Minimum redundancy – Maximum relevance with extreme learning machines for global solar radiation forecasting: Toward an optimized dimensionality reduction for solar time series

Abstract Solar energy is expected to provide a major contribution to the future global energy supply, while helping the transition toward a carbon-free economy. Because of its variable character, its efficient use will necessitate trustworthy forecast information of its availability in a variety of spatial and time scales, depending on application. This study proposes a new forecasting approach for irradiance time series that combines mutual information measures and an Extreme Learning Machine (ELM). The method is referred to as Minimum Redundancy – Maximum Relevance (MRMR). To assess the proposed approach, its performance is evaluated against four scenarios: long window (latest 50 variables), short window (latest 5 variables), standard Principal Components Analysis (PCA) and clear-sky model. All these scenarios are applied to three typical forecasting horizons (15-min ahead, 1-h ahead and 24-h ahead). Based on measured irradiance data from 20 sites representing a variety of climates, the test results reveal that the selection of a good set of relevant variables positively impacts the forecasting performance of global solar radiation. The present findings show that the proposed approach is able to improve the accuracy of solar irradiance forecasting compared to other proposed scenarios.

[1]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[2]  Cyril Voyant,et al.  Multi-horizon solar radiation forecasting for Mediterranean locations using time series models , 2013, ArXiv.

[3]  Khalil Benmouiza,et al.  Small-scale solar radiation forecasting using ARMA and nonlinear autoregressive neural network models , 2016, Theoretical and Applied Climatology.

[4]  Sancho Salcedo-Sanz,et al.  Prediction of Daily Global Solar Irradiation Using Temporal Gaussian Processes , 2014, IEEE Geoscience and Remote Sensing Letters.

[5]  Shahaboddin Shamshirband,et al.  Potential of radial basis function based support vector regression for global solar radiation prediction , 2014 .

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

[7]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[8]  L. Zarzalejo,et al.  Prediction of global solar irradiance based on time series analysis: Application to solar thermal power plants energy production planning , 2010 .

[9]  G. Mihalakakou,et al.  The total solar radiation time series simulation in Athens, using neural networks , 2000 .

[10]  Adnan Sözen,et al.  Estimation of solar potential in Turkey by artificial neural networks using meteorological and geographical data , 2004 .

[11]  Jianzhou Wang,et al.  A novel hybrid model based on artificial neural networks for solar radiation prediction , 2016 .

[12]  Jiacong Cao,et al.  Application of the diagonal recurrent wavelet neural network to solar irradiation forecast assisted with fuzzy technique , 2008, Eng. Appl. Artif. Intell..

[13]  Gordon Reikard.  Predicting solar radiation at high resolutions: A comparison of time series forecasts , 2009 .

[14]  Athanasios Sfetsos,et al.  Univariate and multivariate forecasting of hourly solar radiation with artificial intelligence techniques , 2000 .

[15]  B. McArthur,et al.  Baseline surface radiation network (BSRN/WCRP) New precision radiometry for climate research , 1998 .

[16]  J. Sanz-Justo,et al.  A CRO-species optimization scheme for robust global solar radiation statistical downscaling , 2017 .

[17]  Shahaboddin Shamshirband,et al.  A comparison of the performance of some extreme learning machine empirical models for predicting daily horizontal diffuse solar radiation in a region of southern Iran , 2017 .

[18]  M. Milligan,et al.  Integrating Variable Renewable Energy: Challenges and Solutions , 2013 .

[19]  Hsu-Yung Cheng,et al.  Predicting solar irradiance with all-sky image features via regression , 2013 .

[20]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[21]  M. Diagne,et al.  Review of solar irradiance forecasting methods and a proposition for small-scale insular grids , 2013 .

[22]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Soteris A. Kalogirou,et al.  Chapter 11 – Designing and Modeling Solar Energy Systems , 2014 .

[24]  Michel Verleysen,et al.  Mutual information for the selection of relevant variables in spectrometric nonlinear modelling , 2006, ArXiv.

[25]  Kasra Mohammadi,et al.  A support vector machine–firefly algorithm-based model for global solar radiation prediction , 2015 .

[26]  James Allen Fill,et al.  The Moore-Penrose Generalized Inverse for Sums of Matrices , 1999, SIAM J. Matrix Anal. Appl..

[27]  Kamaruzzaman Sopian,et al.  A review of solar energy modeling techniques , 2012 .

[28]  S. Chandel,et al.  Selection of most relevant input parameters using WEKA for artificial neural network based solar radiation prediction models , 2014 .

[29]  Sancho Salcedo-Sanz,et al.  Daily global solar radiation prediction based on a hybrid Coral Reefs Optimization – Extreme Learning Machine approach , 2014 .

[30]  Richard A. Davis,et al.  Introduction to time series and forecasting , 1998 .

[31]  Nabil Benoudjit,et al.  Multiple architecture system for wind speed prediction , 2011 .

[32]  Sancho Salcedo-Sanz,et al.  Feature selection in solar radiation prediction using bootstrapped SVRs , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[33]  Joseph A. Jervase,et al.  Solar radiation estimation using artificial neural networks , 2002 .

[34]  C. Long,et al.  Identification of clear skies from broadband pyranometer measurements and calculation of downwelling shortwave cloud effects , 2000 .

[35]  Stéphanie Monjoly,et al.  Hourly forecasting of global solar radiation based on multiscale decomposition methods: A hybrid approach , 2017 .

[36]  A. Mellit,et al.  A 24-h forecast of solar irradiance using artificial neural network: Application for performance prediction of a grid-connected PV plant at Trieste, Italy , 2010 .

[37]  H. Pedro,et al.  Benefits of solar forecasting for energy imbalance markets , 2016 .

[38]  Cyril Voyant,et al.  Optimization of an artificial neural network dedicated to the multivariate forecasting of daily glob , 2011 .

[39]  Alberto Tesi,et al.  On the Problem of Local Minima in Backpropagation , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[40]  Shahaboddin Shamshirband,et al.  Daily global solar radiation prediction from air temperatures using kernel extreme learning machine: A case study for Iran , 2015 .

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

[42]  J. Kleissl,et al.  Chapter 8 – Overview of Solar-Forecasting Methods and a Metric for Accuracy Evaluation , 2013 .

[43]  John Boland,et al.  Forecasting solar radiation on an hourly time scale using a Coupled AutoRegressive and Dynamical System (CARDS) model , 2013 .

[44]  Betul Bektas Ekici,et al.  A least squares support vector machine model for prediction of the next day solar insolation for effective use of PV systems , 2014 .

[45]  J. A. Ruiz-Arias,et al.  Extensive worldwide validation and climate sensitivity analysis of direct irradiance predictions from 1-min global irradiance , 2016 .

[46]  Amit Kumar Yadav,et al.  Solar radiation prediction using Artificial Neural Network techniques: A review , 2014 .

[47]  A. Will,et al.  On the use of niching genetic algorithms for variable selection in solar radiation estimation , 2013 .

[48]  Soteris A. Kalogirou,et al.  Machine learning methods for solar radiation forecasting: A review , 2017 .

[49]  J. Sanz-Justo,et al.  A novel Grouping Genetic Algorithm–Extreme Learning Machine approach for global solar radiation prediction from numerical weather models inputs , 2016 .

[50]  Hassen Bouzgou,et al.  A fast and accurate model for forecasting wind speed and solar radiation time series based on extreme learning machines and principal components analysis , 2014 .

[51]  Soteris A. Kalogirou,et al.  An adaptive wavelet-network model for forecasting daily total solar-radiation , 2006 .

[52]  Shengjun Wu,et al.  Assessing the potential of support vector machine for estimating daily solar radiation using sunshine duration , 2013 .

[53]  Badia Amrouche,et al.  Artificial neural network based daily local forecasting for global solar radiation , 2014 .

[54]  F. Hocaoglu,et al.  A novel adaptive approach for hourly solar radiation forecasting , 2016 .

[55]  R. Inman,et al.  Solar forecasting methods for renewable energy integration , 2013 .

[56]  Ali Cheknane,et al.  Forecasting hourly global solar radiation using hybrid k-means and nonlinear autoregressive neural network models , 2013 .

[57]  F. Hocaoglu,et al.  Hourly solar radiation forecasting using optimal coefficient 2-D linear filters and feed-forward neural networks , 2008 .