Multi-Criteria decision analysis for determining prioritization of virtual computing resources for scheduling operations
An apparatus comprises a processing device configured to select prioritization criteria for a plurality of virtual computing resources and to determine, for at least one criterion in the selected prioritization criteria, at least one directional correlation between the at least one criterion and at least one other criterion in the selected prioritization criteria. The processing device is also configured to generate a prioritization of the plurality of virtual computing resources utilizing a multi-criteria decision analysis algorithm. The multi-criteria decision analysis algorithm is based at least in part on the determined at least one directional correlation. The processing device is further configured to perform one or more scheduling operations for the plurality of virtual computing resources based at least in part on the generated prioritization of the plurality of virtual computing resources.
1. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured to perform steps of:
selecting prioritization criteria for a plurality of virtual computing resources;
determining, for at least one criterion in the selected prioritization criteria, at least one directional correlation between the at least one criterion and at least one other criterion in the selected prioritization criteria;
generating a prioritization of the plurality of virtual computing resources utilizing a multi-criteria decision analysis algorithm, the multi-criteria decision analysis algorithm being based at least in part on the determined at least one directional correlation; and
performing one or more scheduling operations for the plurality of virtual computing resources based at least in part on the generated prioritization of the plurality of virtual computing resources.
2. The apparatus of claim 1 wherein determining the at least one directional correlation comprises constructing a weighted decision matrix, wherein each element of the weighted decision matrix comprises a value of a given criterion of the selected prioritization criteria for a given one of the plurality of virtual computing resources multiplied by a weight of the given criterion for the given virtual computing resource.
3. The apparatus of claim 2 wherein the value of the given criterion for the given virtual computing resource comprises a normalized value.
4. The apparatus of claim 2 wherein the given criterion comprises a categorical criterion, and wherein the value of the given criterion for the given virtual computing resource comprises a numeric value obtained by applying a transformation to a categorical value of the categorical criterion.
5. The apparatus of claim 2 wherein the weight of the given criterion for the given virtual computing resource is determined based at least in part on an entropy of the value of the given criterion for the given virtual computing resource.
6. The apparatus of claim 2 wherein determining the at least one directional correlation further comprises constructing a covariance matrix, wherein diagonal element values of the covariance matrix comprise variance measures, and wherein non-diagonal element values of the covariance matrix comprise directional covariance measures.
7. The apparatus of claim 6 wherein determining the at least one directional correlation further comprises:
determining positive and negative separation measure solutions for each of the plurality of virtual computing resources, the positive and negative separation measure solutions being determined based at least in part utilizing Mahalanobis distance, the weighted decision matrix, and the covariance matrix; and
determining a relative closeness rating for each of the plurality of virtual computing resources based at least in part on the determined positive and negative separation measure solutions for each of the plurality of virtual computing resources.
8. The apparatus of claim 7 wherein generating the prioritization of the plurality of virtual computing resources comprises sorting the plurality of virtual computing resources based on the determined relative closeness ratings.
9. The apparatus of claim 1 wherein the multi-criteria decision analysis algorithm comprises a Technique for Order of Preference by Similarity to Ideal Solution (TOPIS) algorithm.
10. The apparatus of claim 1 wherein the one or more scheduling operations are performed in response to detecting one or more events.
11. The apparatus of claim 10 wherein detecting the one or more events comprises detecting one or more power interruption events affecting one or more uninterruptable power supply devices associated with physical infrastructure running virtualization infrastructure hosting the plurality of virtual computing resources, and wherein performing the one or more scheduling operations comprises determining an ordering for shutdown of the plurality of virtual computing resources following detection of the one or more power interruption events affecting the one or more uninterruptable power supply devices.
12. The apparatus of claim 10 wherein detecting the one or more events comprises detecting one or more power interruption events affecting a first set of one or more uninterruptable power supply devices associated with first physical infrastructure running first virtualization infrastructure hosting the plurality of virtual computing resources, and wherein performing the one or more scheduling operations comprises determining an ordering for migration of the plurality of virtual computing resources from the first physical infrastructure running the first virtualization infrastructure to second physical infrastructure running second virtualization infrastructure, the second physical infrastructure being associated with a second set of one or more uninterruptable power supply devices different than the first set of one or more uninterruptable power supply devices.
13. The apparatus of claim 10 wherein detecting the one or more events comprises detecting initiation of one or more backup operations for at least one of a virtualization infrastructure hosting the plurality of virtual computing resources and a physical infrastructure on which the virtualization infrastructure runs, and wherein performing the one or more scheduling operations comprises determining an ordering for backing up the plurality of virtual computing resources.
14. The apparatus of claim 10 wherein detecting the one or more events comprises identifying one or more workloads that are to be scheduled, and wherein performing the one or more scheduling operations comprises determining placement of the identified one or more workloads on the plurality of virtual computing resources based at least in part on the prioritization of the plurality of virtual computing resources.
15. A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device to perform steps of:
selecting prioritization criteria for a plurality of virtual computing resources;
determining, for at least one criterion in the selected prioritization criteria, at least one directional correlation between the at least one criterion and at least one other criterion in the selected prioritization criteria;
generating a prioritization of the plurality of virtual computing resources utilizing a multi-criteria decision analysis algorithm, the multi-criteria decision analysis algorithm being based at least in part on the determined at least one directional correlation; and
performing one or more scheduling operations for the plurality of virtual computing resources based at least in part on the generated prioritization of the plurality of virtual computing resources.
16. The computer program product of claim 15 wherein determining the at least one directional correlation comprises:
constructing a weighted decision matrix, wherein each element of the weighted decision matrix comprises a value of a given criterion of the selected prioritization criteria for a given one of the plurality of virtual computing resources multiplied by a weight of the given criterion for the given virtual computing resource;
constructing a covariance matrix, wherein diagonal element values of the covariance matrix comprise variance measures, and wherein non-diagonal element values of the covariance matrix comprise directional covariance measures;
determining positive and negative separation measure solutions for each of the plurality of virtual computing resources, the positive and negative separation measure solutions being determined based at least in part utilizing Mahalanobis distance, the weighted decision matrix, and the covariance matrix; and
determining a relative closeness rating for each of the plurality of virtual computing resources based at least in part on the determined positive and negative separation measure solutions for each of the plurality of virtual computing resources.
17. The computer program product of claim 16 wherein generating the prioritization of the plurality of virtual computing resources comprises sorting the plurality of virtual computing resources based on the determined relative closeness ratings.
18. A method comprising:
selecting prioritization criteria for a plurality of virtual computing resources;
determining, for at least one criterion in the selected prioritization criteria, at least one directional correlation between the at least one criterion and at least one other criterion in the selected prioritization criteria;
generating a prioritization of the plurality of virtual computing resources utilizing a multi-criteria decision analysis algorithm, the multi-criteria decision analysis algorithm being based at least in part on the determined at least one directional correlation; and
performing one or more scheduling operations for the plurality of virtual computing resources based at least in part on the generated prioritization of the plurality of virtual computing resources;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.
19. The method of claim 18 wherein determining the directional correlations comprises:
constructing a weighted decision matrix, wherein each element of the weighted decision matrix comprises a value of a given criterion of the selected prioritization criteria for a given one of the plurality of virtual computing resources multiplied by a weight of the given criterion for the given virtual computing resource;
constructing a covariance matrix, wherein diagonal element values of the covariance matrix comprise variance measures, and wherein non-diagonal element values of the covariance matrix comprise directional covariance measures;
determining positive and negative separation measure solutions for each of the plurality of virtual computing resources, the positive and negative separation measure solutions being determined based at least in part utilizing Mahalanobis distance, the weighted decision matrix, and the covariance matrix; and
determining a relative closeness rating for each of the plurality of virtual computing resources based at least in part on the determined positive and negative separation measure solutions for each of the plurality of virtual computing resources.
20. The method of claim 19 wherein generating the prioritization of the plurality of virtual computing resources comprises sorting the plurality of virtual computing resources based on the determined relative closeness ratings.