A*STAR’s Institute of High-Performance Computing (IHPC) and a Singapore-based data centre solutions company have developed an energy-efficient cooling system, which uses an innovative heat exchange and phase change approach that can reduce energy consumption at data centres by up to 50%. Using Computational Fluid Dynamics, IHPC accelerated and optimised the cooling system’s product design and validated its performance.
A growing digital economy means the demand for data centres will increase, supported by emerging technologies in 5G, Artificial Intelligence (AI) and the Internet of Things (IoT). In Singapore, about 60 data centres are accounting for about 7 per cent of the country’s total electricity consumption in 2020. With the region becoming one of the fastest-growing data centre hubs globally, Southeast Asia will also continue to see significant investment in digital infrastructure and data centre development.
However, data centres are intensive users of water and electricity, and their cooling systems typically use an estimated 35 to 40 per cent of the total power required to run a data centre. The Singapore government informed the industry of a temporary pause on the development of new data centres to ensure their growth in a sustainable manner and with a reduced carbon footprint.
Data centres are in great demand as data form the backbone of the digital economy. However, they also contribute significantly to the carbon footprint. IHPC is pleased to work with the company to help data centres operate more sustainably using such novel cooling solutions, leveraging our capabilities in computational fluid dynamics and high-performance computing. This public-private partnership is testament to A*STAR’s efforts to encourage businesses to adopt innovative technologies to become more competitive, and pivot into new markets and new products.
– Dr Lim Keng Hui, Executive Director of A*STAR’s of IHPC
Recognising these opportunities and the need for more effective cooling solutions, IHPC and ERS co-developed the cooling system, a novel cooling solution using phase change physics that transforms the way to cool data centres.
Compared to conventional computer room air conditioning (CRAC) cooling systems, the cooling system provides targeted cooling to remove heat from servers directly. The system also recycles and redeploys the waste heat discharged by servers for the refrigerant phase change cycle. Such novel designs create substantial energy savings and thus lower carbon emissions.
The cooling system is also modular and scalable to address cooling requirements. This eliminates typical high overhead costs such as raised flooring, row cooling equipment, booster fans, refrigerant pumps or compressors, and the use of aisle containment systems.
As reported by OpenGov Asia, a team of researchers from the Agency for Science, Technology and Research’s (A*STAR) Genome Institute of Singapore (GIS) have developed a software that extracts RNA modifications (an additional layer of the information above the genetic molecule RNA) from genomics data. Their research was published in Nature Biotechnology.
For RNAs, chemical molecules may change the function of the same RNA. These RNA modifications are widespread, but because they do not change the letters of the RNA, they are very difficult to identify. More than 100 RNA modifications are known to play different roles in cells. Some of these RNA modifications are associated with disease risk, while others are used in mRNA vaccines.
By collaborating with the National University Cancer Institute, Singapore (NCIS), the team successfully detected the m6A RNA modification using the AI tool in multiple myeloma cancer patient samples, showing the AI tool’s potential for large-scale clinical analyses. The scientists have been interested in studying m6A modification in myeloma as this may have important clinical and therapeutic implications for patients with poor outcomes. Now with the AI tool, they have an important tool to facilitate their studies.