Behavioral Generative Agents for Energy Operations

TL;DR

This work introduces a novel approach leveraging generative agents-artificial agents powered by large language models-to simulate sequential customer decisions under dynamic electricity prices and outage risks, and suggests that behavioral generative agents can serve as scalable and flexible tools for studying consumer behavior in energy operations.

Abstract

Problem definition: Accurately modeling consumer behavior in energy operations is challenging due to uncertainty, behavioral heterogeneity, and limited empirical data-particularly in low-frequency, high-impact events. While generative AI trained on large-scale human data offers new opportunities to study decision behavior, its role in operational applications remains unclear. We examine how generative agents can support customer behavior discovery in energy operations, complementing rather than replacing human-based experiments. Methodology/results: We introduce a novel approach leveraging generative agents-artificial agents powered by large language models-to simulate sequential customer decisions under dynamic electricity prices and outage risks. We find that these agents behave more optimally and rationally in simpler market scenarios, while their performance becomes more variable and suboptimal as task complexity rises. Furthermore, the agents exhibit heterogeneous customer preferences, consistently maintaining distinct, persona-driven reasoning patterns in both operational decisions and textual reasoning. Comparisons with dynamic programming and greedy policy benchmarks show alignment between specific personas and distinct heuristic decision policies. In low-frequency, high-impact events such as blackouts, agents prioritize energy reliability over cost or profit, demonstrating their ability to uncover behavioral patterns beyond the rigidity of traditional mathematical models. Managerial Implications: Our findings suggest that behavioral generative agents can serve as scalable and flexible tools for studying consumer behavior in energy operations. By enabling controlled experiments across heterogeneous customer types and rare events, these agents can enhance the design of energy management systems and support more informed analysis of energy policies and incentive programs.

Figures (14)

• Figure 1: Accumulated rewards and battery SoC under greedy heuristic (left) and optimal DP policy (right).
• Figure 2: Mean values of SoC and accumulated reward over time in the hard task with $\rho = 0.909$.
• Figure 3: Cluster distribution shifts in normal and blackout cases.
• Figure 4: SoC and accumulated reward over time. Top: hard task with $\rho = 0.909$; middle: Medium task with $\rho = 0.333$; bottom: easy task with $\rho=0.067$.
• Figure 5: Histogram of $\rho$ from randomized sampled price trajectories.