Mark Gaydos, Chief Marketing Officer
According to TechTarget: “The Internet of Things (IoT) is a system of interrelated computing devices, mechanical and digital machines, objects, animals or people that are provided with unique identifiers and the ability to transfer data over a network without requiring human-to-human or human-to-computer interaction.”
Gartner has reported that in 2015, there were 4.9 billion connected “things” in use. This number is expected to increase to 25 billion by 2020. (Some analysts put this estimate closer to 50 billion.) These devices consist of not only the ubiquitous smart phones and computers, but smart homes, cars, sensors, displays, controls, alarms, medical devices and much more.
Gartner also predicts that IoT’s powerful force for “business transformation, and its disruptive impact will be felt across all industries and all areas of society.”
This is presumably a great leap forward towards a more efficient lifestyle that will make our lives better, safer and easier.
But let’s not forget what all these connected devices mean – countless bytes of data, created each and every day. All that data has to go somewhere, to be stored, processed and made accessible. Although the number of data centers is not increasing, their size and density are.
So how can you make sure that your data center is ready for this onslaught of data? Here are 5 steps to make sure that your data center is prepared for the IoT.
1. Understand What Questions you Want Answered
IoT is not an end in itself. It’s a path to a destination. What are you most concerned about? What are you trying to accomplish? Where are you trying to go? How will you get there? What are your initial steps going to be?
Start with one thing. You don’t have to do it all at once, nor should you attempt to; it’s a process that requires achievable goals.
A great first step is a complete inventory of what’s in your data center and what it’s doing. You can’t improve anything you’re not measuring.
Discover where your assets are, what work they are performing and the energy and space they are using. It’s also a good idea to know the lifecycle stages of each of your assets. At a certain point, it gets more expensive to keep old, inefficient assets running than to do a tech refresh and retire them.
Do you know the temperature throughout your data center? If you have real-time insight into data room temperature, you cannot only keep equipment from overheating, you can actually rearrange assets or loads to eliminate hot and cold spots. You may even be able to raise the ambient temperature and save on cooling.
2. Ensure You Have the Ability to Consume Massive Amounts of Data
Numbers 2 and 3 are both related to scalability. A gigantic amount of information is generated by the IoT every day. You need to determine:
- How fast are you polling?
- How much of the information that you’re polling needs to be stored long-term?
- Do you have a Big Data Repository?
- Can you support all this data?
- Can you store it?
- Do you have the personnel to handle the volume?
3. Ensure You Have the Capacity to Store Massive Amounts of Data
After you know where your assets are and what they’re doing, analyze the capacity of those assets to determine how much capacity is being used and how much is left. If some devices are underutilized, consolidation could be undertaken to save space and optimize energy efficiency. You may even be able to delay or completely eliminate the need for physical plant expansion.
Another vital capability is predictive analysis – the ability to run “what-if” scenarios. What if this particular piece of equipment or system failed? Where would the load go? What other systems might fail as a result? Would you have a cascade of failure? What if the power went out? This predictive capability helps with disaster planning before it happens to minimize risk.
This “what if” process helps to ensure that you’re using your assets and resources most efficiently, including energy, space and cooling.
4. Ensure You Have the Ability to Normalize Data from Disparate Systems
Data Centers are complex and by nature include many different systems. You may have a BMS, EPMS, Data Center Infrastructure Management (DCIM) software, other monitoring tools, various vendors’ equipment etc. Many times these systems are siloed, separated in different departments. For maximum efficiency, you need a way to tie all these disparate systems together – to unify all this data from different sources in a single pane of glass, to eliminate conflict.
The DCIM system you select must offer this capability, and be “vendor neutral” in order to interact with all these other systems smoothly.
Also because the IoT encompasses so many devices, enterprise as well as consumer, security becomes a major concern, and needs to be addressed.
5. Ensure You Have the Analytics Capability for Varying Stakeholders
Various people and departments inside your organization (and maybe outside) will be involved in this ongoing monitoring process. They are all invested, but depending on who they are, they are going to need different data from the devices from which you’ve collected information. You’ll have to provide reports to answer their various questions. Maybe even custom dashboards, which stakeholders can understand quickly and easily, to make the information actionable. Your DCIM system should have that kind of flexibility to become a true asset to IT, facilities personnel and of course the C-Suite.
Needless to say as more and more data arrives in your environment, the analytics are likely to get more and more complex.
So you have all this information: now what? You need to have the ability to analyze the data so that it’s usable and helps with crucial business decisions. How will you use the data? What improvements will you make because of what you now know?
Then the process starts all over again, with a whole new set of questions.
The IoT is here. And it’s growing at an exponential pace. To assure that your Data Center is ready for the IoT, a solid but scalable DCIM system will become more and more essential.
Mark Gaydos is Chief Marketing Officer for Nlyte Software, the leading data center service management (DCSM) solution provider for seamlessly automating data center operations and infrastructure into an enterprise’s IT ecosystem.