Paper 2

Compression Planner for Time Series Database with GPU Support

Authors: Piotr Przymus and Krzysztof Kaczmarski

Volume 15 (2014)

Abstract

Nowadays, we can observe increasing interest in processing and exploration of time series. Growing volumes of data and needs of efficient processing pushed research in new directions. This paper presents a lossless lightweight compression planner intended to be used in a time series database system. We propose a novel compression method which is ultra fast and tries to find the best possible compression ratio by composing several lightweight algorithms tuned dynamically for incoming data. The preliminary results are promising and open new horizons for data intensive monitoring and analytic systems.