公开(公告)号：US11816612B1

公开(公告)日：2023-11-14

申请号：US16822251

申请日：2020-03-18

Applicant: Amazon Technologies, Inc.

Inventor： Abhinav Maurya ,  Andrew C. Becker

IPC: G06Q30/00 ,  G06N5/04 ,  G06Q10/0631 ,  G06Q30/0204 ,  H04L67/306 ,  H04L9/40 ,  H04L41/147 ,  G06Q10/0635

CPC classification number: G06Q10/06315 ,  G06N5/04 ,  G06Q10/0635 ,  G06Q30/0204 ,  H04L41/147 ,  H04L63/102 ,  H04L67/306

Abstract: Various embodiments are disclosed for predicting true demand of network services that impose usage constraints. A computing environment may be configured to provide a network service for a user account, where a usage constraint for the network service is imposed on the user account. A truncated usage distribution of the network service may be generated based on usage history data. A demand curve of the network service may be generated for the user account, where the demand curve comprises at least a portion of the truncated usage distribution and a predicted usage of the at least one network service beyond the usage constraint. One or more actions may be performed based on the demand curve, such as increasing the usage constraint.

公开(公告)号：US11470144B1

公开(公告)日：2022-10-11

申请号：US17216431

申请日：2021-03-29

Applicant: Amazon Technologies, Inc.

Inventor： Abhinav Maurya

IPC: H04L67/10 ,  G06F9/455 ,  G06F9/50 ,  H04L43/08 ,  H04L9/40

Abstract: Techniques for optimization-based pool protection for a cloud provider network are described. An exemplary method includes receiving historical usage data of virtual machine instances of a capacity pool of a cloud provider network for each account of a plurality of accounts of the cloud provider network, generating a linearly extrapolated usage, based at least in part on an extrapolating parameter, for each account based at least in part on respective usage percentiles of the virtual machine instances from the historical usage data, determining a usage of the virtual machine instances for each account based at least in part on the linearly extrapolated usage for a same extrapolating parameter value, receiving, by the cloud provider network, a request to launch a computing resource for an account, determining a usage limit for the account based at least in part on the usage for that account, and launching the computing resource when a requested usage for the computing resource is less than or equal to the usage limit and not launching the computing resource when the requested usage for the computing resource is greater than the usage limit.

公开(公告)号：US11245640B1

公开(公告)日：2022-02-08

申请号：US16997615

申请日：2020-08-19

Applicant: Amazon Technologies, Inc.

Inventor： Abhinav Maurya ,  Pawel Cholewinski ,  Kerem Bulbul ,  John David Dunagan

IPC: H04L12/911 ,  G06F9/455 ,  G06F17/18 ,  G06N3/04 ,  G06N20/20 ,  G06N5/02 ,  G06K9/62

Abstract: Techniques for predicting the availability of a resource are described. An exemplary method includes obtaining capacity data indicating an amount of capacity available in a cloud provider network to satisfy the request; generating, using a machine learning model that has been trained based at least in part on an output of an automated historical hindsight learner that is an integer linear program, an approval prediction, wherein the approval prediction indicates that the request is to be approved based on one or more launch parameters of the request and the capacity data; receiving information from a downstream component that controls the resource that the approval prediction is incorrect; and evaluating the incorrect approval prediction using a hindsight learner and predictor explainer.