Predictive Maintenance in the Data Centre: The Power of AI

With insights from experts at NTT Data and Vertiv, we consider how AI-powered predictive maintenance is a game-changer for the data centre

Predictive maintenance is becoming an increasingly important part of the data centre industry as, with the power of AI, businesses are presented with an even clearer picture than ever before.

Put simply, predictive maintenance refers to a more preemptive approach to data centre operation by utilising AI technology to predict what needs repairing. According to Deloitte, predictive maintenance is able to increase enterprise productivity by 25%, reduce breakdowns by 70% and lower maintenance costs by 25% - as opposed to reactive maintenance.

With industry-leading advice from experts at Vertiv and NTT Data, this month we examine the impact of AI predictive maintenance on the data centre industry, and how it enables sales growth and improved sustainability.

Optimising data centre efficiency and resource management

A valuable solution for data centre operators, predictive maintenance works to help spot when a piece of equipment is about to fail and is quickly becoming a more integrated part of data centre infrastructure. As the digital transformation landscape continues to evolve, industry leaders anticipate that predictive maintenance will boast an even greater presence in data centre facilities – in part thanks to the fast development of AI technologies.

By leveraging the power of AI, data centre operators can implement predictive maintenance strategies that go beyond traditional approaches, which can help to deliver optimal performance, minimise risks and reduce downtime.

Flora Cavinato, Global Service Product Portfolio Director at Vertiv, says: “Predictive maintenance plays a vital role in enhancing data centre efficiency and resource management. AI not only aids in predicting and preventing potential equipment failures, maintenance needs, and environmental risks, but also facilitates adaptive infrastructure optimisation. 

AI algorithms learn from data collected over time. As a result, Cavinato says that these algorithms can recommend adjustments to optimise the use of critical equipment. This can be utilised by businesses to reduce energy waste and streamline operations, with the AI being able to align with the changing dynamics of the infrastructure and improve overall performance. 

“Monitoring and management systems should empower operators and decision-makers with actionable insights derived from AI analysis,” Cavinato says. “This collaborative approach minimises the risk of errors and enhances decision-making processes. It allows human operators to focus on strategic tasks while AI handles routine monitoring, creating a synergistic relationship that maximises operational resilience in the digital era.”

Facilitating data centre growth in line with digital transformation

In line with businesses seeking to advance their technological evolutions, AI ultimately aims to ensure that predictive maintenance scales with data centre growth.

Likewise, the power of other new technologies such as digital twins and IoT devices can also be leveraged to predict equipment failures and schedule preventive maintenance to physical infrastructure. This proactive approach to getting data can lead to reduced repair costs, in addition to extending equipment life.

“By its very nature, AI needs an enormous amount of data to learn and evolve, so as data centres grow, more data will be available for AI to use,” Cavinato says. “At the same time, predictive maintenance will naturally scale. This means that the more dense and varied data population there is, the better the data trending, pattern recognition, insight learning and predictions.

“The technology evolution driving new product design that incorporates the enablement of data communication as a critical driver will enable algorithms to scale, thanks to enhanced data breadth and quality of the data. Through algorithm evolution, the precision of the prediction related to data trending can continuously improve enabling better learning.”

Bill Wilson, Chief Environmental Sustainability Officer and Head of Data & Intelligence Solutions at NTT DATA UK&I, has seen the power of predictive maintenance in other industries such as transport, defence, and telecoms – and says he would like to see similar optimisations and problem-solving methods applied in the energy sector. 

“In manufacturing, audio information and audio learning models can partly replace the trained engineer who knows when a machine does not sound healthy,” he explains. “Of course, the same predictive techniques can be used to gather data from several sources to inform condition maintenance. This requires less predictive power because it’s more concerned with accurately understanding the overall condition of an asset based on multiple inputs. 

“Sensors can give false readings, but techniques such as cohort analysis allow these anomalies to be identified by comparing each sensor with others doing a similar role.”

Using AI to move towards a more sustainable data centre

Data centre operators can also use AI-led predictive maintenance to support their sustainability initiatives, especially when it comes to curbing energy use and reducing carbon emissions. As AI becomes more frequently used within data centre operations, issues of transparency and sustainability will need continually addressing.

Energy-efficiency is expected to be a driving force for the development of the data centre industry over the next twelve months. With data centres accounting for roughly 2% of the world’s greenhouse gas emissions - a figure that is expected to rise to 8% by 2030 - industry-leading companies are having to quickly harness new and innovative solutions to combat rising energy demands. 

The technology can end up playing a pivotal role by identifying opportunities to enhance energy efficiency, reduce resource wastage and make operations more efficient. Cavinato states that predictive maintenance can also help to evolve data lakes to robust predictive tools.

“Incorporating environmental considerations into infrastructure management involves optimising energy usage, reducing carbon footprints, and implementing eco-friendly technologies and processes,” she says. “Environmental responsibility also extends to the energy sources powering critical infrastructure. 

“By leveraging AI in the data lake, organisations can analyse power consumption patterns and explore opportunities to integrate alternative energy sources. This not only aligns with eco-friendly initiatives but also enhances operational resilience by diversifying the energy mix and reducing dependence on conventional power grids.”


******

Make sure you check out the latest edition of Data Centre Magazine and also sign up to our global conference series - Tech & AI LIVE 2024

******

Data Centre Magazine is a BizClik brand

Share

Featured Articles

How Kove Unlocks Transformative Growth for Your Organisation

Kove helps clients maximise infrastructure performance using software-defined memory. Learn how

US Data Centres Confront the Strain of Rising Power Demands

Data centres across the United States (US) are preparing for a continued surge in power demand, as customers seeking technology like AI strain power grids

Data storage, memory and generation with IEEE’s Tom Coughlin

We speak with Tom Coughlin, President and CEO of IEEE, about power-hungry AI and memory technologies within the telco market

Digital Realty Continues Renewable Rollout to the US

Google Axion Processors: A New Era of Data Centre Efficiency

MWC24: Harnessing AI to Modernise Telcos with Tech Mahindra