Research on a Two-Layer Demand Response Framework for Electric Vehicle Users and Aggregators Based on LLMs
Zhaoyi Zhang, Chenggang Cui, Ning Yang, Chuanlin Zhang
TL;DR
This paper addresses coordinating EV charging to balance grid supply and demand in the face of rising EV adoption. It proposes a two-layer bilevel framework in which an aggregator uses PSO-guided dynamic retail prices \lambda(t) to maximize profit, while EV user responses are simulated with LLMs in a multi-agent setting. An LLM-driven user behavior simulation framework—comprising profiling, environmental state, and decision generation—provides personalized, context-aware demand responses along with a dialog-based decision support mechanism. Simulation results indicate improved charging efficiency, reduced peak loads, and enhanced grid stability, suggesting practical applicability for smart-grid operations.
Abstract
The widespread adoption of electric vehicles (EVs) has increased the importance of demand response in smart grids. This paper proposes a two-layer demand response optimization framework for EV users and aggregators, leveraging large language models (LLMs) to balance electricity supply and demand and optimize energy utilization during EV charging. The upper-layer model, focusing on the aggregator, aims to maximize profits by adjusting retail electricity prices. The lower-layer model targets EV users, using LLMs to simulate charging demands under varying electricity prices and optimize both costs and user comfort. The study employs a multi-threaded LLM decision generator to dynamically analyze user behavior, charging preferences, and psychological factors. The framework utilizes the PSO method to optimize electricity prices, ensuring user needs are met while increasing aggregator profits. Simulation results show that the proposed model improves EV charging efficiency, alleviates peak power loads, and stabilizes smart grid operations.