Modeling Hourly Average Solar Radiation Time Series

This chapter deals with the problem of short-term prediction of hourly average solar radiation time series, recorded at ground level, by using embedding phase-space (EPS) models. Two different neural approaches have been considered to identify the nonlinear map underlying the identification problem, namely the neuro-fuzzy (NF) approach and the feedforward neural network (NN) approach. Performances are evaluated in terms of mae, rmse and skill index, in comparison with two popular reference models, namely the clear sky model and the \(P_{24}\) persistent model.

[1]  Zhengrong Li,et al.  New decomposition models to estimate hourly global solar radiation from the daily value , 2015 .

[2]  K. Uma Rao,et al.  Development of statistical time series models for solar power prediction , 2015 .

[3]  Philippe Lauret,et al.  Use of satellite data to improve solar radiation forecasting with Bayesian Artificial Neural Networks , 2015 .

[4]  Ozgur Kisi,et al.  Modeling solar radiation of Mediterranean region in Turkey by using fuzzy genetic approach , 2014 .

[5]  Nikolaos Nikolaidis,et al.  Solar radiation prediction model based on Empirical Mode Decomposition , 2014, 2014 IEEE International Conference on Imaging Systems and Techniques (IST) Proceedings.

[6]  Huaiwei Sun,et al.  Empirical investigation on modeling solar radiation series with ARMA–GARCH models , 2015 .

[7]  C. K. Chan,et al.  Prediction of hourly solar radiation using a novel hybrid model of ARMA and TDNN , 2011 .

[8]  P. Ineichen,et al.  A new operational model for satellite-derived irradiances: description and validation , 2002 .

[9]  Chul-Hwan Kim,et al.  Determination Method of Insolation Prediction With Fuzzy and Applying Neural Network for Long-Term Ahead PV Power Output Correction , 2013, IEEE Transactions on Sustainable Energy.

[10]  Nian Zhang,et al.  Solar radiation prediction based on recurrent neural networks trained by Levenberg-Marquardt backpropagation learning algorithm , 2012, 2012 IEEE PES Innovative Smart Grid Technologies (ISGT).

[11]  Prashant J. Shenoy,et al.  Predicting solar generation from weather forecasts using machine learning , 2011, 2011 IEEE International Conference on Smart Grid Communications (SmartGridComm).

[12]  John Boland,et al.  Bayesian statistical analysis applied to solar radiation modelling , 2013 .

[13]  Nian Zhang,et al.  Solar radiation prediction based on particle swarm optimization and evolutionary algorithm using recurrent neural networks , 2013, 2013 IEEE International Systems Conference (SysCon).

[14]  Ozgur Kisi,et al.  Modelling solar radiation reached to the Earth using ANFIS, NN-ARX, and empirical models (Case studies: Zahedan and Bojnurd stations) , 2015 .

[15]  P. Ineichen,et al.  A new airmass independent formulation for the Linke turbidity coefficient , 2002 .