Abstract
Queueing systems are usually subject to several random and uncontrollable variables that need to be taken into account while designing the system. For a robust design analysis of the system, these noise factors are explicitly factored into a response surface model. This model can then be used to design a system that has desirable average performance as well as an acceptable level of variation in performance. A newly developed approach for robust design is used to create response surfaces for the mean and variance of a queueing performance measure. A two-stage estimation technique is proposed that performs better than ordinary least squares for estimating the variance response surface. Such response surfaces are useful in learning more about the system and can be used to adjust system parameters without further experimentation when the properties of random variables affecting the system change.
Original language | English (US) |
---|---|
Pages | 1321-1326 |
Number of pages | 6 |
State | Published - 2004 |
Event | IIE Annual Conference and Exhibition 2004 - Houston, TX, United States Duration: May 15 2004 → May 19 2004 |
Other
Other | IIE Annual Conference and Exhibition 2004 |
---|---|
Country/Territory | United States |
City | Houston, TX |
Period | 5/15/04 → 5/19/04 |
All Science Journal Classification (ASJC) codes
- General Engineering