Correlating server power and server utilization for deriving billing from power consumption data

1. A method comprising:

receiving, at a server and at a data transmission rate, power consumption data of a remote server used by a customer, wherein the power consumption data was measured by a controller at the remote server at a power sampling rate that is more frequent than the data transmission rate;

deriving a power-utilization correlation between power consumption of the remote server with utilization of the remote server;

determining utilization of the remote server from the power consumption data and the power-utilization correlation;

preparing a bill for the customer based on the determined utilization of the remote server; and

making the bill available to the customer.

2. The method of claim 1 , wherein deriving the power-utilization correlation comprises:

compiling power consumption data and corresponding utilization data for the remote server; and

correlating the remote server utilization data with the power consumption data.

3. The method of claim 2 , wherein correlating the remote server utilization data with the power consumption data comprises:

determining power consumption of the remoter server during a no load condition;

determining power consumption of the remote server during a fully loaded condition; and

constructing an equation for remote server utilization between a minimum utilization and a maximum utilization of the remote server,

wherein the minimum utilization correlates with the power consumption of the remote server at the no load condition, and

wherein the maximum utilization correlates with the power consumption of the remote server at the fully loaded condition.

4. The method of claim 3 , wherein the equation for remote server utilization is constructed using a curve fitting algorithm selected to match the correlation between the remote server utilization data and the power consumption data.

5. The method of claim 3 , wherein the equation for remote server utilization is:

P current =P idle +( P busy −P idle ) u

where:

P current is an amount of power consumption of the remote server at a particular point in time;

P idle is the power consumption of the remoter server during the no load condition;

P busy is the power consumption of the remote server during the fully loaded condition; and

u is the utilization of the remote server at the particular point in time of P current .

6. The method of claim 3 , wherein the equation for remote server utilization is:

P current =P idle +( P busy −P idle )(2 u−u r )

where:

P current is an amount of power consumption of the remote server at a particular point in time;

P idle is the power consumption of the remoter server during the no load condition;

P busy is the power consumption of the remote server during the fully loaded condition;

u is the utilization of the remote server at the particular point in time of P current ; and

r is a number selected so that the equation for the remote server utilization matches the correlation between the remote server utilization data and the power consumption data using a curve fitting algorithm.

7. The method of claim 3 , further comprising using the equation for remote server utilization and the received power consumption data of the remote server to derive utilization of the remote server over a billing period and deriving the bill based on the utilization during the billing period.

8. The method of claim 1 , wherein receiving the power consumption data further comprises decrypting the power consumption data and storing the power consumption data in a computer readable storage device accessible for at least determining utilization of the remote server from the power consumption data and the power-utilization correlation.

9. The method of claim 1 , wherein storing the power consumption data is in a first-in/first-out (“FIFO”) buffer, wherein the FIFO buffer comprises a capacity to store measurements of power consumption data for a time period at least twice as much as the data transmission rate.

10. An apparatus comprising:

a processor;

non-transitory computer readable storage media that stores code executable by the processor to:

receive, at a data transmission rate, power consumption data of a remote server used by a customer, wherein the power consumption data was measured by a controller at the remote server at a power sampling rate that is more frequent than the data transmission rate;

derive a power-utilization correlation between power consumption of the remote server with utilization of the remote server;

determine utilization of the remote server from the power consumption data and the power-utilization correlation;

prepare a bill for the customer based on the determined utilization of the remote server; and

make the bill available to the customer.

11. The apparatus of claim 10 , wherein deriving the power-utilization correlation comprises:

compiling power consumption data and corresponding utilization data for the remote server; and

correlating the remote server utilization data with the power consumption data.

12. The apparatus of claim 11 , wherein correlating the remote server utilization data with the power consumption data comprises:

determining power consumption of the remoter server during a no load condition;

determining power consumption of the remote server during a fully loaded condition; and

constructing an equation for remote server utilization between a minimum utilization and a maximum utilization of the remote server,

wherein the minimum utilization correlates with the power consumption of the remote server at the no load condition, and

wherein the maximum utilization correlates with the power consumption of the remote server at the fully loaded condition.

13. The apparatus of claim 12 , wherein the equation for remote server utilization is constructed using a curve fitting algorithm selected to match the correlation between the remote server utilization data and the power consumption data.

14. The apparatus of claim 12 , wherein the equation for remote server utilization is:

P current =P idle +( P busy −P idle ) u

where:

P current is an amount of power consumption of the remote server at a particular point in time;

P idle is the power consumption of the remoter server during the no load condition;

P busy is the power consumption of the remote server during the fully loaded condition; and

u is the utilization of the remote server at the particular point in time of P current .

15. The apparatus of claim 12 , wherein the equation for remote server utilization is:

P current =P idle +( P busy −P idle )(2 u−u r )

where:

P current is an amount of power consumption of the remote server at a particular point in time;

P idle is the power consumption of the remoter server during the no load condition;

P busy is the power consumption of the remote server during the fully loaded condition;

u is the utilization of the remote server at the particular point in time of P current ; and

r is a number selected so that the equation for the remote server utilization matches the correlation between the remote server utilization data and the power consumption data using a curve fitting algorithm.

16. The apparatus of claim 12 , further comprising using the equation for remote server utilization and the received power consumption data of the remote server to derive utilization of the remote server over a billing period and deriving the bill based on the utilization during the billing period.

17. A program product comprising a non-transitory computer readable storage medium that stores code executable by a processor, the executable code comprising code to:

receive, at a server and at a data transmission rate, power consumption data of a remote server used by a customer, wherein the power consumption data was measured by a controller at the remote server at a power sampling rate that is more frequent than the data transmission rate;

derive a power-utilization correlation between power consumption of the remote server with utilization of the remote server;

determine utilization of the remote server from the power consumption data and the power-utilization correlation;

prepare a bill for the customer based on the determined utilization of the remote server; and

make the bill available to the customer.

18. The program product of claim 17 , wherein deriving the power-utilization correlation comprises:

compiling power consumption data and corresponding utilization data for the remote server; and

correlating the remote server utilization data with the power consumption data.

19. The program product of claim 18 , wherein correlating the remote server utilization data with the power consumption data comprises:

determining power consumption of the remoter server during a no load condition;

determining power consumption of the remote server during a fully loaded condition; and

constructing an equation for remote server utilization between a minimum utilization and a maximum utilization of the remote server,

wherein the minimum utilization correlates with the power consumption of the remote server at the no load condition,

wherein the maximum utilization correlates with the power consumption of the remote server at the fully loaded condition, and

wherein the equation for remote server utilization is constructed using a curve fitting algorithm selected to match the correlation between the remote server utilization data and the power consumption data.