A New Approach to Capacity Scaling Augmented with Unreliable Machine Learning Predictions

DOI10.1287/MOOR.2023.1364arXiv2101.12160OpenAlexW3121596971MaRDI QIDQ6149403FDOQ6149403

Authors: Debankur Mukherjee 

Publication date: 5 March 2024

Published in: Mathematics of Operations Research (Search for Journal in Brave)

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 $(1+varepsilon)$-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.

Full work available at URL: https://arxiv.org/abs/2101.12160

Recommendations

• Algorithms for energy conservation in heterogeneous data centers
• Algorithms for energy conservation in heterogeneous data centers
• Self-Learning Threshold-Based Load Balancing
• Sleep management on multiple machines for energy and flow time

zbMATH Keywords

online algorithmscompetitive analysisenergy efficiencyspeed scalingcompetitive ratio

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27) Performance evaluation, queueing, and scheduling in the context of computer systems (68M20)

This page was built for publication: A New Approach to Capacity Scaling Augmented with Unreliable Machine Learning Predictions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6149403)