Optimizing data center controls using neural networks

Patent metadata

Field	Value
Publication number	US-2018204116-A1
Application number	US-201715410547-A
Country	US
Kind code	A1
Filing date	Jan 19, 2017
Priority date	Jan 19, 2017
Publication date	Jul 19, 2018
Grant date	—

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for improving operational efficiency within a data center by modeling data center performance and predicting power usage efficiency. An example method receives a state input characterizing a current state of a data center. For each data center setting slate, the state input and the data center setting slate are processed through an ensemble of machine learning models. Each machine learning model is configured to receive and process the state input and the data center setting slate to generate an efficiency score that characterizes a predicted resource efficiency of the data center if the data center settings defined by the data center setting slate are adopted t. The method selects, based on the efficiency scores for the data center setting slates, new values for the data center settings.

First claim

What is claimed is:

1 . A method comprising:
receiving a state input characterizing a current state of a data center; for each data center setting slate in a first set of data center setting slates that each define a respective combination of possible data center settings that affect a resource efficiency of the data center:
processing the state input and the data center setting slate through each machine learning model in an ensemble of machine learning models, wherein each machine learning model in the ensemble is configured to:
receive the state input and the data center setting slate, and
process the state input and the data center setting slate to generate an efficiency score that characterizes a predicted resource efficiency of the data center if the data center settings defined by the data center setting slate are adopted in response to receiving the state input; and

selecting, based on the efficiency scores for the data center setting slates in the first set of data center setting slates, new values for the data center settings.

2 . The method of claim 1 , wherein the efficiency score is a predicted long-term power usage effectiveness (PUE) of the data center if the data center settings defined by the data center setting slate are adopted in response to receiving the state input.

3 . The method of claim 2 , wherein the machine learning models have been configured to generate the predicted long-term PUE of the data center through training the machine learning models on training data that includes a plurality of training state inputs and, for each training state input, a target PUE that was the PUE of the data center a predetermined time after the data center was in the state characterized by the training state input.

4 . The method of claim 3 , further comprising:
receiving raw training state inputs; and preprocessing the raw training state inputs to generate the training state inputs.

5 . The method of claim 3 , wherein the predetermined time is greater than thirty minutes.

6 . The method of claim 5 , wherein the predetermined time is one hour.

7 . The method of claim 1 , wherein selecting new values for the data center settings comprises:
determining, for each data center setting slate, an aggregate resource efficiency score from the efficiency scores generated for the data center setting slate by the ensemble of models; determining, for each data center setting slate, a measure of variation of the efficiency scores generated for the data center setting slate by the ensemble of models; ranking the data center setting slates based on the aggregate resource efficiency scores and the measures of variation; and selecting the combination of possible data center settings defined by a highest-ranked data center setting slate as the new values for the data center settings.

8 . The method of claim 7 , wherein the aggregate resource efficiency score is a measure of central tendency of the efficiency scores generated by the ensemble of models.

9 . The method of claim 7 , wherein ranking the data center setting slates comprises ranking the data center slates in an exploitative manner by penalizing data center setting slates that have higher measures of variation more in the ranking than data center setting slates that have lower measures of variation.

10 . The method of claim 7 , wherein ranking the data center setting slates comprises ranking the data center slates in an explorative manner by promoting data center setting slates that have higher measures of variation more in the ranking than data center setting slates that have lower measures of variation.

11 . The method of claim 1 , further comprising:
obtaining data identifying a second set of data center setting slates; and generating the first set of data center setting slates by removing from the second set of data center slates any data center setting slate that would, if the data center settings defined by the data center setting slate were adopted in response to receiving the state input, result in any of one or more operating constraints for the data center being violated.

12 . The method of claim 11 , wherein generating the first set of data center setting slates comprises, for each operating constraint:
for each data center setting slate in the second set of data center setting slates:
processing the state input and the data center setting slate through one or more constraint machine learning models that are specific to the operating constraint, wherein each constraint machine learning model is configured to:
receive the state input and the data center setting slate, and
process the state input and the data center setting slate to generate a constraint score that characterizes a predicted value of an operating property of the data center that corresponds to the operating constraint if the data center settings defined by the data center setting slate are adopted in response to receiving the state input;

generating a final constraint score for each data center setting slate from the constraint scores generated by the one or more constraint machine learning models that are specific to the constraint; and removing from the second set any data center setting slates from the second set of data center setting slates based on the constraint scores to generate the first set of data center setting slates.

13 . The method of claim 12 , wherein one of the operating constraints is a constraint on the temperature of the data center over a next hour and the operating property of the data center that corresponds to the operating constraint is the temperature of the data center over the next hour.

14 . The method of claim 12 , wherein one of the operating constraints is a constraint on the pressure of the data center over a next hour and the operating property of the data center that corresponds to the operating constraint is the pressure of the data center over the next hour.

15 . The method of claim 1 , wherein each machine learning model in the ensemble has been trained on a different sample of training data from each other machine learning model in the ensemble or has a different model architecture from each other machine learning model in the ensemble.

16 . The method of claim 1 , further comprising:
receiving data identifying a true value of the efficiency score for the data center at a time after the data center was in the current state; and using the current state input, the new values for the data center settings, and the true value of the efficiency score in re-training the ensemble of machine learning models.

17 . A system comprising:
one or more computers; and one or more storage devices storing instructions that are operable, when executed by one or more computers, to cause the one or more computers to perform operations comprising: receiving a state input characterizing a current state of a data center; for each data center setting slate in a first set of data center setting slates that each define a respective combination of possible data center settings that affect a resource efficiency of the data center:
processing the state input and the data center setting slate through each machine learning model in an ensemble of machine learning models, wherein each machine learning model in the ensemble is configured to:
receive the state input and the data center setting slate, and
processing the state input and the data center setting slate to generate an efficiency score that characterizes a predicted resource efficiency of the data center if the data cent

Assignees

• Google Inc

Inventors

• Evans Richard Andrew
• Gao Jim
• Ryan Michael C
• Dulac-Arnold Gabriel
• Scholz Jonathan Karl
• Hester Todd Andrew

Classifications

• G06N3/045 Primary

  Combinations of networks · CPC title

• G06N20/20 Primary

  Ensemble learning · CPC title

• G06N3/0499

  Feedforward networks · CPC title

• G06N3/092

  Reinforcement learning · CPC title

• G06N3/09

  Supervised learning · CPC title