The subject matter described herein relates to a system and a method for generation of energy consumption profiles corresponding to a plurality of computing systems. For each of the plurality of the computing systems, a plurality of consumption parameters from at least one measurement device is rece
The subject matter described herein relates to a system and a method for generation of energy consumption profiles corresponding to a plurality of computing systems. For each of the plurality of the computing systems, a plurality of consumption parameters from at least one measurement device is received. The consumption parameters include a processor utilization parameter and an energy consumption parameter. Further, a normalization factor corresponding to each of the plurality of the computing systems is identified. Based on the normalization factor, the processor utilization parameter is normalized. Based on the normalized processor utilization parameter and the energy consumption parameter, the energy consumption profile is generated. The energy consumption profile is indicative of energy efficiency of the plurality of the computing systems.
대표청구항▼
1. A profile generation system comprising: a processor; anda memory coupled to the processor, the memory comprising, a normalization module configured to: identify a normalization factor corresponding to each of a plurality of computing systems, wherein the normalization factor indicates configurati
1. A profile generation system comprising: a processor; anda memory coupled to the processor, the memory comprising, a normalization module configured to: identify a normalization factor corresponding to each of a plurality of computing systems, wherein the normalization factor indicates configuration of a processor of a computing system with respect to a reference processor;normalize a processor utilization parameter of each of the plurality of computing systems, based on the normalization factor, wherein the processor utilization parameter is indicative of a percentage of time for which the processor of the computing system is being used for processing instructions; andfractionally normalize the normalized processor utilization parameter of each of the plurality of computing systems to obtain a corresponding fractional processor utilization parameter, wherein the fractional processor utilization parameter of the computing system is a ratio of the normalized processor utilization parameter to a data-center consumption parameter corresponding to processor utilization, the data-center consumption parameter being indicative of cumulative sum of normalized processor utilizations of the plurality of computing systems; andan analysis module configured to generate an energy consumption profile for the plurality of computing systems based on the fractional processor utilization parameter of the plurality of computing systems, wherein the energy consumption profile is indicative of an association between the processor utilization and energy consumption of the plurality of computing systems. 2. The profile generation system as claimed in claim 1, wherein the normalization module is configured to average, for each of the plurality of computing systems, the processor utilization parameter and an energy consumption parameter over a predetermined time-interval. 3. The profile generation system as claimed in claim 1, wherein the normalization module is configured to fractionally normalize an energy consumption parameter of each of the plurality of computing systems, to obtain a fractional energy consumption parameter, and wherein the fractional energy consumption parameter is a ratio of the energy consumption parameter and a data-center consumption parameter corresponding to the energy consumption, and wherein the data-center consumption parameter corresponding to the energy consumption is indicative of cumulative sum of energy consumptions of the plurality of computing systems. 4. The profile generation system as claimed in claim 1, wherein the normalization module is configured to determine a normalization factor based on at least one normalization parameter, the at least one normalization parameter being indicative of a configuration of the reference processor. 5. The profile generation system as claimed in claim 4, wherein the at least one normalization parameter is selected from the group consisting of a processor family, a processor clock speed, and a number of cores in a processor. 6. The profile generation system as claimed in claim 1, wherein the analysis module is configured to compute cumulative consumption parameters for the plurality of computing systems, based on fractional consumption parameters, to generate the energy consumption profile, the fractional consumption parameters including the fractional processor utilization parameters and fractional energy consumption parameters. 7. A method to generate energy consumption profiles for a plurality of computing systems, the method comprising: identifying a normalization factor corresponding to each of the plurality of computing systems, wherein the normalization factor indicates configuration of a processor of a computing system with respect to a reference processor;normalizing, based on the normalization factor, processor utilization parameter corresponding to each of the plurality of the computing systems, wherein the processor utilization parameter is indicative of a percentage of time for which the processor of the computing system is being used for processing instructions;determining, for each of the plurality of computing systems, a fractional processor utilization parameter, based on a corresponding normalized processor utilization parameter wherein the fractional processor utilization parameter of the computing system is a ratio of the normalized processor utilization parameter to a data-center consumption parameter corresponding to processor utilization, the data-center consumption parameter being indicative of cumulative sum of normalized processor utilizations of the plurality of computing systems; andgenerating an energy consumption profile based on the fractional processor utilization parameter corresponding to each of the plurality of the computing systems, wherein the energy consumption profile is indicative of an association between the processor utilization and energy consumption of the plurality of computing systems. 8. The method as claimed in claim 7, wherein the method further comprises averaging the processor utilization parameter and an energy consumption parameter for each of the plurality of computing systems over a predetermined time interval. 9. The method as claimed in claim 7, wherein the method further comprises determining, for each of the plurality of the computing systems, a fractional energy consumption parameter and wherein the fractional energy consumption parameter is a ratio of the energy consumption parameter and a data-center consumption parameter corresponding to the energy consumption, and wherein the energy consumption profile is generated based on the fractional energy consumption parameter. 10. The method as claimed in claim 7, wherein generating the energy consumption profile comprises determining cumulative consumption parameters for the plurality of computing systems, based on fractional processor utilization parameters and fractional energy consumption parameters. 11. A computer-readable medium having embodied thereon a computer program for executing a method comprising: identifying a normalization factor corresponding to each of a plurality of computing systems, wherein the normalization factor indicates configuration of a processor of a computing system with respect to a reference processor;normalizing, based on the normalization factor, a processor utilization parameter corresponding to each of the plurality of computing systems, wherein the processor utilization parameter is indicative of a percentage of time for which the processor of the computing system is being used for processing instructions;determining, for each of the plurality of computing systems, a fractional processor utilization parameter, based on a corresponding normalized processor utilization parameter wherein the fractional processor utilization parameter of the computing system is a ratio of the normalized processor utilization parameter to a data-center consumption parameter corresponding to processor utilization, the data-center consumption parameter being indicative of cumulative sum of normalized processor utilizations of the plurality of computing systems; andgenerating an energy consumption profile based on the fractional processor utilization parameter corresponding to each of the plurality of computing systems, wherein the energy consumption profile is indicative of an association between the processor utilization and energy consumption of the plurality of computing systems. 12. The computer readable medium as claimed in claim 11, wherein the method further comprises averaging the processor utilization parameter for each of the plurality of computing systems over a predetermined time interval and averaging energy consumption parameter for each of the plurality of computing systems over the predetermined time interval. 13. The computer readable medium as claimed in claim 11, wherein the method further comprises determining, for each of the plurality of the computing systems, a fractional energy consumption parameter and wherein the fractional energy consumption parameter is a ratio of the energy consumption parameter and a data-center consumption parameter corresponding to the energy consumption, and wherein the energy consumption profile is generated based on the fractional energy consumption parameter. 14. The computer readable medium as claimed in claim 13, wherein generating the energy consumption profile comprises determining cumulative consumption parameters for the plurality of computing systems, based on the fractional energy consumption parameters and the fractional processor utilization parameters. 15. The computer-readable medium as claimed in claim 11, wherein the method further comprises receiving a plurality of consumption parameters for each of the plurality of computing systems from at least one resource measurement device, the plurality of consumption parameters including the processor utilization parameter and an energy consumption parameter.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (9)
Weber, Wolf-Dietrich; Fan, Xiaobo; Barroso, Luiz Andre, Data center load monitoring for utilizing an access power amount based on a projected peak power usage and a monitored power usage.
Ghiasi,Soraya; Keller, Jr.,Thomas Walter; Kotla,Ramakrishna; Rawson, III,Freeman Leigh, Scheduling processor voltages and frequencies based on performance prediction and power constraints.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.