Optimal feature selection for classification of the power quality events using wavelet transform and least squares support vector machines

In this paper, a new optimal feature selection based power quality event recognition system is proposed for the classification of power quality events. While Apriori algorithm is capable of processing categorical data, an effective feature vector, which represents distinctive features of digital power quality event data, has been obtained by means of the proposed k-means based Apriori algorithm feature selection approach. The proposed k-means based Apriori algorithm feature selection approach is presented with a power quality event recognition system. In the power quality event recognition system, normalization and segmentation processes have been applied to three-phase event voltage signals. Using 9-level multiresolution analysis, wavelet transform coefficients of the event signals have been obtained. By applying nine different feature extraction processes to these coefficients, a 90 dimensional feature vector belonging to three-phase event voltage signals has been extracted. Optimal feature vector has been obtained by applying the k-means based Apriori algorithm feature selection approach to the obtained feature vector, which has been applied as the last step to the input of the least squares support vector machine classifier and recognition performance results have been obtained. Real power quality event data have been used to evaluate the performance of the proposed feature selection approach and power quality event recognition system. According to the results, the proposed k-means based Apriori algorithm feature selection approach and power quality event recognition system are efficient, reliable and applicable and classify three-phase event types with a high degree of accuracy.     

An effective wavelet-based feature extraction method for classification of power quality disturbance signals

This paper presents a wavelet norm entropy-based effective feature extraction method for power quality (PQ) disturbance classification problem. The disturbance classification schema is performed with wavelet-neural network (WNN). It performs a feature extraction and a classification algorithm composed of a wavelet feature extractor based on norm entropy and a classifier based on a multi-layer perceptron. The PQ signals used in this study are seven types. The performance of this classifier is evaluated by using total 2800 PQ disturbance signals which are generated the based model. The classification performance of different wavelet family for the proposed algorithm is tested. Sensitivity of WNN under different noise conditions which are different levels of noises with the signal to noise ratio is investigated. The rate of average correct classification is about 92.5% for the different PQ disturbance signals under noise conditions.     

Directional relaying using support vector machine for double circuit transmission lines including cross-country and inter-circuit faults

The conventional distance relaying algorithms are unable to detect the inter-circuit faults, cross-country faults, high resistance faults which may occur in a double circuit line. This paper presents combined Discrete Wavelet Transform (DWT) and Support Vector Machine (SVM) based directional relaying and fault classification scheme including inter-circuit faults, cross-country faults and high resistance faults. SVM modules are designed for forward or reverse fault identification and fault classification using single terminal data. The 3rd level approximate discrete wavelet transform coefficients of three phase current signals only have been used. Proposed method is tested with variations in fault type, fault location, fault inception angle, fault resistance, inter-circuit faults, and cross-country faults. The proposed method based on SVM does not need any threshold to operate which is an exceptional attribute for a protective function. As SVMs are not based on comparing with some threshold, rather initially the SVMs are trained with the wide variety of fault patterns which is an offline process and then the trained SVMs are tested online to detect and classify the fault within short time. The test results show that all types of shunt faults can be identified within half cycle time. The proposed scheme offers both primary protection to 95% of the line section and also backup protection to 95% of the adjacent reverse and forward line section also.     

Detection and classification of voltage disturbances using a Fuzzy-ARTMAP-wavelet network

This paper presents a method for automatic detection and classification of voltage disturbances for problems related to power quality using signal processing techniques and intelligent systems. This support tool for decision making is composed of four modules. The first module continuously evaluates the system's operation state. The second module extracts the essential features from the three-phase voltage signal based on the discrete wavelet transform, multiresolution analysis and entropy norm concepts. The signal signature is processed via standardization and codification in the third module. The fourth module classifies the type of disorder using a Fuzzy-ARTMAP neural network. A total of 7023 power quality events, including voltage swell, voltage sag, outage, harmonics, swell with harmonics, sag with harmonics, oscillatory transient and flicker, were obtained through mathematical models and simulations using the ATP software. To demonstrate the performance of this method, an application is submitted considering a real electric energy distribution system composed of 134 buses with measurements performed on a 13.8 kV and 7.065 MVA feeder. The results indicate that the proposed method is efficient, robust and has high computing performance (low processing time), which allows, a priori, its application in real time.     

A real-time classification method of power quality disturbances

This paper describes a real-time classification method of power quality (PQ) disturbances. With an acceptable computation burden, both the elementary parameters of the power signal and the types of the disturbances in the power signal are obtained easily. The proposed method addresses the selection of discriminative features for detection and classification of PQ disturbances. Five distinguished time-frequency statistical features of PQ disturbances are extracted using RMS (root-mean-square) method and discrete Fourier transform (DFT). Using a rule-based decision tree (RBDT), the nine types of PQ disturbances can be recognized easily and there is no need to use other complicated classifiers. Finally, the proposed method is tested using the simulated waveforms. And some preliminary experimental results of the accuracy characterization of an initial development instrument are reported. The simulation and application results validate the accuracy and efficiency of the proposed method.     

Novel power quality indices based on wavelet packet transform for non-stationary sinusoidal and non-sinusoidal disturbances

High power quality (PQ) level represents one of the main objectives towards smart grid. The currently used PQIs that are a measure of the PQ level are defined under the umbrella of the Fourier foundation that produces unrealistic results in case of non-stationary PQ disturbances. In order to accurately measure those indices, wavelet packet transform (WPT) is used in this paper to reformulate the recommended PQIs and hence benefiting from the WPT capabilities in accurately analyzing non-stationary waveforms and providing a uniform time–frequency sub-bands leading to reduced size of the data to be processed which is a necessity to facilitate the implementation of smart grid. Numerical examples’ results considering non-stationary waveforms prove the suitability of the WPT for PQIs measurement; also the results indicate that Daubechies 10 could be the best candidate wavelet basis function that could provide acceptable accuracy while requiring less number of wavelet coefficients and hence reducing the data size. Moreover, a new time–frequency overall and node crest factors are introduced in this paper. The new node crest factor is able to determine the node or the sub-band that is responsible for the largest impact which could not be achieved using traditional approaches.     

Detection and classification of single and combined power quality disturbances using fuzzy systems oriented by particle swarm optimization algorithm

In this paper, a new approach for the detection and classification of single and combined power quality (PQ) disturbances is proposed using fuzzy logic and a particle swarm optimization (PSO) algorithm. In the proposed method, suitable features of the waveform of the PQ disturbance are first extracted. These features are extracted from parameters derived from the Fourier and wavelet transforms of the signal. Then, the proposed fuzzy system classifies the type of PQ disturbances based on these features. The PSO algorithm is used to accurately determine the membership function parameters for the fuzzy systems. To test the proposed approach, the waveforms of the PQ disturbances were assumed to be in the sampled form. The impulse, interruption, swell, sag, notch, transient, harmonic, and flicker are considered as single disturbances for the voltage signal. In addition, eight possible combinations of single disturbances are considered as the PQ combined types. The capability of the proposed approach to identify these PQ disturbances is also investigated, when white Gaussian noise, with various signal to noise ratio (SNR) values, is added to the waveforms. The simulation results show that the average rate of correct identification is about 96% for different single and combined PQ disturbances under noisy conditions.     

Fault classification in SEIG system using Hilbert-Huang transform and least square support vector machine

This paper presents the transient performance analysis of self excited induction generator (SEIG) during both balanced and unbalanced faults using stationary frame d–q axis. Significance of fault detection and fault classification is also investigated in this study. Current signal of SEIG is extracted. Non stationary distorted current waveforms of SEIG during fault condition are considered as superimposition of various oscillating modes. To separate out these oscillating components known as intrinsic mode functions (IMFs), empirical-mode decomposition (EMD) is used. Hilbert transform (HT) is applied on the first four IMFs to extract instantaneous amplitude and frequency. Combination of EMD and HT is known as Hilbert-Huang transform. To classify different faults of SEIG system, least square support vector machine (LSSVM) is used. Finally the superiority of the proposed SVM is established through comparison with support vector machine and probabilistic neural network.     

基于粗糙集理论和最小二乘支持向量机的中长期负荷预测

根据电力系统中长期负荷预测的特点,提出了粗糙集理论与最小二乘支持向量机相结合的预测方法。应用粗糙集理论对影响负荷的众多因素进行约简,得到与负荷关系最为密切的核心因素,将其作为最小二乘支持向量机的输入矢量进行预测。实际算例分析表明,该预测模型符合中长期负荷预测的特点并具有较高的精度,方法是可行和有效的。     

A new reactive,distortion and non-active power measurement method for nonstationary waveforms using wavelet packet transform

The definitions of power components that are contained in the IEEE Standard 1459-2000 [IEEE Std. 1459-2000, Definitions for the measurement of electric quantities under sinusoidal, non-sinusoidal, balanced or unbalanced conditions, 2000] are based on the Fourier transform (FT) which is suitable only for the case of stationary waveforms. However, for nonstationary waveforms, the FT produces large errors. Therefore, the power components based on this transform become inaccurate. A new approach based on the wavelet packet transform (WPT) for defining these power components is developed in this paper. The advantages of using the wavelet transform are that it can accurately represent and measure nonstationary waveforms, providing uniform frequency bands while preserving both time and frequency information. In addition, this paper addresses the problem of choosing the most appropriate mother wavelet for power components measurements. The results of applying both approaches to stationary and nonstationary waveforms show that the currently used definitions according to the IEEE Standard 1459-2000 result in large errors for the case of nonstationary waveforms while the proposed approach (WPT based) gives more accurate results in this situation.     

改进LS-SVM的直吹式制粉出力软测量建模

针对火电厂双进双出钢球磨煤机直吹式制粉系统这一大滞后、强非线性系统,其制粉出力较难直接测量的问题,在Suykens的最小二乘支持向量机稀疏化算法的基础上,提出一种更好的改进方式,即在删除一些过大或过小的训练样本的同时,也将变化率过大的数据删除,避免了坏样本对模型的影响,简化了LS - SVM模型.改进后的最小二乘支持向...     

基于小波变换和改进的RVM的电能质量扰动分类

为了提高相关向量机的回归预测的准确率,本文提出了一种改进的相关向量机算法.该算法从相关向量机的核函数角度出发,将实际中大部分噪声属于正态分布这一个特性引入到核函数中,并在其基础上加入了幅度调节因子,实现了对核函数的改进.为了进一步提高电能质量扰动分类性能,将改进的相关向量机应用于电能质量扰动分类.首先,采用小波变换对电能质量信号进行分解,将分解后得到的各层小波系数能量所占的比例值作为特征量,然后,用改进后的相关向量机对特征量进行分类,进而实现基于小波变换和改进的相关向量机的电能质量扰动分类.实验结果表明,该方法能够对各种电能质量扰动信号进行分类,并且其分类准确率优于支持向量机和未改进前的相关向量机等其他分类方法.     

Detection and classification of power quality disturbances using S-transform and modular neural network

This paper presents an S-transform based modular neural network (NN) classifier for recognition of power quality disturbances. The excellent time—frequency resolution characteristics of the S-transform makes it an attractive candidate for the analysis of power quality (PQ) disturbances under noisy condition and has the ability to detect the disturbance correctly. On the other hand, the performance of wavelet transform (WT) degrades while detecting and localizing the disturbances in the presence of noise. Features extracted by using the S-transform are applied to a modular NN for automatic classification of the PQ disturbances that solves a relatively complex problem by decomposing it into simpler subtasks. Modularity of neural network provides better classification, model complexity reduction and better learning capability, etc. Eleven types of PQ disturbances are considered for the classification. The simulation results show that the combination of the S-transform and a modular NN can effectively detect and classify different power quality disturbances.     

Study of a new method for power system transients classification based on wavelet entropy and neural network

The detection and classification of transient signals are widely applied in many fields of power system. The study of transient signal detection and classification is a sustaining focus of researchers as well as a difficult issue. There are still many problems needed to be solved in this area. Based on the wavelet transform (WT), the idea of entropy and weight coefficient is introduced, and the wavelet energy entropy (WEE) and wavelet entropy weight (WEW) are defined in this paper. The distribution picture of WEE and WEW along with scales are presented for the first time. PSCAD/EMTDC models for six types of transients, namely breaker switching, capacitor switching, short circuit fault, primary arc, lightning disturbance and lightning strike fault, are constructed. With WEE and WEW, the eigenvectors for the six transients are established and a model which uses the eigenvectors as the input of the BP (back-propagation) neural network is set up to realize the classification of these transients. The simulation has been executed based on a 500 kV transmission line model in China and the results show that feature extraction based on WEE and WEW can effectively discover the useful local features. With the help of neural network classifier, it has effective classifying result. This method is applicable in the power system.     

Characterization of power quality disturbances using hybrid technique of linear Kalman filter and fuzzy-expert system

This paper presents a hybrid technique for characterizing power quality (PQ) disturbances. The hybrid technique is based on Kalman filter for extracting three parameters (amplitude, slope of amplitude, harmonic indication) from the captured distorted waveform. Discrete wavelet transform (DWT) is used to help Kalman filter to give a good performance; the captured distorted waveform is passed through the DWT to determine the noise inside it and the covariance of this noise is fed together with the captured voltage waveform to the Kalman filter. The three parameters are the inputs to fuzzy-expert system that uses some rules on these inputs to characterize the PQ events in the captured waveform. This hybrid technique can classify two simultaneous PQ events such as sag and harmonic or swell and harmonic. Several simulation and experimental data are used to validate the proposed technique. The results depict that the proposed technique has the ability to accurately identify and characterize PQ disturbances.     

Forecasting electricity consumption: A comparison of regression analysis,neural networks and least squares support vector machines

Accurate electricity consumption forecast has primary importance in the energy planning of the developing countries. During the last decade several new techniques are being used for electricity consumption planning to accurately predict the future electricity consumption needs. Support vector machines (SVMs) and least squares support vector machines (LS-SVMs) are new techniques being adopted for energy consumption forecasting. In this study, the LS-SVM is implemented for the prediction of electricity energy consumption of Turkey. In addition to the traditional regression analysis and artificial neural networks (ANNs) are considered. In the models, gross electricity generation, installed capacity, total subscribership and population are used as independent variables using historical data from 1970 to 2009. Forecasting results are compared using diverse performance criteria in this study with each other. Receiver operating characteristic (ROC) analysis is realized for determining the specificity and sensitivity of the empirical results. The results indicate that the proposed LS-SVM model is an accurate and a quick prediction method.     

Design and allocation of power system stabilizers using the particle swarm optimization technique for an interconnected power system

In this paper, three particle swarm optimization (PSO) based power system stabilizers (PSSs) are developed for three power systems. The system under study here is a power pool consisting of 3 power systems. System I represents the Egyptian power system, system II represents the Jordan and Syrian power systems, and system III for the Libyan power system, which are originally self standing and completely independent systems. As a matter of fact each of them should equipped with its own PSS. For this reason this work is started by designing an optimum power stabilizer for each of them standing alone. After which, the developed PSSs are firstly installed one at a time. Then the three PSSs are installed together in the interconnected power system and their effect on its dynamic performance is studied.As a test for stabilization efficiency, the detailed power system model is subjected to a forced outage of a 600-MW generator, which is the biggest unit in the pool, when it is fully loaded. This outage results in loosing of about 3% of the spinning capacity of system I and about 2% of the spinning capacity of the whole interconnected system. The obtained results show an improvement in the power pool performance accompanied with an improvement in the inter-area oscillation.     

Support vector classification and regression for fault location in distribution system using voltage sag profile

Fault location identification is an important task to provide reliable service to the customer. Most existing artificial intelligence methods such as neural network, fuzzy logic, and support vector machine (SVM) focus on identifying the fault type, section, and distance separately. Furthermore, studies on fault type identification are focused on overhead transmission systems and not on underground distribution systems. In this paper, a fault location method in the distribution system is proposed using SVM, addressing the limitations of existing methods. Support vector classification (SVC) and regression analysis are performed to locate the fault. The method uses the voltage sag data during a fault measured at the primary substation. The type of fault is identified using SVC. The fault resistance and the voltage sag for the estimated fault resistance are identified using support vector regression (SVR) analysis. The possible faulty sections are identified from the estimated voltage sag data and ranked using the Euclidean distance approach. The proposed method identifies the fault distance using SVR analysis. The performance of the proposed method is analyzed using Malaysian distribution system of 40 buses. Test results show that the proposed method gives reliable fault location.     

暂态零序电荷-电压特征与支持向量机结合的谐振接地系统故障选线研究

提出了一种暂态零序电荷-零序电压(Q-U)特征与支持向量机(SVM)相结合的配电网谐振接地系统故障选线方法。为解决配电网故障选线不可靠的问题,从配电网暂态故障特征出发,研究单相接地故障后馈线暂态零序电荷与零序电压的故障特征关系。并以各条馈线零序电荷与电压相关系数作为选线特征输入量,通过结合支持小样本分类的支持向量机分类算法,建立了一套基于暂态零序Q-U特征的配电网故障选线流程。在PSCAD/EMTDC仿真软件下建立35 kV的谐振接地系统模型,大量仿真结果表明该方法不受故障距离,故障时刻的影响,特别在高阻,电弧等工况下仍然能够实现正确故障选线。     

基于蚁群优化算法的电力系统暂态稳定评估特征选择

暂态稳定评估的特征选择是一个典型的组合优化问题。针对该问题解的离散性特点,提出基于蚁群优化算法的特征选择方法。该方法以最小二乘支持向量机作为暂态稳定评估分类器,以分类错误率最低和特征选择比率最小为优化目标,通过二进制编码形式的蚁群优化算法实现特征的选择。这样能选择出计及分类器特性的最优特征子集,减少了特征维数,提高了分类正确率。通过对综合程序EPRI-36节点系统的仿真计算,验证了该方法的有效性。