IoT and the hyper-sensed data centre dividend

With the introduction of a new generation of IoT enabled sensors, the fully-sensed data centre is on the horizon, bringing with it indispensable improvements in monitoring, management and maximisation of facility performance, writes Dean Boyle, CEO of EkkoSense

Despite the best efforts of their operations teams, even the best run data centres will inevitably end up with cooling, power and space issues to resolve. With cooling now representing around 30 percent of a data centre’s operating costs, it’s particularly important that organisations are able to concentrate on providing the kind of thermal optimisation approach that can remove thermal risk and unlock cooling energy savings.

However, if you’re serious about optimising your data centre performance then you really need to know what’s happening right now – not what was going on yesterday or last week. It’s only when data rooms are carefully mapped with all the appropriate data fields that operations teams can really start to benefit from a real-time understanding of their overall data centre performance.

That’s why – for true cooling optimisation – it’s necessary for data centres to start going further and getting more granular in a hurry. Because when a data room is carefully mapped with appropriate thermal data fields – right down to an individual rack or server level –  a whole new level of understanding and cooling efficiency becomes possible which in turn enables the benefits to be maximised.

Getting serious about sensing

To address this, organisations need to work out how to build a rack-level detailed map of their data centre estate that displays all their cooling and thermal performance in real-time.

It’s only by then combining this kind of granular cooling and thermal data with smart monitoring and analysis software that organisations can start to track their data centre cooling loads in real-time – a valuable intelligence to enable thermal optimisation decisions to be made.

To achieve this kind of true thermal optimisation requires a proven, safe process that’s based on thousands of real-time sensors and expert spatial models that combine to remove the uncertainty from data centre cooling. Until recently this presented a barrier due to the market cost of sensors.

With today’s typical data centre cooling unit utilisation rates still only averaging 34 percent, the reality is that organisations continue to spend far more than they need to on expensive data centre cooling systems.  To address this, they need to find ways to become much more precise in their operation – and this certainly shouldn’t involve uniformly applying space, power, cooling and other inputs across their data rooms.

Securing new levels of precision is a key driver behind ASHRAE’s recommendation that data centre operations teams equip each of their racks with as many as three temperature sensors. Having surveyed hundreds of individual data centre rooms at EkkoSense, we estimate that sensing at ASHRAE’s suggested level would typically require around 10x more sensors than are typically deployed in today’s data centres.

Expanding sensing to stay within ASHRAE’s recommended limits

ASHRAE suggests that simply positioning temperature sensors on data centre columns and walls is no longer enough, and that data centre operators should – as a minimum – be collecting temperature data from at least one point for every 3m to 9m of rack aisle.

It also goes on to suggest that unless components such as IT racks actually have their own dedicated thermal sensors, there’s realistically no way for them to stay within target thermal limits.

Unfortunately, it’s rare for data centres to sense to this level. That’s probably a key reason why, when we recently analysed over 70 major UK data centres, we found that 11 percent of racks weren’t actually ASHRAE thermally compliant. That’s a problem, because without comprehensive sensing you really can’t determine which of your business-critical racks are compliant and which aren’t.

However, by combining this kind of sensor installation with the real-time optimisation capabilities of the latest 3D visualisation and monitoring software, you can now not only ensure ASHRAE compliance across your entire data centre estate, but also start to unlock significant data centre cooling energy savings.

For example, we have found that by adopting this kind of approach we can now deliver an impressive average energy saving of at least 23 percent, with a typical payback of less than 12 months.

Once this real-time, rack level data is collected and analysed by a 3D spatial model, specialist software can accurately determine the thermal quality of a location, and start to identify what needs to be done to improve that quality and even to warn operators of specific areas that are at risk.

Evolving towards software-enabled real-time data centre optimisation to monitor, manage and maximise

Having access to real-time, rack-level environmental data also starts to provide exactly the data platform needed for the kind of software-enabled real-time decision-making and scenario planning capabilities that data centres need if they’re to evolve towards true cooling optimisation – effectively removing the uncertainty from data centre cooling and ensuring that all of your racks remain ASHRAE thermally compliant.

This kind of fully-sensed data centre is an essential element on the journey towards truly AI-managed precision data centres. At EkkoSense this has already started with the creation of intelligent feedback loops that analyse airflow data into ‘zone of influence’ modules that we can then combine with standard BMS systems to enable automated, zone-by-zone data centre cooling.

Factor in cooling and power capacity planning coverage, as well as real-time ‘what-if?’ simulation support, and organisations can start to see exactly where and how they’re currently under or over-cooling across their data centre estate.