Edge function-guided artificial intelligence request routing

A computer system comprising:

• a memory;
• and
• a processor in communication with the memory, wherein the computer system is configured to perform a method comprising:
• applying a machine learning model to predictors of cloud endpoint hydration to determine hydration levels of a plurality of cloud endpoints, of a hybrid cloud environment, that provide artificial intelligence (AI) processing, wherein a hydration level of a cloud endpoint indicates a capacity of the cloud endpoint to service additional requests for AI processing;
• determining, for each edge component of a plurality of edge components of the hybrid cloud environment and each cloud endpoint of the plurality of cloud endpoints, alternative flow paths between the edge component and the cloud endpoint, the alternative flow paths being differing routes for routing data between the edge component and the cloud endpoint, and the alternative flow paths being of varying flow rates determined based at least in part on the hydration levels of the plurality of cloud endpoints;
• and
• dynamically deploying edge functions on one or more edge components of the plurality of edge components, the edge functions configuring the one or more edge components to alternate among the alternative flow paths available in routing AI processing requests from the one or more edge components to target cloud endpoints of the plurality of cloud endpoints wherein a maximum flow path having a maximum flow rate among the alternative flow paths and a minimum flow path having a minimum flow rate among the alternative flow paths are included in the alternative flow paths among which the one or more edge components are configured to alternate.

A computer program product comprising:

• a computer readable storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising:
• applying a machine learning model to predictors of cloud endpoint hydration to determine hydration levels of a plurality of cloud endpoints, of a hybrid cloud environment, that provide artificial intelligence (AI) processing, wherein a hydration level of a cloud endpoint indicates a capacity of the cloud endpoint to service additional requests for AI processing;
• determining, for each edge component of a plurality of edge components of the hybrid cloud environment and each cloud endpoint of the plurality of cloud endpoints, alternative flow paths between the edge component and the cloud endpoint, the alternative flow paths being differing routes for routing data between the edge component and the cloud endpoint, and the alternative flow paths being of varying flow rates determined based at least in part on the hydration levels of the plurality of cloud endpoints;
• and
• dynamically deploying edge functions on one or more edge components of the plurality of edge components, the edge functions configuring the one or more edge components to alternate among the alternative flow paths available in routing AI processing requests from the one or more edge components to target cloud endpoints of the plurality of cloud endpoints, wherein a maximum flow path having a maximum flow rate among the alternative flow paths and a minimum flow path having a minimum flow rate among the alternative flow paths are included in the alternative flow paths among which the one or more edge components are configured to alternate.