Minimizing Total Completion Time in Multiprocessor Job Systems with Energy Constraint

TL;DR

This paper addresses the challenge of scheduling multiprocessor jobs to minimize total completion time within an energy budget, analyzing complexity and proposing approximation algorithms for specific cases.

Contribution

It investigates the complexity of multiprocessor job scheduling with energy constraints and introduces approximation algorithms for particular scenarios.

Findings

Complexity results for parallel and dedicated multiprocessor scheduling.

Approximation algorithms based on job sequencing and list scheduling.

Feasible solutions balancing energy use and completion time.

Abstract

We consider the problem of scheduling multiprocessor jobs to minimize the total completion time under the given energy budget. Each multiprocessor job requires more than one processor at the same moment of time. Processors may operate at variable speeds. Running a job at a slower speed is more energy efficient, however it takes longer time and affects the performance. The complexity of both parallel and dedicated versions of the problem is investigated. We propose approximation algorithms for various particular cases. In our algorithms, initially a sequence of jobs and their processing times are calculated and then a feasible solution is constructed using list-type scheduling rule.