On AI Verification in Open RAN

TL;DR

This paper presents a scalable, interpretable verification method using decision trees to ensure reliable AI-driven RAN slicing and scheduling in Open RAN, addressing the opacity of AI models.

Contribution

It introduces a lightweight, real-time verification approach with decision trees for validating DRL agents in Open RAN, enhancing trustworthiness of AI systems.

Findings

Decision tree verifiers enable near-real-time consistency checks.

The approach is scalable and suitable for runtime validation.

Feasibility demonstrated through a slice-verifier prototype.

Abstract

Open RAN introduces a flexible, cloud-based architecture for the Radio Access Network (RAN), enabling Artificial Intelligence (AI)/Machine Learning (ML)-driven automation across heterogeneous, multi-vendor deployments. While EXplainable Artificial Intelligence (XAI) helps mitigate the opacity of AI models, explainability alone does not guarantee reliable network operations. In this article, we propose a lightweight verification approach based on interpretable models to validate the behavior of Deep Reinforcement Learning (DRL) agents for RAN slicing and scheduling in Open RAN. Specifically, we use Decision Tree (DT)-based verifiers to perform near-real-time consistency checks at runtime, which would be otherwise unfeasible with computationally expensive state-of-the-art verifiers. We analyze the landscape of XAI and AI verification, propose a scalable architectural integration, and demonstrate feasibility with a DT-based slice-verifier. We also outline future challenges to ensure trustworthy AI adoption in Open RAN.