Data center cooling using model-predictive control

By Nevena Lazic, Craig Boutilier, Tyler Lu, Eehern Wong, Binz Roy, Moonkyung Ryu, Gregory P. Imwalle. 2018

197 citations recorded by the source corpus.

Subfields: Reinforcement Learning, ML Systems & Hardware

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

1. Yuxi Li
2. Marcin Michalski
3. Craig Boutilier
4. Carlos Riquelme
5. Anton Raichuk
6. Sanmit Narvekar
7. Sylvain Gelly
8. Olivier Bachem

In ML Systems & Hardware

1. Craig Boutilier
2. Piotr Sta'nczyk
3. Yuxi Li
4. Na Li

Citations in the corpus

• Google Research Football: A Novel Reinforcement Learning Environment (2019, background): “Real-world applications include robotics (Haarnoja et al. 2018), self-driving cars (Bansal, Krizhevsky, and Ogale 2018), and control problems such as increasing the power efficiency of data centers (Lazic et al. 2018).”
• RecSim: A Configurable Simulation Platform for Recommender Systems (2019, background): “…RL has shown considerable success in games, robotics, physical system control and computational modeling [Mnih et al., 2015, Silver et al., 2016, Haarnoja et al., 2018, Lazic et al., 2018], large-scale deployment of RL in real-world applications has proven challenging [Dulac-Arnold et al., 2019].”
• Deep Reinforcement Learning (2018, background): “tributed operation of power management. Google deploy machine learning for data centre power management, reducing energy consumption by 40%. See blogs at http://goo.gl/4PHcos and http://goo.gl/N3Aoxm.Lazic et al. (2018) study data center cooling with model-predictive control (MPC). Optimizing memory”
• Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis (2019, background): “data center management [1, 2], robotics [3], autonomous driving [4, 5], energy systems [6], manufacturing [7, 8].”