analytics for faster insight and action
Capgemini announced a breakthrough solution giving mobile operators a
significant advantage to monetize 5G services faster. Entitled “Project
Marconi”, the solution conforms to O-RAN (Open Radio Access Network) guidelines
to maximize spectrum efficiency. The solution intelligently boosts subscriber
quality of experience (QoE) with real-time predictive analytics.
Project Marconi is the industry’s first Artificial Intelligence /
Machine Learning (AI/ML) based radio network application for 5G Medium Access
Control (MAC) scheduler. Optimized with Intel AI Software and 3rd
Gen Intel Xeon Scalable processors.
Network providers globally have invested heavily in spectrum and
are looking for solutions to develop and gain 5G services faster. According to
the Global Mobile Suppliers Association, the total value of spectrum auctions
reached over $27
billion in 2020. Capgemini’s solution on
Intel Architecture increases the amount of traffic each cell can handle. It
allows operators to serve more subscribers and deliver an outstanding
experience, while launching new Industry 4.0 services such as enhanced Mobile
Broadband (eMBB) and Ultra Reliable Low Latency Communications (URLLC) use
cases.
Walid Negm, Chief Research and Innovation Officer at Capgemini
Engineering said: “Our teams worked closely with Intel
to create a truly innovative solution that can really move the needle for
operators. We gathered and utilized over one terabyte of data and conducted
countless test runs with NetAnticipate5G to fine-tune the predictive analytics
to meet diverse operator requirements. In short, machine learning can be
deployed for intelligent decision-making on the RAN without any additional
hardware requirement. This makes it cost efficient in the short run and future
proof in the long run as we move into Cloud Native RAN implementations.”
Cristina Rodriguez, VP of Wireless Access Network Division at
Intel said: “Our 3rd Gen Intel Xeon Scalable processors with
built-in AI acceleration provide high performance for deep learning on the Net
Anticipate 5G platform. Together, our collaboration delivered ultra-fast
inference data to enhance the Open-Source ML libraries resulting in an
intelligent RAN that can predict and quickly react to subscriber coverage
requirements while reducing TCO.”
Capgemini deployed its NetAnticipate5G and RATIO O-RAN platform to
introduce advanced AI/ML techniques. The AI powered predictive analytical
solution forecasts and assigns the appropriate MCS (modulation and coding
scheme) values for signal transmission through forecasting of the user signal
quality and mobility patterns accurately. In this way, the RAN can
intelligently schedule MAC resources to achieve up to 40% more accurate MCS
prediction and yield to 15% better spectrum efficiency in the case studies and
testing. As a result, it delivers faster data speeds, better and more
consistent QoE to subscribers and robust coverage for use cases that rely on
low latency connectivity such as robotics-based manufacturing and V2X
(vehicle-to-everything).
Source: Capgemini media announcement