Recognition and Classification of Power Quality Disturbances by DWT-MRA and SVM Classifier

Jandan, Fayyaz Ali; Khokhar, Suhail; Shaha, Syed Abid Ali; Abbasi, F.

doi:10.14569/ijacsa.2019.0100348

Cited by 8 publications

(12 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The authors further explained that suitable mother wavelet can be determined based on properties such as PQ indices calculation, orthogonality, maximum number of vanishing moments, and compactness support. In the literature, the most frequently used mother wavelet class for PQD studies is the fourth order daubechies 4 wavelet (DB4) as it possesses the described characteristics and it is known to have a close similarity to power disturbance signal [51], Daubechies was deployed in studies such as the works in [23], [50], [57], [62]. With regards to feature vector decomposition modes, various authors have decomposed generated signal samples at various resolution levels to get wavelet coefficients that suits their classification specifications.…”

Section: ) Pqd Feature Extraction/signal Analysis Stagementioning

confidence: 99%

“…Ahila et al [51] deployed a PSO based wrapper selection model to obtain the optimal number of hidden nodes and to select the beneficial subset of features in their PQD classification study. Despite the fact that the work in [50] did not deploy any feature selection method, the authors acknowledged that the use of optimization technique for feature selection creates better classification even though they may require huge computational resources, time and complex simulations. As a means to obtain optimal structure coupled with reduced feature vector dimension, Abdoos et al [49] deployed sequential forward selection (SFS) and sequential backward selection (SBS) as wrapper based methods and Gram-Schmidt orthogonalization (GSO) as feature selection and optimization techniques respectively.…”

Section: ) Pqd Feature Selection/optimization Stagementioning

confidence: 99%

See 1 more Smart Citation

A Review of Machine Learning Approaches to Power System Security and Stability

2020

View full text Add to dashboard Cite

Increasing use of renewable energy sources, liberalized energy markets and most importantly, the integrations of various monitoring, measuring and communication infrastructures into modern power system network offer the opportunity to build a resilient and efficient grid. However, it also brings about various threats of instabilities and security concerns in form of cyberattack, voltage instability, power quality (PQ) disturbance among others to the complex network. The need for efficient methodologies for quicker identification and detection of these problems have always been a priority to energy stakeholders over the years. In recent times, machine learning techniques (MLTs) have proven to be effective in numerous applications including power system studies. In the literature, various MLTs such as artificial neural networks (ANN), Decision Tree (DT), support vector machines (SVM) have been proposed, resulting in effective decision making and control actions in the secured and stable operations of the power system. Given this growing trend, this paper presents a comprehensive review on the most recent studies whereby MLTs were developed for power system security and stability especially in cyberattack detections, PQ disturbance studies and dynamic security assessment studies. The aim is to highlight the methodologies, achievements and more importantly the limitations in the classifier(s) design, dataset and test systems employed in the reviewed publications. A brief review of reinforcement learning (RL) and deep reinforcement learning (DRL) approaches to transient stability assessment is also presented. Finally, we highlighted some challenges and directions for future studies.

show abstract

Section: ) Pqd Feature Extraction/signal Analysis Stagementioning

confidence: 99%

Section: ) Pqd Feature Selection/optimization Stagementioning

confidence: 99%

A Review of Machine Learning Approaches to Power System Security and Stability

2020

View full text Add to dashboard Cite

show abstract

“…En la construcción de la matriz de mediciones [] es donde se puede analizar la potencialidad del sensado comprimido, si hablamos de un sistema eléctrico por ejemplo, la matriz [] puede ser armada en función de la matriz de admitancias y se podría estimar estados en cada una de las barras, encontrar distorsiones armónicas en las barras, estimar las cargas de menor factor de potencia del sistema eléctrico, estimar pérdidas no técnicas del sistema, estimar despachos de carga, estimar curvas de demanda eso solo tomando como referencia a un sistema eléctrico, el sensado comprimido puede escalar a otras ramas de la ciencia y poder estimar parámetros en los que se tenga pocos datos con una buena aproximación y bajos recursos computacionales (13,(28)(29)(30)(31)(32)(33)(34)(35) .…”

Section: Figura 4 Como Formar La Matriz De Mediciones [] Fuente: Propiaunclassified

Localización de Distorsiones Armónicas en Sistemas Eléctricos usando Sensado Comprimido

Vásquez

Inga

2021

inycomp

View full text Add to dashboard Cite

El presente artículo es un estudio del estado del arte, donde se analiza las ventajas y desventajas de las diferentes técnicas clásicas de procesamiento digital de señales usadas para identificar frecuencias armónicas que distorsiona las formas de onda de voltaje y corriente de una red eléctrica. Tomando como referencia las técnicas clásicas que determinan la distorsión armónica de una señal eléctrica. Se propone una alternativa para la detección de frecuencias armónicas en una forma de onda eléctrica, basada en algoritmos de sensado comprimido; esta técnica extrae una muestra eficiente y reducida de la señal en estudio, dicha muestra es transformada al dominio de la frecuencia mediante una base de transformación que, para el presente caso de estudio es la transformada discreta del coseno (DCT). La señal reducida en el dominio de la frecuencia es sometida a un proceso de optimización no lineal, el cual clasifica los coeficientes, extrae los más representativos y convierte en cero a los menos representativos, es aquí donde salen a relucir de una forma clara y precisa las frecuencias armónicas, inmersas en la forma de onda eléctrica, con las cuales se calcula la distorsión armónica (THD). Este artículo muestra un ejemplo de la técnica de sensado comprimido, para la detección de frecuencias armónicas en una señal sinusoidal teórica la cual está contaminada por armónicos de tercero y quinto orden, se extrae el vector de coeficientes optimizado y se identifica las frecuencias armónicas.

show abstract

“…Wavelet-based transform often being categorized into continuous wavelet transform (CWT) and discrete wavelet transform (DWT). It is said that CWT requires higher computing power than DWT [7] and that it needs an infinite number of inputs resulting in the redundancy of provided information [8]. Most of the time, researchers combine DWT with multi-resolution analysis (MRA) to increase their effectiveness in detecting PQDs [8].…”

Section: Introductionmentioning

confidence: 99%

“…It is said that CWT requires higher computing power than DWT [7] and that it needs an infinite number of inputs resulting in the redundancy of provided information [8]. Most of the time, researchers combine DWT with multi-resolution analysis (MRA) to increase their effectiveness in detecting PQDs [8]. A study in 2016 used maximum overlap discrete wavelet transform [9].…”

Section: Introductionmentioning

confidence: 99%

Comparison analysis of different classification methods of power quality disturbances

Zakaria

Said

Rosmin

et al. 2022

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Good power quality delivery has always been in high demand in power system utilities where different types of power quality disturbances are the main obstacles. As these disturbances have distinct characteristics and even unique mitigation techniques, their detection and classification should be correct and effective. In this study, eight different types of power quality disturbances were synthetically generated, by using a mathematical approach. Then, continuous wavelet transform (CWT) and discrete wavelet transform with multi-resolution analysis (DWT-MRA) were applied, which eight features were then extracted from the synthesized signals. Three classifiers namely, decision tree (DT), support vector machine (SVM) and k-nearest neighbors (KNN) were trained to classify these disturbances. The accuracy of the classifiers was evaluated and analyzed. The best classifier was then integrated with the full model, which the performance of the proposed model was observed with 50 random signals, with and without noise. This study found that wavelet-transform was effective to localize the disturbances at the instant of their occurrence. On the other hand, the SVM classifier is superior to other classifiers with an overall accuracy of 94%. Still, the need for these classifiers to be further optimized is crucial in ensuring a more effective detection and classification system.</span>

show abstract

Recognition and Classification of Power Quality Disturbances by DWT-MRA and SVM Classifier

Cited by 8 publications

References 28 publications

A Review of Machine Learning Approaches to Power System Security and Stability

A Review of Machine Learning Approaches to Power System Security and Stability

Localización de Distorsiones Armónicas en Sistemas Eléctricos usando Sensado Comprimido

Comparison analysis of different classification methods of power quality disturbances

Contact Info

Product

Resources

About