Online Capacity Scaling Augmented With Unreliable Machine Learning Predictions
This work addresses energy efficiency for data center operators, offering an incremental improvement by integrating unreliable predictions into existing capacity scaling methods.
The paper tackles the problem of minimizing power consumption and operational costs in data centers through dynamic server activation, proposing an algorithm that uses machine learning predictions to achieve a (1+ε)-competitive ratio when predictions are accurate while maintaining robustness against inaccurate predictions.
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.