Electric Vehicle User Charging Behavior Analysis Integrating Psychological and Environmental Factors: A Statistical-Driven LLM based Agent Approach

Researchers developed a novel framework using large language models (LLMs) to analyze electric vehicle taxi driver charging behavior by integrating psychological traits and environmental factors. The study demonstrates that LLMs can reliably simulate real-world charging decisions across multiple urban environments, providing insights for optimizing charging infrastructure and energy policy.

• →LLMs successfully simulate EV taxi driver charging behaviors by incorporating psychological factors like time sensitivity, price awareness, and range anxiety.
• →The framework integrates statistical priors with natural language reasoning to anchor decisions in empirical behavioral patterns.
• →Simulation results show reliable reproduction of real-world charging behaviors across multiple urban environments.
• →The study reveals behavioral heterogeneity among different EV user groups through joint analysis of environmental and psychological variables.
• →Findings can inform optimization of charging infrastructure and support integration of behavioral models into smart transportation systems.