Sustainable RAS balancing based on predictive models
AssigneeInternational Business Machines Corporation
InventorsAndrew C. M. Hicks, Michael E Gildein, Michael Terrence Cohoon
Life of this patent
Estimating the term…
Abstract
Methods, systems, and products for sustainable Reliability, Availability, and Serviceability (RAS) balancing based on predictive models includes predicting, based on one or more predictive models, a potential failure within a computing system, and provisioning, based on the potential failure, one or more redundant resources for failover.
Claims20
A method of sustainable reliability, availability, and serviceability (RAS) balancing based on predictive models, the method comprising:
- predicting, based on one or more predictive models, a potential failure within a computing system;
- determining a predicted time for the potential failure to occur;
- determining predicted times for provisioning different redundant resources, associated with the computing system, to address failures within the computing system;
- selecting one or more resources, of the different redundant resources, based on the predicted time for the potential failure to occur and based on one or more predicted times for provisioning the one or more redundant resources to address the potential failure;
- and
- provisioning, based on the potential failure, the one or more redundant resources for failover.
A computer program product comprising a computer readable storage medium and computer program instructions stored therein that, when executed, are configured to:
- predict, based on one or more predictive models, a potential failure within a computing system;
- determine a predicted time for the potential failure to occur;
- determine predicted times for provisioning different redundant resources, associated with the computing system, for failover within the computing system;
- select one or more resources, of the different redundant resources, based on the predicted time for the potential failure to occur and based on one or more predicted times for provisioning the one or more redundant resources for failover for the potential failure;
- and
- provision, based on the potential failure, the one or more redundant resources for failover.
A system comprising:
- a computing system;
- a plurality of redundant resources;
- and
- a processor configured to:
- predict, based on one or more predictive models, a potential failure within the computing system;
- determine a predicted time for the potential failure to occur;
- determine predicted times for provisioning different redundant resources, associated with the computing system, for failover within the computing system,
- select one or more resources, of the different redundant resources, based on the predicted time for the potential failure to occur and based on one or more predicted times for provisioning the one or more redundant resources for failover for the potential failure;
- and
- provision, based on the potential failure, the one or more redundant resources for failover.
Dependencies are inferred from the claim text.