A copula-based Bayesian method for probabilistic solar power forecasting
Abstract
With increased penetration of solar energy sources, solar power forecasting has become more crucial and challenging. This paper proposes a copula-based Bayesian approach to improve probabilistic solar power forecasting by capturing the joint distribution between solar power and ambient temperature. A prior forecast distribution is first obtained using different underlying point forecasting models. Parametric and empirical copulas of solar power and temperature are then developed to update the prior distribution to the posterior forecast distribution. A public solar power database is used to demonstrate effectiveness of the proposed method. Numerical results show that the copula-based Bayesian method outperforms the forecasting method that directly uses temperature as a feature. The Bayesian method is also compared with persistent models and show improved performance. Furthermore, this article includes supplementary material (data and code) for reproducibility.
- Authors:
-
- Univ. of Central Florida, Orlando, FL (United States)
- Univ. of North Carolina, Charlotte, NC (United States)
- Publication Date:
- Research Org.:
- Univ. of Central Florida, Orlando, FL (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office
- OSTI Identifier:
- 1820624
- Grant/Contract Number:
- EE0007998
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Solar Energy
- Additional Journal Information:
- Journal Volume: 196; Journal ID: ISSN 0038-092X
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 24 POWER TRANSMISSION AND DISTRIBUTION; Bayesian inference; Solar power forecasting; Copulas; Probabilistic forecasting
Citation Formats
Panamtash, Hossein, Zhou, Qun, Hong, Tao, Qu, Zhihua, and Davis, Kristopher O. A copula-based Bayesian method for probabilistic solar power forecasting. United States: N. p., 2019.
Web. doi:10.1016/j.solener.2019.11.079.
Panamtash, Hossein, Zhou, Qun, Hong, Tao, Qu, Zhihua, & Davis, Kristopher O. A copula-based Bayesian method for probabilistic solar power forecasting. United States. https://doi.org/10.1016/j.solener.2019.11.079
Panamtash, Hossein, Zhou, Qun, Hong, Tao, Qu, Zhihua, and Davis, Kristopher O. Fri .
"A copula-based Bayesian method for probabilistic solar power forecasting". United States. https://doi.org/10.1016/j.solener.2019.11.079. https://www.osti.gov/servlets/purl/1820624.
@article{osti_1820624,
title = {A copula-based Bayesian method for probabilistic solar power forecasting},
author = {Panamtash, Hossein and Zhou, Qun and Hong, Tao and Qu, Zhihua and Davis, Kristopher O.},
abstractNote = {With increased penetration of solar energy sources, solar power forecasting has become more crucial and challenging. This paper proposes a copula-based Bayesian approach to improve probabilistic solar power forecasting by capturing the joint distribution between solar power and ambient temperature. A prior forecast distribution is first obtained using different underlying point forecasting models. Parametric and empirical copulas of solar power and temperature are then developed to update the prior distribution to the posterior forecast distribution. A public solar power database is used to demonstrate effectiveness of the proposed method. Numerical results show that the copula-based Bayesian method outperforms the forecasting method that directly uses temperature as a feature. The Bayesian method is also compared with persistent models and show improved performance. Furthermore, this article includes supplementary material (data and code) for reproducibility.},
doi = {10.1016/j.solener.2019.11.079},
journal = {Solar Energy},
number = ,
volume = 196,
place = {United States},
year = {Fri Dec 20 00:00:00 EST 2019},
month = {Fri Dec 20 00:00:00 EST 2019}
}
Works referenced in this record:
Preliminary assessment of two spatio-temporal forecasting technics for hourly satellite-derived irradiance in a complex meteorological context
journal, January 2019
- André, Maïna; Perez, Richard; Soubdhan, Ted
- Solar Energy, Vol. 177
Time-adaptive quantile-copula for wind power probabilistic forecasting
journal, April 2012
- Bessa, Ricardo J.; Miranda, V.; Botterud, A.
- Renewable Energy, Vol. 40, Issue 1
A synthetic, spatially decorrelating solar irradiance generator and application to a LV grid model with high PV penetration
journal, May 2017
- Bright, Jamie M.; Babacan, Oytun; Kleissl, Jan
- Solar Energy, Vol. 147
KPV: A clear-sky index for photovoltaics
journal, July 2014
- Engerer, N. A.; Mills, F. P.
- Solar Energy, Vol. 105
Prediction bands for solar energy: New short-term time series forecasting techniques
journal, May 2018
- Fliess, Michel; Join, Cédric; Voyant, Cyril
- Solar Energy, Vol. 166
Stochastic optimal battery storage sizing and scheduling in home energy management systems equipped with solar photovoltaic panels
journal, October 2017
- Hemmati, Reza; Saboori, Hedayat
- Energy and Buildings, Vol. 152
Global energy forecasting competition 2017: Hierarchical probabilistic load forecasting
journal, October 2019
- Hong, Tao; Xie, Jingrui; Black, Jonathan
- International Journal of Forecasting, Vol. 35, Issue 4
QCPV: A quality control algorithm for distributed photovoltaic array power output
journal, February 2017
- Killinger, Sven; Engerer, Nicholas; Müller, Björn
- Solar Energy, Vol. 143
Dynamic discrete copula models for high‐frequency stock price changes
journal, August 2018
- Koopman, Siem Jan; Lit, Rutger; Lucas, André
- Journal of Applied Econometrics, Vol. 33, Issue 7
A Review of PV System Performance and Life-Cycle Costs for the SunSmart Schools Program
conference, October 2008
- Lynn, Kevin; Szaro, Jennifer; Wilson, William
- ASME 2006 International Solar Energy Conference
A copula method for simulating correlated instantaneous solar irradiance in spatial networks
journal, February 2017
- Munkhammar, Joakim; Widén, Joakim; Hinkelman, Laura M.
- Solar Energy, Vol. 143
Probabilistic forecasting of high-resolution clear-sky index time-series using a Markov-chain mixture distribution model
journal, May 2019
- Munkhammar, Joakim; van der Meer, Dennis; Widén, Joakim
- Solar Energy, Vol. 184
Modeling of uncertainty of solar irradiance forecasts on numerical weather predictions with the estimation of multiple confidence intervals
journal, March 2018
- Murata, Akinobu; Ohtake, Hideaki; Oozeki, Takashi
- Renewable Energy, Vol. 117
Modelling Time-Varying Exchange Rate Dependence using the Conditional Copula
journal, January 2001
- Patton, Andrew J.
- SSRN Electronic Journal
Detecting clear sky images
journal, May 2019
- Pawar, Prathamesh; Cortés, Cristian; Murray, Keenan
- Solar Energy, Vol. 183
Assessment of machine learning techniques for deterministic and probabilistic intra-hour solar forecasts
journal, August 2018
- Pedro, Hugo T. C.; Coimbra, Carlos F. M.; David, Mathieu
- Renewable Energy, Vol. 123
A probabilistic approach to the estimation of regional photovoltaic power production
journal, May 2017
- Saint-Drenan, Y. M.; Good, G. H.; Braun, M.
- Solar Energy, Vol. 147
Short term solar irradiance forecasting using a mixed wavelet neural network
journal, May 2016
- Sharma, Vishal; Yang, Dazhi; Walsh, Wilfred
- Renewable Energy, Vol. 90
Residential probabilistic load forecasting: A method using Gaussian process designed for electric load data
journal, May 2018
- Shepero, Mahmoud; van der Meer, Dennis; Munkhammar, Joakim
- Applied Energy, Vol. 218
Probabilistic forecasting of solar power, electricity consumption and net load: Investigating the effect of seasons, aggregation and penetration on prediction intervals
journal, September 2018
- van der Meer, D. W.; Munkhammar, J.; Widén, J.
- Solar Energy, Vol. 171
Review on probabilistic forecasting of photovoltaic power production and electricity consumption
journal, January 2018
- van der Meer, D. W.; Widén, J.; Munkhammar, J.
- Renewable and Sustainable Energy Reviews, Vol. 81
Solar irradiance forecasting in the tropics using numerical weather prediction and statistical learning
journal, March 2018
- Verbois, Hadrien; Huva, Robert; Rusydi, Andrivo
- Solar Energy, Vol. 162
Probabilistic forecasting of day-ahead solar irradiance using quantile gradient boosting
journal, October 2018
- Verbois, Hadrien; Rusydi, Andrivo; Thiery, Alexandre
- Solar Energy, Vol. 173
On the properties of aggregate clear-sky index distributions and an improved model for spatially correlated instantaneous solar irradiance
journal, November 2017
- Widén, Joakim; Shepero, Mahmoud; Munkhammar, Joakim
- Solar Energy, Vol. 157
A universal benchmarking method for probabilistic solar irradiance forecasting
journal, May 2019
- Yang, Dazhi
- Solar Energy, Vol. 184
Post-processing of NWP forecasts using ground or satellite-derived data through kernel conditional density estimation
journal, March 2019
- Yang, Dazhi
- Journal of Renewable and Sustainable Energy, Vol. 11, Issue 2
Reconciling solar forecasts: Geographical hierarchy
journal, April 2017
- Yang, Dazhi; Quan, Hao; Disfani, Vahid R.
- Solar Energy, Vol. 146
History and trends in solar irradiance and PV power forecasting: A preliminary assessment and review using text mining
journal, July 2018
- Yang, Dazhi; Kleissl, Jan; Gueymard, Christian A.
- Solar Energy, Vol. 168
Optimal Operation of Battery Energy Storage System Considering Distribution System Uncertainty
journal, July 2018
- Zheng, Yu; Zhao, Junhua; Song, Yue
- IEEE Transactions on Sustainable Energy, Vol. 9, Issue 3