A newly installed data center in the NEST research building is not only used for data processing, but also helps to heat the entire building. The server facility is part of the EU research project “ECO-Qube”, which is investigating the integration of data centers into building systems and their energy-efficient operation.
A click on the Internet leaves traces. Not only in the network itself, but also in the form of a large ecological footprint. Because even though all our data supposedly floats in the cloud, physical data centers are needed to process and store it, and these consume huge amounts of energy – a significant portion of which is used to cool the facilities. The big tech giants are now well aware of their responsibilities, investing generously in renewable energy and looking for ways to optimize the energy efficiency of their server farms. One of these paths leads to the Arctic Circle, for example, where some of the largest data centers are now located. The cold temperatures there help reduce the amount of energy needed to cool the equipment.
However, with the latest digital trends such as artificial intelligence (AI), “augmented reality” or “Internet of Things” (IoT) come the next challenges: The volumes of data to be processed are increasing immeasurably, and at the same time, reactions are required in real time – without latency. To achieve this, the processing location of the data must once again move much closer to the point of origin of the same. For example, in the form of a micro data center in the neighborhood. In the best case, however, this local data center is not only used for data processing, but – connected to the energy supply – is also used to heat the buildings. A field test with micro-computing centers in the NEST research building at Empa and at two other sites in Turkey and the Netherlands aims to explore the potential of this idea.
Intelligent cooling
The project, called “ECO-Qube,” is supported by the EU’s Horizon 2020 funding program and brings together research and industry partners from Switzerland, Turkey, Spain, Germany, the Netherlands and Sweden. “Our goal is to reduce both the energy demand and CO2 emissions of small data centers by one-fifth each,” says Çağatay Yılmaz, Innovation Manager at Turkish IT solutions provider Lande and project manager of “ECO-Qube.” According to the Sustainable Digital Infrastructure Alliance, another project partner, conventional data centers often only operate at a utilization rate of around 15 percent. Nevertheless, the servers constantly need power and are cooled. To counter this problem, the cooling of the “ECO-Qube” data centers is made intelligent: The sensor data of the individual IT components are accumulated in Big Data structures and help to ensure that the heat distribution within the facility is accurately recorded at all times. Artificial intelligence combines this data with airflow simulations so that cooling can be highly targeted. At the same time, the computing loads in the three test data centers in Switzerland, Turkey and the Netherlands are distributed in such a way that all three facilities can be operated as energy-efficiently as possible.
Use waste heat
The three data centers will be integrated directly into the energy systems of the surrounding neighborhoods and will be powered by renewable energy whenever possible. In NEST, for example, the power for operating the data center comes from the photovoltaic systems of the NEST units and the mobility demonstrator move, among others. The waste heat from the data center is discharged to the existing medium- or low-temperature network. In winter, it thus directly feeds the building’s heating system and, throughout the year, simultaneously serves as a source for a heat pump that provides domestic hot water.
“For us, it is interesting to look at the micro data center not just as an electrical consumer, but as a dynamic component in the overall system that we can use so that calculations take place when it makes ecological sense. Coupling the electrical and thermal world with the IT infrastructure and data processing offers great optimization potential towards sustainable operation,” says Philipp Heer, head of the “Energy Hub” (ehub) at Empa.
The project will last about three years. Upon completion, the team hopes to be able to provide guidelines for planners and building operators to help them integrate data centers into buildings and neighborhoods in an energy-efficient manner.