Selection of number of hidden neurons in neural networks in renewable energy systems

This paper presents a new approach to select number of hidden neurons in neural network in renewable energy systems. The random selection of number of hidden neurons might cause over fitting and under fitting problems in neural networks. The proper selection of neurons in hidden layer is important in the design of neural network model. To fix hidden neurons, 91 various criteria are examined based on estimated mean squared error. The convergence analysis is performed for the various proposed criteria. To verify the effectiveness of the proposed model, simulations were conducted on real time wind data. Results show that with minimum error the proposed approach can be used in renewable energy systems.

[1]  Hao Yu,et al.  Selection of Proper Neural Network Sizes and Architectures—A Comparative Study , 2012, IEEE Transactions on Industrial Informatics.

[2]  Shin'ichi Tamura,et al.  Capabilities of a four-layered feedforward neural network: four layers versus three , 1997, IEEE Trans. Neural Networks.

[3]  Yue Liu,et al.  Optimizing number of hidden neurons in neural networks , 2007, Artificial Intelligence and Applications.

[4]  T.W.S. Chow,et al.  The estimation theory and optimization algorithm for the number of hidden units in the higher-order feedforward neural network , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[5]  Kazuyuki Murase,et al.  A new algorithm to design compact two-hidden-layer artificial neural networks , 2001, Neural Networks.

[6]  Xiaofeng Yang,et al.  A hybrid strategy of short term wind power prediction , 2013 .

[7]  Daniel S. Yeung,et al.  Hidden neuron pruning of multilayer perceptrons using a quantified sensitivity measure , 2006, Neurocomputing.

[8]  Osamu Fujita,et al.  Statistical estimation of the number of hidden units for feedforward neural networks , 1998, Neural Networks.

[9]  Jinchuan Ke,et al.  Empirical Analysis of Optimal Hidden Neurons in Neural Network Modeling for Stock Prediction , 2008, 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application.

[10]  Tomonobu Senjyu,et al.  A new strategy for predicting short-term wind speed using soft computing models , 2012 .

[11]  Yuan Lan,et al.  Constructive hidden nodes selection of extreme learning machine for regression , 2010, Neurocomputing.

[12]  Shuxiang Xu,et al.  A novel approach for determining the optimal number of hidden layer neurons for FNN’s and its application in data mining , 2008 .