Lucas Alberto Reynoso
Bio: Lucas Alberto Reynoso is an academic researcher. The author has contributed to research in topics: Electric power system. The author has an hindex of 1, co-authored 1 publications receiving 4 citations.
Topics: Electric power system
07 May 2019
TL;DR: This chapter presents a review on main application of wavelet transform in electric power systems, which has received great importance in the last years on the power system analysis because the multi-resolution analysis presents proprieties good for the transient signal analysis.
Abstract: The wavelet transform has received great importance in the last years on the power system analysis because the multi-resolution analysis presents proprieties good for the transient signal analysis. This chapter presents a review on main application of wavelet transform in electric power systems. The study areas have been classified as power system protection, power quality disturbances, power system transient, partial discharge, load forecasting, faults detection, and power system measurement. The areas in which more works have been developed are the power quality and protections field, where both cover 51% of the articles analyzed.
TL;DR: The statistical analysis revealed that the proposed DWT-PSO-RBFNN method performed better based on MAPE, MAD, and RMSE emphasizing its great potential.
Abstract: Availability of electrical energy affects many facets of an entire economy of a country. This has made short-term electrical load forecasting an important area in recent years for policy makers and academic researchers. However, it has been found that the actual load series exhibit some complex behaviours which are often characterised by nonlinearity, nonstationarity, and temporal variations. In this study, a three-level hybrid ensemble short-term load forecasting method consisting of Discrete Wavelet Transform (DWT), Particle Swarm Optimization (PSO), and Radial Basis Function Neural Network (RBFNN) is proposed. The DWT is applied to decompose the data to get a well-behaved requisite series for forecasting since the data becomes stable before using PSO. PSO is used to obtain the required optimal adjustable parameters of the RBFNN for the forecasting. The proposed hybrid ensemble method (DWT-PSO-RBFNN) was evaluated using Ghana Grid Company daily average demand data from 1 st December 2018 to 30th November 2019. The DWT-PSO-RBFNN approach was compared with three other DWT coupling methods namely RBFNN, Backpropagation Neural Network (BPNN), and Self Adaptive Differential Evolution – Extreme Learning Machine (SaDE-ELM). The statistical analysis revealed that the proposed method performed better based on MAPE, MAD, and RMSE emphasizing its great potential.
TL;DR: This paper presents a methodology to evaluate hybrid energy storage systems in hybrid energy systems, using the stretched-thread method to evaluate the influence of energy storage, instead of conventional optimization techniques, conferring a visual approach.
Abstract: This paper presents a methodology to evaluate hybrid energy storage systems in hybrid energy systems. While Wavelet is used to decompose the net load in temporal segments, the stretched-thread method is used to evaluate the influence of energy storage, instead of conventional optimization techniques, conferring a visual approach. Proper selection of energy storage technologies for each time frame, as long as several sizing of different energy storage technologies is evaluated as well. The use of different methods and their application in a hybrid system are the main contributions of this piece.
••31 Aug 2021
TL;DR: In this paper, a machine learning based model for power quality event classification is developed and tested and 16 categories of the most commonly occurring power quality events are classified by means of wavelet transform and select machine learning-based methods to evaluate the best performing machine learning model.
Abstract: With the penetration of non-linear loads, renewables and distributed generation with power electronic converters, solutions for maintaining good power quality have become a major concern for the stakeholders of electrical power systems. In this paper, a machine learning based model for power quality event classification is developed and tested. 16 categories of the most commonly occurring power quality events are classified by means of wavelet transform and select machine learning based methods to evaluate the best performing machine learning model. The outcome of classifications and effectiveness of machine learning methods is evaluated using the ‘Classification Learners’ application in MATLAB. The selected machine learning model is implemented in Simulink for test distribution grid circuits. The results obtained from simulation showed acceptable accuracy and performance and demonstrated the efficiency of the model in different operating conditions.
TL;DR: In this article , an acoustic-based sensing method is employed to estimate, in real time, a snapshot of the different feed size fractions presented to a laboratory-scale semi-autogenous (SAG) mill.
Abstract: The harsh and hostile internal environment of semi-autogenous (SAG) mills renders real-time monitoring of some critical variables practically unmeasured. Typically, feed size fractions are known to cause mill fluctuations and impede the consistent processing behaviour of ores. There is, therefore, the need for continuous monitoring of mill parameters for optimal operation. In this paper, an acoustic-based sensing method is employed to estimate, in real time, a snapshot of the different feed size fractions presented to a laboratory-scale SAG mill. Employing the MATLAB 2020b programme, the mill acoustic signal is processed using various transform techniques such as power spectral density estimate (PSDE) by Welch’s method, discrete wavelet transform (DWT), wavelet packet transform (WPT), empirical mode decomposition (EMD), and variational mode decomposition (VMD). Different fractional bandpowers are obtained from the PSDE spectrum, while the statistical root mean square values are further extracted from DWT, WPT, EMD, and VMD as feature vectors. The features are used as input features in different machine-learning classification algorithms for different mill feed size fractions predictions. The various transform techniques and feed size fraction predictions are evaluated using the various performance indicators obtained from the confusion matrix such as accuracy, precision, sensitivity and F1 score. The study showed that the acoustic signal feature extraction techniques used in conjunction with the Support Vector Machine (SVM), linear discriminant analysis (LDA), and ensemble with subclass discriminant machine learning algorithms demonstrated improved performance for predicting feed size variations.
••10 Jan 2019
TL;DR: This chapter elaborates on signal processing, feature extraction, their application in fault detection and obtaining its location with illustrations.
Abstract: Electrical power is the backbone for the survival of mankind and technological development. The vast span of power system network is expanding its tentacles to all possible corners of the world. Fault is an inevitable phenomenon in every such network. Determination of the type of fault and finding its location is essential to ensure uninterruptible supply of power to the consumers. Conventional methods of fault analysis become more complicated with the increase in complexity of network configuration. They involve modelling of sequence networks, complex mathematical calculations, data of line parameters, fault location and fault resistance. The magnitudes of fault resistance and location are not always accessible. Evolution of soft computational techniques has made the process of power system relaying smarter and faster. These techniques mainly involve signal processing tools like wavelet transform and S-transform. The current and voltage signals are observed at any position of a power system network, and they are processed to extract suitable features. Methods of feature extraction are, therefore, very significant. These features are subsequently analysed by various approaches/methods for determination of the faulty phase and estimating its location. The methods are based on artificial neural network, fuzzy logic, combination of neuro-fuzzy technique, decision tree-based classifier, support vector machine, and so on. The results obtained are promising and independent of the magnitudes of fault resistance, location and line parameters. The networks are simulated in high-end software like MATLAB, EMTP and PSCAD. This chapter elaborates on signal processing, feature extraction, their application in fault detection and obtaining its location with illustrations.