Sequence-to-sequence models for workload interference

no code implementations • 25 Jun 2020 • David Buchaca Prats, Joan Marcual, Josep Lluís Berral, David Carrera

In this work we propose a methodology for modeling co-scheduling of jobs on data-centers, based on their behavior towards resources and execution time, using sequence-to-sequence models based on recurrent neural networks.

BIG-bench Machine Learning Scheduling