Optimal Feature Selection for Power-Quality Disturbances Classification

Lee, Chun‐Yao; Shen, Yi-Xing

doi:10.1109/tpwrd.2011.2149547

Cited by 151 publications

(105 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It can also be seen that the new method can use the same feature subset to achieve satisfying classification accuracy under different noise environments. This overcomes the disadvantage that existing research [15] needs to select different feature subsets under different noise environments. Meanwhile, when RF is used as classifier and the dimension of the selected feature subset increases from 4 to 10, the classification accuracy of high SNR environment has not improved, but the classification accuracy of SNR is 20 dB has improved 1.2%.…”

Section: Comparison Experiments and Analysismentioning

confidence: 98%

“…Referring to [13,15], 15 kinds of PQ signals are generated by simulation, including normal (C0), sag (C1), swell (C2), interruption (C3), flicker (C4), transient (C5), harmonic (C6), notch (C7), spike (C8), harmonic with sag (C9), harmonic with swell (C10), harmonic with flicker (C11), sag with transient (C12), swell with transient (C13) and flicker with transient (C14). The sampling frequency is 3.2 kHz, and the fundamental frequency is 50 Hz.…”

Section: Feature Extraction Of Pq Signalsmentioning

confidence: 99%

“…The calculation methods of these features mainly refer to [13,15]. Among them, the calculation methods of features from F1 to F24 refer to [13], and calculation methods of features from F26 to F35 refer to [15].…”

Section: Feature Extraction Of Pq Signalsmentioning

confidence: 99%

“…Among them, the calculation methods of features from F1 to F24 refer to [13], and calculation methods of features from F26 to F35 refer to [15]. Moreover, there are six kinds of complex disturbances needed to be classified, and the classification of complex disturbances with transient is easy to be disturbed by noise and time-frequency energy of starting and ending points of voltage sag.…”

Section: Feature Extraction Of Pq Signalsmentioning

confidence: 99%

“…In past studies, feature selection was either in accordance with the filter method based on the features' statistical characteristics, which made it difficult to analyze the classification ability of the feature combination [13,14], or used the wrapper method combined with the particle swarm optimization [15], genetic algorithm [16], rough set theory [17] or other intelligent algorithms, then according to the classification results chose the optimal or sub-optimal feature subset, but the efficiency of the search algorithm is unsatisfactory. Meanwhile, existing feature selection methods have to select different feature subsets under different noise conditions, and this limits the application possibilities of feature selection methods in practical engineering.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Section: Comparison Experiments and Analysismentioning

confidence: 98%

Section: Feature Extraction Of Pq Signalsmentioning

confidence: 99%

Section: Feature Extraction Of Pq Signalsmentioning

confidence: 99%

Section: Feature Extraction Of Pq Signalsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

show abstract

Review of Signal Processing Techniques and Machine Learning Algorithms for Power Quality Analysis

Rahul

2020

Advcd Theory and Sims

View full text Add to dashboard Cite

The issue of power quality (PQ) has become more prominent over the last few decades as the demand of clean and high quality power is increasing around the globe. The effect of power quality disturbances on the equipment most of the time is very destructive, usually generates disruptions, which consecutively affects the other load connected to the power systems. The main purpose of this article is to present a comprehensive review of various power quality analysis techniques such as heuristic optimization, signal processing, machine learning, neural networks, artificial intelligence, and hardware implementation, so that a brief overview will be presented to the researcher and power engineers working in the field of power quality. Additionally, a comparative analysis is also reported on various methods based on several criteria including timing and accuracy, use of industrial and non-industrial data set, noisy and noiseless conditions, and finally single and multiple power quality events for analysis. More than 200 research publications are included for analysis and listed in reference so that it will be easy for the researcher in the domain of power quality to explore the possibility of further improvement in this field.

show abstract

A methodology for detection and classification of power quality disturbances using a real‐time operating system in the context of home energy management systems

et al. 2020

View full text Add to dashboard Cite

Demand-side management comprises a portfolio of actions on the consumers' side to ensure reliable power indices from the electrical system. The home energy management system (HEMS) is used to manage the consumption and production of energy in smart homes. However, the technology of HEMS architecture can be used for the detection and classification of power quality disturbances. This paper presents low-voltage metering hardware that uses an ARM Cortex M4 and real-time operating system to detect and classify power quality disturbances. In the context of HEMS, the proposed metering infrastructure can be used as a smart meter, which provides the service of power quality monitoring. For this type of application, there is a need to ensure that the development of this device has an acceptable cost, which is one of the reasons for the choice of an ARM microprocessor. However, managing a wide range of operations (data acquisition, data preprocessing, disturbance detection and classification, energy consumption, and data exchange) is a complex task and, consequently, requires the optimization of the embedded software. To overcome this difficulty, the use of a real-time operating system provided by Texas Instruments (called TI-RTOS) is proposed with the objective of managing operations at the hardware level. Thus, a methodology with low computational cost has been defined and embedded. The proposed approach uses a preprocessing stage to extract some features that are used as inputs to detect and classify disturbances. In this way, it was possible to evaluate and demonstrate the performance of the embedded algorithm when applied to synthetic and real power quality signals. Consequently, it is noted that the results are

show abstract

Optimal Feature Selection for Power-Quality Disturbances Classification

Cited by 151 publications

References 25 publications

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

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

Review of Signal Processing Techniques and Machine Learning Algorithms for Power Quality Analysis

A methodology for detection and classification of power quality disturbances using a real‐time operating system in the context of home energy management systems

Contact Info

Product

Resources

About