Scholarlink

Microgrids have emerged as a promising solution for enhancing the reliability and efficiency of power distribution systems. The integration of both AC and DC sources in a microgrid poses unique challenges, particularly in the context of fault detection, classification, and location. This study presents an innovative approach utilizing artificial neural networks (ANNs) for fault detection, classification, and location in AC-DC Solar PV microgrids. The research focuses on enhancing the reliability of microgrid systems by leveraging the capabilities of ANNs. The methodology involves training ANNs to accurately detect and classify faults while precisely calculating their locations within the intricate AC-DC hybrid architecture of Solar PV microgrids. The results demonstrate the effectiveness of the proposed approach in improving fault analysis, thereby contributing to the robustness and efficiency of renewable energy systems. This research not only advances fault detection techniques but also underscores the significance of ANNs in addressing challenges specific to AC-DC Solar PV microgrids. This method can apply to other microgrids also.

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

Artificial Neural Network-Based Fault Detection, Classification, and Location of AC-DC Microgrid

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Aravinda Shilpa Konathala,
  • Jasmitha Kandregula,
  • Saranya Munukutla,
  • Chandrika Bankupalli,
  • Pujitha Vugiri,
  • Villuri Mahalakshmi Naidu

摘要

Microgrids have emerged as a promising solution for enhancing the reliability and efficiency of power distribution systems. The integration of both AC and DC sources in a microgrid poses unique challenges, particularly in the context of fault detection, classification, and location. This study presents an innovative approach utilizing artificial neural networks (ANNs) for fault detection, classification, and location in AC-DC Solar PV microgrids. The research focuses on enhancing the reliability of microgrid systems by leveraging the capabilities of ANNs. The methodology involves training ANNs to accurately detect and classify faults while precisely calculating their locations within the intricate AC-DC hybrid architecture of Solar PV microgrids. The results demonstrate the effectiveness of the proposed approach in improving fault analysis, thereby contributing to the robustness and efficiency of renewable energy systems. This research not only advances fault detection techniques but also underscores the significance of ANNs in addressing challenges specific to AC-DC Solar PV microgrids. This method can apply to other microgrids also.