This $2,159,268 Project Grant awarded by the National Telecommunications and Information Administration (NTIA) under the Public Wireless Supply Chain Innovation Fund Grant Program (CFDA 11.038) supports Virginia Polytechnic Institute & State University (Virginia Tech) in developing a new neural network-based methodology to optimize testing and performance evaluation for Open Radio Access Network (Open RAN) systems. The key activities include:
Analyzing the statistical relationships between key performance indicators in current O-RAN testing to reduce redundant testing,
Developing new neural network-based performance metrics that can be integrated with existing O-RAN interfaces, and
Exploring data-driven performance indicators that can enable specific O-RAN deployments to adapt measurements to target applications.
The expected outcomes are feature-level algorithms that can generate interpretable and guaranteed results for O-RAN engineering problems using neural networks, reducing overall learning costs. The project includes a $187,419 subaward to the Massachusetts Institute of Technology to support the work of Dr. Lizhong Zheng.