Forecasting of photovoltaic power using deep belief network

This main focus of this paper aims to forecast photovoltaic power. The accuracy for forecasting Renewable Energy Sources (RES) are important as it is needed for power grids to operate. It can help make necessary adjustments to operate with RES, which can be highly complexed. As penetration level of renewable generation increases overtime, there may result in a shift towards a generation-dominant grid, causing severe power quality concerns. The proposed methodology of this paper is artificial neural network (ANN) and the training algorithm is Deep Belief Network (DBN). The parameters that are used to configure the software are studied in close observation. The objective of this paper is to determine the parameters of the DBN to accurately forecast photovoltaic power. The proposed methodology is validated by cross-validation and comparing it with another training algorithm.

[1]  Joos Vandewalle,et al.  Multi-Valued and Universal Binary Neurons: Theory, Learning and Applications , 2012 .

[2]  C. Lee Giles,et al.  What Size Neural Network Gives Optimal Generalization? Convergence Properties of Backpropagation , 1998 .

[3]  T. Logenthiran,et al.  Fuzzy logic control of energy storage system in microgrid operation , 2016, 2016 IEEE Innovative Smart Grid Technologies - Asia (ISGT-Asia).

[4]  Kunikazu Kobayashi,et al.  Time Series Forecasting Using Restricted Boltzmann Machine , 2012, ICIC.

[5]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[6]  N. Panwar,et al.  Role of renewable energy sources in environmental protection: A review , 2011 .

[7]  T. Logenthiran,et al.  Forecasting of photovoltaic power using extreme learning machine , 2015, 2015 IEEE Innovative Smart Grid Technologies - Asia (ISGT ASIA).

[8]  Henrik Lund,et al.  Renewable energy strategies for sustainable development , 2007 .

[10]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  T. Logenthiran,et al.  A multilevel threshold detection method for single-sensor multiple DC appliance states sensing , 2016, 2016 IEEE International Conference on Power System Technology (POWERCON).

[12]  ImageNet Classification with Deep Convolutional Neural , 2013 .

[13]  Yann LeCun,et al.  Generalization and network design strategies , 1989 .

[14]  T. Logenthiran,et al.  Smart Sensing of Loads in an Extra Low Voltage DC Pico-Grid Using Machine Learning Techniques , 2017, IEEE Sensors Journal.

[15]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[16]  Jeff Heaton,et al.  Introduction to neural networks for C , 2008 .

[17]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[18]  K. Gnana Sheela,et al.  Review on Methods to Fix Number of Hidden Neurons in Neural Networks , 2013 .

[19]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[20]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[21]  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.

[22]  Xiaodong Liang,et al.  Emerging Power Quality Challenges Due to Integration of Renewable Energy Sources , 2016, IEEE Transactions on Industry Applications.

[23]  T. Logenthiran,et al.  Forecasting of photovoltaic power using regularized ensemble Extreme Learning Machine , 2016, 2016 IEEE Region 10 Conference (TENCON).

[24]  Ting-Chung Yu,et al.  The forecast of the electrical energy generated by photovoltaic systems using neural network method , 2011, 2011 International Conference on Electric Information and Control Engineering.