.png)
Data centre operators need to prioritise the development of infrastructure capable of accommodating future growth
From personalised shopping experiences to smart transport systems, Artificial intelligence (AI) is becoming ubiquitous, fundamentally changing how we live and work. And, as our need for computing power grows, data centres are becoming even more crucial in enabling this technological revolution.
To meet the escalating demand, data centre operators are prioritising the development of infrastructure capable of not only satisfying current needs but also accommodating future growth. This necessitates a holistic approach to data centre design, emphasising adaptability, energy efficiency, and reliability to effectively navigate the dynamic tech landscape.
Pressure on Powers
Ireland is a popular destination for data centres with more than 75 facilities operating in the country and more under construction and planned. According to the Central Statistics Office, electricity used in Ireland has risen by 400% since 2015, and consumption by data centres alone has increased by 31% between 2021 and 2022.
This power usage is unlikely to slow down any time soon. Driven by the adoption of specialised processors necessary for handling complex tasks, the rise of AI is changing High Performance Computing (HPC). And according to Omdia’s 2022 Data Center Thermal Management Market Analysis report, typical data centre computer racks are expected to increase from 5 kW to 7 kW today (equivalent to the size of a small residential backup generator) to 50 kW or more in the not-too-distant future.
Adapting to this situation demands that data centres adopt creative solutions that are capable of delivering increasing computing power, whilst employing energy-efficient methods. This includes expanding the use of alternative energy, smart grids, hybrid grids and innovative data centre designs to deliver reliable solutions for customers, while lessening the negative impacts on our planet.
It is evident that data centres are facing an unprecedented demand for computing power, so alongside this AI transformation, alternative energy sources and energy storage play pivotal roles in shaping the evolving landscape. The rise of specialised AI processors providing the required computing power has only heightened the need for energy efficiency, and alternative sources such as solar and wind power should be used to meet the growing demand for more sustainable electricity generation and consumption. These options not only provide environmentally friendly solutions but also contribute to grid stability and enable efficient resource use.
The strategic focus on power efficiency extends beyond immediate operational needs. By prioritising power efficiency, data centres can not only tackle the demands posed by growing AI workloads but also contribute to a more environmentally conscious and sustainable future.
Optimising Thermal Management
The heightened heat generated by the advancements in processor technology such as high performance Central Processing Units (CPU’s) and Graphics Processing Units (GPU’s) present another challenge. As supercomputers continue to shrink and become more power-dense, the data centre industry must look at how it can keep them cool for efficiency and optimum performance, whilst concurrently tapping alternative power sources to support the increased energy demand. In recent years, data centre thermal management designs have evolved significantly and there is currently a renewed interest in chilled water options offering two rack-level liquid cooling choices.
The first option involves directing liquid to the server itself, using a room-based heat exchanger to expel heat back into the air. This modular system allows seamless integration without substantial changes to existing infrastructure. The second option introduces a Cooling Distribution Unit (CDU), directly circulating liquid from the server or GPU, connecting to a chilled water system.
It is most likely that both air-cooled and liquid-cooled solutions are likely to coexist due to persisting air-cooling needs within liquid-cooled servers because even within liquid-cooled servers, elements necessitating air cooling persist, highlighting the nuanced nature of the evolving thermal management landscape.
However, the technical intricacies of cooling systems must also consider sustainability. Implementing efficient thermal management solutions, such as waste heat recovery to support the circular economy, not only enables optimal performance but also contributes to reducing the environmental footprint of data centres. By minimising energy consumption and maximising resource utilisation, innovative cooling practices play a pivotal role in mitigating the ecological impact of data centre operations.
A holistic approach
In preparation for even more AI workloads, data centre operators are rethinking their strategies. They're not just aiming to minimise energy consumption but also to boost overall performance. This journey toward sustainability requires a comprehensive approach, which involves integrating energy-efficient hardware and capitalising on advancements in processor technology.
At the core of these efforts lies a commitment to align data centre operations with global efficiency goals. Sustainability goes beyond simply optimising efficiency; it's about responsibly managing resources, embracing renewable energy sources, minimising waste, supporting the circular economy and reducing the industry's environmental footprint.
In the pursuit of future-ready design, collaboration is key. Engaging stakeholders from various disciplines allows a deep understanding of data centre needs, fostering innovation and adaptability. As data centres evolve with denser configurations and rapid technological advancements, holistic design goes beyond technical specifications. It involves efficient decision-making and proactive engagement with industry experts to navigate the challenges of AI-driven transformations.
Integrating diverse perspectives allows data centre owners to navigate these complexities with agility and foresight. Collaboration enables operators to tap into collective expertise, identifying innovative solutions and anticipating emerging trends for adaptability.
Moreover, technology interchangeability is crucial. With the tech landscape evolving rapidly, data centres must prepare for seamless integration of new technologies. Balancing CPU and GPU environments is essential for adaptability over the long term, achieved through a flexible infrastructure that accommodates diverse landscapes and evolving demands.
In essence, the strategic alignment of innovation and efficiency within data centres not only reinforces their role as critical infrastructure in the digital age but also underscores their commitment to responsible stewardship of resources. In doing so, they're not only meeting the challenges posed by AI workloads but also paving the way for a more environmentally conscious digital future.
By Sam Bainborough, Sales Director EMEA-Strategic Segment Colocation & Hyperscale at Vertiv
For more information, please visit: http://www.vertiv.com