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

Electronic business transaction infr...

Feller, Andrew Lee.

Linked to FindBook

Google Book

Amazon

博客來

Electronic business transaction infrastructure analysis using Petri nets and simulation.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Electronic business transaction infrastructure analysis using Petri nets and simulation./
Author:	Feller, Andrew Lee.
Description:	85 p.
Notes:	Source: Dissertation Abstracts International, Volume: 71-06, Section: B, page: 3914.
Contained By:	Dissertation Abstracts International71-06B.
Subject:	Information Technology. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3410531
ISBN:	9781124026589

Electronic business transaction infrastructure analysis using Petri nets and simulation.
Feller, Andrew Lee.

Electronic business transaction infrastructure analysis using Petri nets and simulation. - 85 p.

Source: Dissertation Abstracts International, Volume: 71-06, Section: B, page: 3914.

Thesis (Ph.D.)--Arizona State University, 2010.

Rapid growth in eBusiness has made industry and commerce increasingly dependent on the hardware and software infrastructure that enables high-volume transaction processing across the Internet. Large transaction volumes at major industrial-firm data centers rely on robust transaction protocols and adequately provisioned hardware capacity to ensure that the high-volume flow of daily business transactions is not interrupted. This research analyzes the robustness of eBusiness transaction infrastructure using Petri nets and simulation to characterize two critical elements that were found to be problematic in industry: 1) a widely used electronic messaging protocol for eBusiness transactions called RosettaNet (RN), and 2) capacity planning for the bottlenecked application-server tier of hardware infrastructure used to process eBusiness transactions. Analysis of the RN protocol is based on reusable patterns for Petri net modeling of common protocol mechanisms such as retries, time-outs, and fault handling. These new patterns translate abstract representations of the RN standard into an executable model. A stochastic Petri net constructed from the patterns is simulated to generate performance curves based on varying network conditions, and analyzed using linear temporal logic to prove that the protocol can end processing in unsynchronized failure states that make resolution of the interchange problematic. This leads to suggested improvements in the protocol. Analysis of the application-server tier of the infrastructure used for processing eBusiness transactions is also performed to enable better capacity planning for robust operations. Improved planning for this infrastructure requires characterization of resource consumption patterns driven by two key factors affecting service performance and capacity: 1) the varying transaction load patterns, and 2) the variable delays incurred by downstream application services. Both factors are considered because servers consume and hold computing resources both when transactions arrive and also while requesting and waiting for responses from external services needed to fulfill transaction requests. A two-step, emulation-simulation approach is used that empirically determines consumption patterns for a single test server by emulation testing under controlled load and latency conditions; then data from the emulation tunes a scaled-up discrete event simulation model to predict production server consumption.

ISBN: 9781124026589Subjects--Topical Terms:

1030799
Information Technology.

Electronic business transaction infrastructure analysis using Petri nets and simulation.
LDR:03388nam 2200289 4500 001 1401598
005 20111017084401.5
008 130515s2010 ||||||||||||||||| ||eng d
020 $a 9781124026589
035 $a (UMI)AAI3410531
035 $a AAI3410531
040 $a UMI $c UMI
100 1 $a Feller, Andrew Lee. $3 1680744
245 1 0 $a Electronic business transaction infrastructure analysis using Petri nets and simulation.
300 $a 85 p.
500 $a Source: Dissertation Abstracts International, Volume: 71-06, Section: B, page: 3914.
500 $a Adviser: Dan Shunk.
502 $a Thesis (Ph.D.)--Arizona State University, 2010.
520 $a Rapid growth in eBusiness has made industry and commerce increasingly dependent on the hardware and software infrastructure that enables high-volume transaction processing across the Internet. Large transaction volumes at major industrial-firm data centers rely on robust transaction protocols and adequately provisioned hardware capacity to ensure that the high-volume flow of daily business transactions is not interrupted. This research analyzes the robustness of eBusiness transaction infrastructure using Petri nets and simulation to characterize two critical elements that were found to be problematic in industry: 1) a widely used electronic messaging protocol for eBusiness transactions called RosettaNet (RN), and 2) capacity planning for the bottlenecked application-server tier of hardware infrastructure used to process eBusiness transactions. Analysis of the RN protocol is based on reusable patterns for Petri net modeling of common protocol mechanisms such as retries, time-outs, and fault handling. These new patterns translate abstract representations of the RN standard into an executable model. A stochastic Petri net constructed from the patterns is simulated to generate performance curves based on varying network conditions, and analyzed using linear temporal logic to prove that the protocol can end processing in unsynchronized failure states that make resolution of the interchange problematic. This leads to suggested improvements in the protocol. Analysis of the application-server tier of the infrastructure used for processing eBusiness transactions is also performed to enable better capacity planning for robust operations. Improved planning for this infrastructure requires characterization of resource consumption patterns driven by two key factors affecting service performance and capacity: 1) the varying transaction load patterns, and 2) the variable delays incurred by downstream application services. Both factors are considered because servers consume and hold computing resources both when transactions arrive and also while requesting and waiting for responses from external services needed to fulfill transaction requests. A two-step, emulation-simulation approach is used that empirically determines consumption patterns for a single test server by emulation testing under controlled load and latency conditions; then data from the emulation tunes a scaled-up discrete event simulation model to predict production server consumption.
590 $a School code: 0010.
650 4 $a Information Technology. $3 1030799
650 4 $a Operations Research. $3 626629
650 4 $a Artificial Intelligence. $3 769149
690 $a 0489
690 $a 0796
690 $a 0800
710 2 $a Arizona State University. $3 1017445
773 0 $t Dissertation Abstracts International $g 71-06B.
790 1 0 $a Shunk, Dan, $e advisor
790 $a 0010
791 $a Ph.D.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3410531