東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Renewable Energy Integration in Dist...

Gu, Yi.

Linked to FindBook

Google Book

Amazon

博客來

Renewable Energy Integration in Distribution System with Artificial Intelligence.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Renewable Energy Integration in Distribution System with Artificial Intelligence./
Author:	Gu, Yi.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
Description:	151 p.
Notes:	Source: Dissertations Abstracts International, Volume: 82-05, Section: B.
Contained By:	Dissertations Abstracts International82-05B.
Subject:	Electrical engineering. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28030030
ISBN:	9798678178589

Renewable Energy Integration in Distribution System with Artificial Intelligence.
Gu, Yi.

Renewable Energy Integration in Distribution System with Artificial Intelligence. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 151 p.

Source: Dissertations Abstracts International, Volume: 82-05, Section: B.

Thesis (Ph.D.)--University of Denver, 2020.

With the increasing attention of renewable energy development in distribution power system, artificial intelligence (AI) can play an indispensiable role. In this thesis, a series of artificial intelligence based methods are studied and implemented to further enhance the performance of power system operation and control. Due to the large volume of heterogeneous data provided by both the customer and the grid side, a big data visualization platform is built to feature out the hidden useful knowledge for smart grid (SG) operation, control and situation awareness. An open source cluster calculation framework with Apache Spark is used to discover big data hidden information. The data is transmitted with an Open System Interconnection (OSI) model to the data visualization platform with a high-speed communication architecture. Google Earth and Global Geographic Information System (GIS) are used to design the visualization platform and realize the results. Based on the data visualization platform above, the external manifestation of the data is studied. In the following work, I try to understand the internal hidden information of the data. A short-term load forecasting approach is designed based on support vector regression (SVR) to provide a higher accuracy load forecasting for the network reconfiguration. The nonconvexity of three-phase balanced optimal power flow is relaxed to an optimal power flow (OPF) problem with the second-order cone program (SOCP). The alternating direction method of multipliers (ADMM) is used to compute the optimal power flow in distributed iimanner. Considering the reality of distribution systems, a three-phase unbalanced distribtion system is built, which consists of the hourly operation scheduling at substation level and the minutes power flow operation at feeder level. The operaion cost of system with renewable generation is minimized at substation level. The stochastoc distribution model of renewable generation is simulated with a chance constraint, and the derived deterministic form is modeled with Gaussian Mixture Model (GMM) with genetic algorithm-based expectationmaximization (GAEM). The system cost is further reduced with OPF in real-time (RT) scheduling. The semidefinite programming (SDP) is used to relax the nonconvexity of the three-phase unbalanced distribution system into a convex problem, which helps to achieve the global optimal result. In the parallel manner, the ADMM is realizing getting the results in a short time. Clouds have a big impact on solar energy forecasting. Firstly, a convolutional neural network based mathod is used to estimate the solar irradiance, Secondly, the regression results are collected to predict the renewable generation. After that, a novel approach is proposed to capture the Global horizontal irradiance (GHI) conveniently and accurately. Considering the nonstationary property of the GHI on cloudy days, the GHI capturing is cast as an image regression problem. In traditional approaches, the image regression problem is treated as two parts, feature extraction and regression, which are optimized separately and no interconnections. Considering the nonlinear regression capability, a convolutional neural network (CNN) based image regression approach is proposed to provide an End-toEnd solution for the cloudy day GHI capturing problem in this paper. For data cleaning, the Gaussian mixture model with Bayesian inference is employed to detect and eliminate the anomaly data in a nonparametric manner. The purified data are used as input data for the proposed image regression approach. The numerical results demonstrate the feasibility and effectiveness of the proposed approach. Visit TextFancy.com to make your strings more stylish. Pick emojis and other characters, generate ascii art and more.

ISBN: 9798678178589Subjects--Topical Terms:

649834
Electrical engineering.
Subjects--Index Terms:

Artificial intelligence

Renewable Energy Integration in Distribution System with Artificial Intelligence.
LDR:04912nmm a2200361 4500 001 2399532
005 20240916075359.5
006 m o d
007 cr#unu||||||||
008 251215s2020 ||||||||||||||||| ||eng d
020 $a 9798678178589
035 $a (MiAaPQ)AAI28030030
035 $a AAI28030030
040 $a MiAaPQ $c MiAaPQ
100 1 $a Gu, Yi. $3 1935777
245 1 0 $a Renewable Energy Integration in Distribution System with Artificial Intelligence.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 151 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-05, Section: B.
500 $a Advisor: Gao, Wenzhong.
502 $a Thesis (Ph.D.)--University of Denver, 2020.
520 $a With the increasing attention of renewable energy development in distribution power system, artificial intelligence (AI) can play an indispensiable role. In this thesis, a series of artificial intelligence based methods are studied and implemented to further enhance the performance of power system operation and control. Due to the large volume of heterogeneous data provided by both the customer and the grid side, a big data visualization platform is built to feature out the hidden useful knowledge for smart grid (SG) operation, control and situation awareness. An open source cluster calculation framework with Apache Spark is used to discover big data hidden information. The data is transmitted with an Open System Interconnection (OSI) model to the data visualization platform with a high-speed communication architecture. Google Earth and Global Geographic Information System (GIS) are used to design the visualization platform and realize the results. Based on the data visualization platform above, the external manifestation of the data is studied. In the following work, I try to understand the internal hidden information of the data. A short-term load forecasting approach is designed based on support vector regression (SVR) to provide a higher accuracy load forecasting for the network reconfiguration. The nonconvexity of three-phase balanced optimal power flow is relaxed to an optimal power flow (OPF) problem with the second-order cone program (SOCP). The alternating direction method of multipliers (ADMM) is used to compute the optimal power flow in distributed iimanner. Considering the reality of distribution systems, a three-phase unbalanced distribtion system is built, which consists of the hourly operation scheduling at substation level and the minutes power flow operation at feeder level. The operaion cost of system with renewable generation is minimized at substation level. The stochastoc distribution model of renewable generation is simulated with a chance constraint, and the derived deterministic form is modeled with Gaussian Mixture Model (GMM) with genetic algorithm-based expectationmaximization (GAEM). The system cost is further reduced with OPF in real-time (RT) scheduling. The semidefinite programming (SDP) is used to relax the nonconvexity of the three-phase unbalanced distribution system into a convex problem, which helps to achieve the global optimal result. In the parallel manner, the ADMM is realizing getting the results in a short time. Clouds have a big impact on solar energy forecasting. Firstly, a convolutional neural network based mathod is used to estimate the solar irradiance, Secondly, the regression results are collected to predict the renewable generation. After that, a novel approach is proposed to capture the Global horizontal irradiance (GHI) conveniently and accurately. Considering the nonstationary property of the GHI on cloudy days, the GHI capturing is cast as an image regression problem. In traditional approaches, the image regression problem is treated as two parts, feature extraction and regression, which are optimized separately and no interconnections. Considering the nonlinear regression capability, a convolutional neural network (CNN) based image regression approach is proposed to provide an End-toEnd solution for the cloudy day GHI capturing problem in this paper. For data cleaning, the Gaussian mixture model with Bayesian inference is employed to detect and eliminate the anomaly data in a nonparametric manner. The purified data are used as input data for the proposed image regression approach. The numerical results demonstrate the feasibility and effectiveness of the proposed approach. Visit TextFancy.com to make your strings more stylish. Pick emojis and other characters, generate ascii art and more.
590 $a School code: 0061.
650 4 $a Electrical engineering. $3 649834
650 4 $a Alternative energy. $3 3436775
653 $a Artificial intelligence
653 $a Machine learrning
653 $a Smart grid
653 $a Renewable energy
690 $a 0544
690 $a 0363
710 2 $a University of Denver. $b Computer Science and Engineering. $3 3276481
773 0 $t Dissertations Abstracts International $g 82-05B.
790 $a 0061
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28030030