國立虎尾科技大學 |

Intelligent and Machine Learning-Based Approaches for Congestion Management and Cascading Failure and Blackout Prevention in Smart Grids.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Intelligent and Machine Learning-Based Approaches for Congestion Management and Cascading Failure and Blackout Prevention in Smart Grids./
作者:	Zarrabian, Sina.
面頁冊數:	1 online resource (209 pages)
附註:	Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9781369808865

Intelligent and Machine Learning-Based Approaches for Congestion Management and Cascading Failure and Blackout Prevention in Smart Grids.
Zarrabian, Sina.

Intelligent and Machine Learning-Based Approaches for Congestion Management and Cascading Failure and Blackout Prevention in Smart Grids. - 1 online resource (209 pages)

Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.

Thesis (Ph.D.)--Tennessee Technological University, 2017.

Includes bibliographical references

The smart grid concept based on communication and information technology infrastructures has significantly improved the performance of modern and wide area power systems in the past few decades. However, due to the large interconnections, complexity of power grids, and sophisticated control structures, still the major concern in the smart grids is dealing with these vulnerabilities to enhance stability, reliability, and security. One of the catastrophic challenges in power systems is cascading failure (CF), where a single fault or contingency in the system can initiate a series of unexpected outages and disturbances that can lead to total wide area blackout.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369808865Subjects--Topical Terms:

596380
Electrical engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Intelligent and Machine Learning-Based Approaches for Congestion Management and Cascading Failure and Blackout Prevention in Smart Grids.
LDR:03336ntm a2200361K 4500 001 912318
005 20180608141652.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9781369808865
035 $a (MiAaPQ)AAI10254716
035 $a (MiAaPQ)tntech:10733
035 $a AAI10254716
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Zarrabian, Sina. $3 1184625
245 1 0 $a Intelligent and Machine Learning-Based Approaches for Congestion Management and Cascading Failure and Blackout Prevention in Smart Grids.
264 0 $c 2017
300 $a 1 online resource (209 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
500 $a Adviser: Rabie Belkacemi.
502 $a Thesis (Ph.D.)--Tennessee Technological University, 2017.
504 $a Includes bibliographical references
520 $a The smart grid concept based on communication and information technology infrastructures has significantly improved the performance of modern and wide area power systems in the past few decades. However, due to the large interconnections, complexity of power grids, and sophisticated control structures, still the major concern in the smart grids is dealing with these vulnerabilities to enhance stability, reliability, and security. One of the catastrophic challenges in power systems is cascading failure (CF), where a single fault or contingency in the system can initiate a series of unexpected outages and disturbances that can lead to total wide area blackout.
520 $a In this work, three distinct intelligent-based approaches are designed and developed for congestion management in transmission lines and preventing consecutive failure of lines and blackout by adaptive adjustment of generating output power through frequency control of the generators.
520 $a The first intelligent approach is designed and developed based on Artificial Neural Networks (ANN). In this method, a multi-layer feed-forward neural network (FFNN) is proposed and the Levenberg-Marquardt Back Propagation (LMBP) method is developed for training the neural network.
520 $a The second intelligent approach is developed based on Multi-Agent System (MAS) architecture. In this method, a multi-agent system is built in real-time and based on interaction of the agents in different levels of the power system. Then an algorithm is developed for implementation of the MAS and interaction of the agents for adaptive adjustment of power through frequency control.
520 $a The third intelligent approach is designed and developed based on machine learning concept. Reinforcement learning (RL) method and Q-learning algorithm is the proposed approach for solving cascading failure problem through adaptive adjustment of the output power. In this method, a Q-learning approach which is an off-policy model free temporal difference method is developed for adaptive and intelligent action selection for power adjustment.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Tennessee Technological University. $b Electrical Engineering. $3 1184626
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10254716 $z click for full text (PQDT)