CPC H04L 67/1097 (2013.01) [G06N 20/00 (2019.01); H04L 41/0816 (2013.01); H04L 41/16 (2013.01); H04L 67/51 (2022.05)] | 20 Claims |
1. A cloud-based point-to-point data transfer system, comprising: one or more physical processors configured by machine-readable instructions to:
obtain, by the transfer system, a request for a transfer of data from a sending system to a receiving system, the request including at least one current sending system parameter indicative of one or more current characteristics of at least one of the sending system or the data as it is stored at the sending system prior to the transfer that has an impact on one or both of read size or read latency;
obtain, by the transfer system, at least one receiving system parameter indicative of one or more current characteristics of at least one of the receiving system or the data as it is to be stored at the receiving system according to the transfer;
determine, by the transfer system, a value of at least one current network parameter;
determine, by the transfer system and based on a machine learning algorithm, a value of at least one transfer parameter for performing the transfer of the data from the sending system to the receiving system based at least in part on one or more of the at least one current sending system parameter, the least one current receiving system parameter, and the value of the at least one current network parameter, the at least one transfer parameter comprises a transport layer parameter, and the determination comprises setting a value of the transport layer parameter by choosing between different transport protocols;
perform, by the transfer system, the transfer of the data between the sending system and the receiving system based at least in part on the value of the at least one transfer parameter;
obtain, by the transfer system, results information indicative of one or more characteristics of the transfer; and
provide, by the transfer system, the results information to the machine-learning algorithm.
|