Large Language Model Interface for Home Energy Management Systems

2025-01-14

AI Summary

Non-technical users face significant challenges in configuring parameters of home energy management systems (HEMS), hindering widespread adoption. Method: This paper proposes an LLM-driven natural language interface that enables intuitive, conversational interaction with HEMS. We introduce a novel parameterization framework integrating the ReAct reasoning paradigm with few-shot prompting to automatically translate colloquial user energy preferences into executable, structured HEMS configurations. Additionally, we design an LLM-based multi-level user simulator to enable efficient, scalable, and interactive evaluation of system performance across diverse user expertise levels. Contribution/Results: Experimental evaluation demonstrates an 88% average accuracy in parameter extraction—substantially outperforming baseline models. The system seamlessly accommodates users ranging from novices to domain experts, significantly enhancing HEMS usability, accessibility, and real-world deployment potential.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Home Energy Management Systems
• Natural Language Processing
• User-Friendly Interface

Innovation

• Natural Language Processing
• Reason and Act Method
• User Simulation