Intelligent dataset migration and delivery to mobile internet of things devices using fifth-generation networks

• US 10,785,297 B2
• Filed: 10/23/2018
• Issued: 09/22/2020
• Est. Priority Date: 10/23/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Trim, Craig M., Keen, Martin G., Sivakumar, Gandhi, Patel, Kushal, Patel, Sarvesh
• Primary Examiner(s): Rahman, Sm A
• Application Number:
  US16/168,264
• Publication Number:
  US 20200128072A1
• Time in Patent Office: 700 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/047 Probabilistic or stochastic networks
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06N 3/088 Non-supervised learning, e.g. competitive learning
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04L 67/303 Terminal profiles
• CPC Class Codes: H04L 67/5681 Pre-fetching or pre-delivering data based on network characteristics
• CPC Class Codes: H04W 4/023 using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/70 Services for machine-to-machine communication [M2M] or machine type communication [MTC]

Abstract

Migrating and delivering datasets to mobile Internet of Things (IoT) devices is provided. A time is predicted for delivery of one or more datasets to a target intermediate data delivery destination closest to a current geographic location of a mobile IoT device based on context and type of each detected data delivery event and the current geographic location of the mobile IoT device. The one or more datasets are migrated to the target intermediate data delivery destination closest to the current geographic location of the mobile IoT device according to the predicted time. The one or more datasets are delivered to the mobile IoT device from the target intermediate data delivery destination closest to the current geographic location of the mobile IoT device based on the context and the type of each detected data delivery event that corresponds to a particular dataset in the one or more datasets.

Claims

1. A computer-implemented method comprising:

predicting, by a computer, a time for delivery of one or more of one or more datasets to a target intermediate data delivery destination in a set of target intermediate data delivery destinations closest to a current geographic location of a mobile Internet of Things (IoT) device based on context and type of each detected data delivery event and the current geographic location of the mobile IoT device;

migrating, by the computer, the one or more of the one or more datasets to the target intermediate data delivery destination in the set closest to the current geographic location of the mobile IoT device according to the predicted time for delivery;

delivering, by the computer, the one or more of the one or more datasets to the mobile IoT device from the target intermediate data delivery destination in the set closest to the current geographic location of the mobile IoT device based on the context and the type of each detected data delivery event that corresponds to a particular dataset in the one or more datasets;

receiving, by the computer, an indication that the mobile IoT device needs the one or more of the one or more datasets delivered to the mobile IoT device based on historical and real-time data corresponding to the mobile IoT device;

determining, by the computer, a frequency at which the one or more datasets are to be updated to be current; and

retrieving, by the computer, the one or more datasets at the determined frequency.

2. The computer-implemented method of claim 1 further comprising:

detecting, by the computer, data delivery events corresponding to transmission of the one or more datasets to the mobile IoT device;

parsing, by the computer, the data delivery events to determine the context and the type of each detected data delivery event; and

identifying, by the computer, the set of target intermediate data delivery destinations to transmit the one or more datasets to the mobile IoT device as the mobile IoT device moves according to a movement plan corresponding to the mobile IoT device.

3. The computer-implemented method of claim 2, wherein the type of each detected data delivery event is one of an essential data delivery event, a desired data delivery event, and an optional data delivery event.

4. The computer-implemented method of claim 1 further comprising:

retrieving, by the computer, information regarding dataset access patterns of the mobile IoT device from a device profile corresponding to the mobile IoT device;

retrieving, by the computer, other relevant information corresponding to the delivery of the one or more of the one or more datasets to the mobile IoT device; and

determining, by the computer, a movement plan and a movement type corresponding to the mobile IoT device based on retrieved movement information corresponding to the mobile IoT device.

5. The computer-implemented method of claim 1 further comprising:

classifying, by the computer, the one or more datasets based on a movement plan and a movement type; and

detecting, by the computer, a set of data delivery events based on classification of the one or more datasets.

6. The computer-implemented method of claim 1 further comprising:

migrating, by the computer, the one or more of the one or more datasets to the target intermediate data delivery destination in the set closest to the mobile IoT device based on dataset access patterns, other relevant information, movement plan, movement type, and the data delivery events corresponding to the mobile IoT device.

7. The computer-implemented method of claim 1 further comprising:

updating, by the computer, data routing indices based on the delivery of the one or more of the one or more datasets to the target intermediate data delivery destination; and

learning, by the computer, a set of data delivery events related to the delivery of the one or more of the one or more datasets to the target intermediate data delivery destination using a machine learning component of the computer.

8. The computer-implemented method of claim 1, wherein the computer is located in a service orchestration layer of a fifth-generation (5G) telecommunications network, and wherein the computer-implemented method is provided as-a-service in the 5G telecommunications network;

and wherein the computer collects user mobility information from lower level implementations of the 5G telecommunications network to perform data migration operations.

9. A computer system comprising:

a bus system;

a storage device connected to the bus system, wherein the storage device stores program instructions; and

a processor connected to the bus system, wherein the processor executes the program instructions to;

predict a time for delivery of one or more of one or more datasets to a target intermediate data delivery destination in a set of target intermediate data delivery destinations closest to a current geographic location of a mobile Internet of Things (IoT) device based on context and type of each detected data delivery event and the current geographic location of the mobile IoT device;

migrate the one or more of the one or more datasets to the target intermediate data delivery destination in the set closest to the current geographic location of the mobile IoT device according to the predicted time for delivery;

deliver the one or more of the one or more datasets to the mobile IoT device from the target intermediate data delivery destination in the set closest to the current geographic location of the mobile IoT device based on the context and the type of each detected data delivery event that corresponds to a particular dataset in the one or more datasets;

receive an indication that the mobile IoT device needs the one or more of the one or more datasets delivered to the mobile IoT device based on historical and real-time data corresponding to the mobile IoT device;

determine a frequency at which the one or more datasets are to be updated to be current; and

retrieve the one or more datasets at the determined frequency.

10. The computer system of claim 9, wherein the processor further executes the program instructions to:

detect data delivery events corresponding to transmission of the one or more datasets to the mobile IoT device;

parse the data delivery events to determine the context and the type of each detected data delivery event; and

identify the set of target intermediate data delivery destinations to transmit the one or more datasets to the mobile IoT device as the mobile IoT device moves according to a movement plan corresponding to the mobile IoT device.

11. The computer system of claim 9, wherein the processor further executes the program instructions to:

retrieve information regarding dataset access patterns of the mobile IoT device from a device profile corresponding to the mobile IoT device;

retrieve other relevant information corresponding to the delivery of the one or more of the one or more datasets to the mobile IoT device; and

determine a movement plan and a movement type corresponding to the mobile IoT device based on retrieved movement information corresponding to the mobile IoT device.

12. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:

predicting, by the computer, a time for delivery of one or more of one or more datasets to a target intermediate data delivery destination in a set of target intermediate data delivery destinations closest to a current geographic location of a mobile Internet of Things (IoT) device based on context and type of each detected data delivery event and the current geographic location of the mobile IoT device;

migrating, by the computer, the one or more of the one or more datasets to the target intermediate data delivery destination in the set closest to the current geographic location of the mobile IoT device according to the predicted time for delivery;

delivering, by the computer, the one or more of the one or more datasets to the mobile IoT device from the target intermediate data delivery destination in the set closest to the current geographic location of the mobile IoT device based on the context and the type of each detected data delivery event that corresponds to a particular dataset in the one or more datasets;

receiving, by the computer, an indication that the mobile IoT device needs the one or more of the one or more datasets delivered to the mobile IoT device based on historical and real-time data corresponding to the mobile IoT device;

determining, by the computer, a frequency at which the one or more datasets are to be updated to be current; and

retrieving, by the computer, the one or more datasets at the determined frequency.

13. The computer program product of claim 12 further comprising:

detecting, by the computer, data delivery events corresponding to transmission of the one or more datasets to the mobile IoT device;

parsing, by the computer, the data delivery events to determine the context and the type of each detected data delivery event; and

identifying, by the computer, the set of target intermediate data delivery destinations to transmit the one or more datasets to the mobile IoT device as the mobile IoT device moves according to a movement plan corresponding to the mobile IoT device.

14. The computer program product of claim 12 further comprising:

retrieving, by the computer, information regarding dataset access patterns of the mobile IoT device from a device profile corresponding to the mobile IoT device;

retrieving, by the computer, other relevant information corresponding to the delivery of the one or more of the one or more datasets to the mobile IoT device; and

determining, by the computer, a movement plan and a movement type corresponding to the mobile IoT device based on retrieved movement information corresponding to the mobile IoT device.

15. The computer program product of claim 12 further comprising:

classifying, by the computer, the one or more datasets based on a movement plan and a movement type; and

detecting, by the computer, a set of data delivery events based on classification of the one or more datasets.

16. The computer program product of claim 12 further comprising:

migrating, by the computer, the one or more of the one or more datasets to the target intermediate data delivery destination in the set closest to the mobile IoT device based on dataset access patterns, other relevant information, movement plan, movement type, and the data delivery events corresponding to the mobile IoT device.

17. The computer program product of claim 12 further comprising:

updating, by the computer, data routing indices based on the delivery of the one or more of the one or more datasets to the target intermediate data delivery destination; and

learning, by the computer, a set of data delivery events related to the delivery of the one or more of the one or more datasets to the target intermediate data delivery destination using a machine learning component of the computer.