US 11,755,433 B2
Method and system for health rank based virtual machine restoration using a conformal framework
Shelesh Chopra, Bangalore (IN); Mahantesh M. Ambaljeri, Bangalore (IN); Rahul Deo Vishwakarma, Bangalore (IN); Gopal Singh, Pleasantville, CA (US); and Parmeshwr Prasad, Bangalore (IN)
Assigned to EMC IP Holding Company LLC, Hopkinton, MA (US)
Filed by EMC IP Holding Company LLC, Hopkinton, MA (US)
Filed on Dec. 22, 2020, as Appl. No. 17/131,450.
Prior Publication US 2022/0197762 A1, Jun. 23, 2022
Int. Cl. G06F 11/20 (2006.01); G06F 9/455 (2018.01); G06N 20/00 (2019.01)
CPC G06F 11/203 (2013.01) [G06F 9/45558 (2013.01); G06F 11/2025 (2013.01); G06F 2009/45591 (2013.01); G06F 2009/45595 (2013.01); G06F 2201/815 (2013.01); G06N 20/00 (2019.01)] 16 Claims
OG exemplary drawing
 
1. A method for virtual machine restoration, comprising:
detecting a failure of a source virtual machine;
in response to detecting the failure:
identifying a set of available virtual machines;
collecting performance metrics for each available virtual machine in the set of available virtual machines;
assigning, based on the performance metrics, each available virtual machine in the set of available virtual machines to one selected from a group consisting of a healthy class and an unhealthy class;
ranking, in descending order and to obtain a ranked subset of available virtual machines, a subset of the set of available virtual machines based on a health score calculated for each available virtual machine in the subset of the set of available virtual machines, wherein each available virtual machine in the ranked subset of available virtual machines is a member of the healthy class;
selecting a target virtual machine from the ranked subset of available virtual machines; and
restoring, onto the target virtual machine, at least a defined process once hosted on the source virtual machine,
wherein the health score calculated for each available virtual machine in the subset of the set of available virtual machines is provided using a conformal framework, and
wherein assignment of each available virtual machine in the set of available virtual machines, to one selected from the group consisting of the healthy class and the unhealthy class, resulted from machine learning classification performed through cluster analysis.