Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Hierarchical Decision Mamba Meets Agentic AI: A Novel Approach for RAN Slicing in 6G

Md Arafat Habib, Medhat Elsayed, Majid Bavand, Pedro Enrique Iturria Rivera, Yigit Ozcan, Melike Erol-Kantarci

TL;DR

An Agentic AI framework for 6G RAN slicing is proposed, driven by a super agent built using Hierarchical Decision Mamba controllers and a Large Language Model (LLM), which interprets operator intents and translates them into actionable goals using the LLM.

Abstract

Radio Access Network (RAN) slicing enables multiple logical networks to exist on top of the same physical infrastructure by allocating resources to distinct service groups, where radio resource scheduling plays a key role in ensuring compliance with slice-specific Service-Level Agreements (SLAs). Existing configuration-based or intent-driven Reinforcement Learning (RL) approaches usually rely on static mappings and SLA conversions. The current literature does not integrate natural language understanding with coordinated decision-making. To address these limitations, we propose an Agentic AI framework for 6G RAN slicing, driven by a super agent built using Hierarchical Decision Mamba (HDM) controllers and a Large Language Model (LLM). The super agent interprets operator intents and translates them into actionable goals using the LLM, which are used by HDM to coordinate inter-slice, intra-slice, and self-healing agents. Compared to transformer-based and reward-driven baselines, the proposed Agentic AI framework demonstrates consistent improvements across key performance indicators, including higher throughput, improved cell-edge performance, and reduced latency across different slices.

Hierarchical Decision Mamba Meets Agentic AI: A Novel Approach for RAN Slicing in 6G

TL;DR

An Agentic AI framework for 6G RAN slicing is proposed, driven by a super agent built using Hierarchical Decision Mamba controllers and a Large Language Model (LLM), which interprets operator intents and translates them into actionable goals using the LLM.

Abstract

Radio Access Network (RAN) slicing enables multiple logical networks to exist on top of the same physical infrastructure by allocating resources to distinct service groups, where radio resource scheduling plays a key role in ensuring compliance with slice-specific Service-Level Agreements (SLAs). Existing configuration-based or intent-driven Reinforcement Learning (RL) approaches usually rely on static mappings and SLA conversions. The current literature does not integrate natural language understanding with coordinated decision-making. To address these limitations, we propose an Agentic AI framework for 6G RAN slicing, driven by a super agent built using Hierarchical Decision Mamba (HDM) controllers and a Large Language Model (LLM). The super agent interprets operator intents and translates them into actionable goals using the LLM, which are used by HDM to coordinate inter-slice, intra-slice, and self-healing agents. Compared to transformer-based and reward-driven baselines, the proposed Agentic AI framework demonstrates consistent improvements across key performance indicators, including higher throughput, improved cell-edge performance, and reduced latency across different slices.
Paper Structure (10 sections, 14 equations, 2 figures)

This paper contains 10 sections, 14 equations, 2 figures.

Table of Contents

  1. Introduction
  2. System Model
  3. Network Model
  4. Slice Types
  5. Problem Formulation
  6. Proposed Methodology Based on Agentic AI
  7. Performance Evaluation
  8. Simulation Setup
  9. Simulation Results
  10. Conclusions

Figures (2)

  • Figure 1: Agentic architecture of the proposed system guided by Hierarchical Decision Mamba
  • Figure 2: Performance comparison: (a) URLLC latency, (b) eMBB throughput, and (c) 5th percentile throughput (proposed method vs. the baselines) (d) Self-healing property.