Translator Disclaimer
December 2018 Bottom-up estimation and top-down prediction: Solar energy prediction combining information from multiple sources
Youngdeok Hwang, Siyuan Lu, Jae-Kwang Kim
Ann. Appl. Stat. 12(4): 2096-2120 (December 2018). DOI: 10.1214/18-AOAS1145

Abstract

Accurately forecasting solar power using the data from multiple sources is an important but challenging problem. Our goal is to combine two different physics model forecasting outputs with real measurements from an automated monitoring network so as to better predict solar power in a timely manner. To this end, we propose a new approach of analyzing large-scale multilevel models with great computational efficiency requiring minimum monitoring and intervention. This approach features a division of the large scale data set into smaller ones with manageable sizes, based on their physical locations, and fit a local model in each area. The local model estimates are then combined sequentially from the specified multilevel models using our novel bottom-up approach for parameter estimation. The prediction, on the other hand, is implemented in a top-down matter. The proposed method is applied to the solar energy prediction problem for the U.S. Department of Energy’s SunShot Initiative.

Citation

Download Citation

Youngdeok Hwang. Siyuan Lu. Jae-Kwang Kim. "Bottom-up estimation and top-down prediction: Solar energy prediction combining information from multiple sources." Ann. Appl. Stat. 12 (4) 2096 - 2120, December 2018. https://doi.org/10.1214/18-AOAS1145

Information

Received: 1 December 2016; Revised: 1 January 2018; Published: December 2018
First available in Project Euclid: 13 November 2018

zbMATH: 07029448
MathSciNet: MR3875694
Digital Object Identifier: 10.1214/18-AOAS1145

Rights: Copyright © 2018 Institute of Mathematical Statistics

JOURNAL ARTICLE
25 PAGES


SHARE
Vol.12 • No. 4 • December 2018
Back to Top