Technology Category
Multiagent Systems: Agent CommunicationNatural Language Processing: Conversational AI/Dialog SystemsHumans and AI: Interaction Techniques and Devices
Conversational Demand Response: Bidirectional Aggregator-Prosumer Coordination through Agentic AI
🤖 AI Summary
This study addresses the lack of bidirectional communication in existing residential demand response mechanisms, which hinders informed user decision-making and sustained engagement. To overcome this limitation, the authors propose a novel conversational demand response framework powered by multi-agent artificial intelligence that introduces, for the first time, bidirectional natural language interaction, enabling prosumers to initiate dialogues proactively. The system integrates optimization tools to evaluate the feasibility and cost-effectiveness of flexibility requests in real time. Built upon a two-layer multi-agent architecture, it combines optimization algorithms, large language model prompt engineering, and agent orchestration logic. A proof-of-concept demonstrates that interactions can be completed within 12 seconds. The system is open-sourced, offering strong scalability, transparency, and reproducibility.
Technology Category
Application Category
📝 Abstract
Residential demand response depends on sustained prosumer participation, yet existing coordination is either fully automated, or limited to one-way dispatch signals and price alerts that offer little possibility for informed decision-making. This paper introduces Conversational Demand Response (CDR), a coordination mechanism where aggregators and prosumers interact through bidirectional natural language, enabled through agentic AI. A two-tier multi-agent architecture is developed in which an aggregator agent dispatches flexibility requests and a prosumer Home Energy Management System (HEMS) assesses deliverability and cost-benefit by calling an optimization-based tool. CDR also enables prosumer-initiated upstream communication, where changes in preferences can reach the aggregator directly. Proof-of-concept evaluation shows that interactions complete in under 12 seconds. The architecture illustrates how agentic AI can bridge the aggregator-prosumer coordination gap, providing the scalability of automated DR while preserving the transparency, explainability, and user agency necessary for sustained prosumer participation. All system components, including agent prompts, orchestration logic, and simulation interfaces, are released as open source to enable reproducibility and further development.
Problem
Research questions and friction points this paper is trying to address.
Demand Response
Prosumer Participation
Aggregator-Prosumer Coordination
Bidirectional Communication
Residential Energy Management
Innovation
Methods, ideas, or system contributions that make the work stand out.
Conversational Demand Response
Agentic AI
Bidirectional Coordination
Prosumer Engagement
Multi-agent Architecture
🔎 Similar Papers
No similar papers found.
