US 12,190,172 B2
Carbon footprint-based control of cloud resource consumption
Kim Poh Wong, Singapore (SG); Firas Bouz, Singapore (SG); Seema Nagar, Bangalore (IN); and Pramod Vadayadiyil Raveendran, Machiplavu (IN)
Assigned to Kyndryl, Inc., New York, NY (US)
Filed by KYNDRYL, INC., New York, NY (US)
Filed on Oct. 29, 2021, as Appl. No. 17/513,992.
Prior Publication US 2023/0138727 A1, May 4, 2023
Int. Cl. G06F 9/50 (2006.01); G06Q 30/018 (2023.01)
CPC G06F 9/5088 (2013.01) [G06F 9/505 (2013.01); G06F 9/5072 (2013.01); G06F 9/5094 (2013.01); G06Q 30/018 (2013.01); G06F 2209/501 (2013.01); G06F 2209/5015 (2013.01); G06F 2209/5019 (2013.01); G06F 2209/504 (2013.01); G06F 2209/506 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A computer system comprising:
a central processing unit (CPU) that, when executing instructions stored in an associated memory, is configured to:
register a cloud consumer organization in a portal of a publish-subscribe platform;
receive, by a cloud service provider, a request for cloud resources from the cloud consumer organization, wherein the cloud service provider does not have custody of all of the cloud resources that have been requested, and wherein the request comprises requirements of the cloud resources and a carbon footprint cap of a workload of the cloud consumer organization;
receive a service level agreement (SLA) requirement of the workload, a criticality level of the workload, a peak load duration of the workload, and previous success rates of cloud service providers satisfying cloud resource requirements for the cloud consumer organization;
based on the SLA requirement, the criticality level, the peak load duration, and the previous success rates, select an optimized configuration of one or more cloud resources from a list of cloud resources that satisfy the requirements of the cloud resources and the requirements of the carbon footprint cap, wherein the one or more cloud resources that are selected from the list do not exceed the carbon footprint cap at a given load level based on an initial facility of the cloud service provider;
submit a bid to the publish-subscribe platform to use an initial cloud service provider and the initial facility to provide the one or more cloud resources;
determine that a load level of the workload has increased to exceed a threshold amount;
in response to the load level of the workload being determined to exceed the threshold amount, submit a bid for a trade-off with one or more other cloud consumer organizations that are in custody of one or more other cloud resources, wherein the trade-off includes trading the one or more of the cloud resources in the selected optimized configuration;
perform the trade-off with the one or more other cloud consumer organizations;
after the peak load duration, return the one or more of the cloud resources to the one or more other cloud consumer organizations;
detect an increase in a carbon emission value of the workload;
determine that the increased carbon emission value of the workload exceeds the carbon footprint cap measured in CO2e units for the cloud consumer organization;
dynamically select another cloud service provider and automatically submit a re-bid to the publish-subscribe platform; and
in response to the determination that the increased carbon emission value of the workload exceeds the carbon footprint cap for the cloud consumer organization, dynamically switch to the another cloud service provider to provide the one or more of the cloud resources for the workload, so that a new carbon emission value of the workload using the another cloud service provider does not exceed the carbon footprint cap for the cloud consumer organization.