Grid-aware approach to data statistics, data understanding and data preprocessing
Alexander Wöhrer, Lenka Nováková, Peter Brezány, A Min Tjoa · International Journal of High Performance Computing and Networking · 2009
In recent years the focus of grid computing shifted towards more data intensive applications, increasingly needing access to various public and private databases. Relocating the code for Data Preprocessing (DPP) closer towards the data source is the overall task of the D³Gframework. This paper presents the data service side architecture to gather Data Statistics (DS) on-the-fly, use them in remote DPP methods on query results and gather exact continuous DS for whole tables inside a database. The performance results are showing low running costs for the continuous DS and the feasibility of the service side DPP functionality.