Accelerating data centre optimisation through machine learning and AI
CEO & Co Founder
My first article in this innovations series highlighted the five trends that are expected to drive further IT innovation across the data centre sector through 2022 and beyond. In this article I’ll focus on AI and Automation, and explain why a more focused approach around machine learning and AI is likely to be most applicable for data centre operations.
Almost all the analyst firms cite AI and Automation as one of the IT sector’s key transformational trends. Most CIOs also find it hard to overlook what they perceive as the clear benefits that could result from more aggressive data centre automation. At EkkoSense we believe that, rather than treat machine learning and AI as a universal solution, data centre teams in 2022 should focus on those areas – such as cooling optimisation and airflow management – where these technologies can be applied and deliver significant results. But instead of trusting to unwieldy automation solutions, we believe the real opportunities will come from having a much more light–touch DCIM approach – one where data centre operations teams are continuously supported by AI-powered, actionable recommendations.
EkkoSense is the only organisation to directly address the fundamental challenge of allowing operations teams to gather and visualise data centre cooling, power, and space data at a granular level, while incorporating machine learning. We do this by bringing together an exclusive mix of technology and capabilities – including an innovative SaaS platform, low-cost Internet of Things (IoT) sensors, machine learning, AI analytics and PhD-level thermal skills.
Greater monitoring granularity means that we now have over a billion optimisation data points in our system, gathered from a broad range of whitespace and data centre environments. Being able to overlay and process this volume of data points allows operators to work through highly complex mechanical load, thermal load and power load datasets in real time, enabling us to provide real insights to directly translate into operational benefits and savings. And that doesn’t require a whole load of extra resource to be in place to prove that data.
Drawing on our machine learning and smart AI algorithms we have created a powerful 3D visualisation and analytics platform that’s particularly easy for operations teams to implement, use and understand (short taster video here). This enables customers tovisualise airflow management improvements, manage complex capacity decisions, and quickly highlight any worrying trends in cooling performance.
Our unique Cooling Advisor machine learning and AI-powered advisory software tool also provides operators with specific instruction sets on actions they can take to optimize their environment and reduce risk. Cooling Advisor provides valuable proactive thermal advice, that’s always backed by clear recommendations that enable operations teams to make immediate improvements.
Rather than relying on unwieldy automation solutions, Cooling Advisor enables a more light-touch approach to DCIM with operations teams supported by AI-powered, actionable recommendations for greater human auditability. Operators always maintain control over decisions, with the ability to discount Cooling Advisor recommendations where they have additional site insights. And instead of just monitoring and alerting, Cooling Advisor is able to translate data collected into valuable management information that enables data centres to stay optimised and secure both cooling energy and cost savings.
By following the clear recommendations offered by Cooling Advisor’s algorithms, data centre teams can keep on track in their journey to secure an average 30% cooling energy savings. We’ve also built-in a range of active risk mitigation features that provide clearly defined steps, clear back-out mechanisms and logging of all user inputs within Cooling Advisor to give teams the confidence they need to take advantage of our recommendations. Now it’s even easier for operations teams to deploy machine learning and AI techniques to make sure their critical facilities stay optimised on a year-round basis.
To find out more about how EkkoSense harnesses the power of AI and Automation, check out this series of articles by my colleague Tracy Collins who examines the practical issues surrounding AI-based optimisation. The next article in this series will focus on the importance of data granularity, detailing how Internet of Things connectivity and the latest ultra-low-cost wireless sensors are transforming monitoring and enabling an entirely new approach to data centre optimisation.