A Comparative Study on Static Voltage Stability Analysis of Power System using Feed Forward Neural Network and Radial Basis Function Neural Network with Reduced Set of Inputs

Direct stability analysis using an energy function has recently been widely used for angular and voltage stability analysis in electric power systems. Considerable efforts have concentrated on seeking energy functions for lossy power systems, accomplished only for the simple two-bus system. A new approach is presented to derive an energy function by using the complex integral of bus current equations with respect to bus voltages. Under an assumption that all transmission lines have a uniform R/X ratio, it is shown that the energy function can be developed for multimachine power systems with losses. The proposed energy function is tested on sample systems by comparing the time simulation method, which shows the validity of the proposed method.

This paper uses a radial basis function (RBF) neural network for star identification. A feature vector consisting of distance and angle cosine values is constructed as a library of recognition feature stars and input to the neural network. Then, the network’s output is the number of the corresponding primary star. Comparing the training efficiency and robustness of the grid algorithm with the BP neural network and radial basis function neural network for star identification, the experimental results show that the radial basis function neural network has a strong anti-interference ability against noise and pseudo-star interference. The following conclusions are drawn from the simulation tests: the sample recognition rate of radial basis function neural network algorithm can reach 96% for star position and star addition noise; when the proportion of pseudo-star reaches 20%, the sample recognition rate of radial basis function neural network algorithm is still higher than grid algorithm and BP neural network, which indicates that the radial basis function neural network algorithm has the solid anti-interference ability to both noise and pseudo-star. Therefore, the radial basis function neural network algorithm based on star Identification has specific application prospects.

This paper discusses voltage stability analysis of power systems using two static voltage stability analyses: voltage sensitivity, modal analysis including participation factor. These methods determine how far the power system is from its break point providing relative measure of voltage instability proximately. Results show all method indices share voltage stability margins having a precise voltage collapse point when a power system is subjected to sudden load increase. The application has been demonstrated on the IEEE 14-bus System.

Comprehensive evaluation of voltage stability based on EW-AHP and Fuzzy-TOPSIS

A new decomposition-aggregation approach is developed to perform transient stability analysis of an N-machine power system with a speed governor. The system decomposition is performed so that every subsystem includes four machines, instead of only two or three machines as considered in other work. The system model is derived and decomposed into (N − 1)/3 11th-order interconnected subsystems considering transfer conductances, nonuniform mechanical damping, electromagnetic damping and speed governor action. Each of these subsystems is decomposed into a free subsystem containing 12 nonlinearities and interconnections. A square aggregation matrix of order (N − 1)/3 is obtained instead of orders N and (N + 1)/2 for the pair-wise and triple-wise decompositions, respectively. The approach is applied to a 10-machine power system and an estimate for the system asymptotic stability domain is determined. System transient stability computations are carried out considering a three-phase short circuit fault, with successful reclosure, near a system bus or a sudden loss of one of the system loads. The approach is used to determine a reclosure time for the faulted line and a reconnection time for the lost load required for the system to regain its prefault (normal) conditions. The approach developed is suitable and can be easily used for stability analysis of power systems (the number of machines may be more than 10). The developed approach can also reduce the conservativeness of the decomposition-aggregation method.

More electric aircraft (MEA) is using more electrical power on board and the stability analysis of the aircraft electric power system (AEPS) becomes more important. This paper presents a modeling study and stability analysis of the EPS for MEA. Averaging technique is used to model the aircraft EPS, which includes a generator, an autotransformer rectifier and an inverter-motor load. The proposed model is accurate and simple for the large signal stability analysis of MEA power system. Brayton-Moser mixed potential and Lyapunov stability theorems are employed to estimate the large-signal stability region of the system. Simulation results are used to verify the effectiveness and feasibility of the proposed analytical method.

Both Angle and voltage stability are discussed in the context of the energy function approach. It is shown that complete decoupling of the two phenomena is not possible in general, particularly in stressed systems. It is demonstrated that the UEP (unstable equilibrium point) concept is a valid one for both types of stability analysis. >

This article presents the results of a study aimed at the development of a system for short-term electric power load forecasting. This was attempted by training feedforward neural networks (FFNNs) and cosine radial basis function (RBF) neural networks to predict future power demand based on past power load data and weather conditions. This study indicates that both neural network models exhibit comparable performance when tested on the training data but cosine RBF neural networks generalize better since they outperform considerably FFNNs when tested on the testing data. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 591–605, 2005.

As wind generation begins to contribute significantly to power systems, the need arises to assess the impact of this new source of variable generation on the stability of the system. This work provides a detailed methodology to assess the impact of wind generation on the voltage stability of a power system. It will also demonstrate the value of using time-series ac power flow analysis techniques in assessing the behavior of a power system. Traditional methods are insufficient in describing the nature of wind for steady-state analyses, and as such, a new methodology is presented to address this issue. Using this methodology, this paper will show how the voltage stability margin of the power system can be increased through the proper implementation of voltage control strategies in wind turbines.

The wide application of WAMS (Wide Area Measurement System) provided a new thinking for transient stability analysis of power system. Based on real-time measurement information from WAMS, a method to quickly analysis power system transient stability that does not depend on network structure, model and parameters of power system is proposed in this paper. Firstly, the parameters of system are identified online by improved least squares method on basis of that the multi-machine power system is equivalently reduction to one machine infinity bus system. The equilibrium point and stability margin of equivalent system are rapidly computed, and then the stability of system is quickly judged. The simulation results show that the algorithm can accurately judge transient stability of system and has better antidisturbance ability and robustness. The issue of dependence of transient stability analysis on system model and parameter is solved. The adverse influences of data lose and measurement errors in actual measurement of the WAMS on analysis results are avoided effectively. Keywords-power system; wide-area measurement system; parameter identification; energy function; transient stability analysis

This study presents an analysis of voltage stability of the electrical power system with the integration of renewable energy and the improvement of the conventional analysis using the artificial neural network (ANN), which is mainly focused on the effect of distributed generator-solar (DG-Solar) towards the electric power system. Real power and reactive power margins of both voltage stability are expressed as VSM (P) and VSM (Q), respectively. They are obtained from the actual power-voltage (PV) and reactive-power (QV) curve, which is created for each series by a series of load flows by incrementing P and Q load. Then, the system will integrate with 5MW, 50MW and 100MW of DG-Solar to compare the electric power system before and after the integration. The results are observed and compared for both situations. After that, an analysis improvement is made by using ANN-based model to predict the values of VSM (P) and VSM (Q) without having to perform PV QV Curve and calculate VSM (P) and VSM (Q). IEEE 30-bus was chosen as the electrical power system. The load flow analysis and ANN-based model are simulated and developed by using MATLAB software.

Multi-bus grid connected in a pi network has shunt admittance with series lumped impedance of transmission line. The voltage’s stability is very important to maintain supply. So, the estimation of voltage stability of two-bus model is considered for the study. This paper indicates the improvement of the same pi-network representation employing a new methodology known as a generalized global voltage stability margin (GVSM). It is used to assess the general voltage stability status of the facility system accurately. To predict the current status of the system and in provisions of accuracy two topologies of artificial neural network (ANN) such as the radial basis function neural network (RBFN) and feedforward backprop network (FFBP) are used to compare the results which are simulated from the offline N-R method. The input data of ANN are derived from the Newton–Raphson (N-R) load flow analysis in the interior of the platform of MATLAB 2015a. The new method is validated on IEEE 14 and IEEE 30 test bus cases. Simulation results of the pi-equivalent network are carried out for standard test bus system IEEE 30 and IEEE 14. The proposed technique is very accurate for assessing the voltage stability of any power grid at any operating point at some stage in a better way compared to the series equivalent model.

The transient stability analysis of power systems can be described by differential and algebraic equations, and due to the increased speed with parallel computing techniques, use of the waveform relaxation method to solve these equations has attracted much attention. In order to enhance the calculation speed of the waveform relaxation method, it is of prime importance to reduce the required number of iterations for each time window. To this end, an initialization and preconditioning techniques have been proposed to improve convergence of the iterative procedure. In this paper, in order to enhance convergence, we developed a new global initialization technique that consists of linear analysis and a preconditioning technique. Specifically, global initialization is the result of the repeated application of conventional initialization and preconditioning techniques before each of the nonlinear iterative procedures, and then using linear analysis to determine the interaction between the CPUs. By calculating the initial waveforms more accurately, it is expected that additional speedup can be achieved by reducing the required number of iterations necessary for convergence of the nonlinear analysis.

Wavelet based feature extraction of voltage profile for online voltage stability assessment using RBF neural network

The diagnosis of cardiovascular arrhythmias needs accurate predictive models to test abnormalities in the functioning of the heart. The proposed work manifests a comparative analysis of different classifiers like K-nearest neighbour (KNN), support vector machine (SVM), back propagation neural network (BPNN), feed forward neural network (FFNN) and radial basis function neural network (RBFNN) with discrete wavelet transform (DWT) to assess an Electrocardiogram (ECG). For DWT, different wavelets such as Daubechies, Haar, Symlet, Biorthogonal, reverse Biorthogonal and Coiflet are used for feature extraction and their performances are compared. SVM and RBFNN have shown 100% accuracy with reduced dataset testing time of 0.0025 s and 0.0174 s, respectively, whereas BPNN, FFNN and KNN provided 95.5%, 97.7% and 84.0% accuracy with 0.0176 s, 0.0189 s and 0.0033 s of testing time, respectively. This proposed scheme builds an efficient selection of wavelet with best-suited classifier for timely perusal of cardiac disturbances.