Data Centres have become an indispensable part of everyday life. For example, when complex applications are initiated on smartphones, the calculations are usually performed in data centres. Whether we are searching the Internet, downloading the weather forecast, or simply ordering from a delivery service. Science and research also relies heavily on data centres in its daily work. Data-intensive high-performance computing (HPC) and cloud computing are already integrated into the daily routines of scientists. Of course, this also applies to the scientific domain of environmental science, where applications and simulations for a wide variety of aspects are executed in data centres. At the same time, the environmental impact of data centre operations must be considered, as data centers are among the large consumers of power (and water). In many places, the expected computing and storage capacities exceed the resources available to operate them and require more than ever an ecologically, economically, socially, but also technologically oriented development.
The possibilities offered by today's data centres come at a price. At some sites, operation is comparable to the energy consumption of a small town. With more energy-efficient systems in terms of performance per computing operation (Watts/FLOPS) more powerful and environmentally compatible systems can already be realized today. In addition to primary cooling, the focus is also on the reuse of the waste heat generated, as well as the optimization of the energy used. Machine learning algorithms are increasingly being used to process the data flow from the sensors in real time. And finally, comparatively short life cycles of systems, which are regularly replaced by more energy-efficient and at the same time more powerful ones, lead to a burden through the production and disposal of the hardware, which can have a significant impact on the environment.
Due to these factors, the operation of data centres is not only financially costly, but above all complex, if they are to be operated as resource-efficiently as possible. Optimizations are not only essential for increasing economic sustainability, but also offer advantages for the environment.
Flexible architectures for data centre design, hybrid approaches to cooling and scalability of new, more efficient technologies are just some of the topics to be discussed in this special track.
Example Topics are (but not limited to):
- Green Data Centre IT and Software
- Optimizing the energy efficiency of systems
- Models for energy and resource efficiency assessment
- Certification of energy consumption and efficiency
- Resource conservation through the use of smart technologies and
- artificial intelligence
- Machine learning to predict and regulate energy consumption in real time
- Efficient facility infrastructures and hybrid cooling technologies
- Secondary use of waste heat and integrated community heating systems
- Scalable, hybrid and flexible compute- and datasystem architectures
- Raise awareness of the need for data centres to operate in a sustainable and resource-efficient manner
- Focused discussions on optimizing energy efficiency
- Exchange of ideas on the reuse of waste heat
Addressed Sustainable Development Goals (SDGs):
Special Track Co-Chairs:
Maximilian Höb, Leibniz Supercomputing Centre, LRZ (Garching, Germany)
Dieter Kranzlmüller, Leibniz Supercomputing Centre, LRZ (Garching, Germany)