國立虎尾科技大學 |

A Comparative Study of Deep Learning Architectures for Multivariate Cloud Workload Prediction = = COk Degiskenli Bulut is Yuku Tahmini Icin Derin Ogrenme Mimarilerinin Karsilastirmali Calismasi.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	A Comparative Study of Deep Learning Architectures for Multivariate Cloud Workload Prediction =/
其他題名:	COk Degiskenli Bulut is Yuku Tahmini Icin Derin Ogrenme Mimarilerinin Karsilastirmali Calismasi.
作者:	Gozen, Derya.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	67 p.
附註:	Source: Masters Abstracts International, Volume: 84-05.
Contained By:	Masters Abstracts International84-05.
標題:	Deep learning. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29469867
ISBN:	9798352969212

A Comparative Study of Deep Learning Architectures for Multivariate Cloud Workload Prediction = = COk Degiskenli Bulut is Yuku Tahmini Icin Derin Ogrenme Mimarilerinin Karsilastirmali Calismasi.
Gozen, Derya.

A Comparative Study of Deep Learning Architectures for Multivariate Cloud Workload Prediction =COk Degiskenli Bulut is Yuku Tahmini Icin Derin Ogrenme Mimarilerinin Karsilastirmali Calismasi. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 67 p.

Source: Masters Abstracts International, Volume: 84-05.

Thesis (M.Sc.)--Bilkent Universitesi (Turkey), 2022.

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

Cloud computing and use of cloud data centers are in high demand due to their benefits to customers including but not limited to low cost, high availability, reliability, robustness and scalability. Cloud service providers are obliged to fulfill service level agreements that promise high quality of service to their customers. This brings out the need for effective and efficient utilization of data center resources, especially the resources of the compute servers. To achieve proactive and effective resource allocation and scaling policies, accurate prediction of workloads in cloud computing environments plays a critical role. Cloud workload prediction is a challenging task due to high dimensionality, variance and complexity of the workload data. In addition, workload prediction models are expected to work with sufficient amount of past observations to correctly learn workload patterns, at the same time, handle longer forecast horizons accurately. In order to tackle this problem and address the challenges, we investigated and compared five deep learning-based schemes for multivariate time series forecasting to predict the CPU utilization of virtual machines in cloud data centers. The performance of the deep learning schemes is analyzed and compared by using two real-world data sets: Alibaba cluster trace and Bitbrains trace. Our study reveals the relative strengths and weaknesses of the compared schemes for cloud workload prediction. We also observed that, among the compared schemes, Encoder-Decoder LSTM Network with Attention is a more effective solution for workload prediction in cloud computing.

ISBN: 9798352969212Subjects--Topical Terms:

1127428
Deep learning.

A Comparative Study of Deep Learning Architectures for Multivariate Cloud Workload Prediction = = COk Degiskenli Bulut is Yuku Tahmini Icin Derin Ogrenme Mimarilerinin Karsilastirmali Calismasi.
LDR:04342nam a2200397 4500 001 1104675
005 20230619080117.5
006 m o d
007 cr#unu||||||||
008 230907s2022 ||||||||||||||||| ||eng d
020 $a 9798352969212
035 $a (MiAaPQ)AAI29469867
035 $a (MiAaPQ)Bilkent_11693110418
035 $a AAI29469867
040 $a MiAaPQ $c MiAaPQ
100 1 $a Gozen, Derya. $3 1413634
245 1 0 $a A Comparative Study of Deep Learning Architectures for Multivariate Cloud Workload Prediction = $b COk Degiskenli Bulut is Yuku Tahmini Icin Derin Ogrenme Mimarilerinin Karsilastirmali Calismasi.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 67 p.
500 $a Source: Masters Abstracts International, Volume: 84-05.
500 $a Advisor: Korpeoglu, Ibrahim.
502 $a Thesis (M.Sc.)--Bilkent Universitesi (Turkey), 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Cloud computing and use of cloud data centers are in high demand due to their benefits to customers including but not limited to low cost, high availability, reliability, robustness and scalability. Cloud service providers are obliged to fulfill service level agreements that promise high quality of service to their customers. This brings out the need for effective and efficient utilization of data center resources, especially the resources of the compute servers. To achieve proactive and effective resource allocation and scaling policies, accurate prediction of workloads in cloud computing environments plays a critical role. Cloud workload prediction is a challenging task due to high dimensionality, variance and complexity of the workload data. In addition, workload prediction models are expected to work with sufficient amount of past observations to correctly learn workload patterns, at the same time, handle longer forecast horizons accurately. In order to tackle this problem and address the challenges, we investigated and compared five deep learning-based schemes for multivariate time series forecasting to predict the CPU utilization of virtual machines in cloud data centers. The performance of the deep learning schemes is analyzed and compared by using two real-world data sets: Alibaba cluster trace and Bitbrains trace. Our study reveals the relative strengths and weaknesses of the compared schemes for cloud workload prediction. We also observed that, among the compared schemes, Encoder-Decoder LSTM Network with Attention is a more effective solution for workload prediction in cloud computing.
520 $a Bulut veri merkezleri; musterilere sunulan dusuk maliyet, yuksek kul- lanilabilirlik, guvenilirlik, dayaniklilik ve olceklenebilirlik gibi faydalar sebebi ile revactadir. Ancak, bulut hizmet saglayicilari, hizmet seviyesi anlasmalarini yer- ine getirirken, musterilerine yuksek kalite hizmet vermek ile yukumludur. Bu durum, veri merkezi yonetiminde kaynaklarin etkin ve verimli kullanim ihtiyacini ortaya cikarmaktadir. Proaktif kaynak paylastirma ve olcekleme politikalari elde etme yolunda, bulut ortamlardaki is yukunun dogru tahmin edilmesi kritik oneme sahiptir. Is yuku tahmini; is yuku verisindeki yuksek boyutluluk, varyans ve karmasiklik sebebi ile zorlu bir problemdir. Buna ek olarak, is yuku tahmin modellerinin, yeterli sayida gecmis is yuku gozlemleri ile calismasi, ayni zamanda gelecege yonelik uzun tahmin ufku ile basa cikabilmesi beklenmektedir. Bu prob- lemi cozmek ve zorluklarini irdelemek amaci ile bulut veri merkezlerindeki sanal makinelerin CPU kullanimini tahmin eden, bes farkli derin ogrenme tabanli cok degiskenli zaman serisi tahmin modeli kurulmustur. Model performanslari iki gercek dunya veri seti kullanilarak karsilastirilmis ve analiz edilmistir: Alibaba kume izleri ve BitBrains izleri. Karsilastirmali calisma ve analiz sonucunda, Dikkat Mekanizmali Kodlayici-Kodcozucu Uzun-Kisa Sureli Bellek Aginin bu- lut veri merkezlerinde is yukunun tahmini icin etkin ve verimli bir cozum oldugu gorulmustur.
590 $a School code: 1159.
650 4 $a Deep learning. $3 1127428
650 4 $a Back propagation. $3 1252564
650 4 $a Forecasting. $3 632960
650 4 $a Genetic algorithms. $3 655041
650 4 $a Voice recognition. $3 1413635
650 4 $a Signal processing. $3 561459
650 4 $a Neural networks. $3 1011215
650 4 $a Feature selection. $3 1413636
650 4 $a Clustering. $3 1413637
650 4 $a Time series. $3 1413638
650 4 $a Kalman filters. $3 1413639
650 4 $a Cloud computing. $3 716205
650 4 $a Short term. $3 1413640
650 4 $a Computer science. $3 573171
650 4 $a Electrical engineering. $3 596380
650 4 $a Physics. $3 564049
690 $a 0800
690 $a 0984
690 $a 0544
690 $a 0629
690 $a 0454
690 $a 0605
710 2 $a Bilkent Universitesi (Turkey). $3 1413631
773 0 $t Masters Abstracts International $g 84-05.
790 $a 1159
791 $a M.Sc.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29469867