Scholarlink

Solar photovoltaic (PV) systems play a crucial role in the global shift toward renewable energy sources. Their efficiency can be significantly impacted by issues such as partial shading, degradation, short circuits, and inverter faults. Identifying problems accurately and diagnosing them is essential for ensuring the system’s longevity and maintaining optimal performance. This research investigates the utilization of artificial intelligence of things (AIOT) and complex IT methods to detect issues and perform diagnostics in SPV systems using Matlab. By integrating IoT sensors with AI algorithms, real-time monitoring and analysis of SPV systems become feasible. An automated learning model using IoT devices can identify trends indicating malfunction and deliver timely notifications and valuable insights. This approach improves overall energy production, reduces downtime, and enhances predictive maintenance capabilities. The study emphasizes the effectiveness of various AI and computational techniques in recognizing and diagnosing different SPV problems, including supervised and unsupervised learning, neural networks, and edge computing.

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

Different Computational Techniques for Identification of Faults in SPV

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Rachit Saxena,
  • Nagendra Kumar Swarnkar,
  • Gaurav Jain,
  • Rajnandani Yadav,
  • R. K. Kumawat,
  • N. P. Patidar

摘要

Solar photovoltaic (PV) systems play a crucial role in the global shift toward renewable energy sources. Their efficiency can be significantly impacted by issues such as partial shading, degradation, short circuits, and inverter faults. Identifying problems accurately and diagnosing them is essential for ensuring the system’s longevity and maintaining optimal performance. This research investigates the utilization of artificial intelligence of things (AIOT) and complex IT methods to detect issues and perform diagnostics in SPV systems using Matlab. By integrating IoT sensors with AI algorithms, real-time monitoring and analysis of SPV systems become feasible. An automated learning model using IoT devices can identify trends indicating malfunction and deliver timely notifications and valuable insights. This approach improves overall energy production, reduces downtime, and enhances predictive maintenance capabilities. The study emphasizes the effectiveness of various AI and computational techniques in recognizing and diagnosing different SPV problems, including supervised and unsupervised learning, neural networks, and edge computing.