Understanding Conflict and Compatibility Conditions for Agents in AI-RAN

2026-10-05

AI Summary

This study addresses the conflict arising when multiple agents control the same parameter in AI-RAN, where existing methods lack objective compatibility assessment. We propose a control-theoretic shared control framework that models threshold-based agents as sampled dead-zone feedback controllers, defining compatibility conditions according to KPI targets and tolerances. A pairwise testing algorithm is designed to determine compatibility among arbitrarily scaled agent populations, triggering arbitration only upon incompatibility while otherwise permitting shared control authority. Simulations conducted on the NIST ns3-oran platform demonstrate that when objectives are compatible and feasible ranges are reachable, SLA drift approaches zero; under incompatible conditions, performance matches that of priority-based mitigation strategies.

Abstract

Disaggregated mobile networks expose open interfaces for independent agents to control the Radio Access Network (RAN). The interactions between agents with contrasting objectives can result in conflicts. However, existing conflict mitigation methods treat agents that control the same parameter as being in a conflict that requires arbitration of their actions, without assessing whether their objectives can be satisfied simultaneously. In this paper, we introduce a control-theoretic approach to determine when agents can coexist and share control of the same parameters. We model threshold-based agents often encountered in the literature as sampled deadband feedback controllers and represent their objectives through Key Performance Indicator (KPI) targets and tolerances that define acceptable deadband bounds. We derive compatibility conditions from these bounds and show that compatibility for any number of agents and monitored KPIs can be established through pairwise tests. We propose a conflict mitigation policy that allows compatible agents to share control of the same network parameters while restricting arbitration to cases where their objectives cannot be satisfied simultaneously. We evaluate our policy through simulations using NIST's ns3-oran extension of ns-3, and our results show that it enables agents to share control with near-zero Service Level Agreement (SLA) drift when their objectives are compatible and the shared acceptable range is attainable, while matching Priority Mitigation when their objectives are incompatible.

Problem

• AI-RAN
• conflict mitigation
• agent compatibility
• disaggregated mobile networks
• KPI targets

Innovation

• AI-RAN
• Deadband Feedback Controller
• Compatibility Conditions
• Conflict Mitigation
• Sampled Control