Back to Search
Start Over
Minimum non detection zone for islanding detection using an optimal Artificial Neural Network algorithm based on PSO.
- Source :
-
Renewable & Sustainable Energy Reviews . Dec2015, Vol. 52, p1-18. 18p. - Publication Year :
- 2015
-
Abstract
- Islanding is one of the most important concerns of the grid connected distributed resources due to personnel and equipment safety. Many approaches have been proposed for islanding detection, which can be categorized into passive and active schemes. The main concern of the passive schemes is related to their large Non Detection Zone (NDZ), while the main problem of the active methods is related to their negative impact on power quality. This paper propose an efficient and intelligent islanding detection algorithm using combination of an optimal Artificial Neural Network (ANN) based on Particle Swarm Optimization (PSO) with a simple active method. The intelligent islanding detection method based on ANN, may have mal-detection in the case of change in the power network structure. In the proposed scheme, ANN is adapted with change in power network structure to reduce NDZ. Optimal parameters of the ANN such as weight coefficients and biases are derived using the PSO in order to minimize the technique NDZ. Also the performance of the various structures of ANN such as Multilayer Perceptron (MLP), Radial Basis Function (RBF) and Probabilistic Neural Network (PNN) in combination with PSO is compared for islanding detection purpose. The proposed method is simulated and tested in various operation conditions such as islanding conditions, motor starting, capacitor bank switching and nonlinear load switching. The test results showed that it correctly detects the islanding operation and does not mal-operate in the other situations and has a small NDZ. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 13640321
- Volume :
- 52
- Database :
- Academic Search Index
- Journal :
- Renewable & Sustainable Energy Reviews
- Publication Type :
- Academic Journal
- Accession number :
- 111529097
- Full Text :
- https://doi.org/10.1016/j.rser.2015.07.080