Go back to publications

Optimal EV Charging Station Location through a Dominant-Strategy Incentive-Compatible and LLM-Assisted Multilevel Auction

January 2026 Donghe Li, Qinchuan Cheng, Wenzhuo Li, Xiao Liao, Junhan Xu, Meng Zhao, Huan Xi, Qingyu Yang Applied Energy (revision)
#LLM #Mechanism Design #Optimization #Energy Systems

Overview

This work studies EV charging station planning under mixed strategic behavior, public preference uncertainty, and real-world demand expressed in natural language rather than clean tabular form.

Core Idea

We propose a Multilevel Joint Auction (MJA) framework that integrates:

  • semantic parsing of user preferences with large language models,
  • mixed-integer optimization for facility planning,
  • mechanism design for incentive compatibility.

The main goal is to bridge the gap between unstructured user demand and a tractable planning model.

My Contribution

I contributed to the mechanism design, optimization setup, experiment design, result analysis, and paper writing. A key part of the project is translating public natural-language preferences into structured planning inputs.

Current Status

The paper is in advanced review at Applied Energy, where it has progressed through multiple rounds of revision.