Fast voltage estimation using an artificial neural network

Hsu, Yuan‐Yih; Yang, Chien-Chun

doi:10.1016/0378-7796(93)90054-i

Cited by 15 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A NN with two hidden layers and entropy-based selection of input variables is proposed in [14], and it was found that the selection of appropriate input variables is of crucial importance.…”

Section: Introductionmentioning

confidence: 99%

Validation of a robust neural real-time voltage estimator for active distribution grids on field data

Pertl

Douglass

Heussen

et al. 2018

Electric Power Systems Research

View full text Add to dashboard Cite

The installation of measurements in distribution grids enables the development of data driven methods for the power system. However, these methods have to be validated in order to understand the limitations and capabilities for their use. This paper presents a systematic validation of a neural network approach for voltage estimation in active distribution grids by means of measured data from two feeders of a real low voltage distribution grid. The approach enables a real-time voltage estimation at locations in the distribution grid, where otherwise only non-real-time measurements are available. The method shows robust behavior in all analyzed aspects, which is vital for real world applications. A methodology to select the most relevant input variables and find the best achievable performance for a particular number of inputs is presented. Moreover, the paper shows that the performance is not sensitive to the number of neurons in the hidden layer of the neural network as long as the model is not underdetermined. The paper examines the quantity of historical data needed to establish an adequately functioning model. To accommodate grid evolution and seasonal effects, the impact of different retraining intervals is investigated. Furthermore, the performance of the model during periods of high PV generation is evaluated. The validation shows that accurate voltage estimation models for distribution grids with high share of dispersed generation can be established with approximately one month of historical data. The model has to be retrained every 10 to 20 days to retain estimation mean squared errors below 0.35 V 2. It was also found that the performance does not decline during times of high PV generation.

show abstract

Section: Introductionmentioning

confidence: 99%

Validation of a robust neural real-time voltage estimator for active distribution grids on field data

Pertl

Douglass

Heussen

et al. 2018

Electric Power Systems Research

View full text Add to dashboard Cite

show abstract

“…The standard load flow methods such as Newton-Raphson (NR) and Gauss-Seidel have already been proved to be suitable for off-line applications (Stott et al, 1987;Wood and Wollenberg, 1984). In the literature, several approaches such as DFs (Lee and Chen, 1992;Singh and Srivastava, 1996), concentric relaxation method (Zaborszky et al, 1980), a method using four layered artificial neural networks (Hsu and Yang, 1993), an approach based on self-organizing hierarchical neural networks (Srivastava et al, 2001), a method based on fuzzy logic (Ramaswamy and Nayar, 2004) and new approaches based on sensitivities and genetic algorithms (Pablo and Peter, 2007;Ozdemir et al, 2005) have been proposed to predict bus voltages for different loading and outage conditions. Ramana et al (2012) and An et al (2006), have proposed approaches based on Thevenin theorem which their application is limited just for steady state voltage stability limit at a given bus due to load apparent power fluctuations and cannot handle voltage estimation problem after system reconfiguration.…”

Section: Introductionmentioning

confidence: 99%

A novel and fast voltage estimation scheme for assessment of power system component outages

Fatemi

Abedi

Vahidi

et al. 2014

COMPEL: The International Journal for Computation and Mathematics in Electrical and Electronic Engineering

View full text Add to dashboard Cite

Purpose -The purpose of this paper is to pursue two following main goals: first, theorizing a new concept named as equivalent bus load in order to make a promising simplification over power system analysis. Second, proposing an outstanding fast and simple approach based on introduced concept for voltage estimation after multiple component outages while satisfying required accuracy. Design/methodology/approach -Equivalent load bus theory introduces three transfer matrices that describe power system topology. Mentioned matrices could be calculated simply after system reconfiguration without matrix inversion. Using transfer matrices a large-scale power system can be modeled by a simple two-bus power system from the viewpoint of any desired bus so that load flow calculation leads to same value. The analysis of simplified power system yields to extract a new incremental model based on equivalent bus load theory that will be distinguished as an outstanding fast method for voltage estimation aim. Findings -A deep study for fast voltage estimation aim is dedicated to evaluate proposed method from the accuracy and quickness point of view and the outcomes are compared to a well-known method as Distribution Factors (DF). Results and computational times unveil that presented approach is more accurate and much faster. Originality/value -A novel and new fast voltage estimation method for assessment of power system component outages is introduced. present, he has been with the Department of Electrical Engineering of the Amirkabir University of Technology, where he is now a Professor. His main fields of research are high voltage, electrical insulation, power system transient, lightning protection, and pulse power technology. He has authored and coauthored more than 300 papers and six books on high-voltage engineering and power system. Professor Behrooz Vahidi is the corresponding author and can be contacted at: vahidi@aut.ac.ir Sajjad Abedi received the BS Degree in Electrical engineering from the Isfahan University of Technology (IUT), Isfahan, Iran, in 2008, and the MS Degree (with honors) in Electrical Engineering, majoring in electrical energy management, from the Amirkabir University of Technology (AUT), Tehran, Iran, in 2011. Presently, he is a Graduate Research and Teaching Assistant in Electrical Engineering Department at AUT. He currently leads a number of research projects related to power system planning and economics, stochastic optimization, renewable energy integration, as well as smart grids development and deployment.Dr Hassan Rastegar received the BSc, MSc, and PhD Degrees in Electrical Engineering from the Amirkabir University of Technology, Tehran, Iran, in 1987, 1989, and 1998 Currently, he is an Associate Professor at the Amirkabir University of Technology. He has published many papers in journals and conferences. His research interests include power system control, application of computational intelligence in power systems, simulation and analysis of power systems, and renewable energy.

show abstract

“…This motivated many researchers to focus on ANN based voltage estimation problem. Hsu et al [11] employed MLP to estimate the bus voltages in normal and post fault conditions. But, if the range of load variation at different buses is increased, the accuracy of voltage estimation greatly suffers and at the same time training process is extremely slow due to the use of conventional back-propagation (BP) algorithm.…”

Section: Introductionmentioning

confidence: 99%

New Parallel Radial Basis Function Neural Network for Voltage Security Analysis

Jain¹,

Srivastava²,

Singh³

et al.

Proceedings of the 13th International Conference On, Intelligent Systems Application to Power Systems

View full text Add to dashboard Cite

On-line monitoring of power system voltage security has become a very demanding task in competitive power market operation and fast estimation of bus voltage is essential for this. In this paper, a novel parallel radial basis function neural network (PRBFN) which is a multistage network, in which stages operate in parallel rather than in series during testing, has been developed to predict bus voltage magnitudes in an efficient manner. The non-linear mapping capability of radial basis function has been exploited along with forward-backward training. Entropy concept has been used to select the input features of PRBFN to reduce the size of the neural network. The proposed method using a single PRBFN is used to estimate bus voltages under different topological and operating conditions of IEEE 30-bus and a practical 75-bus Indian system. R 320 1-59975-028-7/05/$20.00 © 2005 ISAP.

show abstract

Fast voltage estimation using an artificial neural network

Cited by 15 publications

References 33 publications

Validation of a robust neural real-time voltage estimator for active distribution grids on field data

Validation of a robust neural real-time voltage estimator for active distribution grids on field data

A novel and fast voltage estimation scheme for assessment of power system component outages

New Parallel Radial Basis Function Neural Network for Voltage Security Analysis

Contact Info

Product

Resources

About