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

FindBook

Google Book

Amazon

博客來

Efficient Provisioning of Virtual Network Functions Via Machine Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Efficient Provisioning of Virtual Network Functions Via Machine Learning./
作者:	Mushtaq, Maria.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	61 p.
附註:	Source: Masters Abstracts International, Volume: 83-02.
Contained By:	Masters Abstracts International83-02.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28499620
ISBN:	9798534663358

Efficient Provisioning of Virtual Network Functions Via Machine Learning.
Mushtaq, Maria.

Efficient Provisioning of Virtual Network Functions Via Machine Learning. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 61 p.

Source: Masters Abstracts International, Volume: 83-02.

Thesis (M.S.)--Saint Louis University, 2021.

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

Network Function Virtualization is a mechanism that enhances and strengthens the operation and control of networks. It functions by providing network services, such as firewalls, traffic control, or load balancers. Chaining virtual links and virtual network functions in a predefined sequence form a Service Function Chains (SFCs). Placing contrained SFCs is a computationally hard problem that providers have to solve to manage their infrastructure and generate revenue. To minimize capital and maintenance costs and achieve service agility, the efficient dynamic placement of SFCs is hence essential for varying service demands. Most of the existing approaches to place the service chains within multiple data center links and nodes are inefficient and could over or under allocate the network resources. In this thesis, we propose two online and real-time systems that extract information about potential network traffic volume to enable a responsive approach to constructive chain provisioning. In particular, we design and implement Long-Short Term Memory (LSTM) and Convolutional Neural Network (CNN) based Internet traffic predictors to support robust service function chain instantiation. The first system, called Necklace provides guarantees on the performance with respect to the optimal chain allocation. The second system called OctoMap, uses a Multi-Armed Bandit strategy to decide online how to support a chain mapping decision. Our simulation results suggest that leveraging these service demand prediction often improves performance of the chain provisioning thereby reducing provider costs.

ISBN: 9798534663358Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Machine learning

Efficient Provisioning of Virtual Network Functions Via Machine Learning.
LDR:02738nmm a2200361 4500 001 2345951
005 20220613064822.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798534663358
035 $a (MiAaPQ)AAI28499620
035 $a AAI28499620
040 $a MiAaPQ $c MiAaPQ
100 1 $a Mushtaq, Maria. $3 3684967
245 1 0 $a Efficient Provisioning of Virtual Network Functions Via Machine Learning.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 61 p.
500 $a Source: Masters Abstracts International, Volume: 83-02.
500 $a Advisor: Esposito, Flavio.
502 $a Thesis (M.S.)--Saint Louis University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Network Function Virtualization is a mechanism that enhances and strengthens the operation and control of networks. It functions by providing network services, such as firewalls, traffic control, or load balancers. Chaining virtual links and virtual network functions in a predefined sequence form a Service Function Chains (SFCs). Placing contrained SFCs is a computationally hard problem that providers have to solve to manage their infrastructure and generate revenue. To minimize capital and maintenance costs and achieve service agility, the efficient dynamic placement of SFCs is hence essential for varying service demands. Most of the existing approaches to place the service chains within multiple data center links and nodes are inefficient and could over or under allocate the network resources. In this thesis, we propose two online and real-time systems that extract information about potential network traffic volume to enable a responsive approach to constructive chain provisioning. In particular, we design and implement Long-Short Term Memory (LSTM) and Convolutional Neural Network (CNN) based Internet traffic predictors to support robust service function chain instantiation. The first system, called Necklace provides guarantees on the performance with respect to the optimal chain allocation. The second system called OctoMap, uses a Multi-Armed Bandit strategy to decide online how to support a chain mapping decision. Our simulation results suggest that leveraging these service demand prediction often improves performance of the chain provisioning thereby reducing provider costs.
590 $a School code: 0193.
650 4 $a Computer science. $3 523869
650 4 $a Systems science. $3 3168411
650 4 $a Load. $3 3562902
650 4 $a Software. $2 gtt. $3 619355
650 4 $a Deep learning. $3 3554982
650 4 $a Wide area networks. $3 3683705
650 4 $a Protocol. $3 3564384
650 4 $a Bandwidths. $3 3560998
650 4 $a Optimization. $3 891104
650 4 $a Network operating systems. $3 3684968
650 4 $a Network interface cards. $3 3683605
650 4 $a Working groups. $3 3684969
650 4 $a Distance learning. $3 3557921
650 4 $a Traffic congestion. $3 706812
650 4 $a Decision making. $3 517204
650 4 $a Neural networks. $3 677449
650 4 $a Mapping. $3 3355992
650 4 $a Variables. $3 3548259
650 4 $a Design. $3 518875
650 4 $a Algorithms. $3 536374
653 $a Machine learning
653 $a Network function virtulization
653 $a Network traffic prediction
653 $a Service function chains
690 $a 0984
690 $a 0790
690 $a 0389
710 2 $a Saint Louis University. $b Computer Science. $3 3558089
773 0 $t Masters Abstracts International $g 83-02.
790 $a 0193
791 $a M.S.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28499620