A flexible statistical pattern recognition approach in transient stability studies

A statistical pattern recognition approach is presented for the on-line transient stability evaluation of electric power systems. The classifier that is used implements the Bayes' decision rule for classification. A flexible point estimates method is used to provide accurate values of the transient energy statistics, required in the classification procedures.     

A duality principle for state estimation with partially noise-corrupted measurements. Volume 37, number 5, pp. 1039–1056

This paper deals with the design and evaluation of a variable-structure stabilizer (VSS) for a synchronous machine using variable-structure systems theory. The stabilizer design is based on a recently proposed geometric approach for finding out the switching hyperplanes for discontinuous control. The transient response of the variable-structure stabilizer is compared with those obtained using a power system stabilizer (PSS) based on a speed signal. The computer simulation results show that the VSS is more effective in improving system damping, transient stability and post-fault recovery of the terminal voltage. It is also shown that by operating the control system in a sliding mode, the performance of the controlled synchronous machine can be made insensitive to changes in the system parameters.     

A power system nonlinear adaptive decentralized controller design

In this paper, a novel excitation control is designed for improvement of transient stability of power systems. The control algorithm is based on the adaptive backstepping method in a recursive way without linearizing the system model. Lyapunov function method is applied in designing the controller to ensure the convergence of the power angle, relative speed of the generator and the active electrical power delivered by the generator when a large fault occurs. Compared with the existing nonlinear decentralized control approaches, the proposed controller has no requirement for the bounds of interconnections in the power system. And the new approach does not need the existence of solution of a designed algebraic Riccati equation. Furthermore, the transient stability performance of power systems can also be improved by the designed control approach. The efficacy of the designed controller has been demonstrated in a multimachine power system. Simulation results show transient stability enhancement of a power system in the face of a large sudden fault.     

ON THE STABILITY OF LARGE-SCALE POWER SYSTEMS

Abstract

This paper deals with the problem of transient stability of large-scale power systems by visting decomposition-aggregation techniques. In this approach based on a priori criteria, the system is decomposed to N-subsystems, the first (N— 1) subsystems described by linear model and the Nthdescribed by nonlinear model. Then each linear subsystem is reduced by aggregation techniques to an equivalent machine. Using this approach the problem of transient stability of large power systems is investigated. An algorithm for calculating the critical switching time based on this technique is proposed. The validity of this method is examined by studying large power systems of 11 machines, and the results obtained using IBM 370/165 digital computer of L.A-A.S. are reported.     

A Distribution-Index-Based Discretizer for Decision-Making with Symbolic AI Approaches

When symbolic AI approaches are applied to handle continuous valued attributes, there is a requirement to transform the continuous attribute values to symbolic data. In this paper, a novel distribution-index-based discretizer is proposed for such a transformation. Based on definitions of dichotomic entropy and a compound distributional index, a simple criterion is applied to discretize continuous attributes adaptively. The dichotomic entropy indicates the homogeneity degree of the decision value distribution, and is applied to determine the best splitting point. The compound distributional index combines both the homogeneity degrees of attribute value distributions and the decision value distribution, and is applied to determine which interval should be split further; thus, a potentially improved solution of the discretization problem can be found efficiently. Based on multiple reducts in rough set theory, a multiknowledge approach can attain high decision accuracy for information systems with a large number of attributes and missing values. In this paper, our discretizer is combined with the multiknowledge approach to further improve decision accuracy for information systems with continuous attributes. Experimental results on benchmark data sets show that the new discretizer can improve not only the multiknowledge approach, but also the naive Bayes classifier and the C5.0 tree     

Fault diagnosis and fault tolerant control for non-Gaussian time-delayed singular stochastic distribution systems

Stochastic distribution control (SDC) is a new branch of stochastic system control that the system output is the probability density function (PDF) of the output. In practice, some algebraic relations exist between the input and the weights of SDC systems, leading to a singular state space model between the weights and the control input which increases the complexity of the system. The ignorance of time delay in practical systems will make the effectiveness of the fault diagnosis (FD) and fault tolerant control (FTC) be reduced. In this paper, the linear B-spline basis functions are used to approximate the output PDF. A FD approach based on the adaptive observer is established to diagnose the size of fault in the singular time-delayed SDC system. With the fault diagnosis information, a fault tolerant controller based on PI tracking control scheme is constructed to make the post-fault PDF still track the given distribution. The post-fault closed-loop stability analysis with the practical fault tolerant controller is carried out based on the Lyapunov stability theorem. Finally, a numerical simulation is provided to demonstrate the effectiveness of the proposed approach.     

An approach to the automatic design of multiple classifier systems

Multiple classifier systems (MCSs) based on the combination of outputs of a set of different classifiers have been proposed in the field of pattern recognition as a method for the development of high performance classification systems. Previous work clearly showed that multiple classifier systems are effective only if the classifiers forming them are accurate and make different errors. Therefore, the fundamental need for methods aimed to design “accurate and diverse” classifiers is currently acknowledged. In this paper, an approach to the automatic design of multiple classifier systems is proposed. Given an initial large set of classifiers, our approach is aimed at selecting the subset made up of the most accurate and diverse classifiers. A proof of the optimality of the proposed design approach is given. Reported results on the classification of multisensor remote sensing images show that this approach allows the design of effective multiple classifier systems.     

一种限定性的双层贝叶斯分类模型

朴素贝叶斯分类模型是一种简单而有效的分类方法,但它的属性独立性假设使其无法表达属性变量间存在的依赖关系,影响了它的分类性能.通过分析贝叶斯分类模型的分类原则以及贝叶斯定理的变异形式,提出了一种基于贝叶斯定理的新的分类模型DLBAN(double-level Bayesian network augmented naive Bayes).该模型通过选择关键属性建立属性之间的依赖关系.将该分类方法与朴素贝叶斯分类器和TAN(tree augmented naive Bayes)分类器进行实验比较.实验结果表明,在大多数数据集上,DLBAN分类方法具有较高的分类正确率.     

A novel recursive approach for real-time transient stability assessment based on corrected kinetic energy

Real-time assessment of transient stability is one of the main issues of power system operators in online applications. This paper proposes a novel recursive approach based on corrected kinetic energy which has the capability of real-time assessment and real time computation of transient stability margin in the power system. This approach considers all details of power system by using network preserving model to simulate transient stability. This paper uses a hybrid method based on the new concept of equal area criterion to estimate initial value of critical point of the system and corrected Kinetic Energy Function to estimate high precision value of the critical point. Also, this paper proposes a recursive method which uses large change sensitively (LCS) analysis to correct initial condition point of the system when the topology of system is changed by a disturbance. In order to validate the proposed method, comprehensive case studies have been conducted on IEEE39-bus test system. Comprehensiveness in considering the details, simplicity in implementation and low computational cost are the outstanding features of the proposed approach. Also, simulation results approve that the proposed approach can be used in real-time application without loss of any detail in the transient stability assessment.     

On the classification of remote sensing high spatial resolution image data

In this paper is investigated a methodology implementing an object-based approach to digital image classification using spectral and spatial attributes in a multiple-stage classifier structured as a binary tree. It is a well-established fact that object-based image classification is particularly appropriate when dealing with high spatial resolution image data. Following this approach, the image is initially segmented into objects that carry informational value. Next, spectral and spatial attributes are extracted from every object in the scene, and implemented into a classifier to produce a thematic map. As the combined number of spectral and spatial variables may become large compared to the number of available training samples, a reduction in the data dimensionality may be required whenever parametric classifiers are used, in order to mitigate the effects of the Hughes phenomenon. To this end the sequential feature selection (SFS) procedure is applied in a multiple-stage classifier structured as a binary tree. The advantage of a binary tree classifier lies in the fact that only one pair of classes is considered at each stage (node), allowing for an optimal selection of features. This proposed approach was tested using Quickbird image data covering an urban scene. The results are compared against results yielded by the traditional single-stage Gaussian maximum likelihood classifier. The results suggest the proposed methodology is adequate in the classification of high spatial resolution image data.     

Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance

For high dimensional data, if no preprocessing is carried out before inputting patterns to classifiers, the computation required may be too heavy. For example, the number of hidden units of a radial basis function (RBF) neural network can be too large. This is not suitable for some practical applications due to speed and memory constraints. In many cases, some attributes are not relevant to concepts in the data at all. In this paper, we propose a novel separability-correlation measure (SCM) to rank the importance of attributes. According to the attribute ranking results, different attribute subsets are used as inputs to a classifier, such as an RBF neural network. Those attributes that increase the validation error are deemed irrelevant and are deleted. The complexity of the classifier can thus be reduced and its classification performance improved. Computer simulations show that our method for attribute importance ranking leads to smaller attribute subsets with higher accuracies compared with the existing SUD and Relief-F methods. We also propose a modified method for efficient construction of an RBF classifier. In this method we allow for large overlaps between clusters corresponding to the same class label. Our approach significantly reduces the structural complexity of the RBF network and improves the classification performance.     

A Nonlinear Coordinated Approach to Enhance the Transient Stability of Wind Energy-Based Power Systems

This paper proposes a novel framework that enables the simultaneous coordination of the controllers of doubly fed induction generators (DFIGs) and synchronous generators (SGs). The proposed coordination approach is based on the zero dynamics method aims at enhancing the transient stability of multi-machine power systems under a wide range of operating conditions. The proposed approach was implemented to the IEEE 39-bus power systems. Transient stability margin measured in terms of critical clearing time along with eigenvalue analysis and time domain simulations were considered in the performance assessment. The obtained results were also compared to those achieved using a conventional power system stabilizer/power oscillation (PSS/POD) technique and the interconnection and damping assignment passivity-based controller (IDA-PBC). The performance analysis confirmed the ability of the proposed approach to enhance damping and improve system’s transient stability margin under a wide range of operating conditions.      

Handwritten Chinese character recognition using fuzzy image alignment

The task of handwritten Chinese character recognition is one of the most challenging areas of human handwriting classification. The main reason for this is related to the writing system itself which encompasses thousands of characters, coupled with high levels of diversity in personal writing styles and attributes. Much of the existing work for both online and off-line handwritten Chinese character recognition has focused on methods which employ feature extraction and segmentation steps. The preprocessed data from these steps form the basis for the subsequent classification and recognition phases. This paper proposes an approach for handwritten Chinese character recognition and classification using only an image alignment technique and does not require the aforementioned steps. Rather than extracting features from the image, which often means building models from very large training data, the proposed method instead uses the mean image transformations as a basis for model building. The use of an image-only model means that no subjective tuning of the feature extraction is required. In addition by employing a fuzzy-entropy-based metric, the work also entails improved ability to model different types of uncertainty. The classifier is a simple distance-based nearest neighbour classification system based on template matching. The approach is applied to a publicly available real-world database of handwritten Chinese characters and demonstrates that it can achieve high classification accuracy and is robust in the presence of noise.     

Particle swarm optimization based K-means clustering approach for security assessment in power systems

Security assessment is a major concern in planning and operation studies of a power system. Conventional method of security evaluation performed by simulation involves long computer time and generates voluminous results. This paper presents a K-means clustering approach for classifying power system states as secure/insecure under a given operating condition and contingency. This paper demonstrates how the traditional K-means clustering algorithm can be profitably modified to be used as a classifier algorithm. The proposed algorithm combines particle swarm optimization (PSO) with the traditional K-means algorithm to satisfy the requirements of a classifier. The proposed PSO based K-means clustering technique is implemented in IEEE 30 Bus, 57 Bus, 118 Bus and 300 Bus standard test systems for static security and transient security evaluation. The simulation results of the proposed algorithm are compared with unsupervised K-means clustering, which uses different methods for cluster center initialization.     

Multimachine power systems: Stability, decomposition, and aggregation

A new approach is proposed for transient stability analysis of interconnected power systems, which is based upon the concept of vector Lyapunov functions and the decomposition-aggregation method. The approach results in an exact procedure for computation of stability region estimates which are expressed explicitly in terms of system parameters. More refined models of the subsystems can be readily accommodated by the new approach. In particular, the transfer conductances are included in the present study, a feature which is almost exclusively missing in transient stability analysis of multimachine systems by Lyapunov's method.     

Fast transient stability assessment of large power system using probabilistic neural network with feature reduction techniques

This paper presents transient stability assessment of a large 87-bus system using a new method called the probabilistic neural network (PNN) with incorporation of feature selection and extraction methods. The investigated power system is divided into smaller areas depending on the coherency of the areas when subjected to disturbances. This is to reduce the amount of data sets collected for the respective areas. Transient stability of the power system is first determined based on the generator relative rotor angles obtained from time domain simulations carried out by considering three phase faults at different loading conditions. The data collected from the time domain simulations are then used as inputs to the PNN. Feature reduction techniques are then incorporated to reduce the number of features to the PNN which is used as a classifier to determine whether the power system is stable or unstable. It can be concluded that the PNN with the incorporation of feature reduction techniques reduces the time taken to train the PNN without affecting the accuracy of the classification results.     

Decentralized multivariable voltage and speed regulator for large-scale power systems with guarantee of stability and transient performance

This paper presents a novel procedure for the design of decentralized regulators for large power systems with a formal proof of ‘global’ stability. The distinctive feature of the solution is that both voltage and rotor speed dynamics are regulated simultaneously contrary to most of the solutions proposed so far in the literature. First, the traditional multimachine power system algebraic-differential equations are reformatted into suitable state equations, more appropriate for modern control tools. Secondly, a voltage and speed controller based on this model is proposed. The design consists of first cancelling some of the dynamical model non-linearities using non-linear excitation and valve input. The resulting subsystems are stabilized by auxiliary controls with linear and non-linear components. The non-linear component, which uses local signals to dominate those with interconnections, is derived from a stability criterion involving the Lyapunov function of the entire power system. The gains of the linear component are computed from the solution of an algebraic Riccati equation similar to the one involved in the full information H _∞ problem. These gains guarantee that effects of interconnection signals on voltage and speed dynamics are considerably reduced. The benefit of the proposed scheme is that the voltage regulation characteristic ensures a good post-fault voltage profile which helps improve rotor oscillations damping. Simulation results on a realistic power system confirm that the system stability is considerably improved in presence of severe contingencies.     

Voltage stability assessment in power network using self organizing feature map and radial basis function

Self-organizing feature map (SOFM) in conjunction with radial basis function (RBF) has been applied in this paper to determine and classify the voltage stability states of a multi-bus power network. Simulations were carried out on a real 203-bus system of an Indian power utility considering load changes and contingencies. The data collected from simulations are then used as inputs to the SOFM which acts as a classifier to classify the voltage stability states of the system under test. To augment the effectiveness of the proposed method, the initial classification results were improved with the application of RBF technique. Studies show that the SOFM-RBF combination delivers high classification accuracy in the order of almost 100% and can be considered an effective soft-computing tool to ease the operation of large-multi bus power network under variable operating conditions.     

Fuzzy clustering-based discretization for gene expression classification

This paper presents a novel classification approach that integrates fuzzy class association rules and support vector machines. A fuzzy discretization technique based on fuzzy c-means clustering algorithm is employed to transform the training set, particularly quantitative attributes, to a format appropriate for association rule mining. A hill-climbing procedure is adapted for automatic thresholds adjustment and fuzzy class association rules are mined accordingly. The compatibility between the generated rules and fuzzy patterns is considered to construct a set of feature vectors, which are used to generate a classifier. The reported test results show that compatibility rule-based feature vectors present a highly- qualified source of discrimination knowledge that can substantially impact the prediction power of the final classifier. In order to evaluate the applicability of the proposed method to a variety of domains, it is also utilized for the popular task of gene expression classification. Further, we show how this method provide biologists with an accurate and more understandable classifier model compared to other machine learning techniques.     

A review of: “THE EFFICACY OF THE SYMBOLIC,VOLUME II: A SYSTEMS MODEL OF REPRESENTATION” (in French), by Norman Lacharité. University of Quebec,Montreal, 1987, 223 pp

Classification, a data mining technique, has widespread applications including medical diagnosis, targeted marketing, and others. Knowledge discovery from databases in the form of association rules is one of the important data mining tasks. An integrated approach, classification based on association rules, has drawn the attention of the data mining community over the last decade. While attention has been mainly focused on increasing classifier accuracies, not much efforts have been devoted towards building interpretable and less complex models. This paper discusses the development of a compact associative classification model using a hill-climbing approach and fuzzy sets. The proposed methodology builds the rule-base by selecting rules which contribute towards increasing training accuracy, thus balancing classification accuracy with the number of classification association rules. The results indicated that the proposed associative classification model can achieve competitive accuracies on benchmark datasets with continuous attributes and lend better interpretability, when compared with other rule-based systems.