Large Language Models for Power Scheduling: A User-Centric Approach

TL;DR

This paper introduces a user-centric resource scheduling architecture using large language models to convert voice requests into optimization problems, demonstrated in electric vehicle charging scenarios, highlighting the potential and challenges of LLM-based systems.

Contribution

It presents a novel LLM-based architecture with three specialized agents for translating voice requests into resource allocation, pioneering user-centric scheduling in energy networks.

Findings

LLM agents effectively convert voice requests into optimization problems.

Larger candidate sets can increase recognition noise and reduce performance.

Open-source code enables reproducibility and further research.

Abstract

While traditional optimization and scheduling schemes are designed to meet fixed, predefined system requirements, future systems are moving toward user-driven approaches and personalized services, aiming to achieve high quality-of-experience (QoE) and flexibility. This challenge is particularly pronounced in wireless and digitalized energy networks, where users' requirements have largely not been taken into consideration due to the lack of a common language between users and machines. The emergence of powerful large language models (LLMs) marks a radical departure from traditional system-centric methods into more advanced user-centric approaches by providing a natural communication interface between users and devices. In this paper, for the first time, we introduce a novel architecture for resource scheduling problems by constructing three LLM agents to convert an arbitrary user's voice request (VRQ) into a resource allocation vector. Specifically, we design an LLM intent recognition agent to translate the request into an optimization problem (OP), an LLM OP parameter identification agent, and an LLM OP solving agent. To evaluate system performance, we construct a database of typical VRQs in the context of electric vehicle (EV) charging. As a proof of concept, we primarily use Llama 3 8B. Through testing with different prompt engineering scenarios, the obtained results demonstrate the efficiency of the proposed architecture. The conducted performance analysis allows key insights to be extracted. For instance, having a larger set of candidate OPs to model the real-world problem might degrade the final performance because of a higher recognition/OP classification noise level. All results and codes are open source.