AI-Powered Conflict Management in Open RAN: Detection, Classification, and Mitigation

2026-02-23

AI Summary

This work addresses the challenge of explicit and implicit conflicts arising from multiple AI-driven xApps/rApps independently adjusting interface control parameters (ICPs) in Open RAN, which can destabilize the network and degrade key performance indicators (KPIs)—a problem poorly handled by traditional rule-based approaches. The authors propose an end-to-end AI framework natively integrated into the Open RAN AI architecture to enable real-time conflict detection, classification, and mitigation. They introduce a novel synthetic conflict generation mechanism, GenC, to construct a large-scale, labeled dataset with controllable parameter sharing and inherent class imbalance. Leveraging a SMOTE-enhanced graph neural network (GNN), the approach is validated on both the ns-3/ORAN simulation platform and a real-world Dublin topology. Experiments demonstrate that, across scenarios with 5–50 concurrent xApps, the method achieves near-perfect classification accuracy and operates 3.2× faster than rule-based baselines, effectively resolving representative conflicts such as those between energy saving and mobility optimization.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Search and Optimization: Algorithm Configuration
• Multiagent Systems: Adversarial Agents

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Open Radio Access Network (RAN) was designed with native Artificial Intelligence (AI) as a core pillar, enabling AI- driven xApps and rApps to dynamically optimize network performance. However, the independent ICP adjustments made by these applications can inadvertently create conflicts- direct, indirect, and implicit, which lead to network instability and KPI degradation. Traditional rule-based conflict management becomes increasingly impractical as Open RAN scales in terms of xApps, associated ICPs, and relevant KPIs, struggling to handle the complexity of multi-xApp interactions. This highlights the necessity for AI-driven solutions that can efficiently detect, classify, and mitigate conflicts in real-time. This paper proposes an AI-powered framework for conflict detection, classification, and mitigation in Open RAN. We introduce GenC, a synthetic conflict generation framework for large-scale labeled datasets with controlled parameter sharing and realistic class imbalance, enabling robust training and evaluation of AI models. Our classification pipeline leverages GNNs, Bi-LSTM, and SMOTE-enhanced GNNs, with results demonstrating SMOTE-GNN's superior robustness in handling imbalanced data. Experimental validation using both synthetic datasets (5-50 xApps) and realistic ns3-oran simulations with OpenCellID-derived Dublin topology shows that AI-based methods achieve 3.2x faster classification than rule-based approaches while maintaining near-perfect accuracy. Our framework successfully addresses Energy Saving (ES)/Mobility Robustness Optimization (MRO) conflict scenarios using realistic ns3-oran and scales efficiently to large-scale xApp environments. By embedding this workflow into Open RAN's AI-driven architecture, our solution ensures autonomous and self-optimizing conflict management, paving the way for resilient, ultra-low-latency, and energy-efficient 6G networks.

Problem

• Open RAN
• AI-driven conflict
• xApps
• ICP conflicts
• KPI degradation

Innovation

• AI-powered conflict management
• synthetic conflict generation
• SMOTE-enhanced GNN
• Open RAN
• xApp interaction