An Optimal Real-Time Scheduling Approach: From Multiprocessor to Uniprocessor

TL;DR

This paper presents an optimal real-time scheduling method that transforms multiprocessor scheduling into a uniprocessor problem, achieving optimality with minimal preemptions, thus improving efficiency in real-time systems.

Contribution

It introduces a novel approach that reduces multiprocessor scheduling to a uniprocessor problem, maintaining optimality while limiting preemptions per job.

Findings

Achieves optimal scheduling with minimal preemptions

Produces no more than three preemption points per job

Outperforms existing algorithms in simulation

Abstract

An optimal solution to the problem of scheduling real-time tasks on a set of identical processors is derived. The described approach is based on solving an equivalent uniprocessor real-time scheduling problem. Although there are other scheduling algorithms that achieve optimality, they usually impose prohibitive preemption costs. Unlike these algorithms, it is observed through simulation that the proposed approach produces no more than three preemptions points per job.