Scholarlink

<p>This manuscript presents a comprehensive approach for the energy management of Hybrid Energy Storage Systems in electric vehicles through a novel hybrid technique termed the Zebra Optimization Algorithm combined polam with the Recalling Enhanced Recurrent Neural Network, referred to as ZOA-RERNN method. The proposed method integrates ZOA to create a dataset of potential HESS input parameters, which is then utilized by RERNN to predict optimal input factors for the Hybrid ESS. The ZOA-RERNN approach maximises battery power, current, fluctuations, and super capacitor reference voltage by utilising the bidirectional DC-DC converter in HESS, providing increased efficiency and faster reaction times. The study addresses the limitations of existing Energy Management Systems (EMS) methods, ensuring more proficient and reliable results in energy management. Performance evaluation conducted on a MATLAB/Simulink platform demonstrates the proposed method's efficacy, achieving a battery power of 320W, surpassing existing techniques. This paper contributes to enhancing the efficiency and sustainability of EVs by resolving energy management challenges in HESS.</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

Zebra optimization algorithm and recalling enhanced recurrent neural network with enhancing energy management in electric vehicles for hybrid energy storage systems

  • 期刊论文

  • 发表日期：

    2025年6月21日

查看全文
  • K. R. Sughashini,
  • K. Rahimunnisa

摘要

This manuscript presents a comprehensive approach for the energy management of Hybrid Energy Storage Systems in electric vehicles through a novel hybrid technique termed the Zebra Optimization Algorithm combined polam with the Recalling Enhanced Recurrent Neural Network, referred to as ZOA-RERNN method. The proposed method integrates ZOA to create a dataset of potential HESS input parameters, which is then utilized by RERNN to predict optimal input factors for the Hybrid ESS. The ZOA-RERNN approach maximises battery power, current, fluctuations, and super capacitor reference voltage by utilising the bidirectional DC-DC converter in HESS, providing increased efficiency and faster reaction times. The study addresses the limitations of existing Energy Management Systems (EMS) methods, ensuring more proficient and reliable results in energy management. Performance evaluation conducted on a MATLAB/Simulink platform demonstrates the proposed method's efficacy, achieving a battery power of 320W, surpassing existing techniques. This paper contributes to enhancing the efficiency and sustainability of EVs by resolving energy management challenges in HESS.