A comprehensive review of feature extraction techniques for power quality event detection with novel approaches for enhanced classification in smart grids

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F25%3A10258001" target="_blank" >RIV/61989100:27240/25:10258001 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61989100:27730/25:10258001

Výsledek na webu

<a href="https://link.springer.com/article/10.1007/s00202-025-03149-w" target="_blank" >https://link.springer.com/article/10.1007/s00202-025-03149-w</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s00202-025-03149-w" target="_blank" >10.1007/s00202-025-03149-w</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A comprehensive review of feature extraction techniques for power quality event detection with novel approaches for enhanced classification in smart grids

Popis výsledku v původním jazyce

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. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

Název v anglickém jazyce

A comprehensive review of feature extraction techniques for power quality event detection with novel approaches for enhanced classification in smart grids

Popis výsledku anglicky

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. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20200 - Electrical engineering, Electronic engineering, Information engineering

Projekt

<a href="/cs/project/TN02000025" target="_blank" >TN02000025: Národní centrum pro energetiku II</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Electrical Engineering

ISSN

0948-7921

e-ISSN

1432-0487

Svazek periodika

30.5.2025

Číslo periodika v rámci svazku

30 May 2025

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

33

Strana od-do

nestránkováno

Kód UT WoS článku

001499200400001

EID výsledku v databázi Scopus

2-s2.0-105006920319