On AI Verification in Open RAN
This work addresses the need for trustworthy AI adoption in Open RAN, which is crucial for network operators and vendors dealing with heterogeneous, multi-vendor deployments, but it is incremental as it builds on existing explainable AI and verification methods.
The paper tackles the problem of ensuring reliable AI-driven automation in Open RAN by proposing a lightweight verification approach using interpretable models, specifically Decision Tree-based verifiers, to validate Deep Reinforcement Learning agents for RAN slicing and scheduling, achieving near-real-time consistency checks that are unfeasible with computationally expensive state-of-the-art verifiers.
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.