Statistical Efficiency of Regenerative Simulation Methods for Networks of Queues.
Abstract
When developing simulation methodology, it is important to be able to assess the statistical efficiency of proposed estimation procedures. This paper is concerned with the assessment of the statistical efficiency of regenerative methods for simulation of networks of queues with general service times. Our estimation procedures are applicable to networks that have a single state for passage times; regenerative cycles are defined in terms of the single state. We provide a comparison of two methods for estimation of passage time characteristics in closed networks with priorities among job classes. Passage times(informally the times for a job to traverse a portion of a network) are important in computer and communication system models where they represent job response times.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 1982
- Accession Number
- ADA119154
Entities
People
- Donald Iglehart
- Gerald S. Shedler
Organizations
- Stanford University