Big Data Query Processing

Description

The goal of this project is to perform a proof-of-concept for Big Data query processing with an international industry partner. In particular, we investigate if a Big Data solution based on Apache Hadoop and Cloudera’s Impala can handle the complex query workload of our industry partner subject to minimal response times (near real-time). The main tasks of the project are as follows: Systematic and rigorous evaluation of the query response times, scalability analysis (very large data sets being accessed by hundreds of concurrent users) and evaluation of various fault tolerance scenarios. The results of the project can be found in the following technical report:
pd.zhaw.ch/publikation/upload/207101.pdf