Cloud-based authority to enhance point-to-point data transfer with machine learning

• US 10,735,516 B1
• Filed: 02/15/2019
• Issued: 08/04/2020
• Est. Priority Date: 02/15/2019
• Status: Active Grant

• Current Assignee: Signiant Incorporated
• Original Assignee: Signiant Incorporated
• Inventors: Barnes, Shane Daniel, Belo, Andrew Olatunde, Hamilton, Ian Kennedy
• Primary Examiner(s): Nguyen, Angela
• Application Number:
  US16/278,032
• Time in Patent Office: 536 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 41/0816 the condition being an adaptation, e.g. in response to network events
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• CPC Class Codes: H04L 43/0829 Packet loss
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 43/0888 Throughput
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/51 Discovery or management thereof, e.g. service location protocol [SLP] or web services

Abstract

Systems and methods to facilitate cloud-based point-to-point data transfer via machine learning are described herein. A request for a transfer of data between a sending system and a receiving system may be obtained. Receiving system information for the receiving system may be obtained. Values of transfer parameters for performing the transfer may be determined through machine-learning. The transfer may be performed based on the determined values. Results of the transfer may be obtained and provided to the machine-learning algorithm to further train the algorithm.

Claims

1. A system configured to facilitate cloud-based point-to-point data transfer via machine learning, the system comprising:

one or more physical processors configured by machine-readable instructions to;

obtain a request for a transfer of data between a sending system and a receiving system, the request including sending system information for the sending system, the sending system information including values of sending system parameters, the sending system parameters including at least a sending system identifier parameter and a data identifier parameter, wherein the data identifier parameter specifies one or more characteristics of the data to be transferred;

obtain receiving system information for the receiving system, the receiving system information including values of receiving system parameters, the receiving system parameters including a receiving system identifier parameter and/or a configuration parameter;

determine a value of one or more network parameters based on information related to one or more prior transfers;

determine values of transfer parameters for performing the transfer of the data between the sending system and the receiving system based on the sending system information, the receiving system information, and network information, the network information including at least the determined value of the one or more network parameters, wherein the transfer parameters include one or more transport layer parameters and one or more application layer parameters;

perform the transfer of the data between the sending system and the receiving system based on the values of the transfer parameters;

obtain results information, the results information including one or more of a transfer throughput of the transfer, a transfer duration of the transfer, or the receiving system information; and

provide the results information to a machine-learning algorithm.

2. The system of claim 1, wherein the machine-learning algorithm is unsupervised goal-based machine learning.

3. The system of claim 1, wherein the values of the transfer parameters are determined based further on an output of the machine-learning algorithm.

4. The system of claim 1, wherein a value of the sending system identifier parameter comprises an IP address or host name of the sending system, and wherein a value of the data identifier parameter comprises one or more of a storage type, a container prefix, or a file system path.

5. The system of claim 1, wherein the receiving system parameters include a receiving system identifier parameter and a configuration parameter, wherein a value of the receiving system identifier parameter comprises an IP address or host name of the receiving system, and wherein a value of the configuration parameter comprises one or more of a quantity of CPUs or virtual CPUs, a speed of CPUs, a quantity of network interfaces, a network interface speed, a quantity of memory, or a quantity of GPUs.

6. The system of claim 1, wherein the network parameters comprise one or more of network latency, network bandwidth, or network packet loss.

7. The system of claim 1, wherein a value of the transport layer parameter specifies a transport algorithm, and wherein a value of the application layer parameter specifies a quantity of parts to be transferred and/or a part size of individual parts.

8. The system of claim 1, wherein the one or more physical processors are further configured by the machine-readable instructions to:

obtain read impact information, the read impact information identifying sending system information having an impact on one or both of read size or read latency; and

wherein the values of the transfer parameters are determined based further on the read impact information.

9. The system of claim 1, wherein the one or more physical processors are included in a cloud-based server that is separate and distinct from the receiving system and the sending system.

10. The system of claim 1, wherein the request is obtained from the sending system or the receiving system.

11. The system of claim 1, wherein the data includes a file and/or an object.

12. The system of claim 1, wherein the one or more physical processors are further configured by the machine-readable instructions to:

select a transport mechanism from a set of multiple transport mechanisms to utilize when transferring the data between the sending system and the receiving system based on the values of the transfer parameters, wherein the transfer of the data between the sending system and the receiving system is performed based on the selected transport mechanism.

13. The system of claim 12, wherein the transfer parameters include multiple transport layer parameters, the multiple transport layer parameters comprising at least a first transport layer parameter related to a first transport mechanism and a second transport layer parameter related to a second transport mechanism, wherein to select the transport mechanism from the set of multiple transport mechanisms to utilize when transferring the data between the sending system and the receiving system, the one or more physical processors are further configured by the machine-readable instructions to:

compare the first transport layer parameter related to the first transport mechanism with the second transport layer parameter related to the second transport mechanism, wherein the transport mechanism selected is based on the comparison.

14. A method to facilitate cloud-based point-to-point data transfer via machine learning, the method comprising:

obtaining a request for a transfer of data between a sending system and a receiving system, the request including sending system information for the sending system, the sending system information including values of sending system parameters, the sending system parameters including at least a sending system identifier parameter and a data identifier parameter, wherein the data identifier parameter specifies one or more characteristics of the data to be transferred;

obtaining receiving system information for the receiving system, the receiving system information including values of receiving system parameters, the receiving system parameters including a receiving system identifier parameter and/or a configuration parameter;

determining a value of one or more network parameters based on information related to one or more prior transfers;

determining values of transfer parameters for performing the transfer of the data between the sending system and the receiving system based on the sending system information, the receiving system information, and network information, the network information including at least the determined value of the one or more network parameters, wherein the transfer parameters include one or more transport layer parameters and one or more application layer parameters;

performing the transfer of the data between the sending system and the receiving system based on the values of the transfer parameters;

obtaining results information, the results information including one or more of a transfer throughput of the transfer, a transfer duration of the transfer, or the receiving system information; and

providing the results information to a machine-learning algorithm.

15. The method of claim 14, wherein the machine-learning algorithm is unsupervised goal-based machine learning.

16. The method of claim 14, wherein the values of the transfer parameters are determined based further on an output of the machine-learning algorithm.

17. The method of claim 14, wherein a value of the sending system identifier parameter comprises an IP address or host name of the sending system, and wherein a value of the data identifier parameter comprises one or more of a storage type, a container prefix, or a file system path.

18. The method of claim 14, wherein the receiving system parameters include a receiving system identifier parameter and a configuration parameter, wherein a value of the receiving system identifier parameter comprises an IP address or host name of the receiving system, and wherein a value of the configuration parameter comprises one or more of a quantity of CPUs or virtual CPUs, a speed of CPUs, a quantity of network interfaces, a network interface speed, a quantity of memory, or a quantity of GPUs.

19. The method of claim 14, wherein the network parameters comprise one or more of network latency, network bandwidth, or network packet loss.

20. The method of claim 14, wherein a value of the transport layer parameter specifies a transport algorithm, and a value of the application layer parameter specifies a quantity of parts to be transferred and/or a part size of individual parts.

21. The method of claim 14, the method further comprising:

obtaining read impact information, the read impact information identifying sending system information having an impact on one or both of read size or read latency; and

wherein the values of the transfer parameters are determined based further on the read impact information.

22. The method of claim 14, wherein the method is performed by a cloud-based server that is separate and distinct from the receiving system and the sending system.

23. The method of claim 14, wherein the request is obtained from the sending system or the receiving system.

24. The method of claim 14, wherein the data includes a file and/or an object.

25. The method of claim 14, the method further comprising:

selecting a transport mechanism from a set of multiple transport mechanisms to utilize when transferring the data between the sending system and the receiving system based on the values of the transfer parameters, wherein the transfer of the data between the sending system and the receiving system is performed based on the selected transport mechanism.

26. The method of claim 25, wherein the transfer parameters include multiple transport layer parameters, the multiple transport layer parameters comprising at least a first transport layer parameter related to a first transport mechanism and a second transport layer parameter related to a second transport mechanism, wherein selecting the transport mechanism from the set of multiple transport mechanisms to utilize when transferring the data between the sending system and the receiving system comprises:

comparing the first transport layer parameter related to the first transport mechanism with the second transport layer parameter related to the second transport mechanism, wherein the transport mechanism selected is based on the comparison.