In this second of 2 articles, we look at data centre maintenance and management, specifically from a remote perspective. What are the benefits of remote? Why should it be considered?
It is remarkable how reliable and resilient digital infrastructure, including data centres, has proved to be during the global pandemic despite significant growth in usage and restrictions imposed on travel, site access and data centre maintenance activities. This Covid spotlight begins to question the need for the traditional 24×365 staffing models currently considered standard.
Lessons and experience gained in the current crisis can inform the models needed for remote unmanned Edge sites as dependency on these sites increases.
To support this it is certainly the case that a well designed and built data centre has an increasingly low risk of failure so a permanent team of engineers based on site may not be necessary. Additionally one of the biggest overheads for data centre operators are 24×365 site engineering teams.
Covid restrictions have increasingly shown that these may not be necessary, providing the right monitoring and management tools are available. This is also exactly what we need to effectively and reliably manage remote dark sites as would normally be associated with an Edge deployment.
The typical Edge data centre will be unstaffed and follow a dark site operating model with a smaller footprint than traditional core data centres. Covid has demonstrated that even large sites can be reliably operated with restricted access and reduced personnel as proved by the resilience of our digital infrastructure though a very difficult period.
Without full time engineers on site, detecting potential problems simply by being there and walking the site (feeling increased temperature in certain areas for instance), new operating models and predictive maintenance techniques need to be applied to ensure operational reliability in addition to the standard preventative maintenance plans.
However, predictive data centre maintenance can really only successfully be deployed if the correct level of monitoring is available that also has the insight, trending and analytical capabilities which allow reliable prediction of failure or impending capacity constraints. This is especially important in unmanned remote site where there may be a significant delay in responding to a problem and getting an engineer on the scene.
Site visits will still need to be performed but with greater purpose and range of planned activities / upgrades / installations, depth of knowledge and insight based on far more effective data gathering, analysis and accuracy than would be required for traditional manned data centre sites.
These systems need to be so much more than an enhanced Building Management System (BMS). Rather than merely offering alerts or allowing the changing of set-points based on human calculation or experience, as with a BMS, these systems require the intelligence to not only predict issues but also to provide recommendations and solutions. Offering the correct set-point values rather than trying (typically unsuccessfully) to balance these manually based on limited information.
As well as being more than a simple BMS new monitoring and management systems overcome the difficulties associated with using ‘embedded’ software systems remotely due to security concerns, limited functionality, lack of integration (and age) of those incumbent systems.
BMS and other types of traditional systems are typically wired into a network and often need expensive and cumbersome local client software to offer remote access, whereas the newer, more lightweight and recently developed software platforms can be accessed via simple browsers and subject to that the security restrictions typically applied to this type of access.
These newer systems can also be air gapped from the onsite systems to alleviate security concerns, and are available anytime, even if the facility is physically inaccessible due to Covid restrictions, distance, travel disruption, even terrorism etc.
These tools offer genuine ROI and minimal management resource overhead while solving problems rather than merely alerting. Despite the reduced cost and overhead these remote monitoring and management solutions are still able to offer a consistent interface across the entire estate and same level of granularity from very small rooms to the largest data centres making all sites easier to manage. Allowing fewer people to manage far more, even at a distance.
Remote Monitoring and Management tools with the attributes described in these articles are also a catalyst in getting all the stakeholders to work together around core business processes involving people, facilities and IT infrastructure. The benefits include reduced operating costs, improved utilisation of deployed resources and assets, increased reliability, improved energy savings and deferment of capital costs.