Bayesian Approach To The Design Of Queueing Systems

Abstract

Notwithstanding the continual growth in research into complex waiting line models, questions pertaining to optimal design of such systems have been scantily answered. Most works reported to date bypass the formidable issue of inadequate knowledge of such important parameters as the arrival rate of customers. We demonstrate in this paper how statistical decision theoretic approaches may be gainfully applied to handle the prevalent uncertainties. The pertinent decision theoretic machinery for the resolution of problems of choice in the face of uncertainty is briefly presented and discussed. The application of this machinery is exemplified by consideration of the design problem of a finite waiting space M/M/1 queue. One-time sampling specifications are prescribed for this model on the assumption that there exists the possibility of obtaining additional information through experimentation to supplement prior judgments. The paper concludes with a numerical example to illustrate the procedure.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 14 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.