AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Data center cooling using model-predictive control

Nevena Lazic, Craig Boutilier, Tyler Lu, Eehern Wong, Binz Roy, MK Ryu, Greg Imwalle

NeurIPS 2018 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 114 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
MPC with learned linear model vs local PID controllerscooling control · Data center server flooravg total cost: 142.2 (74.4%) -> 116.7 (74.1%)Improved
MPC vs local PID at low EWT and low loadcooling control · Data center EWT<=20.5 load<=0.7avg total cost: 95.3 -> 106.4Hurt
train model on deliberate exploration data instead of historical PID data (ablation)MPC · Data center server flooravg power+water cost: 117.9 -> 110.2Improved
explore with random perturbations instead of certainty-equivalent controller (ablation)MPC · Data center server flooravg power+water cost: 140.4 -> 110.2Improved
control CAT directly instead of LAT offsetMPC · Data center server floordollar cost: 94% -> 90.7%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy