Abstract
The Mean Value Analysis (MVA) algorithm is one of the most popular for evaluating the performance of separable (or product-form) queueing networks. Although its complexity is modest when jobs are indistinguishable, the introduction of different customer classes rapidly increases its computational cost. The problems of parallelising the algorithm while retaining its conceptual simplicity are examined. In particular, a parallel implementation of MVA on a distributed memory machine is developed using the MPI library for communication. Copyright © 1999 The Society for Computer Simulation International.
Original language | English |
---|---|
Pages (from-to) | 16-22 |
Number of pages | 7 |
Journal | Transactions of the Society for Computer Simulation |
Volume | 16 |
Issue number | 1 |
Publication status | Published - 1999 |
Keywords
- Mean value analysis
- Parallel simulation
- Pipelined algorithm
- Product form
- Queueing networks