Editorial: Scalable Systems for Big Data Management and Analytics

摘要

The growth of datasets of massive size, rates and complexity, termed "Big Data", has received increased attention from researchers, as well as industry and the open source community in the past few years. Management and analytics of Big Data is critical for achieving scientific and engineering breakthroughs, mining for timely and pertinent information, and decision making. Science and engineering, though, have been dealing with increasing quantities of data in the past decade. These are exemplified by data Grids in early 2000's that were motivated by the peta-bytes of data that were to be generated from the Large Hadron Collider (LHC) that recently came online, to more distributed scientific instruments such as next generation sequencing (NGS) machines that could generate terabytes of data per run in individual labs. Industry too has been increasingly dealing with data from massive web logs that motivated Google's MapReduce programming model, and subsequent work on NoSQL databases.