Choose, not Hoard: Information-to-Model Matching for Artificial Intelligence in O-RAN

TL;DR

This paper proposes a flexible approach for training multiple AI models at different RICs in O-RAN, leveraging location-specific data to enhance network control performance over traditional hoarding strategies.

Contribution

It introduces a novel method of creating multiple AI model instances in O-RAN, enabling location-aware training and improved network management.

Findings

Multiple AI models with location-specific training outperform traditional hoarding methods.

Using real-world traces demonstrates performance improvements in network control.

Flexible AI-to-Data matching enhances O-RAN efficiency.

Abstract

Open Radio Access Network (O-RAN) is an emerging paradigm, whereby virtualized network infrastructure elements from different vendors communicate via open, standardized interfaces. A key element therein is the RAN Intelligent Controller (RIC), an Artificial Intelligence (AI)-based controller. Traditionally, all data available in the network has been used to train a single AI model to be used at the RIC. This paper introduces, discusses, and evaluates the creation of multiple AI model instances at different RICs, leveraging information from some (or all) locations for their training. This brings about a flexible relationship between gNBs, the AI models used to control them, and the data such models are trained with. Experiments with real-world traces show how using multiple AI model instances that choose training data from specific locations improve the performance of traditional approaches following the hoarding strategy.