Behavioral Generative Agents for Power Dispatch and Auction
Shaoze Li, Justin S. Kim, Cong Chen

TL;DR
This paper demonstrates how large language model-based generative agents can model human decision-making in power dispatch and auction scenarios, offering a flexible alternative to traditional mathematical models.
Contribution
It introduces a novel approach using LLMs with in-context learning to simulate and analyze human-like decision behaviors in energy management and auction settings.
Findings
LLM agents can outperform dynamic programming in blackout scenarios.
Structured prompting enables LLMs to mimic rational bidding strategies.
Behavioral patterns can be transferred between models via in-context learning.
Abstract
This paper presents positive initial evidence that generative agents can relax the rigidity of traditional mathematical models for human decision-making in power dispatch and auction settings. We design two proof-of-concept energy experiments with generative agents powered by a large language model (LLM). First, we construct a home battery management testbed with stochastic electricity prices and blackout interventions, and benchmark LLM decisions against dynamic programming. By incorporating an in-context learning (ICL) module, we show that behavioral patterns discovered by a stronger reasoning model can be transferred to a smaller LLM via example-based prompting, leading agents to prioritize post-blackout energy reserves over short-term profit. Second, we study LLM agents in simultaneous ascending auctions (SAA) for power network access, comparing their behavior with an optimization…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSmart Grid Energy Management · Auction Theory and Applications · Electric Power System Optimization
