In the first part of this blog on Business Analytics for Data Centers, we explored why Analytics has become critical for Data Center operations . In this second part, we will explore how DCIM fulfills this role as a Business Analytic tool for Data Center operations.
While DCIM in its early days was largely seen as a bridge between Facilities and the IT Infrastructure Groups, it is now being recognized as an analytic tool for data center operations. Maturity in DCIM technology has meant that huge amounts of data from different devices are captured on a real time basis. Data Center Managers rightly expect that DCIM must now be more than just a monitoring tool and deliver meaningful insights from the data lake of power and environment monitoring, server utilization and threshold breaches.
At configuration stage, DCIM is mapped with the critical relationships and dependencies between all the assets, applications and business units in the data center. This makes it possible to identify cascading impacts of an impending failure. DCIM Analytics however goes deeper. Over a period of time, data patterns emerge which lend themselves to modern predictive and prescriptive analytics. Predictive analytics gives the data center team enough time to take measures to either avoid or reduce the impact of the failure when it happens. Prescriptive analytics, on the other hand, provides suggestions on how to achieve or improve benchmark levels on each of the metrics specified in advance.
DCIM works with environment probes that measure rack, row and room temperatures and humidity levels. Analytics can help to determine which areas in the data center need more cooling than others and even which PAC unit may be turned off in the data center at certain times of the day or month. Advanced DCIM, through analytics, recommends ways to reduce power consumption in the data center by raising temperature in zones that do not need extra cooling.
Other Benefits Using DCIM
There is a frequent Move-Add-Change (MAC) in data centers. DCIM has the capacity to deal with these MACs, as well as sudden surges in demand for data center resources. This works especially well with multiple virtual servers in the cloud. Most businesses today do not own just one data center housed in a single location – their data centers are spread around the world. Some are in-house and others are hosted by third-parties. DCIM is the only technology that lets business users control all their data center assets and resources from a single platform.
Data centers are notorious for their high power consumption. Advanced DCIM provides business and operational intelligence to maximize rack space use, minimize power distribution losses and optimize cooling while ensuring the data center meets SLA standards for temperature, availability and energy efficiency metrics like PUE (Power Usage Effectiveness).
Most businesses are finding it hard to make most of the existing space in their data centers, and the use of DCIM software mitigates this problem to a great extent. DCIM can help with reduced rack and floor space utilization, by providing detailed real-time reports on server utilization and capacity. Server utilization reports provide suggestions which of them can be decommissioned or virtualized and therefore overcome space constraints in the data center.
Finally, the most important function of DCIM is to prevent data center failures which can permanently damage the reputation of a business. In an age when a major data center failure can prove fatal for a business, DCIM provides monitoring as well as predictive analytic capability to prevent such a disaster.
There’s a pioneering effort going on in building sustainable data centers. Call them the New Generation Data Centers. Here are a few examples:
Modular Data Center (MDC): portable, flexible and containerized (integrated with all components) to meet scalability requirements of ever growing computing demands. It’s the answer to rapid expansion of a Data Center. Amazon and Google were the early adopters of a MDC.
Combined Heating, Cooling & Power (CHCP): Having a captive CHCP facility that produce both power and thermal energy, can improve PUE significantly. CHCP dramatically improves both energy efficiency and reliability. Princeton University has a CHCP plant for its main campus and High Performance Computing Research Center.
Wind-powered Data Centers: A $70 million data center project is coming up outside Austin, Texas completely powered by wind energy.
Geo-thermal powered Data Center: A new Data Center is coming up in Iceland powered by geo-thermal and will be the world’s first zero-carbon Data Center.
There’s clearly a quiet revolution happening in the world of Data Centers in their quest for driving massive energy efficiencies. We are glad we chose Data Centers as the first sector in our journey of pioneering Sustainable solutions for tomorrow.
Virtualization was one of those pioneering efforts that changed the dynamics of computing and introduced significant operational and energy efficiency. There is however a misconception that Data Center energy efficiency measures stop with Virtualization.
From server and storage point of view, there are two others that can contribute to significant savings:
- Retirement of legacy servers
- Optimization between production and test & development systems
Servers hosting legacy applications that are no longer being used should be decommissioned as they neither offer any business value nor contribute to uptime. If the only reasons they are being kept are for audit or compliance requirements of historical data, Information Lifecycle Management (ILM) strategies should be deployed.
Just as we observe that nearly 55% power consumption are from non-computing that adversely impacts PUE, our experience working with Data Centers show that as much as 70% power consumption are from test & development servers and storage. There are a few reasons for this:
- Older servers reaching end-of-life are allocated for non-production usage. However, they are energy inefficient and should be replaced with newer, more energy efficient equipment. The TCO will definitely be lower, as in all likelihood their AMC will also be lower.
- Full sized production databases are cloned for test & development purpose when only a subset can suffice. Worse, equal number back-ups are taken even of the clones as they are taken of production databases!
Going beyond Virtualization, significant power reductions can be achieved through better operating procedures for test & development, retiring legacy servers and replacing older equipment and of course, cooling.
As a DCIM software vendor, I am frequently asked this question, and I have a simple answer. DCIM is ERP for the Data Center Manager. Consider this.
Like a manufacturing plant, a Data Center has lots of assets.
- Both ERP and DCIM help in Asset Management.
Just as there are raw materials, including Power coming into a manufacturing plant, we have Networks and Power as raw material coming into the Data Center.
- In both cases, usage has to be accounted for and that’s what ERP and DCIM do.
Raw material is processed to produce final products in a manufacturing plant. Similarly, there’s Data Processing happening within the large array of servers and storage in the Data Center using Power and Networks to deliver different Information Service to different users (final products).
- An ERP helps in Production Planning, Order Management and WIP Management. DCIM Software helps in Cooling, Power, and Space Management.
Some manufacturing plants are dependent on Distributed Control Systems at one end and Manufacturing Execution Systems on the other. Similarly, many Data Centers have a Building Management System (used by Facilities team) and a Systems Performance and Management Software (used by IT).
- ERP bridges the gap between Distributed Control Systems and Manufacturing Execution System. Similarly, DCIM bridges the gap between a Building Management System and a Systems Performance & Management Tool.
Manufacturing operations require establishing and measuring KPIs for operational efficiency. Data Centers have the need to establish and measure its own KPIs for both energy and operational efficiency.
- ERPs measure manufacturing KPIs like Inventory Turns and Inventory Accuracy. DCIM measures Power Usage Effectiveness (PUE), Watt per Rack and Watt per square foot in a Data Center.
It’s a world of multiple constraints with multiple variables and different objectives – some of them pulling in different directions - to manage in all operational activities. Modern ERPs are Constraint-based planning software taking into account supply chain constraints. The Next Generation DCIM software are also headed that way as they need to resolve the Data Center Manager’s contradictory objectives like maximizing asset utilization, minimizing power consumption while at the same time delivering high availability at over 99%, which can be treated as a constraint. Just as ERP replaced discrete applications and spreadsheets, so also DCIM is making inroads into the larger Data Centers offering a comprehensive suite to Data Center Infrastructure & Operations Managers.
Having had a few successful DCIM implementations under our belt now, a few lessons to share:
- Baseline your existing Data Center: document what systems and procedures are being followed today. For example, how do I keep track of my assets today?
- Map out your desired Standard Operating Procedures (SOP): mention desired state (wish list) and timeframe in which you can expect to implement the changes. For example: I would like to get real-time the PUE of all my Data Centers, starting 90 days from now.
- Why do I need DCIM? Will DCIM be able to keep track of all assets and maintain an up-to-date accurate asset register? Will DCIM be able to get the real-time PUE? This is what I could call “plugging the gaps”.
- Setting longer term objectives: Is there a corporate goal towards cost reduction? How can DCIM help to reduce annual capital and operating costs? Or, is there a corporate goal for Sustainability? Can DCIM help with less carbon emissions from my Data Center?
During the baseline exercise, review asset and space utilization in the data center as well as power consumption and costs. Also, review the utilization and performance of all equipment. Are there some servers which are heating up too fast? Are there some production servers which have less than 10% utilization?
As Data Centers form the core of a business function, DCIM software should be viewed as a business application that can contribute towards meeting your company’s business objectives.
- Has your company been spending too much money on power in maintaining its data centers? DCIM can help by accurately measuring power and cooling requirements and identifying ways to reduce power costs.
- Do you need to deliver higher SLAs to your customers at a lower price? By enabling proactive alerts and mapping inter-dependencies of all equipment, power and network maps of the entire Data Center, DCIM will be able to predict failures before they actually happen.
- Are you running out of space in your data centers? DCIM can provide you the tools to monitor and manage floor and rack space in a data center enabling you to take timely decisions when to invest in higher density racks.
Identify first the priorities and then implement the features of your DCIM solution in a phased manner. An attempt to implement all features at once will be a sure recipe for disaster, as many ERP implementations in the past have shown.
Keep in mind that DCIM introduces business process changes in the data center making it extremely important that you get the buy-in of all stakeholders at the outset. Since data centers form the heart of any business it is necessary to get management involved right from the start.
I would encourage Data Center practitioners to share what outcomes they would like to see from a successful DCIM implementation as well as get insight from customers who have actually deployed a DCIM Software.