Scholarlink

<p>With the increased prevalence of Electric Vehicles (EVs), efficient charge scheduling has emerged as a critical aspect for ensuring user convenience and managing overall energy demand. Charge scheduling refers to the strategic planning of when, where, and how EVs are charged. However, scheduling a large number of EVs increases grid dependency, potentially leading to overloads during peak demand periods. Furthermore, many existing charge scheduling algorithms require longer waiting times and charge only a minimum number of vehicles. Hence, a Deep Kronecker Network with Harmonic Masterpiece Optimization Algorithm (DKN_Ha-MOA) is established for efficient charge scheduling in this work. Initially, the Internet of Electric Vehicles (IoEV) is simulated, and a path is selected using the Harmonic Masterpiece Optimization Algorithm (Ha-MOA). Here, Ha-MOA is designed by incorporating harmonic analysis and the Masterpiece Optimization Algorithm (MOA). Furthermore, charge scheduling is done using a Deep Kronecker Network (DKN) trained by Ha-MOA. Moreover, charge scheduling is done by considering parameters like charging cost, best slot, waiting time, and cancellation penalty. Moreover, DKN_Ha-MOA effectively optimized the performance measures by attaining a waiting time of 0.688&#xa0;s, a distance of 9.251&#xa0;km, and an energy of 10.230 kWh, and the maximum number of EVs successfully charged is 296.</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

Multi-aggregator Electric Vehicle Charge Scheduling Using a Novel Harmonic Masterpiece Optimization

  • 期刊论文

  • 发表日期：

    2025年11月6日

查看全文
  • J. Anishkumar,
  • Monica P Suresh,
  • S. Sengottaian,
  • S. Krishnan

摘要

With the increased prevalence of Electric Vehicles (EVs), efficient charge scheduling has emerged as a critical aspect for ensuring user convenience and managing overall energy demand. Charge scheduling refers to the strategic planning of when, where, and how EVs are charged. However, scheduling a large number of EVs increases grid dependency, potentially leading to overloads during peak demand periods. Furthermore, many existing charge scheduling algorithms require longer waiting times and charge only a minimum number of vehicles. Hence, a Deep Kronecker Network with Harmonic Masterpiece Optimization Algorithm (DKN_Ha-MOA) is established for efficient charge scheduling in this work. Initially, the Internet of Electric Vehicles (IoEV) is simulated, and a path is selected using the Harmonic Masterpiece Optimization Algorithm (Ha-MOA). Here, Ha-MOA is designed by incorporating harmonic analysis and the Masterpiece Optimization Algorithm (MOA). Furthermore, charge scheduling is done using a Deep Kronecker Network (DKN) trained by Ha-MOA. Moreover, charge scheduling is done by considering parameters like charging cost, best slot, waiting time, and cancellation penalty. Moreover, DKN_Ha-MOA effectively optimized the performance measures by attaining a waiting time of 0.688 s, a distance of 9.251 km, and an energy of 10.230 kWh, and the maximum number of EVs successfully charged is 296.