US 12,379,912 B2
Adjustable execution models for processing usage data for remote infrastructure
Shibi Panikkar, Bangalore (IN); Sisir Samanta, Bangalore (IN); and Bhanu Pratap Singh, Mumbai (IN)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Jun. 7, 2022, as Appl. No. 17/834,691.
Prior Publication US 2023/0393829 A1, Dec. 7, 2023
Int. Cl. G06F 8/61 (2018.01)
CPC G06F 8/63 (2013.01) [G06F 8/62 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining a data structure related to at least one subscription request for hardware infrastructure provided by a service provider, wherein the data structure is obtained by at least one first processing device deployed on the hardware infrastructure at a first geographic location, and wherein the data structure comprises information identifying a plurality of function blocks and an execution order of the plurality of function blocks;
analyzing, by the at least one first processing device, the data structure to build an execution model, wherein the execution model comprises (i) the plurality of function blocks for processing usage data associated with the hardware infrastructure and (ii) one or more instructions to execute the plurality of function blocks in the execution order of the plurality of function blocks indicated in the data structure;
processing the usage data for a given time period in accordance with the execution model;
providing, to at least one second processing device of the service provider, execution data comprising at least one of input data and output data for the given time period for at least one or more function blocks of the plurality of function blocks of the execution model, wherein the at least one second processing device of the service provider is at a second geographic location that is remote from the first geographic location, and wherein the at least one second processing device of the service provider applies a machine learning process trained on historical execution data to predict at least one adjustment to at least one of: (i) the plurality of function blocks for at least one additional time period and (ii) the execution order of the plurality of function blocks for the at least one additional time period; and
automatically adjusting the execution model for the at least one additional time period using information obtained from the at least one second processing device of the service provider, wherein the automatically adjusting comprises automatically modifying, based on the at least one adjustment predicted by the machine learning process, at least one of: (i) the plurality of function blocks and (ii) the execution order of the plurality of function blocks;
wherein the computer-implemented method is performed by the at least one first processing device, and wherein the at least one first processing device comprises a processor coupled to a memory.