A New Approach for Fault Classification in Microgrids Using Optimal Wavelet Functions Matching Pursuit

Abdelgayed, Tamer S.; Morsi, Walid G.; Sidhu, T.S.

doi:10.1109/tsg.2017.2672881

Cited by 100 publications

(57 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the major problem to execute the wavelet transform method is that the system performance is further reduced by the presence of high‐level noises in current or voltage signals. To increase the adaptability, by considering the above issue related to high‐level noises, a hybrid method is suggested in Abdelgayed et al To extract the most suitable components, machine learning‐based algorithm is implemented in this approach. It helps to extract the hidden features in a better and easy way.…”

Section: Protection Strategy For Microgridmentioning

confidence: 99%

Distributed generation hybrid AC/DC microgrid protection: A critical review on issues, strategies, and future directions

2020

View full text Add to dashboard Cite

Summary The integration of distributed energy resources (DERs) with conventional systems emerges as an intelligent solution for providing uninterrupted and secure power even at times of high load demand. Better load management with a mature fault handling mechanism makes AC a viable option which has an efficiency of 78.24%. In contrast with less power loss and slightly better efficiency of 84.6%, DC microgrid is a reliable option in a low power environment. In order to accommodate all operating conditions and load types, a hybrid system can be designed with a theoretical efficiency of more than 90%. Bidirectional power flows, low inertia, the transition between different modes of operations are the challenges for the protection of alternating current (AC) and direct current (DC) microgrid systems. Power balance fluctuation, absence of zero‐crossing currents, selection of suitable grounding, and coordination between different rating devices restrict the hybrid system to achieve the said efficiency constantly. This paper reviews in detail of existing protection along with grid‐connected algorithms for both modes of operation. Finally, the limitation, major hurdles, and future course of action for a reliable, efficient, and secure hybrid grid system are figured out.

show abstract

Section: Protection Strategy For Microgridmentioning

confidence: 99%

Distributed generation hybrid AC/DC microgrid protection: A critical review on issues, strategies, and future directions

2020

View full text Add to dashboard Cite

show abstract

“…Many features such as entropy (Ent), energy (E), mean value (M), standard deviation (Sd), and RMS were widely used in several research papers as the most informative and discriminating features. By carefully evaluating those research studies [14,52,[56][57][58], the feature set provided by probabilistic neural network based artificial bee colony (PNN-ABC) optimal feature collection algorithm by Khokhar et al [51] is exploited in our study. Proposed favorable features are [E (d1), Kurtosis (KT)(d2), RMS (d3), Skewness (SK)(d4), SK (d5), E (d6), RMS (d7), Ent (d8), KT (d8)] which extracted from Daubechies mother wavelet at level 4 and in different levels of decompositions.…”

Section: Signal Features Extraction and Selectionmentioning

confidence: 99%

Online power quality disturbance detection by support vector machine in smart meter

Parvez

Aghili

Sarwat

et al. 2018

J. Mod. Power Syst. Clean Energy

View full text Add to dashboard Cite

Power quality assessment is an important performance measurement in smart grids. Utility companies are interested in power quality monitoring even in the low level distribution side such as smart meters. Addressing this issue, in this study, we propose segregation of the power disturbance from regular values using one-class support vector machine (OCSVM). To precisely detect the power disturbances of a voltage wave, some practical wavelet filters are applied. Considering the unlimited types of waveform abnormalities, OCSVM is picked as a semisupervised machine learning algorithm which needs to be trained solely on a relatively large sample of normal data. This model is able to automatically detect the existence of any types of disturbances in real time, even unknown types which are not available in the training time. In the case of existence, the disturbances are further classified into different types such as sag, swell, transients and unbalanced. Being light weighted and fast, the proposed technique can be integrated into smart grid devices such as smart meter in order to perform a real-time disturbance monitoring. The continuous monitoring of power quality in smart meters will give helpful insight for quality power transmission and management.

show abstract

“…single line to ground (SLG), double line to ground (DLG), double line (LL), and three-phase (TP) fault]. In [26], a matching pursuit algorithm was used to extract hidden fault features from the current signal. The hidden features were then supplied to four different classifiers to detect and classify the faults.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, they are exposed to the communication failure. Furthermore, existing intelligent fault detection schemes [25][26][27] use signal processing methods such as Fourier transform and wavelet transform to extract features from the raw fault signal. The features are then used by intelligent classifiers [e.g.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Network‐Based Intelligent Protection Strategy for Microgrids

Bukhari

Kim

Mehmood

et al. 2020

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

A New Approach for Fault Classification in Microgrids Using Optimal Wavelet Functions Matching Pursuit

Cited by 100 publications

References 30 publications

Distributed generation hybrid AC/DC microgrid protection: A critical review on issues, strategies, and future directions

Distributed generation hybrid AC/DC microgrid protection: A critical review on issues, strategies, and future directions

Online power quality disturbance detection by support vector machine in smart meter

Convolutional Neural Network‐Based Intelligent Protection Strategy for Microgrids

Contact Info

Product

Resources

About