Evaluation of regression and neural network models for solar forecasting over different short-term horizons
Abstract
Forecasting solar irradiation has acquired immense importance in view of the exponential increase in the number of solar photovoltaic (PV) system installations. In this article, analyses results involving statistical and machine-learning techniques to predict solar irradiation for different forecasting horizons are reported. Yearlong typical meteorological year 3 (TMY3) datasets from three cities in the United States with different climatic conditions have been used in this analysis. A simple forecast approach that assumes consecutive days to be identical serves as a baseline model to compare forecasting alternatives. To account for seasonal variability and to capture short-term fluctuations, different variants of the lagged moving average (LMX) model with cloud cover as the input variable are evaluated. Finally, the proposed LMX model is evaluated against an artificial neural network (ANN) model. How the one-hour and 24-hour models can be used in conjunction to predict different short-term rolling horizons is discussed, and this joint application is illustrated for a four-hour rolling horizon forecast scheme. Lastly, the effect of using predicted cloud cover values, instead of measured ones, on the accuracy of the models is assessed. Results show that LMX models do not degrade in forecast accuracy if models are trained with the forecast cloudmore »
- Authors:
-
- Arizona State Univ., Tempe, AZ (United States)
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Publication Date:
- Research Org.:
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1441212
- Grant/Contract Number:
- AC05–76RL01830
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Science and Technology for the Built Environment
- Additional Journal Information:
- Journal Volume: 24; Journal Issue: 9; Journal ID: ISSN 2374-4731
- Publisher:
- Taylor & Francis
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 14 SOLAR ENERGY
Citation Formats
Inanlouganji, Alireza, Reddy, T. Agami, and Katipamula, Srinivas. Evaluation of regression and neural network models for solar forecasting over different short-term horizons. United States: N. p., 2018.
Web. doi:10.1080/23744731.2018.1464348.
Inanlouganji, Alireza, Reddy, T. Agami, & Katipamula, Srinivas. Evaluation of regression and neural network models for solar forecasting over different short-term horizons. United States. https://doi.org/10.1080/23744731.2018.1464348
Inanlouganji, Alireza, Reddy, T. Agami, and Katipamula, Srinivas. Fri .
"Evaluation of regression and neural network models for solar forecasting over different short-term horizons". United States. https://doi.org/10.1080/23744731.2018.1464348. https://www.osti.gov/servlets/purl/1441212.
@article{osti_1441212,
title = {Evaluation of regression and neural network models for solar forecasting over different short-term horizons},
author = {Inanlouganji, Alireza and Reddy, T. Agami and Katipamula, Srinivas},
abstractNote = {Forecasting solar irradiation has acquired immense importance in view of the exponential increase in the number of solar photovoltaic (PV) system installations. In this article, analyses results involving statistical and machine-learning techniques to predict solar irradiation for different forecasting horizons are reported. Yearlong typical meteorological year 3 (TMY3) datasets from three cities in the United States with different climatic conditions have been used in this analysis. A simple forecast approach that assumes consecutive days to be identical serves as a baseline model to compare forecasting alternatives. To account for seasonal variability and to capture short-term fluctuations, different variants of the lagged moving average (LMX) model with cloud cover as the input variable are evaluated. Finally, the proposed LMX model is evaluated against an artificial neural network (ANN) model. How the one-hour and 24-hour models can be used in conjunction to predict different short-term rolling horizons is discussed, and this joint application is illustrated for a four-hour rolling horizon forecast scheme. Lastly, the effect of using predicted cloud cover values, instead of measured ones, on the accuracy of the models is assessed. Results show that LMX models do not degrade in forecast accuracy if models are trained with the forecast cloud cover data.},
doi = {10.1080/23744731.2018.1464348},
journal = {Science and Technology for the Built Environment},
number = 9,
volume = 24,
place = {United States},
year = {Fri Apr 13 00:00:00 EDT 2018},
month = {Fri Apr 13 00:00:00 EDT 2018}
}
Web of Science
Works referenced in this record:
Hourly global solar irradiation forecasting for New Zealand
journal, December 2015
- Ahmad, A.; Anderson, T. N.; Lie, T. T.
- Solar Energy, Vol. 122
Comparison of numerical weather prediction solar irradiance forecasts in the US, Canada and Europe
journal, August 2013
- Perez, Richard; Lorenz, Elke; Pelland, Sophie
- Solar Energy, Vol. 94
Univariate and multivariate forecasting of hourly solar radiation with artificial intelligence techniques
journal, February 2000
- Sfetsos, A.; Coonick, A. H.
- Solar Energy, Vol. 68, Issue 2
Hybrid methodology for hourly global radiation forecasting in Mediterranean area
journal, May 2013
- Voyant, Cyril; Muselli, Marc; Paoli, Christophe
- Renewable Energy, Vol. 53
Numerical weather prediction (NWP) and hybrid ARMA/ANN model to predict global radiation
journal, March 2012
- Voyant, Cyril; Muselli, Marc; Paoli, Christophe
- Energy, Vol. 39, Issue 1
The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data
journal, August 2010
- Behrang, M. A.; Assareh, E.; Ghanbarzadeh, A.
- Solar Energy, Vol. 84, Issue 8
Stochastic modeling and forecasting of solar radiation data
journal, January 1977
- Goh, T. N.; Tan, K. J.
- Solar Energy, Vol. 19, Issue 6
Forecasting solar radiation using an optimized hybrid model by Cuckoo Search algorithm
journal, March 2015
- Wang, Jianzhou; Jiang, He; Wu, Yujie
- Energy, Vol. 81
Forecasting method for global radiation time series without training phase: Comparison with other well-known prediction methodologies
journal, February 2017
- Voyant, Cyril; Motte, Fabrice; Fouilloy, Alexis
- Energy, Vol. 120
Artificial intelligence techniques for photovoltaic applications: A review
journal, October 2008
- Mellit, Adel; Kalogirou, Soteris A.
- Progress in Energy and Combustion Science, Vol. 34, Issue 5, p. 574-632
Prediction of solar radiation for solar systems by using ANN models with different back propagation algorithms
journal, June 2016
- Premalatha, Neelamegam; Valan Arasu, Amirtham
- Journal of Applied Research and Technology, Vol. 14, Issue 3
Comparative study of statistical and artificial neural network's methodologies for deriving global solar radiation from NOAA satellite images
journal, February 2012
- Rahimikhoob, A.; Behbahani, S. M. R.; Banihabib, M. E.
- International Journal of Climatology, Vol. 33, Issue 2
Hourly forecasting of global solar radiation based on multiscale decomposition methods: A hybrid approach
journal, January 2017
- Monjoly, Stéphanie; André, Maïna; Calif, Rudy
- Energy, Vol. 119
The artificial neural network for solar radiation prediction and designing solar systems: a systematic literature review
journal, October 2015
- Qazi, Atika; Fayaz, H.; Wadi, A.
- Journal of Cleaner Production, Vol. 104
Review of photovoltaic power forecasting
journal, October 2016
- Antonanzas, J.; Osorio, N.; Escobar, R.
- Solar Energy, Vol. 136
Artificial Intelligence technique for modelling and forecasting of solar radiation data: a review
journal, January 2008
- Mellit, Adel
- International Journal of Artificial Intelligence and Soft Computing, Vol. 1, Issue 1
Solar radiation estimation using artificial neural networks
journal, April 2002
- Dorvlo, Atsu S. S.; Jervase, Joseph A.; Al-Lawati, Ali
- Applied Energy, Vol. 71, Issue 4
Neural networks and their applications
journal, June 1994
- Bishop, Chris M.
- Review of Scientific Instruments, Vol. 65, Issue 6
Solar forecasting methods for renewable energy integration
journal, December 2013
- Inman, Rich H.; Pedro, Hugo T. C.; Coimbra, Carlos F. M.
- Progress in Energy and Combustion Science, Vol. 39, Issue 6
Forecasting hourly global solar radiation using hybrid k-means and nonlinear autoregressive neural network models
journal, November 2013
- Benmouiza, Khalil; Cheknane, Ali
- Energy Conversion and Management, Vol. 75
Prediction of hourly solar radiation using a novel hybrid model of ARMA and TDNN
journal, May 2011
- Ji, Wu; Chee, Keong Chan
- Solar Energy, Vol. 85, Issue 5
The value of day-ahead solar power forecasting improvement
journal, May 2016
- Brancucci Martinez-Anido, Carlo; Botor, Benjamin; Florita, Anthony R.
- Solar Energy, Vol. 129
A benchmarking of machine learning techniques for solar radiation forecasting in an insular context
journal, February 2015
- Lauret, Philippe; Voyant, Cyril; Soubdhan, Ted
- Solar Energy, Vol. 112
Solar radiation prediction using Artificial Neural Network techniques: A review
journal, May 2014
- Yadav, Amit Kumar; Chandel, S. S.
- Renewable and Sustainable Energy Reviews, Vol. 33
Predicting solar radiation at high resolutions: A comparison of time series forecasts
journal, March 2009
- Reikard, Gordon
- Solar Energy, Vol. 83, Issue 3
Radial Basis Function Network-based prediction of global solar radiation data: Application for sizing of a stand-alone photovoltaic system at Al-Madinah, Saudi Arabia
journal, September 2010
- Benghanem, Mohamed; Mellit, Adel
- Energy, Vol. 35, Issue 9
Estimation of solar radiation using artificial neural networks with different input parameters for Mediterranean region of Anatolia in Turkey
journal, July 2011
- Koca, Ahmet; Oztop, Hakan F.; Varol, Yasin
- Expert Systems with Applications, Vol. 38, Issue 7
Hybrid methodology for hourly global radiation forecasting in Mediterranean area
text, January 2012
- Voyant, Cyril; Muselli, Marc; Paoli, Christophe
- arXiv