A Solar Time-based Analog Ensemble Method for Regional Solar Power Forecasting
Abstract
This paper presents a new analog ensemble method for day-ahead regional photovoltaic (PV) power forecasting with hourly resolution. By utilizing open weather forecast and power measurement data, this prediction method is processed within a set of historical data with similar meteorological data (temperature and irradiance), and astronomical date (solar time and earth declination angle). Further, clustering and blending strategies are applied to improve its accuracy in regional PV forecasting. The robustness of the proposed method is demonstrated with three different numerical weather prediction models, the North American Mesoscale Forecast System, the Global Forecast System, and the Short-Range Ensemble Forecast, for both region level and single site level PV forecasts. Using real measured data, the new forecasting approach is applied to the load zone in Southeastern Massachusetts as a case study. In conclusion, the normalized root mean square error (NRMSE) has been reduced by 13.80%-61.21% when compared with three tested baselines.
- Authors:
-
- Northeastern Univ., Malden, MA (United States)
- Sichuan Univ., Chengdu (China)
- IBM, Yorktown Heights, NY (United States). Thomas J. Watson Research Center
- National Renewable Energy Lab. (NREL), Golden, CO (United States)
- Northeastern Univ., Boston, MA (United States)
- Publication Date:
- Research Org.:
- National Renewable Energy Lab. (NREL), Golden, CO (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE)
- OSTI Identifier:
- 1439549
- Report Number(s):
- NREL/JA-5D00-71656
Journal ID: ISSN 1949-3029
- Grant/Contract Number:
- AC36-08GO28308
- Resource Type:
- Accepted Manuscript
- Journal Name:
- IEEE Transactions on Sustainable Energy
- Additional Journal Information:
- Journal Volume: 10; Journal Issue: 1; Journal ID: ISSN 1949-3029
- Publisher:
- IEEE
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 14 SOLAR ENERGY; solar power forecasting; photovoltaic systems; analog; ensemble; modeling
Citation Formats
Zhang, Xinmin, Li, Yuan, Lu, Siyuan, Hamann, Hendrik, Hodge, Bri-Mathias Scott, and Lehman, Brad. A Solar Time-based Analog Ensemble Method for Regional Solar Power Forecasting. United States: N. p., 2018.
Web. doi:10.1109/TSTE.2018.2832634.
Zhang, Xinmin, Li, Yuan, Lu, Siyuan, Hamann, Hendrik, Hodge, Bri-Mathias Scott, & Lehman, Brad. A Solar Time-based Analog Ensemble Method for Regional Solar Power Forecasting. United States. https://doi.org/10.1109/TSTE.2018.2832634
Zhang, Xinmin, Li, Yuan, Lu, Siyuan, Hamann, Hendrik, Hodge, Bri-Mathias Scott, and Lehman, Brad. Thu .
"A Solar Time-based Analog Ensemble Method for Regional Solar Power Forecasting". United States. https://doi.org/10.1109/TSTE.2018.2832634. https://www.osti.gov/servlets/purl/1439549.
@article{osti_1439549,
title = {A Solar Time-based Analog Ensemble Method for Regional Solar Power Forecasting},
author = {Zhang, Xinmin and Li, Yuan and Lu, Siyuan and Hamann, Hendrik and Hodge, Bri-Mathias Scott and Lehman, Brad},
abstractNote = {This paper presents a new analog ensemble method for day-ahead regional photovoltaic (PV) power forecasting with hourly resolution. By utilizing open weather forecast and power measurement data, this prediction method is processed within a set of historical data with similar meteorological data (temperature and irradiance), and astronomical date (solar time and earth declination angle). Further, clustering and blending strategies are applied to improve its accuracy in regional PV forecasting. The robustness of the proposed method is demonstrated with three different numerical weather prediction models, the North American Mesoscale Forecast System, the Global Forecast System, and the Short-Range Ensemble Forecast, for both region level and single site level PV forecasts. Using real measured data, the new forecasting approach is applied to the load zone in Southeastern Massachusetts as a case study. In conclusion, the normalized root mean square error (NRMSE) has been reduced by 13.80%-61.21% when compared with three tested baselines.},
doi = {10.1109/TSTE.2018.2832634},
journal = {IEEE Transactions on Sustainable Energy},
number = 1,
volume = 10,
place = {United States},
year = {Thu May 03 00:00:00 EDT 2018},
month = {Thu May 03 00:00:00 EDT 2018}
}
Web of Science
Figures / Tables:
Works referencing / citing this record:
Short‐term photovoltaic power dynamic weighted combination forecasting based on least squares method
journal, September 2019
- Yang, Mao; Meng, Lingjian
- IEEJ Transactions on Electrical and Electronic Engineering, Vol. 14, Issue 12
A Framework of Using Machine Learning Approaches for Short-Term Solar Power Forecasting
journal, January 2020
- Munawar, Usman; Wang, Zhanle
- Journal of Electrical Engineering & Technology, Vol. 15, Issue 2
Forecasting of PV plant output using hybrid wavelet-based LSTM-DNN structure model
journal, May 2019
- Ospina, Juan; Newaz, Alvi; Faruque, M. Omar
- IET Renewable Power Generation, Vol. 13, Issue 7
Big data solar power forecasting based on deep learning and multiple data sources
journal, March 2019
- Torres, José F.; Troncoso, Alicia; Koprinska, Irena
- Expert Systems, Vol. 36, Issue 4
Advanced Methods for Photovoltaic Output Power Forecasting: A Review
journal, January 2020
- Mellit, Adel; Massi Pavan, Alessandro; Ogliari, Emanuele
- Applied Sciences, Vol. 10, Issue 2
A Novel Ensemble Algorithm for Solar Power Forecasting Based on Kernel Density Estimation
journal, January 2020
- Lotfi, Mohamed; Javadi, Mohammad; Osório, Gerardo J.
- Energies, Vol. 13, Issue 1
Figures / Tables found in this record: