English

Online Capacity Scaling Augmented With Unreliable Machine Learning Predictions

Data Structures and Algorithms 2022-04-21 v2 Machine Learning Networking and Internet Architecture Performance Optimization and Control

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 (1+ε)(1+\varepsilon)-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.

Keywords

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

R2 v1 2026-06-23T22:37:50.893Z