PACIFISTA: Conflict Evaluation and Management in Open RAN

2024-05-07

arXiv.org

AI Summary

This paper addresses the objective conflicts arising from multi-AI-driven xApp/rApp co-control in O-RAN—e.g., conflicting goals of throughput maximization versus energy minimization—by proposing the first end-to-end framework for conflict detection and severity quantification tailored to O-RAN. Methodologically, it integrates sandbox-based pre-deployment rehearsal, hierarchical graph modeling, and statistical inference to enable predictive, assessable, and mitigatable conflict analysis prior to deployment. Its key contributions include a lightweight conflict assessment model and empirical validation via integration with the Colosseum and OpenRAN Gym simulation platforms. Experimental results demonstrate that the framework proactively identifies latent conflicts, averting an average 16% throughput degradation and up to 30% overall system performance deterioration. It significantly enhances the accuracy of xApp selection and scheduling decisions, thereby establishing a robust foundation for conflict-aware intelligent closed-loop control in O-RAN.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Applications
• Search and Optimization: Algorithm Configuration

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

The O-RAN ALLIANCE is defining architectures, interfaces, operations, and security requirements for cellular networks based on Open Radio Access Network (RAN) principles. In this context, O-RAN introduced the RAN Intelligent Controllers (RICs) to enable dynamic control of cellular networks via data-driven applications referred to as rApps and xApps. RICs enable for the first time truly intelligent and self-organizing cellular networks. However, enabling the execution of many Artificial Intelligence (AI) algorithms making autonomous control decisions to fulfill diverse (and possibly conflicting) goals poses unprecedented challenges. For instance, the execution of one xApp aiming at maximizing throughput and one aiming at minimizing energy consumption would inevitably result in diametrically opposed resource allocation strategies. Therefore, conflict management becomes a crucial component of any functional intelligent O-RAN system. This article studies the problem of conflict mitigation in O-RAN and proposes PACIFISTA, a framework to detect, characterize, and mitigate conflicts generated by O-RAN applications that control RAN parameters. PACIFISTA leverages a profiling pipeline to tests O-RAN applications in a sandbox environment, and combines hierarchical graphs with statistical models to detect the existence of conflicts and evaluate their severity. Experiments on Colosseum and OpenRAN Gym demonstrate PACIFISTA's ability to predict conflicts and provide valuable information before conflicting xApps are deployed on production. We demonstrate that users can experience a 16% throughput loss even in the case of xApps with similar goals, and that applications with conflicting goals might cause instability and result in up to 30% performance degradation. We also show that PACIFISTA can help operators to identify conflicting applications and maintain performance degradation at bay.

Problem

• Conflict management in Open RAN systems
• Detecting and mitigating conflicts in AI-driven applications
• Maintaining performance amidst conflicting app goals

Innovation

• Hierarchical graphs detect conflicts
• Statistical models evaluate severity
• Sandbox environment tests applications