Published Paper Details:

The dimension of the databases used in today�s firms has been developing at exponential rates day via day. Simultaneously, the want to technique and analyze the large volumes of statistics for business selection making has additionally increased. In several business and scientific applications, there is a need to system terabytes of data in efficient manner on each day bases. This has contributed to the huge records trouble confronted with the aid of the industry due to the lack of ability of traditional database structures and software tools to manage or method the large records units within tolerable time limits. Processing of statistics can include more than a few operations depending on utilization like culling, tagging, highlighting, indexing, searching, faceting, and so forth operations. It is not possible for single or few machines to shop or process this large amount of statistics in a restricted time period. This paper reports the investigational effort on big data problem and its best solution using Hadoop cluster, Hadoop Distributed File System (HDFS) intended for storage and using parallel processing to process big data sets by Map Reduce programming framework. We have completed prototype implementation of Hadoop cluster, HDFS storage and Map decrease framework for giving out large data sets by allowing for prototype of big data application situations. The results attained from various experiments designate favorable results of beyond approach to tackle big data problem.