direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

DIMA Researchers@VLDB 2015


Members from TU Berlin’s Database Systems and Information Management Group recently presented their research at the 41st International Conference on Very Large Databases (VLDB’15), which was held from August 31 to September 4 in Hawai’I, USA. DIMA contributions included organizing a co-located workshop and presenting in three additional workshops. Among the attendees were DIMA’s Chair: Prof. Dr. Volker Markl, two DIMA Postdocs: Dr. Asterios Katsifodimos & Dr. Tilmann Rabl, and DIMA PhD Student: Viktor Rosenfeld.

Key highlights include:

I. Conference Organization

DIMA Chair Prof. Dr. Volker Markl was program chair of VLDB 2015 and chaired the invited talk sessions. Dr. Katsifodimos and Dr. Rabl chaired research sessions.

II. Workshop Presentations

DIMA members had four presentations in three workshops. Dr. Katsifodimos gave an invited talk in the BIRTE 2015 workshop with the title:[1] Apache Flink: Scalable Stream and Batch Data Processing. Dr. Rabl presented the papers [2] “Enhancing Data Generation in TPCx-HS with a Non-Uniform Random Distribution” and [3] “Big Data Benchmark Compendium” in the TPC TC’15 workshop and Viktor Rosenfeld presented [4] "The Operator Variant Selection Problem on Heterogeneous Hardware" in the ADMS workshop.

III. The 1st Workshop on Big Data Open Source Systems (BOSS ’15)

The BOSS workshop was organized and chaired by Dr. Tilmann Rabl, and provided an introduction to several active, publicly available, open source systems for big data processing. With more than 80 participants, the workshop was a great success.

It was organized in a novel format: after an introductory session, the attendees had the chance to choose between eight individual tutorials. After a panel on big data and supercomputing, chaired by Chaitanya Baru, the tutorials were repeated and attendees could choose a second tutorial. For the first instance of the BOSS workshop, eight diverse systems were chosen: Apache AsterixDB, Apache Flink, Apache Reef, Apache Singa, Apache Spark, Padres, rasdaman, and SciDB. In these tutorials, experts in each of the systems gave details on installation and non-trivial examples of the usage of the presented system.

DIMA was represented by Dr. Asterios Katsifodimos, who led a team of researchers from KTH – Sweden and ELTE/SZTAKI – Hungary, in a hands-on tutorial on Apache Flink.




[1] Katsifodimos, A. and Markl, V.: Apache Flink: Scalable Stream and Batch Data Processing, BIRTE 2015
[2] Nambiar, R.; Rabl , T.;Kulkarni, K.; FrankM.: Enhancing Data Generation in TPCx-HS with a Non-Uniform Random Distribution, TPCTC 2015
[3] Ivanov, T., Rabl, T., Poess, M., Queralt, A., Poelman, J., Poggi, N., & Buell, J.. (2015). Big Data Benchmark Compendium. In 7th TPC Technology Conference
on Performance Evaluation & Benchmarking (TPCTC 2015), 31 August, 2015, Kohala Coast, Hawai.
[4] Rosenfeld V.; Heimel, M.; Viebig, Ch.; Markl, V.: The Operator Variant Selection Problem on Heterogeneous Hardware. ADMS@VLDB 2015: 1-12.

Zusatzinformationen / Extras