A Novel Method to Select Hidden Neurons in ELMAN Neural Network for Wind Speed Prediction Application

Authors: ,

Abstract: This paper proposes a novel method to select hidden neurons in ELMAN neural networks for wind speed prediction application. Either over fitting or under fitting problem caused due to the random choice of hidden neuron numbers in artificial neural network. This paper suggests the solution to solve either over fitting or under fitting problems. In order to select proper hidden neuron numbers, 75 different criteria tested by the means of statistical errors. The simulation results proved that proposed approach improves the accuracy and reduce the error to the least. The perfect building of ELMAN network with five inputs using fixation criteria is validated based on convergence theorem. To evaluate the performance of the proposed approach simulation were performed on real-time wind data. Comparative analysis has performed to select the hidden neuron numbers in neural networks. The presented approach is very simple, with the least error, and more effective to select the amount of hidden neurons in ELMAN neural network.

WSEAS Transactions on Power Systems, ISSN / E-ISSN: 1790-5060 / 2224-350X, Volume 13, 2018, Art. #2

PDF
XML
Cite
×
Citation Tools
WSEAS AMA
M. Madhiarasan, S. N. Deepa, "A Novel Method to Select Hidden Neurons in ELMAN Neural Network for Wind Speed Prediction Application," WSEAS Transactions on Power Systems, vol. 13, pp. 13-30, 2018, DOI:
M. Madhiarasan, S. N. Deepa. A Novel Method to Select Hidden Neurons in ELMAN Neural Network for Wind Speed Prediction Application. WSEAS Transactions on Power Systems. 2018;13:13-30.
Copy to Clipboard
Citation copied to Clipboard

Certification

---