Server installation as a grid condition sensor
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G05F-001/66
G05B-015/02
G06Q-050/06
출원번호
US-0675163
(2015-03-31)
등록번호
US-9933804
(2018-04-03)
발명자
/ 주소
Janous, Brian
McKnight, Gregory Joseph
James, Sean
Bianchini, Ricardo
Liu, Jie
출원인 / 주소
Microsoft Technology Licensing, LLC
대리인 / 주소
Rainier Patents, P.S.
인용정보
피인용 횟수 :
0인용 특허 :
70
초록▼
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 electr
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.
대표청구항▼
1. A system comprising: a hardware processor; anda hardware computer-readable storage medium storing computer-readable instructions which, when executed by the hardware processor, cause the hardware processor to:train an algorithm using historical grid condition signals obtained from a first electri
1. A system comprising: a hardware processor; anda hardware computer-readable storage medium storing computer-readable instructions which, when executed by the hardware processor, cause the hardware processor to:train an algorithm using historical grid condition signals obtained from a first electrical grid and a second electrical grid, the historical grid condition signals reflecting historical failures on the first electrical grid and the second electrical grid, the first electrical grid being geographically remote from the second electrical grid;obtain current first grid condition signals describing first grid conditions detected by a first data center, wherein the first data center is connected to the first electrical grid;evaluate the current first grid condition signals using the trained algorithm to make a prediction of a future failure event on the second electrical grid; andprior to occurrence of the future failure event, cause an adjustment to a local energy storage device or a local generator at a second data center that is connected to the second electrical grid, the local energy storage device or the local generator powering multiple servers at the second data center. 2. The system of claim 1, wherein the adjustment causes the local energy storage device to begin charging. 3. The system of claim 1, wherein the adjustment causes the local generator to turn on or off. 4. The system of claim 1, wherein the adjustment causes a server action on a particular server at the second data center. 5. The system of claim 4, wherein the server action comprises throttling data processing on the particular server at the second data center. 6. The system of claim 4, wherein the server action comprises configuring the particular server at the second data center into a different power consumption state. 7. The system of claim 4, wherein the server action comprises transferring at least some data processing from the particular server at the second data center to a third data center. 8. The system of claim 4, wherein the server action comprises: based at least on the prediction, identifying a deferrable job at the second data center that is scheduled to be performed during or after a predicted time of the future failure event; andrescheduling the deferrable job prior to the predicted time of the future failure event. 9. A method comprising: obtaining current first grid condition signals describing first grid conditions detected by a first server farm, wherein the first server farm is connected to a first electrical grid;evaluating the current first grid condition signals using a trained algorithm to make a prediction of a future failure event on a second electrical grid that is geographically remote from the first electrical grid, the trained algorithm being trained using historical grid condition signals obtained from the first electrical grid and the second electrical grid, the historical grid condition signals reflecting historical failures on the first electrical grid and the second electrical grid; andbased at least on the prediction and prior to an occurrence of the future failure event, causing an adjustment to a local energy storage device or a local generator at a second server farm that is connected to the second electrical grid, the local energy storage device or the local generator powering multiple servers at the second server farm. 10. The method of claim 9, further comprising training the algorithm. 11. The method of claim 9, wherein the local energy storage device is a local battery at the second server farm, the second server farm can draw power from both the local battery and the second electrical grid, and the adjustment includes charging the local battery at the second server farm using electrical power from the second electrical grid. 12. The method of claim 11, further comprising: drawing a targeted electrical load on the second electrical grid by charging the local battery at a specified wattage. 13. The method of claim 11, further comprising: reducing an electrical load on the second electrical grid by discharging the local battery at a specified wattage. 14. The method of claim 13, further comprising: evaluating previous discharge cycles performed on the local battery at the second server farm; anddetermining an amount to discharge the local battery based at least on the previous discharge cycles. 15. The method of claim 9, wherein the second server farm has the local generator, the second server farm can draw power from both the local generator and the second electrical grid, and the adjustment includes changing a current generator state of the local generator. 16. The method of claim 15, wherein the adjustment comprises turning on the local generator. 17. The method of claim 15, wherein the adjustment comprises synchronizing sine waves of local power from the local generator with grid power from the second electrical grid. 18. A 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:obtain current first grid condition signals describing first grid conditions detected by a first data center that is connected to a first electrical grid;evaluate the current first grid condition signals using a trained algorithm to make a prediction of a future failure event on a second electrical grid that is geographically remote from the first electrical grid, the trained algorithm being trained using historical grid condition signals obtained during historical grid failures; andbased at least on the prediction and prior to occurrence of the future failure event, cause an adjustment to a local energy storage device or a local generator at a second data center that is connected to the second electrical grid, the local energy storage device or the local generator powering multiple servers at the second data center. 19. The system of claim 18, the historical grid failures including first historical grid failures that occurred on the first electrical grid and second grid failures that occurred on the second electrical grid. 20. The system of claim 18, the prediction comprising a conditional probability of the future failure event occurring on the second electrical grid given a recent failure event on the first electrical grid. 21. The system of claim 18, wherein the computer-readable instructions, when executed by the hardware processor, cause the hardware processor to: identify a predicted duration of the future failure event;determine whether to transfer jobs from the second data center to a third data center based at least on the predicted duration of the future failure event;in a first instance when the predicted duration exceeds a specified duration, transfer an individual job from the second data center to the third data center; andin a second instance when the predicted duration does not exceed the specified duration, refrain from transferring another individual job from the second data center to the third data center.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (70)
Sharma, Ratnesh K.; Bash, Cullen E.; Patel, Chandrakant D., Agent based control method and system for energy management.
Graybill, David P.; Iyengar, Madhusudan K; Newcomer, Jeffrey A.; Schmidt, Roger R., Airflow recirculation and cooling apparatus and method for an electronics rack.
Davis Glenn A. (Lilburn GA) Massara James M. (Dunwoody GA), Apparatus and method for controlling an electrical load and monitoring control operations and the electrical load.
Barzegar, Farhad; Gerszberg, Irwin; Henry, Paul Shala; Bennett, Robert; Barnickel, Donald J; Willis, III, Thomas M., Apparatus for powering a communication device and methods thereof.
Fung,Henry T., Apparatus, architecture, and method for integrated modular server system providing dynamically power-managed and work-load managed network devices.
Belady, Christian L.; Larus, James R.; Reed, Danny A.; Borgs, Christian H.; Chayes, Jennifer Tour; Lobel, Ilan; Menache, Ishai; Nazerzadeh, Hamid; Jain, Navendu, Data center system that accommodates episodic computation.
Chassin,David P.; Donnelly,Matthew K.; Dagle,Jeffery E., Electrical power distribution control methods, electrical energy demand monitoring methods, and power management devices.
Karaoguz, Jeyhan; Currivan, Bruce; Diab, Wael William; Kim, Yongbum; Ma, Kenneth; Johas Teener, Michael, Method and system for power-limited switching and/or routing in a network.
Kuelbs,Gustav P.; Kuelbs,John A.; Kuelbs,Gregory G.; Domzalski,Donald, Method of producing, selling, and distributing articles of manufacture through the automated aggregation of orders and the visual representation of standardized shipping volumes.
Ritter, Allen Michael; Harbourt, Cyrus David; Wagoner, Robert Gregory, Methods for coupling an energy storage system to a variable energy supply system.
Kato, Takeshi; Saito, Tatsuya; Okitsu, Jun; Shiga, Yoko; Nakajima, Tadakatsu; Kondo, Yoshihiro, Operational management method for information processing system and information processing system.
Cherkasova, Ludmila; Tang, Wenting, System and method for determining how many servers of at least one server configuration to be included at a service provider's site for supporting an expected workload.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.