Real-time transient stability status prediction using cost-sensitive extreme learning machine

Recently, multilayer extreme learning machine with subnetwork nodes and cost sensitive learning was applied to representation learning and classification. However, the existing ML-ELM methods suffer from several drawbacks: 1) manual tuning for the number of hidden nodes in each layer will influent the training speed of the model, the best optimal determine approach for the number of hidden nodes is still for probing; 2) random projection of the input weight and bias in each layer still suboptimal and the network structure hard to reach best generalization performance. Inspired by the Subnetwork nodes and cost sensitive methods, using multiple hidden output matrix, a novel ELM method which called Multilayer Incremental Hybrid Cost Sensitive Extreme Learning Machine with Multiple Hidden Output Matrix and Subnetwork Hidden Nodes is proposed in this paper. Whose contributions are 1) a hybrid hidden nodes optimization methods is given which based on ant clone method and multiple grey wolf optimization method; 2) a multiple hidden layer output matrices are being using through weighted calculation of different output matrices which can optimize the network architecture effectively; 3) a novel ELM structure is proposed by merging the merits of Cost Sensitive Extreme Learning Machine and Subnetwork Hidden Nodes, while the regularized parameter $C$ is not sensitive to the generalization performance. Extensive experiments results show that the proposed method achieves better performance than existing state-of-art ELM methods.

The main purpose of traditional classification algorithms on bioinformatics application is to acquire better classification accuracy. However, these algorithms cannot meet the requirement that minimises the average misclassification cost. In this paper, a new algorithm of cost-sensitive regularised extreme learning machine (CS-RELM) was proposed by using probability estimation and misclassification cost to reconstruct the classification results. By improving the classification accuracy of a group of small sample which higher misclassification cost, the new CS-RELM can minimise the classification cost. The 'rejection cost' was integrated into CS-RELM algorithm to further reduce the average misclassification cost. By using Colon Tumour dataset and SRBCT (Small Round Blue Cells Tumour) dataset, CS-RELM was compared with other cost-sensitive algorithms such as extreme learning machine (ELM), cost-sensitive extreme learning machine, regularised extreme learning machine, cost-sensitive support vector machine (SVM). The results of experiments show that CS-RELM with embedded rejection cost could reduce the average cost of misclassification and made more credible classification decision than others.

One of the key aspects in the development of power engineering all over the world is the use of distributed small-scale generation. This is both based on fuel carbon resources with a synchronized connection between sources when they are connected to the electric power grids and renewable energy sources operated in the electrical grid via frequency converters (electronic generation). The latter brings an inevitable broad use of inverters in available AC power systems. The objectives of this paper are numerous. First is the desire to study the effect of electronic generation on modes and stability of current electrical grids and electrical power systems. Another objective is to establish requirements for electronic generation control that lets us minimize actions on relay protection coordination and automation upon the integration of electronic generation in power grids. A final objective is to increase the reliability of general electrical modes. This article shows the outcomes of the study on the statical aperiodic stability of the electrical power system upon the integration of electronic generation, requirements for its statical characteristics, and the control when operated within the electrical power system.

Introduction. The article is devoted to the analysis of the stability of the electric power system (EPS) in mountainous areas using the Hurwitz criterion. In mountainous regions, the EPS faces a number of specific problems, such as complex terrain, remoteness of consumers and an increased probability of power transmission line failures. An important task is to develop a mathematical model that takes these features into account and to conduct an analysis of the stability of the system using the Hurwitz criterion. The purpose of the research: stability analysis of the system “high-pressure hydroelectric power plant – electric power system” using the Hurwitz criterion; identification of critical parameters of the system that affect its stability, and application of various optimization methods to improve the reliability and safety of the EPS in mountainous regions. Objects and methods. The object of the study is the high-pressure hydroelectric power plant (HPP) of PJSC RusHydro – Zaramagskaya HPP. The following methods were used for stability analysis: numerical modeling (integration of differential equations); state variable method; Laplace method; frequency response method; analytical methods for finding an exact solution to differential equations. Results and discussions. The results of the study demonstrate that the Gurwitz criterion is an effective tool for analyzing the stability of complex electric power systems, especially in mountainous areas. In the work, this method was successfully applied to analyze the static stability of the system taking into account automatic excitation control. Conclusion. A mathematical model has been developed that takes into account the specific conditions of mountainous areas. An analysis of the static stability of the system has been conducted taking into account the automatic excitation control (AEC). Critical parameters that affect the stability of the system, such as the load angle and the AEC gain factors, have been identified. It has been shown that increasing the accuracy of voltage maintenance can lead to a violation of stability in high-load modes. A method has been proposed for determining the minimum permissible gain factor, which allows avoiding aperiodic instability. Prospects for further research. In the future, possible alternative methods of stability analysis should be considered, such as frequency methods or methods based on Lyapunov theory, which could complement the results obtained using the Hurwitz criterion. A more detailed dynamic stability analysis should also be presented, which could provide a more complete understanding of the system’s behavior in transient conditions.

The objective of the paper is to present a method which can be used to evaluate rapidly the transient stability of an electric power system. The stability evaluation is performed by using a fuzzy pattern recognition approach, incorporating fuzzy membership values for the system operating states. These values classify the operating states into the defined fuzzy sets representing the class of either the stable or the unstable states. The memberhsip evaluation is performed by considering the lack of a known mathematical expression for the membership values and by using the fuzzy ISODATA clustering algorithm. The developed computational method is applied to evaluate the transient stability of a sample electric power system.

The paper sum up an effort that has been done within an initial phase of the project sponsored by the Technology Agency of the Czech Republic (TACR) Application of methods of reliability and risk oriented decision making for operation of complex electric power systems (TA04020956). In the paper, authors present the problem of stability of the electrical power system in the Czech Republic from the point of view of external hazards. The complexity of the electrical power grid and the diversity of its components represent the reason for decomposition of the problem. Possible methodology to deal with external hazards influencing the stability of electrical power system is presented and a few of selected external hazards are discussed more in detail, e.g. wind, sand storm, icing, electromagnetic storms and solar storms.

Diabetes is the fourth cause of death in the world and has some complications such as amputation, visual impairment, kidney disorder and early death. 80% of diabetes symptoms is avoidable by early diagnosis. There are standard methods to diagnose diabetes by measuring the plasma glucose concentration. However, screening all people is impossible due to financial shortages especially in developing countries. Therefore, it is proposed that the people more than 20 years old who are prone to diabetes be tested. Identifying diabetic people is possible by using different methods including machine learning algorithms. Standard machines assume balance in data and use all the available and related features to achieve lower error rates. However, in medical applications misclassification cost should be minimized as misclassification costs for healthy and patient instances are different. In addition, we are facing imbalanced data in the most medical issues including diabetes diagnosis. The features will also have different knowledge levels and costs. As a result, cost-sensitive methods should be applied in such situations. In this paper, we present and compare different cost-sensitive learning methods for diagnosis of type 2 diabetes. For evaluation of the methods two different data sets are used, which one of them is data set of Tabriz, Iran and the other one is for Pima Indian data set. By defining different scenarios, we will show that none of the studied methods has absolute superiority over the other methods and the performance of algorithms will be different due to used data set and defined scenario.

Cost-sensitive matrixized classification learning with information entropy

The use of series compensation devices is one of the methods to increase the capacity of a power transmission line. In addition, the use of controlled series compensation devices affects the steady-state stability of the electric power system. It is also widely known that automatic excitation control of generators has a positive effect on the stability of the system. Thus, it is reasonable to analyze the influence of the adjustable parameters of the controlled series compensation device on the line capacity when considering modes at the boundaries of the stability regions, taking into account automatic excitation controllers on synchronous generators of the power plant. Methods of mathematical modeling of the electric power system, the theory of long-distance power lines and electromechanical transients, methods of analyzing the stability of electric power systems are used. The original software in the C ++ programming language is used as a modeling tool. The authors have selected the regulation laws parameters of controlled series compensation device and automatic excitation controller, provided that steady-state stability is maintained. The stability regions of the electric power-engineering system under study are constructed depending on the tuning parameters of the considered devices. A technique is proposed to select the coefficients of complex regulation of the devices to increase the capacity of a high-voltage power transmission line. The proposed method of the complex selection of regulation coefficients of controlled devices provides the possibility of obtaining their optimal values in a controlled electric power system to ensure stability.

Occurrence of unscheduled electric power flows is one of the most important issues challenging safety of any electric power system. To prevent failures related to the phenomenon, power flows in the system are controlled. This paper contains a review of the causes for which power flow control in a system is necessary, methods used to make flow adjustments, and devices used to control power flows in networks. The practical portion of the presented study includes development of a simulation model for the network with the use of PowerWorld software. Presented are also results of measurements of active power and its losses in the states of equilibrium, increased demand for energy, and with phase shift transformer (PST) and thyristor-controlled series capacitor (TCSC) installed in the system. On the grounds of the obtained measurements it was demonstrated how harmful is the effect of unscheduled active power flows on stability of an electric power system. Moreover, the effect of PST and TCSC on active power flows in the system is discussed including advantages and disadvantages of both device types.

The class imbalance issue occurs when training a computer-aided detection (CAD) system for nodules. This imbalance causes poor prediction performance for true nodules. Moreover, the misclassification costs are different between two classes and high sensitivity of true nodules is essential in the detection. In order to eliminate or reduce the false positives while keeping high sensitivity, we present an effective wrapper framework incorporating the evaluation measure of imbalanced data into the objective function of cost sensitive SVM. We improve the performance of classification by simultaneously optimizing the best pair of misclassification cost parameter, feature subset and intrinsic parameters. We evaluated the method on a 3D Lung nodule dataset, showing that the proposed method outperforms many other exiting common methods, as well as specific imbalanced data learning methods, which indicates the effectiveness of our method on the imbalanced and unequal misclassification cost data classification.

The International Space Station (ISS) adopted a direct-current (DC) electrical power system (EPS). Switching mode DC power converters are playing a major role in power conversion, conditioning, and control. The stability of a switching mode converter has long been studied due to its negative input impedance at low frequencies. Integrated EPS stability will be assured by computer modeling, simulation, and analysis with one of the most advanced and accurate techniques developed academically. The impedance separation criteria and minimum phase margin criteria are used to check the entire system and individual load stability, in addition to the other requirements defined in the power quality specification. The modeling/simulation and testing are to be accomplished both at the individual load and element level. For modeling, the EPCE (electrical power consuming equipment) input filter model with a constant power load is used first for each EPCE for the system-level analysis; it is then replaced by the averaged Vorperian/Ridley model, when available, to finalize the analysis results. The EPCE large-signal model is used for the nonlinear time domain simulation and analysis. The small-signal model will be used for the linear system frequency domain analysis. The EPCE test measurement data is used to validate the accuracy of the EPCE model. The element-level test data is used to validate the accuracy of the element model and assure element-level interface stability. This paper documents the theoretical basis and the approach for the ISS EPS stability assurance for the secondary power circuits.

Abstract: Decision tree induction has been widely studied and applied. In safety applications, such as determining whether a chemical process is safe or whether a person has a medical condition, the cost of misclassification in one of the classes is significantly higher than in the other class. Several authors have tackled this problem by developing cost-sensitive decision tree learning algorithms or have suggested ways of changing the distribution of training examples to bias the decision tree learning process so as to take account of costs. A prerequisite for applying such algorithms is the availability of costs of misclassification. Although this may be possible for some applications, obtaining reasonable estimates of costs of misclassification is not easy in the area of safety. This paper presents a new algorithm for applications where the cost of misclassifications cannot be quantified, although the cost of misclassification in one class is known to be significantly higher than in another class. The algorithm utilizes linear discriminant analysis to identify oblique relationships between continuous attributes and then carries out an appropriate modification to ensure that the resulting tree errs on the side of safety. The algorithm is evaluated with respect to one of the best known cost-sensitive algorithms (ICET), a well-known oblique decision tree algorithm (OC1) and an algorithm that utilizes robust linear programming.

Algorithm for identifying wind power ramp events via novel improved dynamic swinging door

This paper investigates the dynamic stability of a droop-controlled multi-generator system in the more electric aircraft (MEA). Based on the developed state-space model of the potential dc electrical power system (EPS) architecture, the stability boundaries of EPS operation depending on parameter variations including component parameters and operating conditions are investigated. The effect of multiple parametric uncertainties on EPS stability is graphically illustrated by stability regions maps. In addition, the effect of the droop coefficient on the stability is discussed from the impedance point of view. The detailed mathematical models and analytical results of stability assessment are verified by time domain simulation studies.