Scholarlink

<p>This work proposes a hybrid approach to managing the energy of different microgrids (MG) with EV charging. The hybrid method that is being proposed involves the simultaneous use of the golden jackal optimization (GJO) and progressive conditional generative adversarial network (PCGAN). Thus, it is known as the GJO-PCGAN approach. The recommended strategy attempts to manage the energy of numerous MG with EV charging while minimizing transmission losses, operational expenses, and carbon emissions. Energy management of the grid with EV charging comes from fuel cells, wind turbines, and photovoltaic sources. Diesel engines provide the electricity needed to charge electric vehicles on days when renewable energy sources are not enough. The EV’s charging and discharging schedules are optimized using the GJO approach. The PCGAN approach is used to forecast the ideal EV control system. Through the use of the MATLAB platform, the proposed method’s performance is verified and compared with that of previous methods. The proposed approach outperforms all current methods, including the random forest algorithm, salp swarm algorithm and generalized predictive control. In comparison with the existing approaches, the proposed methodology has a lower transmission loss of 0.01&#xa0;MW.</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

Multiple microgrids with electric vehicle charging in a hybrid GJO-PCGAN approach for energy management

  • 期刊论文

  • 发表日期：

    2025年1月2日

查看全文
  • Sankar Rangasamy,
  • S. Arun Prakash,
  • Nitin Nandkumar Sakhare,
  • U. Arun Kumar

摘要

This work proposes a hybrid approach to managing the energy of different microgrids (MG) with EV charging. The hybrid method that is being proposed involves the simultaneous use of the golden jackal optimization (GJO) and progressive conditional generative adversarial network (PCGAN). Thus, it is known as the GJO-PCGAN approach. The recommended strategy attempts to manage the energy of numerous MG with EV charging while minimizing transmission losses, operational expenses, and carbon emissions. Energy management of the grid with EV charging comes from fuel cells, wind turbines, and photovoltaic sources. Diesel engines provide the electricity needed to charge electric vehicles on days when renewable energy sources are not enough. The EV’s charging and discharging schedules are optimized using the GJO approach. The PCGAN approach is used to forecast the ideal EV control system. Through the use of the MATLAB platform, the proposed method’s performance is verified and compared with that of previous methods. The proposed approach outperforms all current methods, including the random forest algorithm, salp swarm algorithm and generalized predictive control. In comparison with the existing approaches, the proposed methodology has a lower transmission loss of 0.01 MW.