Aira Technologies and VMware, in Collaboration with Intel, Demonstrate World’s first xApp to Dramatically Improve 5G MU-MIMO Efficiency and Throughput using AI

Aira Technologies, a pioneer in the application of Machine Learning (ML) to radically improve wireless telecommunications, announced that it plans to deliver a near-real time application (xApp) that will work in concert with the VMware RAN Intelligent Controller (RIC) platform to deliver advanced 5G RAN capabilities that have long been requested by the TIP RIA sub-group of the TIP Open RAN 5G NR Project Group. The TIP RIA subgroup is led by Vodafone, BT and T-Mobile USA.

Aira has used sophisticated ML techniques to develop the industry’s first xApp to enable better channel estimation and unprecedented channel prediction performance to help maximize downlink throughput and range. The Intel FlexRAN reference software, with a software based L1, provided the flexibility to tap into the right part of the L1 to enable the xApp. Accurate channel prediction helps minimize inter-user interference to maximize multi-user MIMO performance.

“The application of ML to wireless baseband processing in this fundamental manner is an industry first. Together with VMware, we are showcasing three very important things – the power of the Open RAN movement to accelerate innovation; the extraordinary potential for ML in cutting edge wireless applications; and, the enormous potential for the RIC and consequently the ability to improve the RAN through xApps and rApps,” said Anand Chandrasekher, Founder and CEO of Aira Technologies.

Recommended AI: Millennium Physician Group and Navina Release Value-Based Results of Technology Implementation

“Radio Access Networks (RAN) operate in varied network conditions and radio environments. ML presents a natural framework to classify these conditions accurately and process the RAN signals optimally for each of these conditions. We are seeing tremendous MU-MIMO throughput gains from our ML-based channel prediction xApp and we are working on applying our ML framework to other RAN functionalities,” said Ravikiran Gopalan, Founder and CTO of Aira Technologies.

VMware’s RIC is designed for service providers to harness programmability and modernize their RAN architecture. This enables service providers to rapidly deploy new and innovative technologies like ML and leapfrog into a new age of user experience and network efficiency. This modern approach decouples RAN intelligence from the data plane and allows for the control and management functions to be performed through xApps and rApps running on the VMware RIC, empowering the service provider to customize their RAN for their own unique business needs and priorities. Aira has chosen to integrate their channel estimation and projection xApp using the VMware RIC SDK to meet the critical timing requirements of baseband processing.

“VMware has been an industry leader in the RIC arena. We believe strongly in the potential for accelerating innovation and monetization of the RAN through network programmability via the RIC platform. We are extremely proud of our work together with the Aira team and commend them on this breakthrough capability. We are excited to work with them to showcase this capability and are looking forward to bringing these and other innovations to market this year,” said Lakshmi Mandyam, Vice President, Product Management and Partner Ecosystems, Service Provider and Edge, VMware.

Recommended AI: Stability AI Partners With Krikey AI to Launch AI Animation Tools

The Intel Xeon platform and their Intel FlexRAN reference platform, along with CapGemini’s L2 and L3 software platforms provided crucial building blocks, and facilitated easy incorporation of Aira’s cutting edge ML technology.

“Machine learning is poised to enhance the operation of virtualized radio access networks, providing new energy and performance efficiencies,” said Cristina Rodriguez, Vice President and General Manager, Wireless Access Networking Division at Intel. “Leveraging Intel Xeon processors and Intel FlexRAN reference software, which provides full software implementation of DU Layer 1 and above, Aira is innovating on top of this platform by applying their sophisticated AI models to the 5G physical layer and improving RAN performance.”

The setup at the TIP community lab sponsored by Meta in Menlo Park, California, consists of a Viavi UE emulator and Viavi channel emulator that simulates varying channel conditions as seen by a Foxconn RU. The RU itself is connected in an end-to-end fashion to the Aira DU, a CapGemini CU and a CapGemini Core. Aira has defined a service model that passes data from the DU to the VMware RIC via the E2 interface. The Aira AI-based High Fidelity MIMO Channel Estimation and Prediction application (xApp) runs atop the RIC. The xApp estimates and predicts the channel which is then compared to ground truth as established by the Viavi channel emulator. The output of the xApp is the prediction of channel evolution in-between S-slots, which results in improvements in RAN throughput and coverage.

Recommended AI: Lion Announces It Will Explore ChatGPT Related AI & NLP Technologies To Empower Digital Program

[To share your insights with us, please write to sghosh@martechseries.com]