Interarrival statistics for time sharing systems

Abstract

The optimization of tlme-shared system performance requires the description of the stochastic processes governing the user inputs and the program activity.This paper provides a statistical description of the user input process in the SDC-ARPA generalpurpose Time.Sharing System (TSS).The input process is assumed to be stationary, and to be defined by the interarrival time distribution.The data obtained appear to justify satisfactorily the common assumption that the interarrival times are serially independent.The data do not appear to justify, except as a very rough approximation, the usual assumption of an exponential distribution for interarrival time.A much more satisfactory approximation to the data can be obtained with a biphase or trlphase hyperexponential distribution.

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 — 24 citations exist upstream.

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