Obtaining Good Heuristics for Big Data Broadcasting Problem Using Novel Pipeline Approach

Prof. Priyadarshani Kalokhe
2016 International Journal Of Engineering And Computer Science  
Today big data computing is a critical challenge faced by many industries .Everyday up to terabytes to petabytes of the data is generated in the cloud computing paradigm. Thus there is a drastic demand for building a service to distribute, manage and process massive data sets that has risen tremendously. Engineers and researchers are dealing with these large dataset. In this paper, we investigate the big data broadcasting problem for single source node to broadcast a big chunk of data to a set
more » ... f nodes with the objective of minimizing the maximum completion time. These nodes may be present in the same data center or across geo distributed data centers. We model the big data broadcasting problem into a LOCKSTEP BROADCAST TREE (LSBT).The main idea of this model is to define a basic unit of upload bandwidth r, such that a node with capacity c broadcast a data to a set of nodes at the rate r. We divide the broadcast data into m chunks. These data chunks can then be broadcasted using a pipeline approach.
doi:10.18535/ijecs/v5i12.20 fatcat:okrw4enjzvhb7e4hudyqtzswha