Speed Scaling on Parallel Processors with Migration

Abstract : We study the problem of scheduling a set of jobs with release dates, deadlines and processing requirements (works), on parallel speed-scalable processors so as to minimize the total energy consumption. We consider that both preemption and migration of jobs are allowed. We formulate the problem as a convex program and we propose a polynomial-time combinatorial algorithm which is based on a reduction to the maximum flow problem. We extend our algorithm to the multiprocessor speed scaling problem with preemption and migration where the objective is the minimization of the maximum lateness under a budget of energy.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00741604
Contributor : Frédéric Davesne <>
Submitted on : Sunday, October 14, 2012 - 8:13:22 PM
Last modification on : Thursday, March 21, 2019 - 2:40:54 PM

Links full text

Identifiers

Citation

Eric Angel, Evripidis Bampis, Fadi Kacem, Dimitrios Letsios. Speed Scaling on Parallel Processors with Migration. 18th International Conference Euro-Par 2012 Parallel Processing, Aug 2012, Rhodes Island, Greece. pp.128--140, ⟨10.1007/978-3-642-32820-6_15⟩. ⟨hal-00741604⟩

Share

Metrics

Record views

217