Static security assessment using radial basis function neural networks based on growing and pruning method

Javan, Dawood Seyed; Mashhadi, Habib Rajabi; Rouhani, Modjtaba

doi:10.1109/epec.2010.5697189

Cited by 9 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Reference 64 presents a novel method based on growing and pruning training algorithm using a radial basis function neural network and winner‐take‐all neural network to assess whether the power system is statically secure under different stable operating points. Active and reactive loads, line active and reactive power flow, active and reactive generations and bus voltages formed input feature set in Reference 64.…”

Section: Categorization Based On Power System Implementationmentioning

confidence: 99%

“…In References 1,63,64, a separation index is defined to identify the most significant variables facilitating the patterns separation between secure and insecure status. The proposed index is as follows:

F_{2} = (||, \frac{m_{i}^{((), S)} - m_{i}^{((), I)}}{σ_{i}^{{(S)}^{2}} + σ_{i}^{{(I)}^{2}}}),

m_{i}^{(S)} = \frac{1}{N^{((), S)}} \sum_{j = 1}^{N ((), S)} y_{ij}^{(S)},

m_{i}^{(I)} = \frac{1}{N^{((), I)}} \sum_{j = 1}^{N ((), I)} y_{ij}^{(I)},

σ_{i}^{{((), S)}^{2}} = \frac{1}{N^{((), S)}} \sum_{j = 1}^{N ((), S)} {\{y_{italicij}^{((), S)} - m_{i}^{((), S)}\}}^{2},

σ_{i}^{{((), I)}^{2}} = \frac{1}{N^{((), I)}} \sum_{j = 1}^{N ((), I)} {\{y_{italicij}^{((), I)} - m_{i}^{((), I)}\}}^{2} .

…”

Section: Categorization Based On Classifiers' Featuresmentioning

confidence: 99%

“…The correlation coefficient is calculated based on the following relation 1,64 :

C_{c_{italicij}} = \frac{({}, \frac{1}{N} \sum_{k = 1}^{N} y_{ik} y_{jk}) - ({}, \frac{1}{N} \sum_{k = 1}^{N} y_{ik}) ({}, \frac{1}{N} \sum_{k = 1}^{N} y_{jk})}{({}, \sqrt{\frac{1}{N} {false\sum}_{k = 1}^{N} {((), y_{ik} - \frac{1}{N} \sum_{k = 1}^{N} y_{ik})}^{2}}) ({}, \sqrt{\frac{1}{N} {false\sum}_{k = 1}^{N} {((), y_{jk} - \frac{1}{N} \sum_{k = 1}^{N} y_{jk})}^{2}})} .

…”

Section: Categorization Based On Classifiers' Featuresmentioning

confidence: 99%

See 2 more Smart Citations

Static security assessment of power systems: A review

Gholami

Sanjari

Safari

et al. 2020

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary The security assessment, based on which determinant decisions should be made for power system design, control and operation, is a challenging issue for utility engineers and network designers, especially in large‐scale power systems. Numerous methods have been proposed and implemented for this purpose, and a variety of indices have been suggested to address the static security condition of power networks. Large‐scale datasets of measurements in continually expanding power systems necessitate advanced knowledge in big data analytics. In this review paper, numerical techniques and machine learning‐based methods are reviewed as two main categories for static security assessment in power systems based on principal features of static security status classification such as type of classifier, the static security index, and feature selection and extraction methods. This paper can be used as a useful reference for static security assessment of power systems.

show abstract

Section: Categorization Based On Power System Implementationmentioning

confidence: 99%

F_{2} = (||, \frac{m_{i}^{((), S)} - m_{i}^{((), I)}}{σ_{i}^{{(S)}^{2}} + σ_{i}^{{(I)}^{2}}}),

m_{i}^{(S)} = \frac{1}{N^{((), S)}} \sum_{j = 1}^{N ((), S)} y_{ij}^{(S)},

m_{i}^{(I)} = \frac{1}{N^{((), I)}} \sum_{j = 1}^{N ((), I)} y_{ij}^{(I)},

σ_{i}^{{((), S)}^{2}} = \frac{1}{N^{((), S)}} \sum_{j = 1}^{N ((), S)} {\{y_{italicij}^{((), S)} - m_{i}^{((), S)}\}}^{2},

σ_{i}^{{((), I)}^{2}} = \frac{1}{N^{((), I)}} \sum_{j = 1}^{N ((), I)} {\{y_{italicij}^{((), I)} - m_{i}^{((), I)}\}}^{2} .

…”

Section: Categorization Based On Classifiers' Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Static security assessment of power systems: A review

Gholami

Sanjari

Safari

et al. 2020

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

show abstract

“…This phase involves selecting small optimal set from a large set of variables that will give more useful information to build the classification function. These variables are termed features and the process of obtaining them is called feature selection [8]. The features form the components of a vector called feature vector represented as Z = {Z1, Z2, …., Zm}.…”

Section: B Feature Selectionmentioning

confidence: 99%

Security assessment and enhancement using RBFNN with feature selection

Srilatha

Yesuratnam

2014

2014 North American Power Symposium (NAPS)

View full text Add to dashboard Cite

Secure operation of the power system in real time requires assessment of rapidly changing system conditions. Traditional security evaluation method involves running full load flow for each contingency, making it infeasible for real time application. This paper presents Radial Basis Function Neural Network (RBFNN) approach with feature selection for static security assessment and enhancement. The security of the system is assessed based on the intensity of contingencies. The necessary corrective control action to be taken in the event of insecure state is also proposed and the effect of this action has also been observed in order to enhance the security. RBFNN improves the response time compared to other neural networks. Feature selection of the input patterns is done to reduce the dimensionality to a large extent, maintaining the classification accuracy. This method is illustrated using New England 39 bus system.

show abstract

“…Atualmente, observa-se um grande interesse por algoritmos de aprendizagem que determinem tanto a estrutura como os pesos da rede neural. Por exemplo, algoritmos construtivos (crescimento, poda, crescimento-poda) e algoritmos evolucionários (Liu et al;Fangju;Miche et al;Feng et al;2009;2009a,b;Javan et al;Pisani e Lorena; Sistemas evolutivos são sistemas adaptativos de alto nível, pois eles determinam sua estrutura e respectivos parâmetros de forma simultânea, gradual e incremental. Portanto, são sistemas capazes de aprender a partir de um fluxo de dados, o que é muito conveniente em ambientes on-line ou tempo real.…”

Section: Os-elmunclassified

Redes neurais evolutivas com aprendizado extremo recursivo

Rosa¹

View full text Add to dashboard Cite

This dissertation studies a class of evolving neural networks for system modeling from data streams. The class encompasses single hidden layer feedforward neural networks with variable and online definition of the number of hidden neurons.Evolving neural network learning uses clustering methods to estimate the number of hidden neurons simultaneously with extreme learning algorithms to compute the weights of the hidden and output layers. A particular case is when the evolving network keeps the number of hidden neurons fixed. In this case, the number of hidden neurons is found a priori, and the hidden and output layer weights updated as data are input. Clustering and extreme learning algorithms are recursive. Therefore, the learning process may occur online or real-time using data stream as input.Two evolving neural networks are suggested in this dissertation. The first is an evolving hybrid fuzzy neural network with unineurons in the hidden layer. Unineurons are fuzzy neurons whose synaptic processing is performed using uninorms. The output neurons are sigmoidals. A recursive clustering algorithm based on density and data clouds is used to granulate the input-output space, and to estimate the number of hidden neurons of the network. Each cloud corresponds to a hidden neuron. The weights of the hybrid fuzzy neural network are found using the extreme learning machine and the weighted recursive least squares algorithm. The second network is an evolving multilayer neural network with sigmoidal hidden and output neurons. Like the hybrid neural fuzzy network, clouds granulate the input-output space and gives the number of hidden neurons. The algorithm to compute the network weights is the same recursive version of the extreme learning machine. A variation of the adaptive OS-ELM (online sequential extreme learning machine) network is also suggested.Similarly as the original, the new OS-ELM fixes the number of hidden neurons, but uses sigmoidal instead of linear neurons in the output layer. The new OS-ELM also uses weighted recursive least square. ix The hybrid and neural networks were evaluated using two classic benchmarks: the gas furnace identification using the Box-Jenkins data, and forecasting of the chaotic Mackey-Glass time series. Synthetic data were produced to evaluate the neural networks when modeling systems with concept drift and concept shift. This a modeling circumstance in which system structure and parameters change simultaneously.Evaluation was done using the root mean square error and the Deibold-Mariano statistical test. The performance of the evolving and adaptive neural networks was compared against neural network with extreme learning, and evolving modeling methods representative of the current state of the art. The results show that the evolving neural networks and the adaptive network suggested in this dissertation are competitive and have similar or superior performance than the evolving approaches proposed in the literature.

show abstract

Static security assessment using radial basis function neural networks based on growing and pruning method

Cited by 9 publications

References 19 publications

Static security assessment of power systems: A review

Static security assessment of power systems: A review

Security assessment and enhancement using RBFNN with feature selection

Redes neurais evolutivas com aprendizado extremo recursivo

Contact Info

Product

Resources

About