LACS: Learning-Augmented Algorithms for Carbon-Aware Resource Scaling with Uncertain Demand

arXiv:2404.15211v1 Announce Type: cross
Abstract: Motivated by an imperative to reduce the carbon emissions of cloud data centers, this paper studies the online carbon-aware resource scaling problem with unknown job lengths (OCSU) and applies it to carbon-aware resource scaling for executing computing workloads. The task is to dynamically scale resources (e.g., the number of servers) assigned to a job of unknown length such that it is completed before a deadline, with the objective of reducing the carbon emissions of executing …

abstract algorithms arxiv carbon cloud cloud data computing cs.dc cs.lg data data centers demand emissions job paper reduce resources scale scaling studies type uncertain workloads