Online Capacity Scaling Augmented With Unreliable Machine Learning Predictions
Abstract
Modern data centers suffer from immense power consumption. As a result, data center operators have heavily invested in capacity scaling solutions, which dynamically deactivate servers if the demand is low and activate them again when the workload increases. We analyze a continuous-time model for capacity scaling, where the goal is to minimize the weighted sum of flow-time, switching cost, and power consumption in an online fashion. We propose a novel algorithm, called Adaptive Balanced Capacity Scaling (ABCS), that has access to black-box machine learning predictions. ABCS aims to adapt to the predictions and is also robust against unpredictable surges in the workload. In particular, we prove that ABCS is -competitive if the predictions are accurate, and yet, it has a uniformly bounded competitive ratio even if the predictions are completely inaccurate. Finally, we investigate the performance of this algorithm on a real-world dataset and carry out extensive numerical experiments, which positively support the theoretical results.
Cite
@article{arxiv.2101.12160,
title = {Online Capacity Scaling Augmented With Unreliable Machine Learning Predictions},
author = {Daan Rutten and Debankur Mukherjee},
journal= {arXiv preprint arXiv:2101.12160},
year = {2022}
}
Comments
47 pages, 9 figures. Changed related works, model description and numerical experiments. Strengthened Lemma 2.5, Proposition 4.17 and Lemma 7.1. Added remarks 4.6, 4.9, 4.10, 4.13 and 6.2