Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

LLM Assisted Alpha Fairness for 6 GHz WiFi and NR_U Coexistence: An Agentic Orchestrator for Throughput, Energy, and SLA

Qun Wang, Yingzhou Lu, Guiran Liu, Binrong Zhu, Yang Liu

TL;DR

This work tackles the coexistence of Wi‑Fi and NR‑U in the unlicensed 6 GHz band under LBT by introducing an agentic controller that separates high‑level policy from low‑level execution. An LLM proposes interpretable knobs within an $\alpha$-fairness framework, while a deterministic, two‑stage optimizer enforces feasibility and computes the allocation, internalizing LBT losses and energy costs. Experiments in a two-channel, mixed‑stack simulator show that LLM‑assisted policies reduce total energy and improve energy efficiency (bits/J) while maintaining or boosting throughput compared with a strong rule baseline; GPT5‑Mini often achieves the best overall trade‑off. The approach provides transparent, auditable policy guidance with safe fallbacks and released code to reproduce results, demonstrating practical applicability for coexistence management in dynamic wireless environments.

Abstract

Unlicensed 6GHz is becoming a primary workhorse for high-capacity access, with Wi-Fi and 5G NR-U competing for the same channels under listen-before-talk (LBT) rules. Operating in this regime requires decisions that jointly trade throughput, energy, and service-level objectives while remaining safe and auditable. We present an agentic controller that separates {policy} from {execution}. At the start of each scheduling epoch the agent summarizes telemetry (per-channel busy and baseline LBT failure; per-user CQI, backlog, latency, battery, priority, and power mode) and invokes a large language model (LLM) to propose a small set of interpretable knobs: a fairness index α, per-channel duty-cycle caps for Wi-Fi/NR-U, and class weights. A deterministic optimizer then enforces feasibility and computes an α-fair allocation that internalizes LBT losses and energy cost; malformed or unsafe policies are clamped and fall back to a rule baseline. In a 6GHz simulator with two 160MHz channels and mixed Wi-Fi/NR-U users, LLM-assisted policies consistently improve energy efficiency while keeping throughput competitive with a strong rule baseline. One LLM lowers total energy by 35.3% at modest throughput loss, and another attains the best overall trade-off, finishing with higher total bits (+3.5%) and higher bits/J (+12.2%) than the baseline. We release code, per-epoch logs, and plotting utilities to reproduce all figures and numbers, illustrating how transparent, policy-level LLM guidance can safely improve wireless coexistence.

LLM Assisted Alpha Fairness for 6 GHz WiFi and NR_U Coexistence: An Agentic Orchestrator for Throughput, Energy, and SLA

TL;DR

This work tackles the coexistence of Wi‑Fi and NR‑U in the unlicensed 6 GHz band under LBT by introducing an agentic controller that separates high‑level policy from low‑level execution. An LLM proposes interpretable knobs within an -fairness framework, while a deterministic, two‑stage optimizer enforces feasibility and computes the allocation, internalizing LBT losses and energy costs. Experiments in a two-channel, mixed‑stack simulator show that LLM‑assisted policies reduce total energy and improve energy efficiency (bits/J) while maintaining or boosting throughput compared with a strong rule baseline; GPT5‑Mini often achieves the best overall trade‑off. The approach provides transparent, auditable policy guidance with safe fallbacks and released code to reproduce results, demonstrating practical applicability for coexistence management in dynamic wireless environments.

Abstract

Unlicensed 6GHz is becoming a primary workhorse for high-capacity access, with Wi-Fi and 5G NR-U competing for the same channels under listen-before-talk (LBT) rules. Operating in this regime requires decisions that jointly trade throughput, energy, and service-level objectives while remaining safe and auditable. We present an agentic controller that separates {policy} from {execution}. At the start of each scheduling epoch the agent summarizes telemetry (per-channel busy and baseline LBT failure; per-user CQI, backlog, latency, battery, priority, and power mode) and invokes a large language model (LLM) to propose a small set of interpretable knobs: a fairness index α, per-channel duty-cycle caps for Wi-Fi/NR-U, and class weights. A deterministic optimizer then enforces feasibility and computes an α-fair allocation that internalizes LBT losses and energy cost; malformed or unsafe policies are clamped and fall back to a rule baseline. In a 6GHz simulator with two 160MHz channels and mixed Wi-Fi/NR-U users, LLM-assisted policies consistently improve energy efficiency while keeping throughput competitive with a strong rule baseline. One LLM lowers total energy by 35.3% at modest throughput loss, and another attains the best overall trade-off, finishing with higher total bits (+3.5%) and higher bits/J (+12.2%) than the baseline. We release code, per-epoch logs, and plotting utilities to reproduce all figures and numbers, illustrating how transparent, policy-level LLM guidance can safely improve wireless coexistence.
Paper Structure (17 sections, 15 equations, 2 figures)

This paper contains 17 sections, 15 equations, 2 figures.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. System Model
  4. Problem Formulation
  5. Method: Agent Architecture
  6. Telemetry encoding and policy interface
  7. Safety, feasibility, and fallbacks
  8. Epoch solver: two-stage optimization
  9. SLA evaluation, queue update, and logging
  10. LLM-Assisted Decision Making
  11. Experimental Setup and Results
  12. Experimental Setup
  13. Results Analysis
  14. Moderate Offered Load (40 Mb/s)
  15. High Offered Load (150 Mb/s)
  16. ...and 2 more sections

Figures (2)

  • Figure 1: Moderate load (40 Mb/s) results.
  • Figure 2: High offered load (150 Mb/s) over 100 epochs. From left to right: cumulative throughput, cumulative energy, and cumulative energy efficiency.