Management of systems over lifetime
AssigneeDell Products L.P.
InventorDHARMESH M. PATEL
Life of this patent
Estimating the term…
Abstract
Methods, systems, and devices are provided for managing operation of a system. To manage the system, varying performance expectations may be used as a basis for identifying desirable from undesirable operation. The varying performance expectations may take into account the impacts of both time and changes in pipelines used by the system to provide desired services. By proactively taking into account potential changes in the pipeline, the operation of the pipeline may be less likely to be flagged as undesirable when the system is not actually operating in an undesirable manner.
Claims20
A method for managing operation of a distributed system, the method comprising:
- obtaining time varying performance expectations for artificial intelligence services provided by the distributed system;
- obtaining metrics for an artificial intelligence workflow pipeline hosted by the distributed system that provides the artificial intelligence services;
- identifying a subset of the time varying performance expectations based on, at least, the metrics;
- monitoring operation of the distributed system based on the subset to obtain performance metrics;
- making a determination regarding whether the performance metrics meet requirements of the subset of the time varying performance expectations;
- in a first instance of the determination where the performance metrics do not meet the requirements of the subset of the time varying performance expectations:
- concluding that the artificial intelligence workflow pipeline is in an undesired state;
- and
- in a second instance of the determination where the performance metrics meet the requirements of the subset of the time varying performance expectations:
- concluding that the artificial intelligence workflow pipeline is in a desired state and continuing provisioning of the artificial intelligence services using the artificial intelligence workflow pipeline.
A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause operations for managing a distributed system to be performed, the operations comprising:
- obtaining time varying performance expectations for artificial intelligence services provided by the distributed system;
- obtaining metrics for an artificial intelligence workflow pipeline hosted by the distributed system that provides the artificial intelligence services;
- identifying a subset of the time varying performance expectations based on, at least, the metrics;
- monitoring operation of the distributed system based on the subset to obtain performance metrics;
- making a determination regarding whether the performance metrics meet requirements of the subset of the time varying performance expectations;
- in a first instance of the determination where the performance metrics do not meet the requirements of the subset of the time varying performance expectations:
- concluding that the artificial intelligence workflow pipeline is in an undesired state;
- and
- in a second instance of the determination where the performance metrics meet the requirements of the subset of the time varying performance expectations:
- concluding that the artificial intelligence workflow pipeline is in a desired state and continuing provisioning of the artificial intelligence services using the artificial intelligence workflow pipeline.
A data processing system, comprising:
- a processor;
- and
- a memory coupled to the processor to store instructions, which when executed by the processor, cause operations for managing a distributed system to be performed, the operations comprising:
- obtaining time varying performance expectations for artificial intelligence services provided by the distributed system;
- obtaining metrics for an artificial intelligence workflow pipeline hosted by the distributed system that provides the artificial intelligence services;
- identifying a subset of the time varying performance expectations based on, at least, the metrics;
- monitoring operation of the distributed system based on the subset to obtain performance metrics;
- making a determination regarding whether the performance metrics meet requirements of the subset of the time varying performance expectations;
- in a first instance of the determination where the performance metrics do not meet the requirements of the subset of the time varying performance expectations:
- concluding that the artificial intelligence workflow pipeline is in an undesired state;
- and
- in a second instance of the determination where the performance metrics meet the requirements of the subset of the time varying performance expectations:
- concluding that the artificial intelligence workflow pipeline is in a desired state and continuing provisioning of the artificial intelligence services using the artificial intelligence workflow pipeline.
Dependencies are inferred from the claim text.