Server installation as a grid condition sensor

Patent metadata

Field	Value
Publication number	US-2016011618-A1
Application number	US-201514675163-A
Country	US
Kind code	A1
Filing date	Mar 31, 2015
Priority date	Jul 11, 2014
Publication date	Jan 14, 2016
Grant date	—

Abstract

This document relates to analyzing electrical grid conditions using server installations. One example obtains first grid condition signals describing first grid conditions detected by a first server installation during a first time period. The first server installation is connected to a first electrical grid and first previous grid failure events have occurred on the first electrical grid during the first time period. The example also obtains second grid condition signals describing second grid conditions detected by a second server installation during a second time period. The second server installation is connected to a second electrical grid that is geographically remote from the first electrical grid and second previous grid failure events have occurred on the second electrical grid during the second time period. The example also includes using the first grid condition signals and the second grid condition signals to predict a future grid failure event on the second electrical grid.

First claim

1 . A control system comprising:
a hardware processor; and a hardware computer-readable storage medium storing computer-readable instructions which, when executed by the hardware processor, cause the hardware processor to implement a grid analysis module and an action causing module, wherein the grid analysis module is configured to:
obtain first grid condition signals describing first grid conditions detected by a first server installation during a first time period, wherein the first server installation is connected to a first electrical grid and a previous grid failure event that has occurred on the first electrical grid during the first time period; and
use the first grid condition signals to obtain a prediction of a future failure event on a second electrical grid; and
wherein the action causing module is configured to:
based on the prediction, cause an adjustment to an energy storage state of an energy storage device or a current generator state of a generator at a second server installation that is connected to the second electrical grid.

2 . The control system of claim 1 , wherein the action causing module is configured to cause the energy storage device to begin charging.

3 . The control system of claim 1 , wherein the action causing module is configured to cause the generator to turn on or off.

4 . The control system of claim 1 , wherein the action causing module is configured to cause a server action on a server at the second server installation.

5 . The control system of claim 4 , wherein the server action comprises throttling a service that is currently executing on the server at the second server installation.

6 . The control system of claim 4 , wherein the server action comprises placing the server at the second server installation into a different power consumption state.

7 . The control system of claim 4 , wherein the server action comprises transferring a job from the server at the second server installation to another server installation.

8 . The control system of claim 4 , wherein the server action comprises:
based on the prediction, identifying a deferrable job at the second server installation that is scheduled to be performed during or after a predicted time of the future failure event; and rescheduling the deferrable job prior to the predicted time of the future failure event.

9 . A method comprising:
obtaining first grid condition signals describing first grid conditions detected by a first server installation during a first time period, wherein the first server installation is connected to a first electrical grid and first previous grid failure events have occurred on the first electrical grid during the first time period; obtaining second grid condition signals describing second grid conditions detected by a second server installation during a second time period, wherein the second server installation is connected to a second electrical grid and second previous grid failure events have occurred on the second electrical grid during the second time period; performing an analysis of the first grid conditions and the second grid conditions; and predicting a likelihood of a future grid failure event based on the analysis.

10 . The method of claim 9 , wherein the likelihood of the future grid failure event is predicted for the second electrical grid.

11 . The method of claim 10 , wherein the analysis comprises identifying historical correlations between the first previous grid failure events and the second previous grid failure events.

12 . The method of claim 9 , wherein the likelihood of the future grid failure event is predicted for a third electrical grid that is geographically remote from both the first electrical grid and the second electrical grid.

13 . The method of claim 9 , wherein the analysis comprises training a learning algorithm to perform the predicting and using the first grid condition signals and the second grid condition signals as training data for the learning algorithm.

14 . The method of claim 13 , further comprising:
determining a hierarchical relationship between the first server installation and the second server installation in a grid hierarchy; and using the hierarchical relationship between the first server installation and the second server installation as further training data for the learning algorithm.

15 . The method of claim 14 , wherein the hierarchical relationship indicates whether the first server installation and the second server installation are connected to a common parent grid or parent substation.

16 . The method of claim 13 , further comprising:
obtaining first weather signals describing first weather conditions at the first server installation; obtaining second weather signals describing first weather conditions at the second server installation; and using the first weather signals and the second weather signals as further training data for the learning algorithm.

17 . A method comprising:
obtaining first grid condition signals describing first grid conditions detected by a first server installation during a first time period, wherein the first server installation is connected to a first electrical grid and first previous grid failure events have occurred on the first electrical grid during the first time period; obtaining second grid condition signals describing second grid conditions detected by a second server installation during a second time period, wherein the second server installation is connected to a second electrical grid that is geographically remote from the first electrical grid and second previous grid failure events have occurred on the second electrical grid during the second time period; performing an analysis of the first grid condition signals and the second grid condition signals to identify a correlation between the first previous grid failure events on the first electrical grid and the second grid failure events on the second electrical grid; and using the correlation to predict a likelihood of a future grid failure event on the second electrical grid based on a recent grid failure event on the first electrical grid.

18 . The method of claim 17 , further comprising identifying the correlation by calculating a conditional probability of the future grid failure event on the second electrical grid given the recent grid failure event on the first electrical grid.

19 . The method of claim 17 , wherein the first grid condition signals describe voltage drop on the first electrical grid.

20 . The method of claim 17 , wherein the first grid condition signals describe frequency of alternating current on the first electrical grid or the first grid condition signals indicate whether power factor is leading or lagging on the first electrical grid.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Janous Brian
• Mcknight Gregory Joseph
• James Sean
• Bianchini Ricardo
• Liu Jie

Classifications

• G06Q50/06

  Energy or water supply · CPC title

• G05F1/66 Primary

  Regulating electric power · CPC title

• G05B15/02 Primary

  electric · CPC title