Scholarlink

<p>The demand for EV charging is dynamic and uncertain and is often overlooked by conventional charging scheduling techniques. As a result, waiting times can differ significantly, which irritates EV owners and reduces overall charging efficiency. To overcome these issues, this manuscript presents an innovative technique for increasing EVCS utilization by reducing the waiting time of users. The proposed approach uses the wombat optimization algorithm (WOA) enhanced by opposition-based learning (OBL) and generalized Lagrangian neural networks (GLNN), which is termed the WOA-GLNN approach. The major aim of the proposed technique is to improve resource allocation efficiency, increase charging station utilization, and reduce waiting times for EV users. The WOA is utilized to optimize the charging schedules. The GLNN algorithm is used to predict the effectiveness of waiting time estimation. The proposed strategy is evaluated and compared using the MATLAB platform to other existing strategies. The proposed strategy determines better outcomes compared to existing techniques such as spotted hyena optimizer (SHO), multi-objective particle swarm optimization (MOPSO), and chaotic Harris Hawks optimization (CHHO). The proposed method achieves an average waiting time of 4.5&#xa0;min, an execution time of 0.35&#xa0;s, a charging station utilization of 95%, and then are source allocation efficiency of 99%. These findings indicate that the proposed technique minimizes the waiting time for EV users while simultaneously increasing charging station utilization compared to existing approaches.</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

Enhancing electric vehicle charging station utilization by reducing users waiting times through WOA-GLNN approach

  • 期刊论文

  • 发表日期：

    2025年7月4日

查看全文
  • R. Gunasekaran,
  • M. R. Mohanraj,
  • R. Senthilkumar,
  • R. S. Kamalakannan

摘要

The demand for EV charging is dynamic and uncertain and is often overlooked by conventional charging scheduling techniques. As a result, waiting times can differ significantly, which irritates EV owners and reduces overall charging efficiency. To overcome these issues, this manuscript presents an innovative technique for increasing EVCS utilization by reducing the waiting time of users. The proposed approach uses the wombat optimization algorithm (WOA) enhanced by opposition-based learning (OBL) and generalized Lagrangian neural networks (GLNN), which is termed the WOA-GLNN approach. The major aim of the proposed technique is to improve resource allocation efficiency, increase charging station utilization, and reduce waiting times for EV users. The WOA is utilized to optimize the charging schedules. The GLNN algorithm is used to predict the effectiveness of waiting time estimation. The proposed strategy is evaluated and compared using the MATLAB platform to other existing strategies. The proposed strategy determines better outcomes compared to existing techniques such as spotted hyena optimizer (SHO), multi-objective particle swarm optimization (MOPSO), and chaotic Harris Hawks optimization (CHHO). The proposed method achieves an average waiting time of 4.5 min, an execution time of 0.35 s, a charging station utilization of 95%, and then are source allocation efficiency of 99%. These findings indicate that the proposed technique minimizes the waiting time for EV users while simultaneously increasing charging station utilization compared to existing approaches.