Scholarlink

<p>The integration of Renewable Energy Sources (RESs) necessitates highly efficient and reliable power conversion systems to ensure maximum energy utilization. This work proposes a novel Interleaved Zeta-Luo Converter (IZLC) topology, designed to enhance voltage conversion efficiency in photovoltaic (PV) systems. By directly interfacing the PV array with the IZLC, the system achieves a simplified design with reduced component count, thereby lowering costs and improving reliability. To further optimize performance under dynamic environmental conditions, a Hippopotamus Optimization Algorithm–based Recurrent Neural Network (HOA-RNN) is employed for Maximum Power Point Tracking (MPPT). The proposed MPPT approach demonstrates superior accuracy and adaptability, achieving a tracking efficiency of 99.87% with an execution time of only 0.015&#xa0;s, outperforming conventional methods such as SSOA with 98.38% and 1.05&#xa0;s, ZOA with 99.84% and 0.38&#xa0;s and MDSGWA-AFLC with 98.66% and 0.0197&#xa0;s. Simulation and hardware validation confirm that the combined IZLC and HOA-RNN framework significantly improves overall system effectiveness, delivering a power conversion efficiency of 93.6%. Both qualitative and quantitative analyses highlight the robustness, fast response and scalability for sustainable solar energy integration into modern power networks.</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

A Design of Interleaved Zeta-Luo Converter with Optimized RNN MPPT for Energy Enhancement in PV Systems

  • 期刊论文

  • 发表日期：

    2025年10月15日

查看全文
  • J. Daniel Sathyaraj,
  • M. Faustino Adlinde,
  • Krishna Prakash Arunachalam,
  • K. Natarajan

摘要

The integration of Renewable Energy Sources (RESs) necessitates highly efficient and reliable power conversion systems to ensure maximum energy utilization. This work proposes a novel Interleaved Zeta-Luo Converter (IZLC) topology, designed to enhance voltage conversion efficiency in photovoltaic (PV) systems. By directly interfacing the PV array with the IZLC, the system achieves a simplified design with reduced component count, thereby lowering costs and improving reliability. To further optimize performance under dynamic environmental conditions, a Hippopotamus Optimization Algorithm–based Recurrent Neural Network (HOA-RNN) is employed for Maximum Power Point Tracking (MPPT). The proposed MPPT approach demonstrates superior accuracy and adaptability, achieving a tracking efficiency of 99.87% with an execution time of only 0.015 s, outperforming conventional methods such as SSOA with 98.38% and 1.05 s, ZOA with 99.84% and 0.38 s and MDSGWA-AFLC with 98.66% and 0.0197 s. Simulation and hardware validation confirm that the combined IZLC and HOA-RNN framework significantly improves overall system effectiveness, delivering a power conversion efficiency of 93.6%. Both qualitative and quantitative analyses highlight the robustness, fast response and scalability for sustainable solar energy integration into modern power networks.