Agentic AI Home Energy Management System: A Large Language Model Framework for Residential Load Scheduling

2025-10-30

AI Summary

The adoption of Home Energy Management Systems (HEMS) remains limited due to complex user interaction, hindering residential demand response capabilities. Method: This paper proposes the first agent-based AI architecture leveraging a large language model (LLM) as an autonomous coordinator. It employs a hierarchical collaboration mechanism and the ReAct reasoning framework to enable end-to-end automation—from natural-language commands to multi-device load scheduling—without requiring in-context examples. Technically, it integrates mixed-integer linear programming (MILP) optimization, Google Calendar–based contextual awareness, and progressive prompt engineering to support full-device coordination under real-world electricity pricing. Contribution/Results: Evaluated on Llama-3.3-70B, the system achieves performance on par with optimal baselines. The complete codebase and tooling are open-sourced to foster reproducible research.

Technology Category

Cognitive Modeling & Cognitive Systems: Agent ArchitecturesHumans and AI: Human-Aware Planning and Behavior PredictionMultiagent Systems: Mechanism Design

Application Category

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

Abstract

The electricity sector transition requires substantial increases in residential demand response capacity, yet Home Energy Management Systems (HEMS) adoption remains limited by user interaction barriers requiring translation of everyday preferences into technical parameters. While large language models have been applied to energy systems as code generators and parameter extractors, no existing implementation deploys LLMs as autonomous coordinators managing the complete workflow from natural language input to multi-appliance scheduling. This paper presents an agentic AI HEMS where LLMs autonomously coordinate multi-appliance scheduling from natural language requests to device control, achieving optimal scheduling without example demonstrations. A hierarchical architecture combining one orchestrator with three specialist agents uses the ReAct pattern for iterative reasoning, enabling dynamic coordination without hardcoded workflows while integrating Google Calendar for context-aware deadline extraction. Evaluation across three open-source models using real Austrian day-ahead electricity prices reveals substantial capability differences. Llama-3.3-70B successfully coordinates all appliances across all scenarios to match cost-optimal benchmarks computed via mixed-integer linear programming, while other models achieve perfect single-appliance performance but struggle to coordinate all appliances simultaneously. Progressive prompt engineering experiments demonstrate that analytical query handling without explicit guidance remains unreliable despite models' general reasoning capabilities. We open-source the complete system including orchestration logic, agent prompts, tools, and web interfaces to enable reproducibility, extension, and future research.

Problem

• Developing autonomous LLM agents for home energy scheduling from natural language
• Overcoming user interaction barriers in residential demand response systems
• Enabling multi-appliance coordination without hardcoded workflows or demonstrations

Innovation

• LLMs autonomously coordinate multi-appliance scheduling
• Hierarchical architecture combines orchestrator with specialist agents
• Uses ReAct pattern for iterative reasoning without hardcoded workflows