A State-Augmented Approach for Learning Optimal Resource Management Decisions in Wireless Networks

TL;DR

This paper introduces a state-augmented learning approach for resource management in wireless networks, combining network states and dual variables to improve power allocation decisions with theoretical guarantees and superior performance.

Contribution

It proposes a novel state-augmented policy framework using GNNs and dual variables, providing theoretical analysis and demonstrating improved trade-offs in network utility.

Findings

Achieves better trade-offs between mean, minimum, and percentile rates.

Provides theoretical guarantees for feasibility and near-optimality.

Demonstrates superior performance over baseline methods in simulations.

Abstract

We consider a radio resource management (RRM) problem in a multi-user wireless network, where the goal is to optimize a network-wide utility function subject to constraints on the ergodic average performance of users. We propose a state-augmented parameterization for the RRM policy, where alongside the instantaneous network states, the RRM policy takes as input the set of dual variables corresponding to the constraints. We provide theoretical justification for the feasibility and near-optimality of the RRM decisions generated by the proposed state-augmented algorithm. Focusing on the power allocation problem with RRM policies parameterized by a graph neural network (GNN) and dual variables sampled from the dual descent dynamics, we numerically demonstrate that the proposed approach achieves a superior trade-off between mean, minimum, and 5th percentile rates than baseline methods.