A New Method for Power Quality Events Detection and Classification using Discrete Wavelet Transform and Correlation Coefficients

This paper presents a new approach for the detection of the power quality events using symmetrical components in time domain. Power quality (PQ) events like sag, swell, interruption, harmonic, flicker, transients, notches, and spike can be easily detected and classified with this method. As this method is free from the computational burden like in wavelets, S-transform and Hubert transform, so it can be easily used for the on-line applications. Single phase PQ event signal is taken along with the two other phases generated 120° and 240° difference using phase locked loop (PLL) so as to calculate the symmetrical components in the time domain. Triggering points for PQ events can be detected easily from the negative symmetric component of PQ event signal and the events can be easily classified from the signatures of the waveforms using the summation of the positive and negative sequence components. Simulated and real time results are presented for a number of power quality events to show the effectiveness of this method for the PQ event detection and classification.

Power quality (PQ) events are referred to any abnormal deviation from the standard sinusoidal behavior of power signals within a power system. PQ events are usually studied by tracking the behavior of voltage signals over observation points of the system. IEEE Standards have defined standard categories for PQ events based on their time behavior. Each class of these events may have different level of importance from different contributors' perspective (utilities, system operators, or costumers). Due to increasing the usage of sensitive technological loads such as transportation, banking systems, and databases on one hand in addition to the uncertainty injected to the system from aggregation of renewables on the other hand, the fast and reliable PQ events classification is an important monitoring task in the future smart grid. In this paper, combining the theory of sparse recovery with a new high-dimensional convex hull approximation framework we have developed a fast, reliable, and adaptive PQ events classification methodology named "compressive-informative sparse representation-based" PQ events classifier. Unlike usual classification approaches, the proposed classifier does not need any training procedure while due to its linear mathematical formulation acts inherently fast. Moreover, it can be easily adapted to recognize the challenging combined PQ events in addition to any permanent change in the behavior of PQ patterns.

The real-time analysis of power quality (PQ) disturbances and islanding detection for distributed generation (DG) system using signal processing algorithms are still at a premature stage. Quick and reliable detection of islanding and PQ disturbances needs renewed focus. This paper is concentrated on the implementation of advanced signal processing techniques in field-programmable gate array (FPGA) to identify PQ and islanding events in real time. The proposed scheme is based on orthogonal empirical mode decomposition (OEMD) implemented in FPGA. This technique does not suffer from the loss of signal characteristics with successive decomposition levels. The performance of said technique is demonstrated for different PQ and islanding events simulated on IEEE 13 bus DG system and experiments conducted on a laboratory setup. The detection ability has been compared with discrete wavelet transform (DWT) and basic empirical mode decomposition (EMD). It is found that DWT completely fails for the signal with noise content, while the performance of basic EMD deteriorates with an increased level of noise content. On the other hand, OEMD reliably and accurately detects the disturbances conducted in the study, both simulated and experimental.

In power distributed generation system, analysis of power quality is a major issue and hence it is essential to implement an efficient power quality system. To address and end this issue, the proposed work is mainly focused on the detection and classification of power quality disturbances or events by applying Hilbert–Huang transform (HHT) technique. HHT technique is a novel signal processing algorithm that comprises two processes. First is the empirical mode decomposition (EMD), which is an iterative process where N number of power quality signals are decomposed into intrinsic mode functions (IMFs). The second process, Hilbert transform, is applied to each IMF component. The advantage of using these two processes makes it an attractive power tool for quality event analysis. Once the IMF is obtained, it is easy to construct a time–frequency representation model. Then, the significant features are extracted from amplitude, phase and frequency instantly, which are the contour of IMFs of each power quality disturbance. For classification, adaptive neuro-fuzzy system (NFS) classifier is used. It is an intelligent system used for the combination of neural network and fuzzy logic. Power quality features are given as input to the NFS system. The experimental simulation is conducted in a MATLAB environment, and proposed HHT has higher efficiency compared to existing methods.

This article presents an efficient method for power quality events (PQEs) detection and classification based on Curvelet transform (CT) and optimized extreme learning machine (OELM). Initially, various PQEs signal data are extracted even under noisy and simultaneously occurred multi-event conditions to reflect the real-time conditions. Relevant features of all these extracted signals are computed by using a multi-resolution and multidirectional fast discrete CT (FDCT) approach. These features are used to classify the events accurately by the proposed OELM. In this classification strategy, a modified differential evolution (MDE) is introduced to optimize the conventional ELM to enhance its precision rate. The proposed novel approach is tested and analyzed under various noisy conditions with 20 dB, 30 dB, and 50 dB with single and multi PQEs conditions. Comparative results with other recently proposed approaches by various authors reveal that the proposed CT- and OELM-based classifier titled CT-OELM can be considered as a competitive choice for implementing in the real-time monitoring system.

Accurate and timely detection of power quality (PQ) events is imperative for adequate corrective measures to be taken. This paper presents a method of PQ event detection development called joint triggering point detection (JTPD) scheme with a view to achieving a more accurate PQ event detection in a voltage waveform. The JTPD combines the advantage of cumulative sum (CUSUM) algorithm for the statistical distribution of a signal waveform and the discrete wavelet transform (DWT) for change-point detection. The performance of JTPD scheme using detection rate was compared with CUSUM and DWT schemes and based on the analysis, the detection rate of JTPD, CUSUM and DWT were 100%, 95% and 50% respectively. With this, the proposed approach outperformed CUSUM and DWT schemes by 5% and 50% respectively. Hence, the proposed approach is suitable for accurate detection of voltage dip, swell and interruption PQ events Keywords: Cumulative Sum, Discrete Wavelet Transform, Joint Triggering Point Detection, Power Quality, Voltage Waveform

This paper presents an effective method for detection and classification of Power Quality Events (PQE), based on Fast Fourier Transformation (FFT) for event identification and Artificial Neural Network (ANN) technique for classifying of these events. Firstly, synthetic data such as pure sine as a reference, voltage sag, voltage swell, flicker, transient, voltage with harmonics are created in MATLAB based on TS EN 50160 standard. Database with 480 PQE waveforms is generated with 80 samples for each of the 6 types of the waveform with randomly different event amplitude, beginning occurrence time, time duration, frequency component and angle according to a type of event. FFT is used to extract features of the events by decomposing the signal. Then, 16384×480 data are reduced to 480×480 data by applying Principal Component Analysis (PCA) that is prevent over-learning, obtain less runtime using less computing power and reduce data and storage space. Finally, a total of 480 PQE are classified by using ANN. 336 of these PQE are used for training cluster, 72 of PQE are used for verification and the remaining 72 are used for testing. Firstly, the ANN has been trained correctly. The classification performance of the ANN in PQE has been examined by inserting the test into ANN. The performance of ANN is 99.8% for these PQE. The purpose of this research is to provide an artificial intelligence assistant that can fast and accurately advise the power system operators for the networks, and the results also show that the goal has been achieved.

In this paper a technique for detection of multiple power quality (PQ) events is illustrated. An algorithm based on wavelet transform and Random Forest based classifier is proposed in this paper. The developed technique is implemented on 11 different power quality events consisting of single stage power quality events such as sag, swell, flicker, interruption and multi stage power quality events such as harmonics combined with sag, swell, flicker, interruption. PQ events are simulated in MATLAB using standard IEEE-1159 standard. Significant features of PQ events are extracted using wavelet transform and used to train random forest based classifier. The efficiency of Random Forest Based classifier is compared with other widely used machine learning algorithms such as K-Nearest Neighbour (KNN) and Support Vector Machine (SVM). From confusion matrix of different algorithms it is concluded that Random Forest shows superior classification accuracy as compared to SVM and KNN.

The increased usage of sensitive equipment by customers led to the importance of the term Power Quality. Classification of power quality events plays an important role to have an effective mitigation. This paper represents a new approach for classification of Power Quality events using S-transform. S-transform is an improved version of wavelet transform that includes phase information as well. S-transform is used for classification of various power quality events like voltage sag, voltage swell, momentary interruption, harmonics which are simulated in MATLAB in accordance with IEEE Std. 1159. The effectiveness of the algorithm is used to identify multiple events. Phase information is also verified for various simulation cases.

Chapter 6 - Adaptive estimation and tracking of power quality disturbances with classification for smart grid applications

The wavelet transform coefficients (WTCs) contain plenty of information needed for transient event identification of power quality (PQ) events. However, adopting WTCs directly has the drawbacks of taking a longer time and too much memory for the recognition system. To solve the abovementioned recognition problems and to effectively reduce the number of features representing power transients, spectrum energies of WTCs in different scales are calculated by Parseval’s Theorem. Through the proposed approach, features of the original power signals can be reserved and not influenced by occurring points of PQ events. The fuzzy neural classification systems are then used for signal recognition and fuzzy rule construction. Success rates of recognizing PQ events from noise‐riding signals are proven to be feasible in power system applications in this paper.

Increased level of renewable energy (RE) penetration in distribution network (DN) deteriorates the power quality (PQ). Since, in the recent years wind energy (WE) integration to utility grids is increasing rapidly, hence there is a need to design effective approaches for identification of PQ issues and identification of events in the presence of high level of WE in DN. This paper designed a technique which uses processing of voltage signal by application of Stockwell transform (ST) and Hilbert transform (HT) for detection of the PQ issues and events in the presence of high level of WE in the DN. PQ indicator (PI) and time location indicator (TLI) are proposed to recognize the PQ disturbances and different nature of the events incident on grid when WE is available. Features are extracted from PI and TLI which are taken as input to decision tree for classifying the operational events. Study is executed on IEEE-13 bus test distribution network where two wind power plants (WPP) are connected. Performance of designed technique is established to be superior in comparison to Discrete Wavelet transform (DWT) supported technique.

Power quality events caused by renewable-energy integration are usually associated with complex disturbances; therefore, their type identification is the primary task of subsequent pollution control. This study proposes a novel three-step classification approach based on time-dependent spectral features (TDSFs) for the classification of complex power quality disturbances (PQDs). First, the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is adopted to decompose the PQDs into several intrinsic mode functions (IMFs). The related IMFs are selected by correlation coefficient and kurtosis. Then the eight eigenvalues of each IMF are extracted, including TDSFs. Finally, the eigenvalue dimension of each IMF is reduced by linear discriminant analysis (LDA). Moreover, the classifier of the adaptive k-nearest neighbor with excluding outliers (AdaKNNEO) can confirm the PQDs type. To verify the effectiveness of the proposed approach, a series of simulations and hardware experiments are conducted. The overall result shows robustness and high accuracy of the proposed method, and especially for the complex PQDs, it possesses the highest entirely correct of 96% compared to other advanced methods.

The worldwide increasing applications of nonlinear loads, mostly consisting of power electronics devices, have made the power quality problems an important concern than ever before for utilities and consumers. Therefore, detection and classification of Power Quality disturbances is highly desirable. Most power quality disturbances are non-stationary and transitory and their detection and classification have proved to be much needed. Hence there is a requirement of advanced tools and techniques for the analysis of Power Quality disturbances. In this work detection and classification of various types of transients and interruptions, caused due to severe fault and reclosing of circuit breaker, is done by using Discrete Wavelet Transform and two-layer feed forward neural network. This work presents new approach aimed at automating the analysis of power quality disturbances including transients, interruption and normal waveform. The disturbance current waveform can be obtained from the disturbance generation model. The Discrete Wavelet Transform is chosen for feature extraction. Feature extraction outputs are the coefficients (detailed and approximate) of Discrete Wavelet Transform represents the power quality disturbance signal at the different levels in time and frequency domain.

Power quality events recognition using enhanced empirical mode decomposition and optimized extreme learning machine