US 12,147,838 B1
Systems and methods for dynamic allocation of compute resources via a machine learning-informed feedback sequence
Richard Keith Wellum, Fuquay-Varina, NC (US); John Hardin Gelpi, Apex, NC (US); and Alexander Daehnrich, Rougemont, NC (US)
Assigned to SAS INSTITUTE INC., Cary, NC (US)
Filed by SAS INSTITUTE INC., Cary, NC (US)
Filed on Apr. 4, 2024, as Appl. No. 18/627,375.
Claims priority of provisional application 63/534,753, filed on Aug. 25, 2023.
Int. Cl. G06F 9/50 (2006.01); G06F 9/455 (2018.01); G06F 9/48 (2006.01); G06F 11/30 (2006.01)
CPC G06F 9/5027 (2013.01) [G06F 9/455 (2013.01); G06F 9/45533 (2013.01); G06F 9/45558 (2013.01); G06F 9/48 (2013.01); G06F 9/4843 (2013.01); G06F 9/4856 (2013.01); G06F 9/4881 (2013.01); G06F 9/50 (2013.01); G06F 9/5005 (2013.01); G06F 9/5044 (2013.01); G06F 9/5083 (2013.01); G06F 9/5088 (2013.01); G06F 11/30 (2013.01); G06F 2009/4557 (2013.01)] 36 Claims
OG exemplary drawing
 
1. A computer-program product embodied in a non-transitory machine-readable storage medium storing computer instructions that, when executed by one or more processors, perform operations comprising:
obtaining an analytical request that specifies an analytical task to be performed using computing resources of an adaptive analytics compute service, wherein the analytical task defines a data analysis operation to be performed on a target dataset;
determining, by the adaptive analytics compute service, an initial set of compute resources for executing the analytical request based on a width of the target dataset, a height of the target dataset, and a type of the analytical request;
deploying, by the adaptive analytics compute service, a compute environment for executing the analytical request based on the initial set of compute resources;
observing utilization data of the initial set of compute resources during a period of executing the analytical request within the compute environment; and
commencing a machine learning-informed feedback sequence for autonomously adapting the compute environment, wherein at least one iteration of the machine learning-informed feedback sequence includes:
determining that a subset of the target dataset, less than a full size of the target dataset, is being used to perform the data analysis operation during the period of executing the analytical request;
generating, using one or more machine learning models, a proposed set of compute resources based on at least the utilization data and determining that the subset of the target dataset is being used to perform the data analysis operation, wherein the proposed set of compute resources includes one or more variations of an extent or a configuration of the initial set of compute resources;
encoding, based on the proposed set of compute resources, a set of instructions for automatically adapting the compute environment, wherein the set of instructions, when executed, enables a target container orchestration service in implementing the proposed set of compute resources; and
in response to executing the set of instructions, automatically adapting the compute environment to an adapted compute environment, wherein:
the adapted compute environment includes the proposed set of compute resources, and
automatically adapting the compute environment to the adapted compute environment includes a scaling operation that causes a decrease in compute core containers allocated to the compute environment based on determining that only the subset of the target dataset is being used to perform the data analysis operation.