東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Uncertainty Quantification for Photo...

Hu, Weiming.

FindBook

Google Book

Amazon

博客來

Uncertainty Quantification for Photovoltaic Energy Production Using Analog Ensemble.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Uncertainty Quantification for Photovoltaic Energy Production Using Analog Ensemble./
作者:	Hu, Weiming.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	169 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
標題:	Forecasting techniques. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28841695
ISBN:	9798460447640

Uncertainty Quantification for Photovoltaic Energy Production Using Analog Ensemble.
Hu, Weiming.

Uncertainty Quantification for Photovoltaic Energy Production Using Analog Ensemble. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 169 p.

Source: Dissertations Abstracts International, Volume: 83-03, Section: B.

Thesis (Ph.D.)--The Pennsylvania State University, 2021.

This item must not be sold to any third party vendors.

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. Its lower computational footprint allows a high resolution analysis over a large domain. This research extends and deepens scientific understand of the Analog Ensemble through the following subject areas: 1. Scalability: An efficient and scalable implementation of the Analog Ensemble is proposed and analyzed. It is used to quantify year-round hourly power production uncertainty throughout the Continental U.S. and to study the optimal configuration of solar panels. 2. Spatio-Temporal Weather Analogs: The weather similarity metric is renovated with a spatio-temporal neural network to incorporate crucial information when finding better weather analogs. 3. Model Interpretability: The neural network trained for weather analogs is "pried open" to show the learned information by the network and to better reason why a neural network outperforms the traditional weather similarity metric. Although the proposed method is applied and studied in the field of solar energy and weather forecasting, the knowledge is domain-independent with implications for other physical science subjects, where 1. operational forecasts and the observational archive are available; 2. quantifiable and justifiable measures of uncertainty are desired; 3. and effective management of computational resources is critical.

ISBN: 9798460447640Subjects--Topical Terms:

3564845
Forecasting techniques.
Subjects--Index Terms:

Solar energy

Uncertainty Quantification for Photovoltaic Energy Production Using Analog Ensemble.
LDR:02739nmm a2200337 4500 001 2285484
005 20211208101836.5
008 220723s2021 ||||||||||||||||| ||eng d
020 $a 9798460447640
035 $a (MiAaPQ)AAI28841695
035 $a (MiAaPQ)PennState_22739wuh20
035 $a AAI28841695
040 $a MiAaPQ $c MiAaPQ
100 1 $a Hu, Weiming. $3 3564844
245 1 0 $a Uncertainty Quantification for Photovoltaic Energy Production Using Analog Ensemble.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 169 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Cervone, Guido.
502 $a Thesis (Ph.D.)--The Pennsylvania State University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a 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. Its lower computational footprint allows a high resolution analysis over a large domain. This research extends and deepens scientific understand of the Analog Ensemble through the following subject areas: 1. Scalability: An efficient and scalable implementation of the Analog Ensemble is proposed and analyzed. It is used to quantify year-round hourly power production uncertainty throughout the Continental U.S. and to study the optimal configuration of solar panels. 2. Spatio-Temporal Weather Analogs: The weather similarity metric is renovated with a spatio-temporal neural network to incorporate crucial information when finding better weather analogs. 3. Model Interpretability: The neural network trained for weather analogs is "pried open" to show the learned information by the network and to better reason why a neural network outperforms the traditional weather similarity metric. Although the proposed method is applied and studied in the field of solar energy and weather forecasting, the knowledge is domain-independent with implications for other physical science subjects, where 1. operational forecasts and the observational archive are available; 2. quantifiable and justifiable measures of uncertainty are desired; 3. and effective management of computational resources is critical.
590 $a School code: 0176.
650 4 $a Forecasting techniques. $3 3564845
650 4 $a Weather forecasting. $3 546213
650 4 $a Time series. $3 3561811
650 4 $a Alternative energy. $3 3436775
650 4 $a Meteorology. $3 542822
653 $a Solar energy
653 $a Weather forecasting
690 $a 0557
690 $a 0363
710 2 $a The Pennsylvania State University. $3 699896
773 0 $t Dissertations Abstracts International $g 83-03B.
790 $a 0176
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28841695