Scholarlink

<p>The accurate detection and classification of power quality events (PQEs) are critical for ensuring the stability, reliability, and efficiency of modern power systems, especially within the evolving landscape of smart grids and microgrids. This paper presents a comprehensive review of state-of-the-art feature extraction techniques for PQE detection, focusing on their application to non-stationary power signals. We systematically analyze and categorize the most widely adopted signal processing techniques and soft computing methodologies, evaluating their effectiveness in addressing the complex challenges of power quality monitoring. The study highlights the strengths and limitations of various feature extraction approaches, ranging from time domain to frequency-domain and time–frequency domain methods, and critically examines their suitability for real-time PQE detection in smart grid environments. A key contribution of this work is the identification of a novel framework for feature selection, which optimizes classification performance while minimizing computational complexity. The paper discusses the inherent trade-offs between computational efficiency and classification accuracy, particularly in applications where real-time processing is crucial. In addition, we address common pitfalls in feature selection, such as the risk of misapplications that may result in erroneous decision making and propose strategies to mitigate these issues. The analysis further explores the gap between theoretical advancements in PQE detection methods and their practical implementation in real-world power systems, offering insights into the integration of advanced computational techniques with current power quality monitoring systems. Through this comprehensive review, we provide a detailed roadmap for researchers and practitioners seeking to enhance the accuracy and efficiency of PQE classification systems. Our findings not only propose novel insights into feature extraction techniques but also highlight key areas for future research, particularly in the context of smart grid applications. This paper lays the groundwork for the development of more robust, real-time PQE detection systems, offering significant implications for the ongoing evolution of power quality management in modern electrical grids.</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 comprehensive review of feature extraction techniques for power quality event detection with novel approaches for enhanced classification in smart grids

  • 期刊论文

  • 发表日期：

    2025年5月30日

查看全文
  • Indu Sekhar Samanta,
  • Sarthak Mohanty,
  • Pravat Kumar Rout,
  • Shubhranshu Mohan Parida,
  • Subhasis Panda,
  • Mohit Bajaj,
  • Vojtech Blazek,
  • Lukas Prokop

摘要

The accurate detection and classification of power quality events (PQEs) are critical for ensuring the stability, reliability, and efficiency of modern power systems, especially within the evolving landscape of smart grids and microgrids. This paper presents a comprehensive review of state-of-the-art feature extraction techniques for PQE detection, focusing on their application to non-stationary power signals. We systematically analyze and categorize the most widely adopted signal processing techniques and soft computing methodologies, evaluating their effectiveness in addressing the complex challenges of power quality monitoring. The study highlights the strengths and limitations of various feature extraction approaches, ranging from time domain to frequency-domain and time–frequency domain methods, and critically examines their suitability for real-time PQE detection in smart grid environments. A key contribution of this work is the identification of a novel framework for feature selection, which optimizes classification performance while minimizing computational complexity. The paper discusses the inherent trade-offs between computational efficiency and classification accuracy, particularly in applications where real-time processing is crucial. In addition, we address common pitfalls in feature selection, such as the risk of misapplications that may result in erroneous decision making and propose strategies to mitigate these issues. The analysis further explores the gap between theoretical advancements in PQE detection methods and their practical implementation in real-world power systems, offering insights into the integration of advanced computational techniques with current power quality monitoring systems. Through this comprehensive review, we provide a detailed roadmap for researchers and practitioners seeking to enhance the accuracy and efficiency of PQE classification systems. Our findings not only propose novel insights into feature extraction techniques but also highlight key areas for future research, particularly in the context of smart grid applications. This paper lays the groundwork for the development of more robust, real-time PQE detection systems, offering significant implications for the ongoing evolution of power quality management in modern electrical grids.