Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Predicting Conflict Impact on Performance in O-RAN

Pietro Brach del Prever, Niloofar Mohamadi, Salvatore D'Oro, Leonardo Bonati, Michele Polese, Łukasz Kułacz, Piotr Jaworski, Adrian Kliks, Heiko Lehmann, Tommaso Melodia

TL;DR

This paper proposes a novel approach that leverages the same data used to determine conflict severity but extends its use to predict the impact of such conflicts on RAN performance based on the frequency at which each agent generates actions, giving more weight to faster applications, which exert control more frequently.

Abstract

The O-RAN Alliance promotes the integration of intelligent autonomous agents to control the Radio Access Network (RAN). This improves flexibility, performance, and observability in the RAN, but introduces new challenges, such as the detection and management of conflicts among the intelligent autonomous agents. A solution consists of profiling the agents before deployment to gather statistical information about their decision-making behavior, then using the information to estimate the level of conflict among agents with different goals. This approach enables determining the occurrence of conflicts among agents, but does not provide information about the impact on RAN performance, including potential service degradation. The problem becomes more complex when agents generate control actions at different timescales, which makes conflict severity hard to predict. In this paper, we present a novel approach that fills this gap. Our solution leverages the same data used to determine conflict severity but extends its use to predict the impact of such conflicts on RAN performance based on the frequency at which each agent generates actions, giving more weight to faster applications, which exert control more frequently. Via a prototype, we demonstrate that our solution is viable and accurately predicts conflict impact on RAN performance.

Predicting Conflict Impact on Performance in O-RAN

TL;DR

This paper proposes a novel approach that leverages the same data used to determine conflict severity but extends its use to predict the impact of such conflicts on RAN performance based on the frequency at which each agent generates actions, giving more weight to faster applications, which exert control more frequently.

Abstract

The O-RAN Alliance promotes the integration of intelligent autonomous agents to control the Radio Access Network (RAN). This improves flexibility, performance, and observability in the RAN, but introduces new challenges, such as the detection and management of conflicts among the intelligent autonomous agents. A solution consists of profiling the agents before deployment to gather statistical information about their decision-making behavior, then using the information to estimate the level of conflict among agents with different goals. This approach enables determining the occurrence of conflicts among agents, but does not provide information about the impact on RAN performance, including potential service degradation. The problem becomes more complex when agents generate control actions at different timescales, which makes conflict severity hard to predict. In this paper, we present a novel approach that fills this gap. Our solution leverages the same data used to determine conflict severity but extends its use to predict the impact of such conflicts on RAN performance based on the frequency at which each agent generates actions, giving more weight to faster applications, which exert control more frequently. Via a prototype, we demonstrate that our solution is viable and accurately predicts conflict impact on RAN performance.
Paper Structure (11 sections, 5 figures, 3 tables, 1 algorithm)

This paper contains 11 sections, 5 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Conflict Mitigation in O-RAN
  4. Primer on PACIFISTA
  5. Prediction System
  6. Experimental Setup
  7. Testbed Setup
  8. Considered xApps
  9. xApp Characterization and Conflicts
  10. RAN Performance Prediction
  11. Conclusions

Figures (5)

  • Figure 1: Graphical representation of the different distance metrics.
  • Figure 2: Prediction system placement and workflow within the O-RAN architecture and relation with PACIFISTA.
  • Figure 3: Profiles of xApps run individually in scenarios BASE and ROME: with 2M traffic.
  • Figure 4: Profiles of xApps executed both individually and at the same time: both applications sending messages at $1s$ interval each, with 2M traffic. The dashed line represents the predicted performance.
  • Figure 5: Profiles of xApps executing individually and concurrently: with 2M traffic. The dashed lines represent the predicted performance.