Uncertainty Quantification for Photovoltaic Energy Production Using Analog Ensemble
Open Access
Author:
Hu, Weiming
Graduate Program:
Geography
Degree:
Doctor of Philosophy
Document Type:
Dissertation
Date of Defense:
June 09, 2021
Committee Members:
George Young, Outside Unit Member Guido Cervone, Chair, Minor Member & Dissertation Advisor Michael Mann, Outside Field Member Andrew Carleton, Major Field Member Cynthia Brewer, Program Head/Chair
Keywords:
Ensemble Forecast Photovoltaic Machine Learning Deep Learning
Abstract:
This dissertation focuses on using the Analog Ensemble and Machine Learning techniques to quantify power production uncertainty from photovoltaic solar and to improve prediction quality. Analog Ensemble is a technique to generate ensemble predictions using fewer computational resources than traditional ensemble prediction models. This research extends Analog Ensemble with a Machine Learning metric and results show that the proposed spatio-temporal weather similarity metric yields accurate and reliable ensemble forecasts.
