MS Thesis Defense - Anurag Bambardekar: "SDR-Based Emulation of ML Enabled Spectrum Sharing in 5G.."

Date: September, 2024
Title: SDR-Based Emulation of Machine Learning-Enabled Spectrum Sharing in 5G Private Networks
Speaker: Anurag Bambardekar
Abstract: As 5G private networks become increasingly prevalent, efficient spectrum-sharing strategies for collocated deployments are critical. This study evaluates machine learning (ML) strategies for interference prediction and dynamic frequency/channel assignment in collocated 5G networks operating in the 3.5 GHz band. Using a Software Defined Radio (SDR) based emulation on the COSMOS testbed, we develop a spectrum management framework that leverages ML for real-time spectrum monitoring and intelligent resource allocation. By identifying spectrum overlaps
and underutilized bands, the framework dynamically optimizes network performance. The system, powered by an XGBoost model with 85% accuracy, effectively predicts interference scenarios and adjusts network frequencies to enhance performance. Key performance indicators, such as Packet Error Rate (PER) and Signal-to-Interference-plus-Noise Ratio (SINR), show significant improvements following frequency reassignment, validating the effectiveness of the model-driven approach. Designed for scalability, this system is poised for application in more complex network environments involving multiple networks and channels.