Recommendation system for replication policies
One example method includes generating a policy recommendation that can be implemented in data protection systems. The generation of the policy is based on information garnered from multiple distinct users. Initially, the users are clustered based on their user profiles. The virtual machines operated by these users are then clustered based on virtual machine profiles. This allows, for each resulting cluster, policy recommendations to be made based on a policy distribution of the corresponding cluster.
1. A method, comprising:
producing a user profile for each user of a data protection system and producing a virtual machine profile for each virtual machine of each user;
clustering the users based on the user profiles of the users to generate first clusters, each of the first clusters associated with a plurality of virtual machines;
within each of the first clusters, clustering the virtual machines based on the virtual machine profiles to produce second clusters;
determining a policy distribution for each of the second clusters; and
generating recommendation policies for at least some of the users based on the policy distribution.
2. The method of claim 1 , further comprising creating the user profile, the user profile including n features.
3. The method of claim 2 , further comprising creating the virtual machine profile, the virtual machine profile defining m features.
4. The method of claim 1 , further comprising determining which of the virtual machines are associated with policies that are outliers based on the policy distribution.
5. The method of claim 4 , further comprising recommending a most common policy to users associated with the outliers based on the policy distribution.
6. The method of claim 5 , further comprising generating the recommendation policies proactively without a request from the users.
7. The method of claim 6 ,
wherein the user profiles include features associated with the users including one or more of company sector, size, location, amount of protected virtual machines, number of data protection systems, user domain, and usage, and
wherein the virtual machine profiles include features including one or more of operating system, space, number of processors, memory, group relative size, relative creation date, and usage.
8. The method of claim 1 , further comprising generating the recommendation based on use of the recommendation by other users.
9. The method of claim 1 , further comprising assigning a policy to a new user based on a user profile of the new user and a cluster to which the new user is assigned.
10. The method of claim 1 , wherein the users are different users and wherein each of the users has at least one data protection policy at one production site.
11. A non-transitory storage medium having stored therein instructions that are executable by one or more hardware processors to perform operations comprising:
producing a user profile for each user of a data protection system and producing a virtual machine profile for each virtual machine of each user;
clustering the users based on the user profiles of the users to generate first clusters, each of the first clusters associated with a plurality of virtual machines;
within each of the first clusters, clustering the virtual machines based on the virtual machine profiles to produce second clusters;
determining a policy distribution for each of the second clusters; and
generating recommendation policies for at least some of the users based on the policy distribution.
12. The non-transitory storage medium of claim 11 , further comprising creating the user profile, the user profile including n features.
13. The non-transitory storage medium of claim 12 , further comprising creating the virtual machine profile, the virtual machine profile defining m features.
14. The non-transitory storage medium of claim 11 , further comprising determining which of the virtual machines are associated with policies that are outliers based on the policy distribution.
15. The non-transitory storage medium of claim 14 , further comprising recommending a most common policy to users associated with the outliers based on the policy distribution.
16. The non-transitory storage medium of claim 15 , further comprising generating the recommendation policies proactively without a request from the users.
17. The non-transitory storage medium of claim 16 ,
wherein the user profiles include features associated with the users including one or more of company sector, size, location, amount of protected virtual machines, number of data protection systems, user domain, and usage, and
wherein the virtual machine profiles include features including one or more of operating system, space, number of processors, memory, group relative size, relative creation date, and usage.
18. The non-transitory storage medium of claim 11 , further comprising generating the recommendation based on use of the recommendation by other users.
19. The non-transitory storage medium of claim 11 , further comprising assigning a policy to a new user based on a user profile of the new user and a cluster to which the new user is assigned.
20. The non-transitory storage medium of claim 11 , wherein the users are different users and wherein each of the users has at least one data protection policy at one production site.