Type something to search...
AUTO-RAN Config Planner Agent
Editor Choice
AUTO-RAN Config Planner Agent

AUTO-RAN Config Planner Agent

Enrico Sbuttoni

An AI-driven config planner agent that designs cell reconfiguration strategies to optimize network performance. It coordinates with the Monitoring Agent to retrieve KPI context and with the Validation Agent to assess candidate configurations before recommending an optimized reconfiguration plan to higher-layer agents.

develop
72
29

Detailed Description

This artifact operates within a multi-agent architecture developed in collaboration with Telenor Maritime and NVIDIA. It performs intelligent cell reconfiguration planning for cloud-native 5G networks using closed-loop coordination with the Monitoring Agent and the Validation Agent. The agent receives high-level intents such as optimizing cell performance, mitigating degradation, improving coverage or capacity trade-offs, reducing interference, or stabilizing QoS. Based on the intent, the agent:

  • Requests KPI and configuration context from the Monitoring Agent (e.g., time-windowed UL/DL throughput, SNR, pZeroNominal, and other exported metrics)
  • Generates candidate cell reconfiguration actions (e.g., power control parameters such as pZeroNominal or other exposed RAN stack controls)
  • Submits candidate plans to the Validation Agent for feasibility, constraint compliance, and predicted KPI impact evaluation (via rule checks or digital twin simulation)
  • Selects and returns the optimal plan, including rationale, expected KPI impact, and rollout guidance (apply/rollback conditions)

The Config Planner Agent acts as the decision and orchestration layer of the workflow. It does not directly measure KPIs (Monitoring Agent responsibility) or validate configurations (Validation Agent responsibility). Instead, it coordinates both components to produce robust, data-driven reconfiguration recommendations.

Key Features

  • Multi-agent closed-loop coordination
  • Intent-driven cell reconfiguration planning

Use Cases

  • Autonomous cell performance optimization
  • Power control parameter tuning
  • Coverage and capacity trade-off management
  • Pre-deployment configuration planning

External Resources

AI Agent Training


BubbleRAN open documentation
View Details

Technical Details


Version2026.02
Published23 Feb, 2026
Base
Platform:
BubbleRAN MX-PDK, MX-AI, and MX-DT

Author


Enrico Sbuttoni
Enrico Sbuttoni

Tags


  • O-RAN
  • Artificial Intelligent
  • Control
  • LITEON

Affiliation


  • BubbleRAN
  • EURECOM

Certified By


  • BubbleRANBubbleRAN

More from Enrico Sbuttoni

AUTO-RAN Monitoring Agent

AUTO-RAN Monitoring Agent

Enrico Sbuttoni

An AI-driven monitoring agent designed to track key network KPIs, including UL/DL throughput, Signal-to-Noise Ratio (SNR), and pZeroNominal values for PUCCH and PUSCH, in cloud-native 5G O-RAN networks. The agent dynamically queries VictoriaMetrics and provides structured KPI responses to higher-layer agents within the multi-agent workflow.

O-RANMonitorArtificial Intelligent+1
develop
66
24
Hermes API Agent

Hermes API Agent

Enrico Sbuttoni

Hermes is an intelligent API agent for managing 5G O-RAN network resources through natural language interaction. It enables conversational deployment, retrieval, modification, and deletion of network entities such as terminals, networks, and infrastructure elements, with automatic YAML generation and schema validation for cloud-native network environments.

O-RANArtificial IntelligentMonitor+7
develop
18
10
SMO Agent

SMO Agent

Andrea Leone
Enrico Sbuttoni

The Service Management and Orchestration (SMO) Agent processes high-level intents for network lifecycle management, including deployment, monitoring, and deletion. It operates on top of the Hermes API Agent, translating service-level intents into structured orchestration requests.

O-RANArtificial IntelligentMonitor+7
develop
46
37

Related Artifacts

AUTO-RAN Monitoring Agent

AUTO-RAN Monitoring Agent

Enrico Sbuttoni

An AI-driven monitoring agent designed to track key network KPIs, including UL/DL throughput, Signal-to-Noise Ratio (SNR), and pZeroNominal values for PUCCH and PUSCH, in cloud-native 5G O-RAN networks. The agent dynamically queries VictoriaMetrics and provides structured KPI responses to higher-layer agents within the multi-agent workflow.

O-RANMonitorArtificial Intelligent+1
develop
66
24