Framework for distribution of computer workloads based on real-time energy costs
First Claim
1. A method for dynamically shifting compute workloads among data center sites based on real-time energy costs, the method comprising:
- evaluating via a processing unit a compute processing task of a compute workload that is capable of being relocated to determine a potential energy consumption needed in watts and a length of time needed to perform the compute task;
determining for each of a plurality of available data center sites respective energy prices per watt of energy provided by the sites and time durations for each of the respective energy prices, via the processing unit; and
relocating via the processing unit the compute task to a second data center site of the plurality of data center sites having a lowest energy price from a first of the data center sites that the compute job is assigned to if;
a total cost to relocate the compute job to the second site and complete the compute job at the second site energy price is lower than a cost to complete the compute job at the first site energy price;
the second site time energy price duration is long enough to complete the compute task if moved to the second site; and
the compute job workload of the first site will remain stable for a minimum required thrashing prevention threshold amount of time after moving the compute job to the second site;
ormoving the compute job to the second site will not exceed a specified threshold maximum number of moves for the compute job.
2 Assignments
0 Petitions
Accused Products
Abstract
Energy costs for conducting compute tasks at diverse data center sites are determined and are then used to route such tasks in a most efficient manner. A given compute task is first evaluated to predict potential energy consumption. The most favorable real-time energy costs for the task are determined at the various data center sites. The likely time period of the more favorable cost as well as the stability at the data center are additional factors. A workload dispatcher then forwards the selected compute task to the data center having the most favorable real-time energy costs. Among the criteria used to select the most favorable data center is a determination that the proposed center presently has the resources for the task.
72 Citations
24 Claims
-
1. A method for dynamically shifting compute workloads among data center sites based on real-time energy costs, the method comprising:
-
evaluating via a processing unit a compute processing task of a compute workload that is capable of being relocated to determine a potential energy consumption needed in watts and a length of time needed to perform the compute task; determining for each of a plurality of available data center sites respective energy prices per watt of energy provided by the sites and time durations for each of the respective energy prices, via the processing unit; and relocating via the processing unit the compute task to a second data center site of the plurality of data center sites having a lowest energy price from a first of the data center sites that the compute job is assigned to if; a total cost to relocate the compute job to the second site and complete the compute job at the second site energy price is lower than a cost to complete the compute job at the first site energy price; the second site time energy price duration is long enough to complete the compute task if moved to the second site; and the compute job workload of the first site will remain stable for a minimum required thrashing prevention threshold amount of time after moving the compute job to the second site;
ormoving the compute job to the second site will not exceed a specified threshold maximum number of moves for the compute job. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A method for effecting compliance with power usage specifications through positive feedback, the method comprising:
-
integrating computer-readable program code into a computer system comprising a processing unit, a computer readable memory and a computer readable tangible storage device, wherein the computer readable program code is embodied on the computer readable tangible storage device and comprises instructions that, when executed by the processing unit via the computer readable memory, cause the processing unit to; evaluate a compute processing task of a compute workload that is capable of being relocated to determine a potential energy consumption needed in watts and a length of time needed to perform the compute task; determine for each of a plurality of available data center sites respective energy prices per watt of energy provided by the sites and time durations for each of the respective energy prices; and relocate the compute task to a second data center site of the plurality of data center sites having a lowest energy price from a first of the data center sites that the compute job is assigned to if; a total cost to relocate the compute job to the second site and complete the compute job at the second site energy price is lower than a cost to complete the compute job at the first site energy price; the second site time energy price duration is long enough to complete the compute task if moved to the second site; and the compute job workload of the first site will remain stable for a minimum required thrashing prevention threshold amount of time after moving the compute job to the second site;
ormoving the compute job to the second site will not exceed a specified threshold maximum number of moves for the compute job. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
13. A system, comprising:
-
a processing unit in communication with a computer readable memory and a tangible computer-readable storage device; wherein the processing unit, when executing program instructions stored on the tangible computer-readable storage device via the computer readable memory; evaluates a compute processing task of a compute workload that is capable of being relocated to determine a potential energy consumption needed in watts and a length of time needed to perform the compute task; determines for each of a plurality of available data center sites respective energy prices per watt of energy provided by the sites and time durations for each of the respective energy prices; and relocates the compute task to a second data center site of the plurality of data center sites having a lowest energy price from a first of the data center sites that the compute job is assigned to if; a total cost to relocate the compute job to the second site and complete the compute job at the second site energy price is lower than a cost to complete the compute job at the first site energy price; the second site time energy price duration is long enough to complete the compute task if moved to the second site; and the compute job workload of the first site will remain stable for a minimum required thrashing prevention threshold amount of time after moving the compute job to the second site;
ormoving the compute job to the second site will not exceed a specified threshold maximum number of moves for the compute job. - View Dependent Claims (14, 15, 16, 17, 18)
-
-
19. An article of manufacture, comprising:
-
a computer readable tangible storage device having computer readable program code embodied therewith, the computer readable program code comprising instructions that, when executed by a computer processing unit, cause the computer processing unit to; evaluate a compute processing task of a compute workload that is capable of being relocated to determine a potential energy consumption needed in watts and a length of time needed to perform the compute task; determine for each of a plurality of available data center sites respective energy prices per watt of energy provided by the sites and time durations for each of the respective energy prices; and relocate the compute task to a second data center site of the plurality of data center sites having a lowest energy price from a first of the data center sites that the compute job is assigned to if; a total cost to relocate the compute job to the second site and complete the compute job at the second site energy price is lower than a cost to complete the compute job at the first site energy price; the second site time energy price duration is long enough to complete the compute task if moved to the second site; and the compute job workload of the first site will remain stable for a minimum required thrashing prevention threshold amount of time after moving the compute job to the second site;
ormoving the compute job to the second site will not exceed a specified threshold maximum number of moves for the compute job. - View Dependent Claims (20, 21, 22, 23, 24)
-
Specification