Reproduce “Conversational Demand Response: Bidirectional Aggregator-Prosumer Coordination through Agentic AI” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Reda El Makroum, Sebastian Zwickl-Bernhard, Lukas Kranzl, Hans Auer
Researchers at TU Wien and NTNU developed Conversational Demand Response (CDR), a two-tier agentic AI system that enables bidirectional natural language communication between energy aggregators and prosumer Home Energy Management Systems (HEMS). This system transparently assesses and coordinates demand response events by integrating optimization tools, demonstrating successful downstream and upstream interactions within seconds and promoting prosumer engagement.
Key insights
- Current Large Language Model (LLM) capabilities are sufficient to enable bidirectional natural-language demand response coordination between aggregators and prosumers within operationally relevant timescales.
- Integrating optimization tools with agentic AI allows for transparent, data-driven cost-benefit analyses of demand response (DR) events, which can be clearly communicated to non-technical prosumers.
- The conversational approach significantly enhances prosumer agency and transparency, addressing behavioral barriers to participation and enabling more adaptive, personalized DR coordination.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.