The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMMUNICATIONS
Transactions ID Number: 52-389
Full Name: Chung-Ping Chen
Position: Student
Age: ON
Sex: Male
Address: 510 Chung Cheng Rd. Hsinchuang, Taipei County 24205
Country: TAIWAN
Tel: 886-2-27712171 ext 2221
Tel prefix:
Fax: 886-2-27317120
E-mail address: 491598038@mail.fju.edu.tw
Other E-mails: cpchen@ntut.edu.tw
Title of the Paper: The Partition Algorithm of an Equivalent Queuing Model for Serial-Parallel Connection Servers
Authors as they appear in the Paper: Chung-Ping Chen, Ying-Wen Bai and Cheng-Yu Chung
Email addresses of all the authors: 491598038@mail.fju.edu.tw, bai@ee.fju.edu.tw, tsauyow168@hotmail.com
Number of paper pages: 11
Abstract: This paper aims at analysis efficiency in estimating the performance of serial-parallel connection servers. We use a queuing model to represent the equivalent performance and service quality of the serial-parallel connection servers. The queue types of the connection servers can be classified as serial, parallel and tree connections. We design an algorithm to simplify the equivalent serial-parallel queues. According to the equivalent queues we compute the system response time of serial-parallel connection servers. We use a network simulation and an analytical software tool to represent the equivalent performance of the queue. Our simulation uses various different service rates and arrival rates of the queue models and finds the system response time. We also measure the average system response time in comparison with the simulation result to find out the service rates of the actual servers and evaluate the accuracy of the algorithm. We will find that the error margi!
n of measurement, simulation and computing ranges from 1.37%-19.27%.
Keywords: Serial-parallel Network, Web Servers, Service Rate, Serial-parallel Connection Servers, System Response Time, Equivalent Queuing Network.
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 140.124.70.139
