Virtual world subgroup determination and segmentation for performance scalability
View Patent ↗A system and method of decreasing server loads and, more particularly, to decrease server load by automatically determining subgroups based on object interactions and computational expenditures. The system includes a plurality of servers; a subgroup optimization module configured to segment a plurality of objects into optimal subgroups; and a server transfer module configured to apportion one or more of the optimal subgroups between the plurality of servers based on a load of each of the plurality of servers. The method includes determining a relationship amongst a plurality of objects; segmenting the objects into optimized subgroups based on the relationships; and apportioning the optimized subgroups amongst a plurality of servers based on server load.
1. A system for reducing server loads, comprising:
a plurality of servers;
a subgroup optimization module configured to:
assign respective costs to interactions amongst a plurality of objects in a virtual universe; and
segment the plurality of objects into subgroups based on the respective costs of the interactions; and
a server transfer module configured to apportion one or more of the subgroups between the plurality of servers,
wherein:
the subgroup optimization module comprises a communication cost estimator configured to assign respective communication costs to the interactions, and
the subgroup optimization module comprises a computation cost estimator configured to determine object computation consumption between each of the plurality of servers.
2. The system for reducing server loads of claim 1 , wherein the plurality of objects include at least one of a plurality of avatars and a plurality of assets.
3. The system for reducing server loads of claim 1 , wherein one or more of the interactions are real-time communications between one or more of the plurality of objects.
4. The system for reducing server loads of claim 1 , wherein the communication cost estimator determines the respective communication costs assigned to the interactions based on respective characteristics of the interactions.
5. The system for reducing server loads of claim 1 , wherein the computation cost estimator obtains a total computation cost for each of the plurality of objects by averaging the object computational consumption over an adjustable time period.
6. The system for reducing server loads of claim 5 , wherein the subgroup optimization module segments the first object and the second object into one of the subgroups based on the total communication cost for the link between the first object the second object.
7. A system for reducing server loads, comprising:
a plurality of servers;
a subgroup optimization module configured to:
assign respective costs to interactions amongst a plurality of objects in a virtual universe; and
segment the plurality of objects into subgroups based on the respective costs of the interactions; and
a server transfer module configured to apportion one or more of the subgroups between the plurality of servers,
wherein:
the subgroup optimization module comprises a communication cost estimator configured to assign respective communication costs to the interactions, and
the communication cost estimator determines a total communication cost for a link between a first object and a second object based on the respective communication costs of one or more of the interactions that involve the first object and the second object.
8. A method for reducing server load, comprising:
determining interactions amongst a plurality of objects in a virtual universe;
assigning respective interaction costs to the interactions;
segmenting the objects into subgroups based on the respective interaction costs; and
apportioning one or more of the subgroups between a plurality of servers based on a load of each of the plurality of servers,
wherein:
the assigning the respective interaction costs to the interactions comprises assigning a respective communication cost to the interactions, and
the assigning the respective communication cost to the interactions comprises determining a total communication cost for a link between a first object and a second object based on the respective communication costs of one or more of the interactions that involve the first object and the second object.
9. The method for reducing server load of claim 8 , wherein the plurality of objects include at least one of a plurality of avatars and a plurality of assets.
10. The method for reducing server load of claim 8 , wherein one or more of the interactions are real-time communications between one or more of the plurality of objects.
11. The method for reducing server load of claim 8 , wherein the assigning the respective communication cost to the interactions comprises determining the respective communication costs based on respective characteristics of the interactions.
12. The method for reducing server load of claim 8 , wherein the segmenting the objects into subgroups comprises segmenting the first object and the second object into one of the subgroups based on the total communication cost for the link between the first object the second object.
13. A method for reducing server load, comprising:
determining interactions amongst a plurality of objects in a virtual universe;
assigning respective interaction costs to the interactions;
segmenting the objects into subgroups based on the respective interaction costs; and
apportioning one or more of the subgroups between a plurality of servers based on a load of each of the plurality of servers,
wherein:
the assigning the respective interaction costs to the interactions comprises assigning a respective communication cost to the interactions, and
the method further comprises determining an object computation consumption between each of the plurality of servers.
14. The method for reducing server load of claim 13 , further comprising determining a total computation cost for each of the plurality of objects by averaging the object computational consumption over an adjustable time period.