Scholarlink

<p>The rapid adoption of electric vehicles (EVs) has positioned Vehicle-to-Grid (V2G) technology as a transformative solution for enhancing grid efficiency and stability. However, scheduling V2G operations remains challenging due to unpredictable EV user behavior, which affects the EV charging demands and limit the service capacities from both EVs and V2G stations. To address these issues, we propose a clustering-based multi-objective optimization framework for vehicle-pile matching and operation scheduling. Leveraging a hybrid canopy + K-means clustering algorithm, this approach dynamically pre-allocates vehicles and V2G stations to meet power regulation demands while accounting for spatial constraints and service capacities. In addition, the multi-objective optimization model integrates user credit and participation willingness to maximize demand satisfaction and V2G revenue. Numerical experiments using real-world vehicle data from T3Go validate the effectiveness of the proposed method, demonstrating its potential to overcome the complexities of V2G scheduling and significantly enhance grid performance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A clustering based multi-objective optimization approach for V2G service operation scheduling

  • 期刊论文

  • 发表日期：

    2025年7月7日

查看全文
  • Wenjun Zhou,
  • Zhouchun Huang,
  • Yuping Huang,
  • Tianren Zhang,
  • Xueying Zhao

摘要

The rapid adoption of electric vehicles (EVs) has positioned Vehicle-to-Grid (V2G) technology as a transformative solution for enhancing grid efficiency and stability. However, scheduling V2G operations remains challenging due to unpredictable EV user behavior, which affects the EV charging demands and limit the service capacities from both EVs and V2G stations. To address these issues, we propose a clustering-based multi-objective optimization framework for vehicle-pile matching and operation scheduling. Leveraging a hybrid canopy + K-means clustering algorithm, this approach dynamically pre-allocates vehicles and V2G stations to meet power regulation demands while accounting for spatial constraints and service capacities. In addition, the multi-objective optimization model integrates user credit and participation willingness to maximize demand satisfaction and V2G revenue. Numerical experiments using real-world vehicle data from T3Go validate the effectiveness of the proposed method, demonstrating its potential to overcome the complexities of V2G scheduling and significantly enhance grid performance.