ML-Based Strategies to Optimize O-RAN VNFs for Latency and Reliability

The Open Radio Access Network (O-RAN) combines the benefits of virtualization and Machine Learning (ML) to enhance Radio Access Networks (RANs), providing advanced automation, self-organization, and closed-loop optimization across the RAN architecture. This approach efficiently manages the sharply rising network traffic in RANs and introduces open interfaces that enable the virtual hosting of its components on the O-Cloud, as well as hosting ML training and inference modules. This transition to a virtualized environment and an ML-supportive architecture paves the way for applying advanced ML-assisted solutions to dynamically optimize, oversee, and monitor the O-RAN. In this study, we begin by offering a straightforward overview of how to implement an ML pipeline in O-RAN. Next, we explore latency and reliability challenges in two O-RAN deployment use cases, suggesting ML-assisted solutions for each. Lastly, we detail our implementation of a deep reinforcement learning solution to boost O-RAN's availability by optimizing the placement of its units. Our proposed solution showcases the effectiveness of ML-assisted solutions by maximizing the availability of a large-scale Critical Internet of Things O-RAN deployment in a reasonable time frame.