Artificial intelligence-based cache distribution
Techniques are disclosed for data management techniques using artificial intelligence-based cache distribution within a distributed information processing system. For example, a cohesive and distributed machine learning approach between the same or similar customer data centers and products predict optimal data needed at each customer data center, and intelligently synchronize or federate the data between customer data centers and a core data center using a combination of customized caching and push techniques according to one or more customer behavior patterns.
1. An apparatus comprising:
a first processing platform comprising at least one processor coupled to at least one memory configured to execute program code, wherein the first processing platform is operatively coupled to at least a second processing platform which is operatively coupled to at least a group of third processing platforms and each of the third processing platforms are located at one or more sites at which one or more products are used, and wherein the first processing platform is configured to:
receive group usage prediction data generated using at least one machine learning algorithm by the second processing platform based on usage prediction data generated using at least one machine learning algorithm by each of the group of third processing platforms based on data related to the usage of the one or more products;
generate product prediction data from the group usage prediction data using at least one machine learning algorithm;
generate a cache data set responsive to the product prediction data; and
dispatch the cache data set to one or more of the second processing platform and ones of the third processing platforms;
wherein the first processing platform is further configured to classify the group of third processing platforms using at least one machine learning algorithm and based on the group prediction data and historical procurement and provisioning data related to the one or more products to identify one or more behavior patterns.
2. The apparatus of claim 1 , wherein the at least one machine learning algorithm used at each of the third processing platforms comprises at least one of a linear regression algorithm and a random forest classification algorithm.
3. The apparatus of claim 1 , wherein the at least one machine learning algorithm used at each of the first processing platform and the second processing platform comprises at least one of a linear regression algorithm and a Bayesian model algorithm.
4. The apparatus of claim 1 , wherein the at least one machine learning algorithm at the second processing platform comprises a support vector machine classification algorithm.
5. The apparatus of claim 1 , wherein the first processing platform dispatches the cache data set to one or more of the second and ones of the third processing platforms using one or more of a point-to-point delivery protocol, a multicast delivery protocol, and a coordinated multipoint delivery protocol.
6. The apparatus of claim 1 , wherein the dispatched cache data set relates to one or more of procurement, provisioning and support related to the one or more products.
7. The apparatus of claim 1 , wherein the first processing platform comprises a cloud-based computing network.
8. The apparatus of claim 1 , wherein the second processing platform comprises a fog-based computing network.
9. The apparatus of claim 1 , wherein each of the third processing platforms comprises an edge-based computing network.
10. A method comprising:
in a system comprising a first processing platform operatively coupled to at least a second processing platform, the second processing platform operatively coupled to at least a group of a third processing platforms, and the third processing platform located at one or more sites at which one or more products are used;
receiving at the first processing platform group usage prediction data from the second processing platform;
generating at the first processing platform product prediction data from the group usage prediction data using at least one machine learning algorithm;
generating at the first processing platform a cache data set responsive to the product prediction data;
dispatching from the first processing platform the cache data set to one or more of the second and ones of the third processing platforms; and
classifying at the first processing platform the group of third processing platforms using at least one machine learning algorithm and based on the group prediction data and historical procurement and provisioning data related to the one or more products to identify one or more behavior patterns.
11. The method of claim 10 , further comprising:
receiving at the second processing platform usage prediction data from each of the group of third processing platforms;
generating at the second processing platform the group usage prediction data from the usage prediction data from each of the group of third processing platforms using at least one machine learning algorithm; and
sending from the second processing platform the group usage prediction data to the first processing platform.
12. The method of claim 11 , further comprising:
collecting data at each of the third processing platforms related to usage of the one or more products;
generating at each of the third processing platforms the usage prediction data from the collected data using at least one machine learning algorithm; and
sending from each of the third processing platforms the usage prediction data to the second processing platform.
13. The method of claim 10 , wherein the first processing platform dispatches the cache data set to one or more of the second and ones of the third processing platforms using one or more of a point-to-point delivery protocol, a multicast delivery protocol, and a coordinated multipoint delivery protocol.
14. The method of claim 10 , wherein the dispatched cache data set relates to one or more of procurement, provisioning and support related to the one or more products.
15. The method of claim 10 , wherein the first processing platform comprises a cloud-based computing network, the second processing platform comprises a fog-based computing network, and each of the third processing platforms comprises an edge-based computing network.
16. A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs in a system comprising a first processing platform operatively coupled to at least a second processing platform, the second processing platform operatively coupled to at least a group of a third processing platforms, and the third processing platform located at one or more sites at which one or more products are used, wherein the program code when executed causes the system to:
receive at the first processing platform group usage prediction data from the second processing platform;
generate at the first processing platform product prediction data from the group usage prediction data using at least one machine learning algorithm;
generate at the first processing platform a cache data set responsive to the product prediction data;
dispatch from the first processing platform the cache data set to one or more of the second and ones of the third processing platforms; and
classify at the first processing platform the group of third processing platforms using at least one machine learning algorithm and based on the group prediction data and historical procurement and provisioning data related to the one or more products to identify one or more behavior patterns.
17. The computer program product of claim 16 , wherein the program code when executed further causes the system to:
receive at the second processing platform usage prediction data from each of the group of third processing platforms;
generate at the second processing platform group usage prediction data from the usage prediction data from each of the group of third processing platforms using at least one machine learning algorithm; and
send from the second processing platform the group usage prediction data to the first processing platform.
18. The computer program product of claim 17 , wherein the program code when executed further causes the system to:
collect data at each of the third processing platforms related to usage of the one or more products;
generate at each of the third processing platforms the usage prediction data from the collected data using at least one machine learning algorithm; and
send from each of the third processing platforms the usage prediction data to the second processing platform.
19. The computer program product of claim 16 , wherein the first processing platform dispatches the cache data set to one or more of the second and third processing platforms using one or more of a point-to-point delivery protocol, a multicast delivery protocol, and a coordinated multipoint delivery protocol.
20. The computer program product of claim 16 , wherein the first processing platform comprises a cloud-based computing network, the second processing platform comprises a fog-based computing network, and each of the third processing platforms comprises an edge-based computing network.