Volume 23, Issue 2, May 2016, Pages 380–411
M. MADHIARASAN1 and S. N. DEEPA2
1 Research Scholar (Ph. D), Department of Electrical and Electronics Engineering, Anna University Regional Campus, Coimbatore, Coimbatore - 641046, Tamil Nadu, India
2 Associate Professor, Department of Electrical and Electronics Engineering, Anna University Regional Campus, Coimbatore, Coimbatore - 641046, Tamil Nadu, India
Original language: English
Copyright © 2016 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Accurate wind speed forecasting is a challenging, crucial and important task because it highly impacts on the power system and wind farm planning, scheduling and control operation. This article presents comparative performance analysis on the wind speed forecasting application based on the six artificial neural network namely, back propagation network (BPN), multi-layer perceptron network (MLPN), radial basis function network (RBFN), ELMAN network (EN), improved back propagation network (IBPN), and recursive radial basis function network (RRBFN). The real-time acquisitions utilized to forecast wind speed by means of six artificial neural networks are the 10 minutes mean wind farm data’s acquired at three acquisition location in Coimbatore region. Wind speed, wind direction, air pressure, temperature, relative humidity and dew point are taken as inputs for the six artificial neural network bases forecasting model to forecast different time scale wind speed forecasting. The effectiveness is validated by means of the five evolution error metrics such as mean absolute percentage error (MAPE), mean relative error (MRE), mean absolute error (MAE), root mean square error (RMSE), and mean square error (MSE). Simulation results revealed that even for the similar data sets, recursive radial basis function network based forecasting model outperform among the six artificial neural networks with the best forecasting accuracy and the lowest statistical errors.
Author Keywords: Back Propagation Network, Multi-layer Perceptron Network, Radial Basis Function Network, ELMAN Network, Improved Back Propagation Network, Recursive Radial Basis Function Network, Wind Speed, Forecasting.
M. MADHIARASAN1 and S. N. DEEPA2
1 Research Scholar (Ph. D), Department of Electrical and Electronics Engineering, Anna University Regional Campus, Coimbatore, Coimbatore - 641046, Tamil Nadu, India
2 Associate Professor, Department of Electrical and Electronics Engineering, Anna University Regional Campus, Coimbatore, Coimbatore - 641046, Tamil Nadu, India
Original language: English
Copyright © 2016 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Accurate wind speed forecasting is a challenging, crucial and important task because it highly impacts on the power system and wind farm planning, scheduling and control operation. This article presents comparative performance analysis on the wind speed forecasting application based on the six artificial neural network namely, back propagation network (BPN), multi-layer perceptron network (MLPN), radial basis function network (RBFN), ELMAN network (EN), improved back propagation network (IBPN), and recursive radial basis function network (RRBFN). The real-time acquisitions utilized to forecast wind speed by means of six artificial neural networks are the 10 minutes mean wind farm data’s acquired at three acquisition location in Coimbatore region. Wind speed, wind direction, air pressure, temperature, relative humidity and dew point are taken as inputs for the six artificial neural network bases forecasting model to forecast different time scale wind speed forecasting. The effectiveness is validated by means of the five evolution error metrics such as mean absolute percentage error (MAPE), mean relative error (MRE), mean absolute error (MAE), root mean square error (RMSE), and mean square error (MSE). Simulation results revealed that even for the similar data sets, recursive radial basis function network based forecasting model outperform among the six artificial neural networks with the best forecasting accuracy and the lowest statistical errors.
Author Keywords: Back Propagation Network, Multi-layer Perceptron Network, Radial Basis Function Network, ELMAN Network, Improved Back Propagation Network, Recursive Radial Basis Function Network, Wind Speed, Forecasting.
How to Cite this Article
M. MADHIARASAN and S. N. DEEPA, “Performance Investigation of Six Artificial Neural Networks for Different Time Scale Wind Speed Forecasting in Three Wind Farms of Coimbatore Region,” International Journal of Innovation and Scientific Research, vol. 23, no. 2, pp. 380–411, May 2016.
