Scholarlink

<p>Electric vehicle (EV) adoption is quickly increasing, necessitating efficient energy management strategies for photovoltaic (PV) electric vehicle charging stations (EVCS). Optimizing the operational cost of EVCS while maintaining efficiency, however, remains a significant challenge. This paper proposes a hybrid technique for energy management in PV EVCS. The proposed approach is the novel integration of Golden Eagle Optimization (GEO) and Multi Fidelity Deep Neural Network (MFDNN) and is referred to as GEO-MFDNN approach. The main objective is to reduce and optimize the EVCS structure’s total operational cost. The proposed GEO strategy is used to reduce the cost of EV charging, while the MFDNN methodology is used to forecast the best solution for the structure accurately. The proposed approach is put into practice on the MATLAB platform, utilizing a structured execution procedure. This technique indicates better performance compared to existing systems like Wild Horse Optimizer (WHO), Heap-Based Optimizer (HBO), and Particle Swarm Optimization (PSO) across various evaluation criteria. The proposed strategy incurs a cost of €13,000 as shown in the results. The results suggest that the primary aim of optimizing and minimizing the overall operational cost of the EVCS structure has been successfully achieved, demonstrating cost reductions and enhanced efficiency compared to previous methods.</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

An efficient hybrid GEO-MFDNN approach for energy management using photovoltaic electric vehicle charging station

  • 期刊论文

  • 发表日期：

    2025年5月2日

查看全文
  • C. Vennila,
  • Venkata Prasad Papana,
  • Ch. Venkata Krishna Reddy,
  • U. Arun Kumar

摘要

Electric vehicle (EV) adoption is quickly increasing, necessitating efficient energy management strategies for photovoltaic (PV) electric vehicle charging stations (EVCS). Optimizing the operational cost of EVCS while maintaining efficiency, however, remains a significant challenge. This paper proposes a hybrid technique for energy management in PV EVCS. The proposed approach is the novel integration of Golden Eagle Optimization (GEO) and Multi Fidelity Deep Neural Network (MFDNN) and is referred to as GEO-MFDNN approach. The main objective is to reduce and optimize the EVCS structure’s total operational cost. The proposed GEO strategy is used to reduce the cost of EV charging, while the MFDNN methodology is used to forecast the best solution for the structure accurately. The proposed approach is put into practice on the MATLAB platform, utilizing a structured execution procedure. This technique indicates better performance compared to existing systems like Wild Horse Optimizer (WHO), Heap-Based Optimizer (HBO), and Particle Swarm Optimization (PSO) across various evaluation criteria. The proposed strategy incurs a cost of €13,000 as shown in the results. The results suggest that the primary aim of optimizing and minimizing the overall operational cost of the EVCS structure has been successfully achieved, demonstrating cost reductions and enhanced efficiency compared to previous methods.