English

A simple and effective predictive resource scaling heuristic for large-scale cloud applications

Distributed, Parallel, and Cluster Computing 2020-08-05 v1 Machine Learning

Abstract

We propose a simple yet effective policy for the predictive auto-scaling of horizontally scalable applications running in cloud environments, where compute resources can only be added with a delay, and where the deployment throughput is limited. Our policy uses a probabilistic forecast of the workload to make scaling decisions dependent on the risk aversion of the application owner. We show in our experiments using real-world and synthetic data that this policy compares favorably to mathematically more sophisticated approaches as well as to simple benchmark policies.

Keywords

Cite

@article{arxiv.2008.01215,
  title  = {A simple and effective predictive resource scaling heuristic for large-scale cloud applications},
  author = {Valentin Flunkert and Quentin Rebjock and Joel Castellon and Laurent Callot and Tim Januschowski},
  journal= {arXiv preprint arXiv:2008.01215},
  year   = {2020}
}
R2 v1 2026-06-23T17:37:03.489Z