CORMO-RAN: Lossless Migration of xApps in O-RAN

2025-06-24

AI Summary

To address the coexisting challenges of low xApp resource utilization, high energy consumption, and migration-induced service disruption during low-traffic periods in O-RAN, this paper proposes CORMO-RAN—a dynamic orchestration framework. It employs a data-driven approach to activate compute nodes on-demand and enables lossless xApp state migration, ensuring uninterrupted RAN control services. Its key contributions are: (1) joint optimization of service availability, scalability, and energy efficiency; (2) support for heterogeneous state sizes and temporal constraints, enabling scenario-adaptive migration policies; and (3) seamless integration as an rApp within OpenShift/Kubernetes, validated end-to-end on a real private 5G testbed comprising commercial RU and RIC hardware. Experimental results demonstrate up to 64% reduction in RIC cluster energy consumption, with no degradation in RAN control performance.

Technology Category

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

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Open Radio Access Network (RAN) is a key paradigm to attain unprecedented flexibility of the RAN via disaggregation and Artificial Intelligence (AI)-based applications called xApps. In dense areas with many active RAN nodes, compute resources are engineered to support potentially hundreds of xApps monitoring and controlling the RAN to achieve operator's intents. However, such resources might become underutilized during low-traffic periods, where most cells are sleeping and, given the reduced RAN complexity, only a few xApps are needed for its control. In this paper, we propose CORMO-RAN, a data-driven orchestrator that dynamically activates compute nodes based on xApp load to save energy, and performs lossless migration of xApps from nodes to be turned off to active ones while ensuring xApp availability during migration. CORMO-RAN tackles the trade-off among service availability, scalability, and energy consumption while (i) preserving xApps' internal state to prevent RAN performance degradation during migration; (ii) accounting for xApp diversity in state size and timing constraints; and (iii) implementing several migration strategies and providing guidelines on best strategies to use based on resource availability and requirements. We prototype CORMO-RAN as an rApp, and experimentally evaluate it on an O-RAN private 5G testbed hosted on a Red Hat OpenShift cluster with commercial radio units. Results demonstrate that CORMO-RAN is effective in minimizing energy consumption of the RAN Intelligent Controller (RIC) cluster, yielding up to 64% energy saving when compared to existing approaches.

Problem

• Dynamically manage xApp load to save energy in O-RAN
• Ensure lossless xApp migration during low-traffic periods
• Balance service availability, scalability, and energy consumption

Innovation

• Dynamic compute node activation based on xApp load
• Lossless xApp migration ensuring service availability
• Energy-efficient RAN control with state preservation