Power system voltage stability monitoring using artificial neural networks with a reduced set of inputs

Bahmanyar, Alireza; Karami, Ali

doi:10.1016/j.ijepes.2014.01.019

Cited by 83 publications

(37 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dimensionality reduction has been performed in order to find a subset of the most important features. This is necessary as having a large number of inputs not only increases the size of the ANN, but also raises the cost as well as the time required for future data collection [29]. A simple method, particularly useful in practice, is the Gram-Schmidt orthogonalization process.…”

Section: Framework Implementationmentioning

confidence: 99%

“…A simple method, particularly useful in practice, is the Gram-Schmidt orthogonalization process. This method is a forward selection algorithm that ranks the input set by progressively adding features, which correlate to the target in the space orthogonal to the already selected [29], [30].…”

Section: Framework Implementationmentioning

confidence: 99%

“…5). This process uses equation 2 to calculate the correlation coefficients to determine the strength of the relationship between each input feature [29], [32]:…”

Section: Framework Implementationmentioning

confidence: 99%

See 2 more Smart Citations

Knowledge extraction using probabilistic reasoning: An artificial neural network approach

Dobbins

Fergus

2015

2015 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Abstract-The World Wide Web (WWW) has radically changed the way in which we access, generate and disseminate information. Its presence is felt daily and with more internetenabled devices being connected the web of knowledge is growing. We are now moving into era where the WWW is capable of 'understanding' the actual/intended meaning of our content. This is being achieved by creating links between distributed data sources using the Resource Description Framework (RDF). In order to find information in this web of interconnected sources, complex query languages are often employed, e.g. SPARQL. However, this approach is limited as exact query matches are often required. In order to overcome this challenge, this paper presents a probabilistic approach to searching RDF documents. The developed algorithm converts RDF data into a matrix of features and treats searching as a machine learning problem. Using a number of artificial neural network algorithms, a successfully developed prototype has been developed that demonstrates the applicability of the approach. The results illustrate that the Voted Perceptron classifier (VPC), perceptron linear classifier (PERLC) and random neural network classifier (RNNC) performed particularly well, with accuracies of 100%, 98% and 93% respectively.

show abstract

Section: Framework Implementationmentioning

confidence: 99%

Section: Framework Implementationmentioning

confidence: 99%

See 1 more Smart Citation

Knowledge extraction using probabilistic reasoning: An artificial neural network approach

Dobbins

Fergus

2015

2015 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…Both ANNs have been widely used, the last years, in the solution of many power system problems presenting very accurate results. MLP and RBF ANNs have been used for the fault location and predictive maintenance of transmission lines [9,10], for the estimation of transmission lines' distance protection [11], for lightning outage calculations and grounding resistance issues [12], for voltage stability monitoring [13], for the estimation of electric fields and the critical flashover voltage along high-voltage insulators [12,14], and for power transformer problems such as insulation aging and fault diagnosis [15,16].…”

Section: Artificial Neural Network' (Anns) Implementationmentioning

confidence: 99%

An artificial neural network software tool for the assessment of the electric field around metal oxide surge arresters

Ekonomou

Mladenov

2015

Neural Comput & Applic

View full text Add to dashboard Cite

The paper presents an artificial neural network (ANN) software tool that has been developed in order to assess the electric field around medium-voltage surge arresters. The knowledge of the electric field around gapless metal oxide surge arresters is very useful for diagnostic tests and design procedures. For the training, validating, and testing of the ANNs, real data have been used collected from hundreds of measurements. The developed ANN software can be used by electric utilities in order to diagnose the condition of the surge arresters without stopping their operation and by laboratories and manufacturing/retail companies dealing with medium-voltage surge arresters and either face a lack of suitable measuring equipment or want to compare/verify their own measurements.

show abstract

“…Most of the earlier studies based on conventional approach primarily depend on load flow simulation over a specific time period of observation and are faced with several limitations such as; complexity in modeling, unavailability of real time database, simulation of contingencies and more so. Hence, most of the present day research is inclined to get an edge over the same by supplementing the analysis with soft computing tools such as fuzzy logic and neural networks [11][12][13][14][15][16]. Being partially motivated by this, the authors of this paper have tried to implement neural network tools for identification of critical conditions in electric power system through a comparative study and performance analysis of the proposed network with the basic objective of evolving an optimal network structure and learning criteria.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Critical Conditions in Electric Power Systems by Feed Forward and Layer Recurrent Neural Networks

Panda¹,

Sahoo²,

Satpathy³

et al. 2014

ijeei

View full text Add to dashboard Cite

Abstract:In this paper, critical conditions in electric power systems are monitored by applying various neural networks. In order to accomplish the stated goal, the authors tried several combinations of Feed Forward Neural Network and Layer Recurrent Neural Networks by imparting appropriate training schemes through supervised learning in order to formulate a comparative analysis on their performance. Once, training goes successful, the neural network learns how to deal with a set of newly presented data through validation and testing mechanism so as to evolve the best network structure and learning criteria. The proposed methodology has been tested on the standard IEEE 30-bus test system with the support of MATLAB based neural network toolbox. The results presented in this paper signify that the multi-layered feed forward neural network with Levenberg-Marquardt back propagation algorithm gives best training performance of all possible cases considered in this paper, thus validating the proposed methodology.

show abstract

Power system voltage stability monitoring using artificial neural networks with a reduced set of inputs

Cited by 83 publications

References 29 publications

Knowledge extraction using probabilistic reasoning: An artificial neural network approach

Knowledge extraction using probabilistic reasoning: An artificial neural network approach

An artificial neural network software tool for the assessment of the electric field around metal oxide surge arresters

Analysis of Critical Conditions in Electric Power Systems by Feed Forward and Layer Recurrent Neural Networks

Contact Info

Product

Resources

About