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 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Machine Learning Model Time-Series Clustering for Energy Optimized Virtual Machine Placement Using Time-Series Performance Data.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Machine Learning Model Time-Series Clustering for Energy Optimized Virtual Machine Placement Using Time-Series Performance Data./
作者:	Kellogg, Tad.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	133 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-02, Section: B.
Contained By:	Dissertations Abstracts International83-02B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28548454
ISBN:	9798516961519

Machine Learning Model Time-Series Clustering for Energy Optimized Virtual Machine Placement Using Time-Series Performance Data.
Kellogg, Tad.

Machine Learning Model Time-Series Clustering for Energy Optimized Virtual Machine Placement Using Time-Series Performance Data. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 133 p.

Source: Dissertations Abstracts International, Volume: 83-02, Section: B.

Thesis (D.C.S.)--Colorado Technical University, 2021.

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

As modern cloud provider growth continues, the need to optimize physical resources to contain and reduce energy consumption is a predominant problem. Prior research has shown solutions for the virtual machine placement problem (VMPP) that can optimize physical resources and reduce energy consumption. However, as the VMPP is an NP-hard type problem, research continues for more optimized approximations. The research presented in this dissertation has demonstrated a unique approximation as a VMPP solution. The use of a convolutional neural network (CNN) and K-Means combinational algorithm-based time-series clustering artifact to identify the initial placement with predicted future workload physical host cohesion as a VMPP solution. The research has demonstrated a rejection of the null hypothesis, in which the energy consumption for the artifact VMPP solution, as measured in the number of activated physical servers, was shown to be less than the energy consumption of a random distribution placement algorithm as a VMPP solution (p < 0.001). The reduction was shown in seven simulation scenarios in which the initial activation of hosts was sustained during a simulated 24 hours. The reduction average of 7.5 physical hosts also matched the performance of prior research VMPP solution algorithms. Finally, the use of CNN and K-Means algorithms combined for time-series clustering can now be considered a valid methodology for VMPP solution research.

ISBN: 9798516961519Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Convolutional neural network

Machine Learning Model Time-Series Clustering for Energy Optimized Virtual Machine Placement Using Time-Series Performance Data.
LDR:02732nmm a2200385 4500 001 2344648
005 20220531064616.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798516961519
035 $a (MiAaPQ)AAI28548454
035 $a AAI28548454
040 $a MiAaPQ $c MiAaPQ
100 1 $a Kellogg, Tad. $3 3683434
245 1 0 $a Machine Learning Model Time-Series Clustering for Energy Optimized Virtual Machine Placement Using Time-Series Performance Data.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 133 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-02, Section: B.
500 $a Advisor: Schmitt, Alexa.
502 $a Thesis (D.C.S.)--Colorado Technical University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a As modern cloud provider growth continues, the need to optimize physical resources to contain and reduce energy consumption is a predominant problem. Prior research has shown solutions for the virtual machine placement problem (VMPP) that can optimize physical resources and reduce energy consumption. However, as the VMPP is an NP-hard type problem, research continues for more optimized approximations. The research presented in this dissertation has demonstrated a unique approximation as a VMPP solution. The use of a convolutional neural network (CNN) and K-Means combinational algorithm-based time-series clustering artifact to identify the initial placement with predicted future workload physical host cohesion as a VMPP solution. The research has demonstrated a rejection of the null hypothesis, in which the energy consumption for the artifact VMPP solution, as measured in the number of activated physical servers, was shown to be less than the energy consumption of a random distribution placement algorithm as a VMPP solution (p < 0.001). The reduction was shown in seven simulation scenarios in which the initial activation of hosts was sustained during a simulated 24 hours. The reduction average of 7.5 physical hosts also matched the performance of prior research VMPP solution algorithms. Finally, the use of CNN and K-Means algorithms combined for time-series clustering can now be considered a valid methodology for VMPP solution research.
590 $a School code: 1271.
650 4 $a Computer science. $3 523869
650 4 $a Computer engineering. $3 621879
650 4 $a Information technology. $3 532993
650 4 $a Artificial intelligence. $3 516317
650 4 $a Software. $2 gtt. $3 619355
650 4 $a Energy efficiency. $3 3555643
650 4 $a Datasets. $3 3541416
650 4 $a Neural networks. $3 677449
653 $a Convolutional neural network
653 $a K-Means clustering
653 $a Machine learning
653 $a Time-series clustering
653 $a Virtual machine placement
690 $a 0984
690 $a 0464
690 $a 0489
690 $a 0800
710 2 $a Colorado Technical University. $b Computer Science. $3 3342445
773 0 $t Dissertations Abstracts International $g 83-02B.
790 $a 1271
791 $a D.C.S.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28548454