Scholarlink

<p>This paper proposes a hybrid method for network expansion planning for electric vehicle charging stations. The hybrid method is the combination of Eurasian Oystercatcher optimizer (EOO) and spiking neural network (SNN) approach and is usually referred as EOO-SNN approach. The major purpose of the work is to extend the optimal charging strategy for EVs, which includes the allocation of charging resources to decrease the charging costs, increase the charging efficiency, and decrease the impact on the power grid. The EOO is used to optimize various aspects, such as charging time, charging station placement, and network expansion planning. The ideal solution is predicted using the SNN. The approach also combined with smart grid technologies, such as demand response mechanisms and fuel cell integration with battery energy storage system, to optimize the energy system and ensure efficient and sustainable EV charging. The proposed method supports scalability/adaptability in EV charging systems, effective charging strategy formulation, and worldwide optimisation of charging infrastructure growth. The proposed method’s effectiveness is then evaluated on the MATLAB platform and compared to other existing approaches. The efficacy of the proposed system is high as 45%.</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

Fuel cell EV for smart charging with stochastic network planning using hybrid EOO-SNN approach

  • 期刊论文

  • 发表日期：

    2025年7月7日

查看全文
  • S. Dhas Bensam,
  • K. S. Kavitha Kumari,
  • Amarendra Alluri,
  • P. Rajesh

摘要

This paper proposes a hybrid method for network expansion planning for electric vehicle charging stations. The hybrid method is the combination of Eurasian Oystercatcher optimizer (EOO) and spiking neural network (SNN) approach and is usually referred as EOO-SNN approach. The major purpose of the work is to extend the optimal charging strategy for EVs, which includes the allocation of charging resources to decrease the charging costs, increase the charging efficiency, and decrease the impact on the power grid. The EOO is used to optimize various aspects, such as charging time, charging station placement, and network expansion planning. The ideal solution is predicted using the SNN. The approach also combined with smart grid technologies, such as demand response mechanisms and fuel cell integration with battery energy storage system, to optimize the energy system and ensure efficient and sustainable EV charging. The proposed method supports scalability/adaptability in EV charging systems, effective charging strategy formulation, and worldwide optimisation of charging infrastructure growth. The proposed method’s effectiveness is then evaluated on the MATLAB platform and compared to other existing approaches. The efficacy of the proposed system is high as 45%.