Three steps to make your data centre ready for the evolving IoT
Thu 5 Oct 2017 | Michael Adams
Future-proof designs need to take a modular approach incorporating scalable physical architecture, management software and a structured fibre backbone to accommodate the bandwidth and data speed requirements of the IOT era.
In a global environment where customers are dictating the rate of transformation operators must decide on an approach that facilitates change. Select the right type of netcomms architecture and build in efficiency. In this fashion operators can continue to manage capacity for reduced OpEx, whilst retaining operational integrity.
Any data centre design requires a comprehensive and reliable infrastructure framework that bridges the gap between the traditional Facility and IT stacks to ensure a seamless physical to logical convergence. Given the enormous expense of operating data centres, organisations must design and deploy an architecture that is adaptable to meet future needs and scalable to meet changing business demands and optimise IT investments. We all must continue to deliver value throughout the data centre lifecycle. Data centre management tools, consultancy and products that accelerate the design cycle, simplify implementation and enhance operations are essential to improve total cost of ownership (TCO).
Fig 1. The Physical Infrastructure must be easily enhanced and upgraded
Preconfigured Systems
Interoperability and speed of deployment are part of a successful data centre deployment. When physical infrastructure components are brought together from numerous manufacturers, elements such as long lead time components and system inconsistency can quickly extend the time needed for live system functionality. Provision of a preconfigured solution mitigates this potential obstacle by assuring that elements ranging from base enclosures to intelligent monitoring systems arrive complete and are 100 percent tested prior to deployment.
Security and access control, whether at the physical or application level, is another challenge that aligns well with integrated infrastructure. By taking that same preconfigured model and utilising HID card or keypad access control as part of the solution, traditionally less secure colocation deployments are immediately protected right out of the box.
The major pain points that are often encountered are downtime and saving money via energy use reduction. Although not immediately apparent, these considerations often have a knock-on impact on costs in terms of installation and moves, adds and changes (MAC) expenditure.
Structured Fibre Backbone
The physical layer represents around 5 percent of data centre project spend and accounts for 59 percent of downtime once operational. These numbers indicate that numerous installations have been found wanting as infrastructure performance requirements have increased. If we consider that 76 percent of data centre traffic is east to west – machine to machine – then infrastructure rationalisation is imperative, whether as an upgrade path or new build site. These problems are especially prevalent in colocation facilities, where these two issues are top of mind and flow directly to the bottom line of the business.
At the same time, the increasing speed of the network has driven an increased focus on the architecture of the network. When the speed of the network increases, for example from 10G Ethernet to 50G Ethernet, the distance that can be spanned with the cabling links is reduced. Additionally, one needs to consider the number of connectors in the link and what impact this has on the data speed across the network.
High Density Fiber Solutions are allowing customers to maximise and transform their data centre space to accommodate next generation technologies and evolve within IoT (Internet of things) and beyond to IoE (Internet of Everything).
Image – High-Speed Server Shipments will transform the need for Fibre Infrastructure
A key challenge for the date centre operator is understanding what type of fibre to install; single-mode or multimode and if multimode, which Category: OM3, OM4, SignatureCore or OM5. Selecting a fibre type depends on cost, future data rate needs, and maximum channel reach.
Single-mode fibre (SMF) will support all future data rates and channel reaches, but the performance comes at a cost premium in the order of 3 to 5 times that of multimode channels.
For the latest technologies such as, SWDM, wide band fibre such as SignatureCore or OM5 will be required to guarantee performance over the specified channel reaches with a high confidence level. The range of options appears broad, however the operator must have an infrastructure development strategy in order to optimise the investment and reduce the requirement to repeatedly install new cabling moving forward.
As a cohesive set of products cabling can help solve in tandem: network performance, system reliability, energy efficiencies, seamless integration, space and savings, installation and uptime, as well as data transfer speed and speed migration to future demands.
Management Software – monitor and control
By far, the largest proportion of the data centre operations budgets is spent on cooling. Energy efficiency being the greatest opportunity for cost savings, increasing numbers of data centre operators are installing turn-key wireless monitoring and cooling control solutions that utilise intelligent software, leading edge wireless nodes, and professional services to gain real-time visibility into current data centre operating conditions.
Frequently operators cite many reasons for needing to control energy utilization, including being green, PUE compliance, good corporate citizenship, and operations leadership in their industry. Often the key benefit is saving money without putting the data centre at risk. That being the case, one can’t manage what one doesn’t measure. Therefore it is essential to incorporate an effective process: Assess, Instrument, Optimise, and Control. This process enables the customer to address two key pain points – energy savings and risk management.
Image – SmartZone Stack
Understanding this balance and how to maintain it provides the basis for enhanced operator return on investment (ROI). Over-provisioning (or over-sizing), has always been a belt and braces response to the need for data centre resilience. However, it permits waste into the system and results in unnecessary expenditure. Too little capacity can increase the risk of unplanned downtime and reduce the resilience, so crucial in the modern data centre. However, Data Centre Infrastructure Management (DCIM) providers have been guilty of delivering only broad and ill-defined solutions, often lacking a structured development path. This has to some extent tainted the DCIM message, which if delivered and implemented successfully can provide clear and defined benefits to the operator and customers.
Designed and configured correctly DCIM power solutions enable comprehensive energy and physical infrastructure efficiency across data centres, facilities and enterprise estates. These focus visibility of power, capacity and environmental information that is accurate and actionable for operational optimisation. The goal is to quickly provide IT and facility professionals with a transparent view of actual consumption and capacity. These diagnostics will help elevate operational efficiencies, reduce operational expenses (OpEx) and increase the resilience of facilities in support of Service Level Agreements (SLAs).
The cost of operating large data centres requires DCIM to become an integral element in the data centre operation. As part of the total solutions approach customer and suppliers work together through comprehensive DCIM consulting and implementation services. In this way they become focused on achieving manageable, measurable and cost effective DCIM strategies.
Conclusion
Today the data centre operations discussion is framed around increased bandwidth, reduced latency, and energy concerns including; lower power usage and reduced heat generated by the system. Clear understanding of the data centre infrastructure and how this bridge technology enhances the development and sustainability of the site will create more efficient data centres. Taking a holistic view of the entire build, its projected purpose and future needs enables operators to conceive future-proof facilities that have the capability to generate consistent return on investment.
