Claims
- 1. A method for managing power consumption in computer servers, said method comprising:selecting a sample window having a plurality of workload samples; determining a maximum sample-to-sample deviation value (DV) of said plurality of workload samples within said selected sample window; determining a capacity envelope, wherein said capacity envelope include a lower limit and an upper limit determined by lower limit=current workload+uplift gain*DV upper limit=current workload+excess gain*DV; and adjusting a current capacity of said plurality of computer servers if said current capacity falls outside said capacity envelope.
- 2. The method of claim 1, wherein said method further includes powering on and powering off said plurality of computer servers alternatively at each sample point when said workload is constant and said upper limit equals said lower limit.
- 3. The method of claim 1, wherein said adjusting a current capacity includes powering on at least one of said plurality of computer servers.
- 4. The method of claim 1, wherein said adjusting a current capacity includes powering off at least one of said plurality of computer servers.
- 5. A computer program product for managing power consumption in computer servers, said computer program product comprising:program code means for selecting a sample window having a plurality of workload samples; program code means for determining a maximum sample-to-sample deviation value of said plurality of workload samples within said selected sample window; program code means for determining a capacity envelope, wherein said capacity envelope include a lower limit and an upper limit determined by lower limit=current workload+uplift gain*DV upper limit=current workload+excess gain*DV; and program code means for adjusting a current capacity of said plurality of computer servers if said current capacity falls outside said capacity envelope.
- 6. The computer program product of claim 5, wherein said computer program product further includes program code means for powering on and powering off said plurality of computer servers alternatively at each sample point when said workload is constant and said upper limit equals said lower limit.
- 7. The computer program product of claim 5, wherein said program code means for adjusting a current capacity includes program code means for powering on at least one of said plurality of computer servers.
- 8. The computer program product of claim 5, wherein program code means for said adjusting a current capacity includes program code means for powering off at least one of said plurality of computer servers.
- 9. An apparatus for managing power consumption in computer servers, said method comprising:means for selecting a sample window having a plurality of workload sample; means for determining a maximum sample-to-sample deviation value of said plurality of workload samples within said selected sample window; means for determining a capacity envelope, wherein said capacity envelope include a lower limit and an upper limit determined by lower limit=current workload+uplift gain*DV upper limit=current workload+excess gain*DV; and means for adjusting a current capacity of said plurality of computer servers if said current capacity falls outside said capacity envelope.
- 10. The apparatus of claim 9, wherein said apparatus further includes means for powering on and powering off said plurality of computer servers alternatively at each sample point when said workload is constant and said upper limit equals said lower limit.
- 11. The apparatus of claim 9, wherein said means for adjusting a current capacity includes means for powering on at least one of said plurality of computer servers.
- 12. The apparatus of claim 9, wherein said means for adjusting a current capacity includes means for powering off at least one of said plurality of computer servers.
RELATED PATENT APPLICATION
The present application is related to co-pending application U.S. Ser. No. 09/584,893, filed on even date, the pertinent portion of which is incorporated herein by reference.
US Referenced Citations (10)