Performance measurement and queueing analysis at medium-high blocking probability of parallel connection servers with identical service rates

  • Authors:
  • Chung-Ping Chen;Ying-Wen Bai

  • Affiliations:
  • Graduate Institute of Applied Science and Engineering, Fu Jen Catholic University and Department of Electronic Engineering, National Taipei University of Technology, Hsinchuang, Taipei County, Tai ...;Department of Electrical Engineering, Fu Jen Catholic University, Hsinchuang, Taipei County, Taiwan, R.O.C.

  • Venue:
  • WSEAS TRANSACTIONS on COMMUNICATIONS
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we propose a performance measurement and queueing analysis for medium-high blocking probability where the service rate is less than equal to the arrival rate of parallel connection servers, and for which we can estimate the system response time. First, we calculate the system response time of the parallel network. Second, we simulate the queueing model of the parallel network and calculate the system response time. Third, we measure the system response time by using different numbers of ASP multiplication loops to represent the different service rates of the parallel network. Fourth, we take 30, 000 data for imitation as the foundation and use linear regression to compare the measurements of both the system response time and the search service rates of the actual system under different service load conditions. Fifth, we compare the system response time of a single server with up to ten parallel connection servers and compute the discrepancy in their efficiency.