Large Data Throughput Optimization Model with Full C order Model Parallel Flow Number Prediction Optical Domain.

In order to address the low efficiency of traditional data-intensive extensible computing system in data source utilization and data transmission, a throughput optimization model of application layer based on parallel flow number prediction has been proposed. Firstly, for the purpose of improving accuracy of parallel flow number prediction and utilization efficiency of bottleneck link, selection method for equivalent parallel flow number has been designed; secondly, an full C order model has been established by using partial C order model and all of second order model as reference, and a low-sampling throughout optimization algorithm framework has been designed to reduce computational complexity; last, experiment based on data set of different sizes shows that prediction model of full C order model parallel flow number is more applicable to data transmission and is more efficient. [ABSTRACT FROM AUTHOR]