A Classification Method for Complex Power Quality Disturbances Using EEMD and Rank Wavelet SVM

Liu, Zhigang; Cui, Yan; Li, Wenhui

doi:10.1109/tsg.2015.2397431

Cited by 161 publications

(84 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proposed methodology does remarkably well in classifying all single disturbances and outperforms most of the contemporary methodologies. The accuracy achieved exceeds those presented in [15] [16] [19] [20]. In addition, the designed method demonstrates that it is possible to identify a significant amount of complex power quality disturbances using only five binary decision stages (one for each single disturbance).…”

Section: Discussionmentioning

confidence: 72%

Optimized Complex Power Quality Classifier Using One vs. Rest Support Vector Machines

Yong¹,

Bhowmik²,

Magnago³

2017

EPE

View full text Add to dashboard Cite

Nowadays, power quality issues are becoming a significant research topic because of the increasing inclusion of very sensitive devices and considerable renewable energy sources. In general, most of the previous power quality classification techniques focused on single power quality events and did not include an optimal feature selection process. This paper presents a classification system that employs Wavelet Transform and the RMS profile to extract the main features of the measured waveforms containing either single or complex disturbances. A data mining process is designed to select the optimal set of features that better describes each disturbance present in the waveform. Support Vector Machine binary classifiers organized in a "One Vs Rest" architecture are individually optimized to classify single and complex disturbances. The parameters that rule the performance of each binary classifier are also individually adjusted using a grid search algorithm that helps them achieve optimal performance. This specialized process significantly improves the total classification accuracy. Several single and complex disturbances were simulated in order to train and test the algorithm. The results show that the classifier is capable of identifying >99% of single disturbances and >97% of complex disturbances.

show abstract

Section: Discussionmentioning

confidence: 72%

Optimized Complex Power Quality Classifier Using One vs. Rest Support Vector Machines

Yong¹,

Bhowmik²,

Magnago³

2017

EPE

View full text Add to dashboard Cite

show abstract

“…C L×N denotes the relative directions between each line and each PQM in the grid, and D N×1 denotes the relative directions between the TVDS and each PQM when disturbance event happens. Their elements are illustrated in Equations (1) and (2). Then the result-matrix R L×1 can be obtained by…”

Section: Limitation Of Existing Matrix-based Methodsmentioning

confidence: 99%

“…While the classification of PQ disturbance types has been the focus in many fruitful studies [2][3][4], the accurate location of a power quality disturbance source remains a problem less studied. Nevertheless, the location plays a critical role in determining the cause, responsibility, and effective mitigation strategies [5].…”

Section: Introductionmentioning

confidence: 99%

A Fault-Tolerant Location Approach for Transient Voltage Disturbance Source Based on Information Fusion

et al. 2016

View full text Add to dashboard Cite

This paper proposed a fault-tolerant approach based on information fusion (IF) to automatically locate the transient voltage disturbance source (TVDS) in smart distribution grids. We first defined three credibility factors that will influence the reliability of the direction-judgments at each power quality monitor (PQM). Then we proposed two rules of influence and a verification factor for the distributed generation (DG) integration. Based on the two sets of direction-judgment criteria, a novel decision-making method with fault tolerance based on the IF theory is proposed for automatic location of the TVDS. Three critical schemes, including credibility fusion, conflict weakening, and correction for DG integration, have been integrated in the proposed fusion method, followed by a reliability evaluation of the location results. The proposed approach was validated on the IEEE 13-node test feeder, and the TVDS location results demonstrated the effectiveness and fault tolerance of the IF based approach.

show abstract

“…From the perspective of classifier design steps, neural network (NN) [18][19][20], support vector machine (SVM) [21][22][23], fuzzy rule (FR) [24], decision tree (DT) [25][26][27] and extreme learning machine (ELM) [28] are commonly applied to the classification of PQ signals, and all achieve good results. However, the NN and SVM have to set more parameters.…”

Section: Introductionmentioning

confidence: 99%

Feature Selection of Power Quality Disturbance Signals with an Entropy-Importance-Based Random Forest

Huang

Cai

et al. 2016

Entropy

View full text Add to dashboard Cite

Power quality signal feature selection is an effective method to improve the accuracy and efficiency of power quality (PQ) disturbance classification. In this paper, an entropy-importance (EnI)-based random forest (RF) model for PQ feature selection and disturbance classification is proposed. Firstly, 35 kinds of signal features extracted from S-transform (ST) with random noise are used as the original input feature vector of RF classifier to recognize 15 kinds of PQ signals with six kinds of complex disturbance. During the RF training process, the classification ability of different features is quantified by EnI. Secondly, without considering the features with zero EnI, the optimal perturbation feature subset is obtained by applying the sequential forward search (SFS) method which considers the classification accuracy and feature dimension. Then, the reconstructed RF classifier is applied to identify disturbances. According to the simulation results, the classification accuracy is higher than that of other classifiers, and the feature selection effect of the new approach is better than SFS and sequential backward search (SBS) without EnI. With the same feature subset, the new method can maintain a classification accuracy above 99.7% under the condition of 30 dB or above, and the accuracy under 20 dB is 96.8%.

show abstract

A Classification Method for Complex Power Quality Disturbances Using EEMD and Rank Wavelet SVM

Cited by 161 publications

References 29 publications

Optimized Complex Power Quality Classifier Using One vs. Rest Support Vector Machines

Optimized Complex Power Quality Classifier Using One vs. Rest Support Vector Machines

A Fault-Tolerant Location Approach for Transient Voltage Disturbance Source Based on Information Fusion

Feature Selection of Power Quality Disturbance Signals with an Entropy-Importance-Based Random Forest

Contact Info

Product

Resources

About