skip to main content

DOE PAGESDOE PAGES

This content will become publicly available on May 3, 2019

Title: A Solar Time-based Analog Ensemble Method for Regional Solar Power Forecasting

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. The normalized root mean square error (NRMSE) has been reduced by 13.80%-61.21% when compared with three tested baselines.
Authors:
 [1] ;  [2] ;  [3] ;  [3] ;  [4] ;  [5]
  1. Northeastern Univ., Malden, MA (United States)
  2. Sichuan Univ., Chengdu (China)
  3. IBM, Yorktown Heights, NY (United States). Thomas J. Watson Research Center
  4. National Renewable Energy Lab. (NREL), Golden, CO (United States)
  5. Northeastern Univ., Boston, MA (United States)
Publication Date:
Report Number(s):
NREL/JA-5D00-71656
Journal ID: ISSN 1949-3029
Grant/Contract Number:
AC36-08GO28308
Type:
Accepted Manuscript
Journal Name:
IEEE Transactions on Sustainable Energy
Additional Journal Information:
Journal Name: IEEE Transactions on Sustainable Energy; Journal ID: ISSN 1949-3029
Publisher:
IEEE
Research Org:
National Renewable Energy Lab. (NREL), Golden, CO (United States)
Sponsoring Org:
USDOE Office of Energy Efficiency and Renewable Energy (EERE)
Country of Publication:
United States
Language:
English
Subject:
14 SOLAR ENERGY; solar power forecasting; photovoltaic systems; analog; ensemble; modeling
OSTI Identifier:
1439549

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., 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. doi:10.1109/TSTE.2018.2832634.
Zhang, Xinmin, Li, Yuan, Lu, Siyuan, Hamann, Hendrik, Hodge, Bri-Mathias Scott, and Lehman, Brad. 2018. "A Solar Time-based Analog Ensemble Method for Regional Solar Power Forecasting". United States. doi:10.1109/TSTE.2018.2832634.
@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. 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 = ,
volume = ,
place = {United States},
year = {2018},
month = {5}
}