Quantitative system performance: computer system analysis using queueing network models
Quantitative system performance: computer system analysis using queueing network models
A central-limit-theorem version of L=λW
Queueing Systems: Theory and Applications
Operations Research
Variance Reduction in Simulations of Loss Models
Operations Research
Efficient simulation of queues in heavy traffic
ACM Transactions on Modeling and Computer Simulation (TOMACS)
Optimizing system configurations quickly by guessing at the performance
Proceedings of the 2007 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Relations in the Central Limit Theorem Version of the Response Time Law
QEST '07 Proceedings of the Fourth International Conference on Quantitative Evaluation of Systems
Hi-index | 0.00 |
The performance of computer systems such as Web systems is measured to guarantee quality of service (QoS) or to compare difference configurations of the systems [8]. We consider the problem of whether we should measure mean response time or throughput to better guarantee QoS or to better compare different configurations of a Web system. Specifically, is measured mean response time or measured throughput more accurate, when the Web system is measured for a fixed period of time?