Optimizing the cloud? Don't train models. Build oracles!
Databases
2023-12-27 v2 Systems and Control
Systems and Control
Abstract
We propose cloud oracles, an alternative to machine learning for online optimization of cloud configurations. Our cloud oracle approach guarantees complete accuracy and explainability of decisions for problems that can be formulated as parametric convex optimizations. We give experimental evidence of this technique's efficacy and share a vision of research directions for expanding its applicability.
Cite
@article{arxiv.2308.06815,
title = {Optimizing the cloud? Don't train models. Build oracles!},
author = {Tiemo Bang and Conor Power and Siavash Ameli and Natacha Crooks and Joseph M. Hellerstein},
journal= {arXiv preprint arXiv:2308.06815},
year = {2023}
}
Comments
Camera-ready publication for CIDR'24: https://www.cidrdb.org/cidr2024/papers/p47-bang.pdf