Ahead Half hour global solar radiation forecasting based on static and dynamic multivariable neural networks
Abstract
The availability of precise global solar radiation (GSR) values in a given location is very essential for designing or supervising the solar energy systems (photovoltaic or thermal systems). In case of the rarity or the absence of these measurements, it is important to have a theoretical or empirical model to compute the GSR values. Therefore, our main goal in this work is to offer, to designer and engineers of solar energy systems, an appropriate and an accurate way to predict the half hour global solar radiation (HHGSR) characteristics from some available variables (relative humidity, air temperature, wind speed, precipitation, acquisition time vector in half hour scale). To predict the HHGSR, two intelligent models are developed. The first one is a multivariable dynamic neural network with feedback connection (M1) and the second one is a multivariable static neural network (M2). The database used to build these models, recorded in Agdal’s meteorological station in Marrakesh, Morocco, during 2013 and 2014 years, is divided in two subsets. The first subset is used for training and validating the models (phase I) and the second subset is used for testing the efficiency and the robustness of the models (phase II). The obtained results, in term of the statistical indicators: mean square error, root mean square error, mean absolute error and correlation coefficient, demonstrate that the developed models M1 and M2, are able to perform accurately the prediction of HHGSR in Marrakesh or others regions having similar climate.References
Chiteka, K. & Enweremadu, C. C. 2016. Prediction of global horizontal solar irradiance in Zimbabwe using artificial neural networks. J. Clean. Prod. 135: 701–711.
Alsina, E. F., Bortolini, M., Gamberi, M. & Regattieri, A. 2016. Artificial neural network optimisation for monthly average daily global solar radiation prediction. Energy Convers. Manag. 120: 320–329.
Gani, A. et al. 2016. Day of the year-based prediction of horizontal global solar radiation by a neural network auto-regressive model. Theor. Appl. Climatol. 125: 679–689.
Gutierrez-Corea, F. V., Manso-Callejo, M. A., Moreno-Regidor, M. P. & Manrique-Sancho, M. T. 2016. Forecasting short-term solar irradiance based on artificial neural networks and data from neighboring meteorological stations. Sol. Energy 134: 119–131.
Shaddel, M., Javan, D. S. & Baghernia, P. 2016. Estimation of hourly global solar irradiation on tilted absorbers from horizontal one using Artificial Neural Network for case study of Mashhad. Renew. Sustain. Energy Rev. 53: 59–67.
Zeroual, A., Ankrim, M. & Wilkinson, A. J. 1995. Stochastic modelling of daily global solar radiation measured in Marrakesh, Morocco. Renew. Energy 6: 787–793.
Zeroual, A., Ankrim, M. & Wilkinson, A. J. 1996 The diffuse-global correlation : Its application to estimating solar radiation on tilted surfaces in Marrakesh, Morocco. Renew. Energy 7, 1–13.
Iqdour, R. & Zeroual, A. 2007. Prediction of daily global solar radiation using fuzzy systems. Int. J. Sustain. Energy 26: 19–29.
Iqdour, R. & Zeroual, A. 2007. The Multi-Layered Perceptrons Neural Networks for the Prediction of Daily Solar Radiation. Int. J. Signal Process. 3: 24–29.
Badaoui, H. El, Abdallaoui, A. & Chabaa, S. 2013. Using MLP neural networks for predicting global solar radiation. Int. J. Eng. Sci. 2: 48–56.
Blackwell, K. I. M. T. et al. 2010. Identification of faces obscured by noise : comparison of an artificial neural network with human observers. 3079.
Zhang, L., Verma, B., Stockwell, D. & Chowdhury, S. 2018. Density Weighted Connectivity of Grass Pixels in image frames for biomass estimation. Expert Syst. Appl. 101: 213–227.
Ushada, M., Okayama, T., Khuriyati, N. & Suyantohadi, A. 2017. Affective Temperature Control in Food SMEs using Artificial Neural Network Affective Temperature Control in Food SMEs using Artificial Neural Network. Appl. Artif. Intell. 00: 1–13.
Subbiah, V., Geetha, K. & Ramaraj, D. 2016. Artificial Neural Network for the Optimal Control of an AC Chopper Fed Induction Motor. 2063: 4–7.
Irani, R., Nasimi, R. & Shahbazian, M. 2015. Approximate Predictive Control of a Distillation Column Using an Evolving Artificial Neural Network Coupled with a Genetic Algorithm. 518–535. doi:10.1080/15567036.2011.572123
Sanjeev Kulshrestha a , Deven J. Chheda a, S. B. C. a & A, R. J. a & S. B. S. 2014. Pole discontinuity removal using artificial neural networks for microstrip antenna design. 37–41. doi:10.1080/00207217.2011.609970
Antari, J., Chabaa, S., Iqdour, R., Zeroual, A. & Safi, S. 2011. Identification of quadratic systems using higher order cumulants and neural networks: Application to model the delay of video-packets transmission. Appl. Soft Comput. J. 11: 1–10.
Yang, C. et al. 2017. A Neural Network Approach to Joint Modeling Social Networks and Mobile Trajectories. ACM Trans. Inf. Syst. ACM Ref. Format .. ACM Trans. Inf. Syst 35.
Maitha H. Al-Shamisi a, A. H. A. b & H. A. N. H. 2015. Artificial neural networks for predicting global solar radiation in al ain city - uae. 37–41. doi:10.1080/15435075.2011.641187
Khatib, T., Mohamed, A., Mahmoud, M. & Sopian, K. 2011. Modeling of Daily Solar Energy on a Horizontal Surface for Five Main Sites in Malaysia. 37–41. doi:10.1080/15435075.2011.602156
El Badaoui, H., Abdallaoui, A. & Chabaa, S. 2014. Multilayer Perceptron and Radial Basis Function network to predict the moisture. Int. J. Innov. Sci. Res. 5: 55–67.
Wang, Z., Wang, F. & Su, S. 2011. Solar irradiance short-term prediction model based on BP neural network. in Energy Procedia. doi:10.1016/j.egypro.2011.10.065
Al-Ghobari, H. M., El-Marazky, M. S., Dewidar, A. Z. & Mattar, M. A. 2018. Prediction of wind drift and evaporation losses from sprinkler irrigation using neural network and multiple regression techniques. Agric. Water Manag. 195: 211–221.
do Nascimento Camelo, H., Sérgio Lucio, P., Verçosa Leal Junior, J., von Glehn dos Santos, D. & Cesar Marques de Carvalho, P. 2018. Innovative Hybrid Modeling of Wind Speed Prediction Involving Time-Series Models and Artificial Neural Networks. Atmosphere (Basel). 9: 77.
Yadav, A. K. & Chandel, S. S. 2014. Solar radiation prediction using Artificial Neural Network techniques: A review. Renewable and Sustainable Energy Reviews. doi:10.1016/j.rser.2013.08.055
Mellit, A. & Pavan, A. M. 2010. A 24-h forecast of solar irradiance using artificial neural network: Application for performance prediction of a grid-connected PV plant at Trieste, Italy. Sol. Energy 84: 807–821.
Chabaa, S., Zeroual, A. & Antari, J. 2010. Identification and Prediction of Internet Traffic Using Artificial Neural Networks. J. Intell. Learn. Syst. Appl. 02: 147–155.
EL Badaoui, H., Abdallaoui, A. & Chabaa, S. 2017. STUDY OF THE ANN MODEL PERFORMANCE CRITERIA FOR THE PREDICTION OF TIME. Int. J. Adv. Sci. Eng. Technol. 5: 117–124.
Mohandes, M., Rehman, S. & Halawani, T. O. 1998. Estimation of global solar radiation using artificial neural networks. Renew. Energy 14: 179–184.
Assi, A. H. 2011. Engineering Education and Research Using MATLAB. doi:10.5772/1532
Li, M., Zhang, H., Chen, B., Wu, Y. & Guan, L. 2018. Prediction of pKa Values for Neutral and Basic Drugs based on Hybrid Artificial Intelligence Methods. Sci. Rep. 8: 3991.
Hesthaven, J. S. & Ubbiali, S. 2017. Non-intrusive reduced order modeling of nonlinear problems using neural networks. J. Comput. Phys. 363: 55–78.
Piersanti, S. & Orlandi, A. 2017. Genetic Algorithm Optimization for the Total Radiated Power of a Meandered Line by Using an Artificial Neural Network. 60: 1–4.
Li, F., Wang, S. & Wei, J. 2018. Long term rolling prediction model for solar radiation combining empirical mode decomposition ( EMD ) and artificial neural network ( ANN ) techniques.
Saha, S. et al. 2018. Prediction of Soil-Water Characteristic Curve for Unbound Material Using Fredlund – Xing Equation-Based ANN Approach. 30: 1–10.
Prabhaker Reddy, G., Radhika, G. & Anil, K. 2012. Control of Continuous Stirred Tank Reactor Using Artificial Neural Networks Based Predictive Control. Adv. Mater. Res. 550–553, 2908–2912.
Bear, G. W., Al‐Shukri, H. J. & Rudman, A. J. 1995. Linear inversion of gravity data for 3-D density distributions. GEOPHYSICS 60: 1354–1364.
Muhammad, S., Burney, A., Jilani, T. A. & Ardil, C. 2008. Levenberg-Marquardt Algorithm for Karachi Stock Exchange Share Rates Forecasting. Comput. Intell. 1: 168–173.
Min, Z. & Cao, L. 2017. Application of the Neural Network in Diagnosis of Breast Cancer Based on Levenberg-Marquardt Algorithm. 268–272.
Wang, D., Luo, H., Grunder, O. & Lin, Y. 2017. Multi-step ahead wind speed forecasting using an improved wavelet neural network combining variational mode decomposition and phase space reconstruction. Renew. Energy 113: 1345–1358.
Badaoui, H. El, Abdallaoui, A. & Chabaa, S. 2017. Optimization numerical the neural architectures by performance indicator with LM learning algorithms. 8: 169–179.
sheng Li, L., jiang Gan, S. & dong Yin, X. 2017. Feedback recurrent neural network-based embedded vector and its application in topic model. Eurasip J. Embed. Syst.
Bonilla Cardona, D. A., Nedjah, N. & Mourelle, L. M. 2017. Online phoneme recognition using multi-layer perceptron networks combined with recurrent non-linear autoregressive neural networks with exogenous inputs. Neurocomputing 265: 78–90.
Hori, T. et al. 2017. Multi-microphone speech recognition integrating beamforming, robust feature extraction, and advanced DNN/RNN backend. Comput. Speech Lang. 46: 401–418.
Dewa, C. K. 2017. Javanese vowels sound classification with convolutional neural network. in Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy 123–128. doi:10.1109/ISITIA.2016.7828645
Kocadagli, O. & Langari, R. 2017. Classification of EEG signals for epileptic seizures using hybrid artificial neural networks based wavelet transforms and fuzzy relations. Expert Syst. Appl. 88: 419–434.
Le, X. & Wang, J. 2014. Robust pole assignment for synthesizing feedback control systems using recurrent neural networks. IEEE Trans. Neural Networks Learn. Syst. 25: 383–393.
Rzadkowski, R., Dominiczak, K., Radulski, W. & Szczepanik, R. 2015. Thermoelastic steam turbine rotor control based on neural network. in Journal of Physics: Conference Series 662.
Diaz, A., Dehghan Firoozabadi, A., Soto, I. & Rojo, P. 2016. Adaptive filter based on NARX model for atmospheric noise removal on exo-planet observations. in CHILECON 2015 - 2015 IEEE Chilean Conference on Electrical, Electronics Engineering, Information and Communication Technologies, Proceedings of IEEE Chilecon 2015 13–17. doi:10.1109/Chilecon.2015.7400345
Jachner, S., van den Boogaart, K. G. & Petzoldt, T. 2007. Statistical Methods for the Qualitative Assessment of Dynamic Models with Time Delay (R Package qualV). J. Stat. Softw. doi:http://dx.doi.org/10.18637/jss.v022.i08
Jallal, M. A., Chabaa, S., Yassini, A. E. L. & Zeroual, A. 2019. Air temperature forecasting using artificial neural networks with delayed exogenous input. 2019 Int. Conf. Wirel. Technol. Embed. Intell. Syst. 1–6.
Loutfi, H., Bernatchou, A. & Tadili, R. 2017. Generation of Horizontal Hourly Global Solar Radiation From Exogenous Variables Using an Artificial Neural Network in Fes ( Morocco ). 7.
Ahmad, A., Anderson, T. N. & Lie, T. T. 2015. Hourly global solar irradiation forecasting for New Zealand. Sol. Energy (2015). doi:10.1016/j.solener.2015.10.055
