Northeastern University demos AI-based O-RAN at MWC LA
BOSTON – The Institute for the Wireless Internet of Things is pleased to announce a first-of-its-kind demonstration on real-time control of an Open RAN cloud-native cellular network based on artificial intelligence.
At Mobile World Congress Americas in Los Angeles from October 26-28, WIoT will provide the first demonstration of orchestrated O-RAN xApps executing Deep Reinforcement Learning algorithms on a RAN Intelligent Controller (RIC) to optimize RAN slicing and radio resource management in a fully programmable and virtualized network at scale.
In the demo, a cloud-native standard-compliant cellular network is controlled through data-driven algorithms that autonomously select scheduling and slicing policies for a diverse set of applications. xApps are deployed through an intelligent orchestrator. Intent-based optimization algorithms developed by the team translate network operator requirements into an optimized allocation of network intelligence at various nodes of the O-RAN network.
The O-RAN-compliant network runs on Colosseum – the world’s largest RF network emulator - that enables large-scale experimentation with virtualized wireless systems at scale, including collecting large-scale datasets and performing experiments in a wide range of wireless scenarios. Colosseum is supported by the National Science Foundation.
The WIoT MWC demo is available at: https://www.youtube.com/watch?v=eaglAZlL5oM
The demo is also part of the O-RAN Virtual Exhibition. WIoT is an academic member of the O-RAN Alliance, and has been leading research projects with several industrial partners in the area. The research on fully programmable, open, and virtualized wireless networks at WIoT has been supported by the U.S. National Science Foundation and the U.S. Office of Naval Research.
WIoT is home to the Platforms for Advanced Wireless Research (PAWR) Project Office, which is co-led by nonprofit US Ignite and Northeastern University.