Logo des Repositoriums

Auflistung nach Schlagwort "high-performance computing"

1 - 2 von 2
  • Zeitschriftenartikel
    ScaDS Dresden/Leipzig – A competence center for collaborative big data research
    (it - Information Technology: Vol. 60, No. 5-6, 2018) Jäkel, René; Peukert, Eric; Nagel, Wolfgang E.; Rahm, Erhard
    The efficient and intelligent handling of large, often distributed and heterogeneous data sets increasingly determines the scientific and economic competitiveness in most application areas. Mobile applications, social networks, multimedia collections, sensor networks, data intense scientific experiments, and complex simulations nowadays generate a huge data deluge. Nonetheless, processing and analyzing these data sets with innovative methods open up new opportunities for its exploitation and new insights. Nevertheless, the resulting resource requirements exceed usually the possibilities of state-of-the-art methods for the acquisition, integration, analysis and visualization of data and are summarized under the term big data. ScaDS Dresden/Leipzig, as one Germany-wide competence center for collaborative big data research, bundles efforts to realize data-intensive applications for a wide range of applications in science and industry. In this article, we present the basic concept of the competence center and give insights in some of its research topics.
  • Konferenzbeitrag
    Transient numerical simulation for optimization of a water-cooled high-performance computing center with dynamic cooling circuit temperatures – Work-in-progress
    (EnviroInfo 2022, 2022) Bayer, Nils; Kerskes, Henner; Stergiaropoulos, Konstantinos
    Due to the high consumption of electrical energy, data center operators are increasingly aiming for a data center that is as energy-optimized and efficient as possible. The cooling system has a crucial role here. In this context, an innovative control strategy with dynamic cooling circuit temperatures will be investigated. For this purpose, a detailed numerical simulation model of an existing water-cooled HPC data center cooling system was developed. The model was validated using real operating data. It includes the complete heat flow from the rack cooling distribution units to the cooling towers and the district cooling supply. The model can correctly simulate the thermal behavior in detail and is the basis for further investigations and optimization in terms of various criteria like energy or cost efficiency. The modeling and validation approach is presented in this paper.