DATA PARTITIONING IN INTERNET-OF-THINGS (IOT) NETWORK

• US 20150163289A1
• Filed: 09/26/2014
• Published: 06/11/2015
• Est. Priority Date: 12/06/2013
• Status: Active Grant

• Current Assignee: TATA Consultancy Services Limited (Tata Sons Pvt Ltd.)
• Original Assignee: TATA Consultancy Services Limited (Tata Sons Pvt Ltd.)
• Inventors: Paul, Himadri Sekhar, Mukherjee, Arijit, Dey, Swarnava, Pal, Arpan, Banerjee, Ansuman
• Granted Patent: US 10,516,726 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 2209/5017 Task decomposition
• CPC Class Codes: G06F 9/5066 Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs mappping at compile time, see G06F8/451
• CPC Class Codes: H04L 43/0811 by checking connectivity
• CPC Class Codes: H04L 43/0817 by checking functioning
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46

Abstract

A method for data partitioning in an internet-of-things (IoT) network is described. The method includes determining number of computing nodes in the IoT network capable of contributing in processing of a data set. At least one capacity parameter associated with each computing node in the IoT network and each communication link between a computing node and a data analytics system can be ascertained. The capacity parameter can indicate a computational capacity for each computing node and communication capacity for each communication link. An availability status, indicating temporal availability, of each of computing nodes and each communication link is determined. The data set is partitioned into subsets, based on the number of computing nodes, the capacity parameter and the availability status, for parallel processing of the subsets.

Claims

1. A computer implemented method for data partitioning in an internet-of-things (IoT) network, the computer implemented method comprising:

determining, by a processor, number of computing nodes in the IoT network capable of contributing in processing of a data set;

ascertaining, by the processor, at least one capacity parameter associated with each of the computing nodes in the IoT network and with each communication link between a computing node and a data analytics system, the capacity parameter being indicative of a computational capacity for each of the computing nodes and communication capacity for each communication link;

determining, by the processor, an availability status of each of the computing nodes and each communication link, wherein the availability status is indicative of temporal availability of each of the computing nodes and each communication link; and

partitioning, by the processor, the data set into subsets, based on the number of computing nodes, the capacity parameter associated with each computing node and each communication link, and the availability status of each computing node and each communication link, for parallel processing of the subsets.

2. The computer implemented method as claimed in claim 1, wherein the at least one capacity parameter associated with each computing node comprises processing speed of the computing node, available memory and associated bus speed, cache size, and operational load on the computing node at a given point in time.

3. The computer implemented method as claimed in claim 1, wherein the at least one capacity parameter associated with each communication link comprises data transfer rates for the communication link.

4. The computer implemented method as claimed in claim 1, wherein the determining the availability status is at least one of advertisement-based, event-based, and poll-based.

5. The computer implemented method as claimed in claim 1, wherein the determining the availability status comprises ascertaining availability based on historical availability data.

6. The computer implemented method as claimed in claim 1, further comprising scheduling, by the processor, data processing tasks to each of the computing nodes based on the partitioning.

7. The computer implemented method as claimed in claim 1, wherein the ascertaining comprises determining the at least one capacity parameter associated with each communication link between a plurality of computing nodes.

8. The computer implemented method as claimed in claim, 1, wherein the partitioning is at least one of time reduction-based and cost reduction-based.

9. A data analytics system for data partitioning in an internet-of-things (IoT) network, the data analytics system comprising:

a processor;

a capacity module coupled to the processor to,

determine a number of computing nodes in the IoT network capable of contributing in processing of a data set; and

ascertain at least one capacity parameter associated with each of the computing nodes in the IoT network and with each communication link between a computing node and the data analytics system, the capacity parameter being indicative of a computational capacity for each of the computing nodes and communication capacity for each communication link;

an availability module coupled to the processor to determine an availability status of each of the computing nodes and each communication link, wherein the availability status is indicative of temporal availability of each of the computing nodes; and

a partitioning-scheduling module coupled to the processor to partition the data set into subsets, based on the number of computing nodes, the capacity parameter associated with each computing node and each communication link, and the availability status of each computing node and each communication link, for parallel processing of the subsets.

10. The data analytics system as claimed in claim 9, wherein the availability module determines the availability on at least one of event-basis, advertisement-basis, and poll-basis.

11. The data analytics system as claimed in claim 9, wherein the availability module determines the availability based on statistical analysis of historical availability data.

12. The data analytics system as claimed in claim 9, wherein the partitioning-scheduling module schedules data processing tasks to each of the computing nodes based on the partitioning.

13. The data analytics system as claimed in claim 12, wherein the partitioning-scheduling module schedules data processing tasks based on static scheduling techniques.

14. The data analytics system as claimed in claim 9, wherein the partitioning-scheduling module achieves at least one of time reduction-based partitioning and cost reduction-based partitioning of the data set.

15. A non-transitory computer-readable medium having embodied thereon a computer program for executing a method for data partitioning in an internet-of-things (IoT) network, the method comprising:

determining a number of computing nodes in the IoT network capable of contributing in processing of a data set;

determining at least one capacity parameter associated with each of the computing nodes in the IoT network and with each communication link between a computing node and a data analytics system, the capacity parameter being indicative of a computational capacity for each of the computing nodes and communication capacity for each communication link;

ascertaining an availability status of each of the computing nodes and each communication link, wherein the availability status is indicative of temporal availability of each of the computing nodes and each communication link;

partitioning the data set into subsets, based on the number of computing nodes, the capacity parameter associated with each computing node and each communication link, and the availability status of each computing node and each communication link, for parallel processing of the subsets; and

scheduling data processing tasks to each of the computing nodes based on the partitioning.

16. The non-transitory computer-readable medium as claimed in claim 15, wherein the ascertaining the availability status is at least one of advertisement-based, event-based, and poll-based.

17. The non-transitory computer-readable medium as claimed in claim 15, wherein the ascertaining the availability status comprises ascertaining availability based on historical availability data.

18. The non-transitory computer-readable medium as claimed in claim 15, wherein determining the at least one capacity parameter comprises determining the at least one capacity parameter associated with each communication link between a plurality of computing nodes.

19. The non-transitory computer-readable medium as claimed in claim 15, wherein the partitioning is at least one of time reduction-based and cost reduction-based.

20. The non-transitory computer-readable medium as claimed in claim 15, the method further comprising scheduling data processing tasks to each of the computing nodes based on the partitioning.