Mean-Value Analysis of Closed Multichain Queuing Networks
Journal of the ACM (JACM)
A Characterization of Product-Form Queuing Networks
Journal of the ACM (JACM)
Performance bound hierarchies for queueing networks
ACM Transactions on Computer Systems (TOCS)
Linearizer: a heuristic algorithm for queueing network models of computing systems
Communications of the ACM
Balanced job bound analysis of queueing networks
Communications of the ACM
Computational algorithms for closed queueing networks with exponential servers
Communications of the ACM
Some Extensions to Multiclass Queueing Network Analysis
Proceedings of the Third International Symposium on Modelling and Performance Evaluation of Computer Systems: Performance of Computer Systems
Performance Bounds Based upon Throughput Curve Properties
Performance '83 Proceedings of the 9th International Symposium on Computer Performance Modelling, Measurement and Evaluation
Bounding algorithms for queueing network models of computer systems
Bounding algorithms for queueing network models of computer systems
Bound hierarchies for multiple-class queuing networks
Journal of the ACM (JACM) - The MIT Press scientific computation series
IEEE Transactions on Computers
SIGMETRICS '86/PERFORMANCE '86 Proceedings of the 1986 ACM SIGMETRICS joint international conference on Computer performance modelling, measurement and evaluation
PASASM: a method for the performance assessment of software architectures
WOSP '02 Proceedings of the 3rd international workshop on Software and performance
An improved balanced job bound analysis of closed queuing networks
Operations Research Letters
| Hi-index | 0.00 |
The time required to find the exact solution of a product-form queueing network model of a computer system can be high. Faster and cheaper methods of solution, such as approximations, are natural alternatives. However, the errors incurred when using an approximation technique should be bounded. Several recent techniques have been developed which provide solution bounds. These bounding techniques have the added benefit that the bounds can be made tighter if extra computational effort is expended. Thus, a smooth tradeoff of cost and accuracy is available. These techniques are based upon mean value analysis. In this paper a new bounding technique based upon the convolution algorithm is presented. It provides a continuous range of cost versus accuracy tradeoffs for both upper and lower bounds. The bounds produced by the technique converge to the exact solution as the computational effort approaches that of convolution. Also, the technique may be used to improve any existing set of bounds.