Models for Dynamic Load Balancing in a Heterogeneous Multiple Processor System

TLDR

The study presents, analyzes, and compares queueing models for a simple heterogeneous multiple processor system. The models employ job routing strategies—deterministic or nondeterministic—to balance load across m processors, with deterministic policies selecting the next processor to optimize a performance criterion and nondeterministic policies using state‑independent branching probabilities.

Abstract

Queueing models for a simple heterogeneous multiple processor system are presented, analyzed, and compared. Each model is distinguished by a job routing strategy which is designed to reduce the average job turnaround time by balancing the total load among the processors. In each case an arriving job is routed by a job dispatcher to one of m parallel processors. The job routing strategies are divided into two classes: deterministic and nondeterministic. The nondeterministic policies are described by state independent branching probabilities. For the deterministic policies, the next processor is chosen to minimize or maximize the expected value of a performance related criterion function.