Large Language Model Interface for Home Energy Management Systems

TL;DR

This paper introduces an LLM-based interface for Home Energy Management Systems that improves user interaction and parameterization accuracy, making HEMS more accessible to non-technical users and enhancing system performance.

Contribution

The paper presents a novel LLM-based interface utilizing ReAct and few-shot prompting, along with a method to simulate user interactions for evaluation, advancing HEMS usability.

Findings

Achieves 88% average parameter retrieval accuracy.

Outperforms benchmark models without ReAct and few-shot prompting.

Effectively simulates diverse user expertise levels for evaluation.

Abstract

Home Energy Management Systems (HEMSs) help households tailor their electricity usage based on power system signals such as energy prices. This technology helps to reduce energy bills and offers greater demand-side flexibility that supports the power system stability. However, residents who lack a technical background may find it difficult to use HEMSs effectively, because HEMSs require well-formatted parameterization that reflects the characteristics of the energy resources, houses, and users' needs. Recently, Large-Language Models (LLMs) have demonstrated an outstanding ability in language understanding. Motivated by this, we propose an LLM-based interface that interacts with users to understand and parameterize their ``badly-formatted answers'', and then outputs well-formatted parameters to implement an HEMS. We further use Reason and Act method (ReAct) and few-shot prompting to enhance the LLM performance. Evaluating the interface performance requires multiple user--LLM interactions. To avoid the efforts in finding volunteer users and reduce the evaluation time, we additionally propose a method that uses another LLM to simulate users with varying expertise, ranging from knowledgeable to non-technical. By comprehensive evaluation, the proposed LLM-based HEMS interface achieves an average parameter retrieval accuracy of 88\%, outperforming benchmark models without ReAct and/or few-shot prompting.