论文标题
通过速度缩放学习增强能量最小化
Learning Augmented Energy Minimization via Speed Scaling
论文作者
论文摘要
随着电源管理已成为现代数据中心的主要问题，计算资源正在动态扩展以最大程度地减少能耗。我们启动对经典在线速度缩放问题的变体的研究，在该变体中，可以自然整合有关未来的机器学习预测。受到最新学习的在线算法的启发，我们提出了一种算法，该算法以黑盒方式结合了预测，如果准确性很高，则以任何在线算法的效果胜过任何在线算法，但如果可预测非常不准确，则可以证明可证明的保证。我们提供理论和实验证据来支持我们的主张。
As power management has become a primary concern in modern data centers, computing resources are being scaled dynamically to minimize energy consumption. We initiate the study of a variant of the classic online speed scaling problem, in which machine learning predictions about the future can be integrated naturally. Inspired by recent work on learning-augmented online algorithms, we propose an algorithm which incorporates predictions in a black-box manner and outperforms any online algorithm if the accuracy is high, yet maintains provable guarantees if the prediction is very inaccurate. We provide both theoretical and experimental evidence to support our claims.
