LLM-OptiRA: LLM-Driven Optimization of Resource Allocation for Non-Convex Problems in Wireless Communications

TL;DR

This paper introduces LLM-OptiRA, a novel framework using large language models to automatically transform and solve complex non-convex resource allocation problems in wireless communications, reducing expert dependency and improving robustness.

Contribution

The paper presents the first LLM-based framework that detects, transforms, and solves non-convex optimization problems in wireless systems automatically, with integrated error correction and validation.

Findings

Achieves 96% execution rate on GPT-4.

Attains 80% success rate in solving complex problems.

Outperforms baseline methods across diverse scenarios.

Abstract

Solving non-convex resource allocation problems poses significant challenges in wireless communication systems, often beyond the capability of traditional optimization techniques. To address this issue, we propose LLM-OptiRA, the first framework that leverages large language models (LLMs) to automatically detect and transform non-convex components into solvable forms, enabling fully automated resolution of non-convex resource allocation problems in wireless communication systems. LLM-OptiRA not only simplifies problem-solving by reducing reliance on expert knowledge, but also integrates error correction and feasibility validation mechanisms to ensure robustness. Experimental results show that LLM-OptiRA achieves an execution rate of 96% and a success rate of 80% on GPT-4, significantly outperforming baseline approaches in complex optimization tasks across diverse scenarios.