Becoming Energy-Efficient Through a Data Center Energy Audit

Green is in, and there is little doubt that companies that can show they are striving to be energy efficient are more productive. To stay proficient, older data centers need to find ways to become more energy efficient, and newer data centers need to implement energy efficient protocols from the outset. The numbers show that proper implementation of energy management can save data centers millions of dollars each year. In order to find these energy management ideas, data centers need an energy audit. There are different types of auditing processes to determine data center energy usage. Understanding the standards, downfalls, and successes of this process is important in understanding its importance.


Types of Energy Audits


There are three different ways to carry out an energy audit, including a walkthrough audit, comprehensive audit, and investment grade audit.


A walk-through is by far the least expensive and time-consuming of the three. However, a simple walk-through audit can easily overlook opportunities for energy savings. Sample readings and measurements recorded generally include:


  • Power
  • Lighting levels
  • Thermal comfort


Normally, an auditor walks through the facility and reviews energy data for the past one or more years to determine opportunities for energy savings. A comprehensive audit may be recommended if the auditor feels that the facility could benefit from one.


A comprehensive energy audit is considered the standard. It usually involves gathering energy data of a facility for three or more years and conducting a detailed investigation into the facility’s energy use process. Since more data is collected and examined, more energy management opportunities may be discovered than a simple walk-through would provide. Since this audit takes more time and manpower to analyze data, it is more expensive than a walk-through.


Investment grade audits are an even more exhaustive process to leave no energy-saving stone unturned.  Everything involving the facility’s energy usage and footprint for the past several years is assessed to find opportunities for energy savings. Detailed energy models are created to illustrate the effect energy efficient actions could have for the facility. It is the most detailed and time consuming of the three audit processes, and therefore more expensive.


Assessing Data Center Energy Usage


The process for assessing data center energy usage starts with data collection. The amount of data collected depends on the type of audit being performed. It is common for data centers to undergo a comprehensive audit that examines three years or more of existing energy usage information. An energy efficiency model may start to form from the data collection alone. An auditor will need to visit the site to document in person energy efficient actions that may need to be taken. It is common for the auditor to assess areas such as:


  • IT equipment and software
  • HVAC
  • Electrical power chain
  • Air Management
  • On-site energy generation


The product of any type of energy audit is the energy audit report, which examines what the current cost of running the data center is and compares it to the projected cost after energy efficient actions are implemented. The report includes steps to take to lower energy costs. Some energy efficient implementations cost money at first, but ultimately serve to save data centers millions over the years.


Standards for Assessing Energy Usage


Ultimately, during the energy audit process, the goal is to produce a number to evaluate the data center’s Power Usage Effectiveness (PUE). PUE is usually quantified by taking total facility energy and dividing that number by the IT equipment energy. The resulting number can be anywhere from 1.0 to infinity. A score of 1.0 means that a data center is operating at 100% energy efficiency. Typically, older data centers generate a PUE of 2.0 to 2.5 (80-85% efficiency). However, there are many data centers (some in that older category) that have managed to get their PUEs to 1.6 or better. Newer data centers that focus on optimal IT power delivery and cooling are more likely to get closer to achieving a score of 1.0.


Common Downfalls in Energy Efficiency During an Energy Audit Assessment


Although PUE assessment is considered standard across the board, it is not an infallible process. There are certain factors that can directly affect the score that a data center receives during an audit, including:


  • The age of the data center
  • Type of processing
  • Type of cooling
  • Temperature levels
  • Location of CRAC units
  • Ventilation


PUE can differ from the actual total energy usage levels of a data center. When a data experiences down time on IT devices, the total energy usage also goes down. However, unless there is a proportional drop in the infrastructure energy and cooling capacity, the PUE number actually goes up, worsening energy efficiency.




It might sound complicated, but there are plenty of data centers that have already undergone energy audits and seen success with energy efficiency protocols. Google and eBay are the towering success stories that have seen PUE levels of 1.2 and 1.4 respectively. More recently, digital realty major DRT has released information that it has dropped its PUE level down to 1.6, saving the company $6-10 million per year at two data centers.


The energy audit process for a data center uses careful analysis of energy usage to determine where energy costs can be efficiently reduced. The ultimate goal is to find ways for a data center to drop its PUE level to as close to 1.0 as possible. Significant benefits generally await those data centers that can find ways to be more energy efficient. For those companies looking to stay in the business effectively, a comprehensive energy audit may be in order.

Posted in Data Center Design, data center equipment | Comments Off

Is it a Data Center Emergency or Just A System Notification?

In the office of today, a lot of machines beep, ring, and create various alarm notifications. Nearly everything from the copy machine to the coffee machine has an alert to bring attention to things such as low toner, finished cycle, or some other status. Unlike the pre-computer offices of the twentieth century, where the only bell usually heard was from the typewriters as the secretaries reached the end of the line, modern offices have a lot of minor little alarms – and of course, a few big and very important alarms, as well. For instance, just one device, the Uninterruptable Power Supply (UPS) that helps to keep a steady power supply to the company data centers, has both small, less-important notifications, and more urgent alarms. Knowing the difference between a status update or alert, and a system critical alarm that requires user action, is one key to keeping an office operating smoothly.


What is That Alarm About?


For workers who are not in the IT department, the computer systems of the office can be both familiar and intimidating. On the one hand, nearly everyone in the company uses the workstations, tablets, laptops, and other devices that are part of operations. On the other hand, though, the complicated computer programs, algorithms, functions and electronics behind the familiar facade of the keyboards and screens that all workers use everyday is mostly not well understood by the average employee.


When the company’s data center UPS activates, for instance, in the event of a power loss for any reason, it will trigger a notification. Some people become alarmed and feel a need to call the experts when they see such a situation. In most cases, though, the truth is that the system worked just as it should, and there is not a problem to report. The UPS is there to keep power supplied in the event of power interruption in the system. If there is an unusual event where the main power will remain unavailable for a longer time, it may be necessary to take immediate action when the UPS system kicks in. Generally, though, full power will soon return, and the system can return to normal operation. In that case, there is no need to call the IT experts, as the system is working properly and doing its job.


Power to Electronics


The computers and devices that smooth the flow of much information and work today naturally require a steady and predictable supply of electricity. Electronic machines can be very sensitive to sudden power bursts or fluctuations. Despite significant advances in power grid technology, the fact remains that in the real world, power systems do not provide an exactly constant, perfect flow of electricity. In reality, the amount of electricity ebbs and flows and surges, depending on needs, demands, and production in the system. While the slight variations in power supply are not harmful to most electrical appliances around the home or office, the very sensitive and sophisticated computer equipment can be damaged or ruined by power supply fluctuations.


Realizing the risks to equipment and data that can come from power surges or sudden unexpected power outages, electronics manufacturers created solutions in the form of UPS devices, as well as Power Distribution Units (PDU). For computer-sensitive companies, a PDU can help to smooth the flow of electricity to various devices, ensuring that none gets hit with a spike of energy that can burn out electronics, and that none are lacking the power they need to do their jobs. Many large industries rely on PDU to moderate the flow of power to a variety of electronic devices. Naturally, data centers are one of the primary users of PDU, but they are also utilized by government operations, hospitals, as well as many data-intensive industries.


The More You Know. . .


While not every employee in every company can be a computer expert with a thorough working knowledge of the ins and outs of the system, it helps to have employees who are thoroughly trained and knowledgeable on the operations that they will come in contact with in their work. Particularly for parts of the system that are not used everyday, but that can be vital in the event of power system problems, such as the UPS and possibly the PDU if in use in the company, it is useful to have thorough training in the basic workings of the system and the various alerts and notifications that the devices may provide in different situations of normal operations.


Workers who are informed of what to watch out for and trained on the various levels of warnings and notifications that will inevitably come from the computer and its power backup systems are generally more confident and less prone to call for expert help that is often unnecessary and costly. One of the key mission functions of a company’s IT operations is to minimize downtime and promote efficient, productive use of the electronic devices that the company uses. The better that all employees can understand some of the more mysterious inner workings of the machinery that tend to be out of sight and out of mind, the more likely they are to be productive and pro-active in resolving small issues in-house and in the simplest way possible. When workers know which notifications are indicators of a system working well and resolving internal problems adequately, and which alarms require quick action to maintain data stability and computer operations, then they can perform their own jobs better, knowing the computers are there for them when they need them.


Posted in data center maintenance, Facility Maintenance | Comments Off

Emerson UPS Systems Product Review

When Power Backup Is Required, Emerson UPS Systems Offers a Variety of Products

Emerson Liebert UPS Product ReviewAs industries become increasingly reliant on computer technology to perform daily tasks, protecting integral company data and equipment becomes more and more urgent. One way to ensure that operations are not affected by an unexpected loss of power is through uninterruptible power supplies, also known as UPS.


Emerson UPS systems are one provider of devices intended on saving crucial company info, as well as ensuring that computer networks can be shut down in the appropriate manner in the event of a full-scale power outage. In some cases, the ability to correctly shut down computer systems can be essential to maintain the integrity of a computer network. Power outages can not only result in a loss of important data, they can also have a disastrous effect on the computing hardware a company needs to perform daily functions.


Company Background


Emerson UPS systems is a leader in offering effective computing solutions that address a number of relevant issues related to power backup. Emerging in the early 2000s as a division of Emerson Electric Company, the primary goal of Emerson UPS systems is to offer user-friendly methods of ensuring a company’s computer bank remains secure no matter what may occur.


Emerson UPS systems specializes in devices that offer auxiliary power solutions in the event of an outage. Causes of outages can include everything from inclement weather to malfunctioning equipment, and as a result of these occurrences vital hardware and devices may be damaged irrevocably. The Emerson UPS systems’ product line includes uninterruptible power supplies that can prevent the loss of crucial company data, as well as protecting costly hardware from being damaged by an unexpected power outage.


How Does UPS Work?


Unlike standard auxiliary backup systems, uninterruptible power supplies feature a near-constant source of power that can allow vital operations to continue in the event that a power outage is imminent. This can be extremely important for select industries, where loss of power can contribute to everything from steeply declining revenue to public safety issues.


A UPS has a relatively short lifespan, but in most cases this period is long enough to enable vital backup power to be initiated. A UPS can also offer time to perform crucial steps to ensure data remains protected before a full-scale power outage occurs. This window of opportunity can make all the difference between saving relevant data and losing this information forever.


Types of UPS Products Offered by Emerson UPS


Depending on a company’s needs, one UPS product may be preferable to another. The following are a few of the items offered by Emerson for the express purpose of supplying backup power in the event of a facility-wide outage:


  • Desktop/Workstation UPS – Depending on the industry, a single workstation could be tasked with performing many critical operations that may be impeded in the event of a power outage. Fortunately, workstation UPSs offer a continuous power source for a range of hardware. Such backup power suppliers offer smaller range of capability, making them more affordable to small business entities and the like.


  • Rackmount UPS – For those at the helm of data centers and other computer-intensive businesses, rackmount UPS systems are preferable because they offer the ability to power more devices from a single piece of hardware. In the case of larger computer networks, such as those necessary for the IT industry or other large-scale operations, a rackmount system can offer the level of protection necessary to ensure daily functions are secure.


  • Network UPS – For many companies, a functioning computer network is integral to maintaining efficient operations. If a network is rendered inaccessible even for a relatively short period of time, it can have disastrous effects on future operations. A network UPS can ensure crucial company networks remain accessible no matter what occurs. Network UPSs can offer auxiliary power to things like servers, routers, bridges, hubs, and other vital network components.


  • Power Management Systems – For those entities with a number of computing devices, power management can be an important issue. Thankfully, there are devices that can ably handle power management to ensure more efficient computer usage. These devices are tasked with dispersing power on an as-needed basis. As a result, power will be used more efficiently, entailing less wasted energy and more resourceful computing overall.


Common Uses for UPS


While not every company or industry may be in need of a UPS, they can be highly beneficial in a number of circumstances. Nuclear power plants are just one example of the important role a UPS can play. Most of the operations at a power plant are automated; this means a failure of power can result in a large-scale catastrophe. As a result, a reliable form of auxiliary power is necessary to ensure important functions can be performed without interruption. A standard source of backup power, such as those offered by auxiliary generators, may not be sufficient in this instance.


Other industries require consistent backup power for different reasons. Brokerage firms necessitate constant communication to stay abreast of market trends and developments. Therefore, a power outage could have devastating financial results on a firm if connectivity can’t be restored right away. A UPS offers a firm enough time to make alternate power arrangements before connectivity is lost. Of course, these are just a sampling of the types of companies and industries that would benefit from a reliable source of backup power.


Computers are a necessary component of the business world these days, and companies must ensure both their equipment and data remain protected. Emerson UPS systems offers an array of devices that can mitigate the ill-effects caused by large-scale outages, no matter the cause.

Posted in Uninterruptible Power Supply | Comments Off

Product Review for Eaton UPS Systems

Eaton UPS SystemEaton UPS systems have a proven track record of protecting mission critical hardware by offering power backup solutions via rack-based and standalone UPS. Eaton has a reputation as a highly innovative brand that specializes in power management solutions, and its current line of surge protective devices, remote monitoring solutions, and power distribution units are all highly effective in data center power management and redundancies.

Eaton Products for Growing Data Centers and Existing Data Centers

Eaton has designed a line of UPS systems to meet the needs of a variety of data centers in different stages. Simple redundancies can be added to data centers that already have most redundancies in place, or state-of-the-art equipment can be ordered for newer data centers. Some of the most interesting features newer Eaton UPS systems and power management systems have to offer are the ability to have the systems pay for themselves during the anticipated lifespan of a new data center.

In addition, Eaton has designed products that support other aspects of data center power supply that may not support mission critical applications, such as emergency lighting systems for on-site offices. Eaton UPS systems are suitable for a variety of different needs. Several examples of different Eaton UPS products are listed below.

List of Current Eaton UPS Products

Eaton places a strong focus on product development that will integrate with next-generation technologies and revolutionize data center construction. Current Eaton UPS products include:

  • Eaton 9355 UPS

The Eaton 9335 UPS has maximum battery runtime and power is packed into a sleek tower. This UPS system is a scalable solution for data centers that want to maximize available space. In addition, this product can be equipped with a maintenance bypass switch as part of a power distribution module.

  • Eaton Emergency Lighting UPS

Emergency lighting requirements are part of building codes, including on-site office space in data centers. This emergency lighting system has high capacity and takes up minimal space. It will typically be used in the event of an emergency situation.

  • Eaton 93E UPS

The Eaton 93E UPS is a cost-effective UPS solution. It is easy to install, and it has removable batteries. It is a practical redundancy for less substantial data center needs.

  • Eaton 9390 UPS

The Eaton 9390 UPS has an innovated Energy Saver System. It will often pay for itself in less than five years without sacrificing quality or reliability. It is suitable for the support of mission critical aspects of medium-sized data centers.

  • Eaton 93PM UPS

The Eaton 93PM UPS was designed to be easy to manage. It is a reliable three-phase solution for various data centers.

Different Data Centers Have Various UPS System Needs

Data centers currently have a relatively short lifespan. Eaton currently provides UPS Systems that meet the needs of data centers in different phases. Logically, almost no data center that will be fully functional for approximately another year would warrant a complete overhaul of power management systems and redundancies. However, a new data center could benefit from many different ways by investing in top UPS Systems from a reputable manufacturer.

New data center construction is notoriously costly. The latest energy-saving UPS Systems from Eaton can realistically diminish the amount of outside power used to the point where the UPS Systems save data center owners cost without increasing liability in the event of a power surge. In addition, advanced UPS Systems from Eaton can help new data centers ensure adequate power supply in the event the main grid cannot fully support the data center in the next several years due to unanticipated population growth in the area.

Simplify the Data Center Construction Process

Data centers have historically been designed to work within the parameters of existing utility infrastructure and existing utility capabilities. More advanced options for power supply and power management from Eaton can help mitigate the direct impact a new data center has on existing infrastructure.

The Right Redundancies at the Right Cost

A complete overhaul of the UPS systems and power management systems for data centers is often realistic when all other mission critical elements are in excellent condition. Additional redundancies can support older data centers under the right conditions, and the cost savings can be substantial. A slightly outdated data center may only need a few simple UPS redundancies that have a low footprint to be fully-functional for another several months.

Cost and Reliability Matter In Data Centers

The cost of downtime due to an ineffective UPS system could be astronomical. Cost should be calculated over the anticipated lifespan of a new or existing data center, and risk should be mitigated. Cost due to loss of power can impact more than equipment replacement and repair. Numerous data centers can suffer cost due to downtime in the form of lawsuits, legal fees, and any payments mandated. Poor reliability due to poorly manufactured UPS products can be a substantial monetary risk for data center owners and operators.

Eaton Products Offer Individualized Data Center UPS Solutions

A critical part of innovation is looking at present needs in addition to future needs. Eaton offers a variety of UPS Systems and solutions that can support mission-critical data center functions for current data centers as well as cutting-edge data centers that are not yet under construction.

Innovation does not stop at looking ahead. Eaton offers individualized products that support all aspects of data centers, from on-site office centers to cutting edge ways that reduce outside power consumption and cut costs. Cost is a key aspect of any data center construction or renovation project, and Eaton provides UPS Systems and power solutions that cut cost without diminishing reliability.




Posted in Uninterruptible Power Supply | Comments Off

A Power Distribution Unit Can Optimize Computer Operations

Computers are at the center of many successful business operations, and there are no signs that this trend will be abating any time soon. Because computers are so integral to the business world, it’s imperative that precautions are put in place to ensure that daily operations can continue unimpeded, no matter what may occur.


A power distribution unit, also known as a PDU, is one such technology intended to simplify businesses operating via large-scale computer networks. This is especially true of things like data centers, which often contain an array of devices necessary to perform key operations. A PDU is tasked with providing power to these many disparate devices from a central location. As a result, PDUs must contain certain protections to ensure all devices remain powered sufficiently for everyday functions to occur.


What Is a PDU?


As briefly mentioned above, a PDU is responsible for distributing electrical power to a number of different devices. As a PDU allocates power usage, it also ensures that unexpected power outages do not damage important hardware or result in a loss of pertinent company data.


While PDUs can be used in a number of industries, they are most commonly seen in data centers. This is because data centers are often comprised of numerous computer devices, all of which require a reliable source of power to maintain integral daily operations.  A PDU can efficiently power many devices concurrently, while also ensuring that these devices remain in operation in the event of an outage.


Types of PDUs


  • Basic Units – The ubiquitous power strip that is now a staple of every home and office is merely a simplified version of a PDU. Power strips serve as a centralized location to disperse electricity to a number of devices. Many power strips even offer protection to devices in the form of surge protectors, which can cause electrical items to shut down before being damaged by an unanticipated spike in power. While other types of PDUs are far more sophisticated, the principle remains the same.


  • Rackmount Units – Rackmount PDUs also disperse electricity to many different devices. However, these larger models can often accomplish other tasks which makes operation safer and more efficient. Unlike standard power strips, a rackmount PDU can allow for intelligent power dispersal. This permits power to be used more efficiently by connected devices, which not only improves operation but also cuts back on wasted energy. A rackmount model can also be accessed remotely, making it beneficial for companies who may have offices spread out over a great distance.


  • Cabinet Units – Cabinet PDUs are most often found in data centers, which often contain a large amount of hardware. As a result, cabinet PDUs are typically far more complex than their less-powerful counterparts. A cabinet PDU may require many sources of high-current power supplies in order to successfully maintain many different devices. Cabinet PDUs also include things like circuit breakers, as well as control panels dedicated to monitoring power distribution.



How Do PDUs Work?


Electrical currents are supplied to the PDU, which then distributes this power to devices accordingly. In some cases, PDUs can be accessed remotely, which allows the operator to change the way power is distributed to different devices. This can be helpful in the event that the number or type of electronic devices changes, or as a means to deal with impending outages or other issues that may affect computer hardware.


PDUs can also differ in the amount of power they can handle, ranging from smaller units to those tasked with allocating power to numerous devices. Many PDUs include means of mitigating the effects of large-scale power outages, which is useful for both protecting data, as well as vital computer equipment.


Who Needs PDUs?


While many businesses can make use of some form of PDUs, for certain industries these devices are crucial. The following are just a few industries and organizations that require PDUs as a part of daily operations:


  • Government Entities/Organizations – Government-run computer networks need to be accessible at all times. For this reason, proper allocation of power is crucial maintaining reasonable operation.


  • Schools – Schools often entail a large bank of computer systems necessary for day-to-day assignments. As a result, a centralized source of power can be a smart choice for keeping all devices up and running, no matter the demand.


  • Hospitals – As technology advances, so do the means in which patients are treated for health issues. Because many hospitals are now utilizing computerized systems, a reliable power source is important for maintaining the health and well-being of patients.


  • Brokerage/Trading Firms – PDUs can ensure that workstations crucial to accessing market information remain online no matter what. Even a few hours of down time can result in financial devastation for a brokerage firm.


Benefits of PDUs


PDUs can be beneficial to companies for a number of reasons. While they primarily allow for a more efficient dispersal of power to many devices, they can also serve as a fail-safe in the event that power is lost unexpectedly. PDUs can also be helpful for those companies that wish to closely monitor their power consumption. Thanks to the monitoring features included within many models, operators can devise ways to more efficiently use allotted power, resulting in far less waste. In many cases, PDUs offer convenience and efficiency in one package.


Whether you are the helm a large-scale data center or a small business, a PDU can prove extremely useful in a number of circumstances. For those companies that rely heavily on technology for daily functions, PDUs are a natural choice.

Posted in data center equipment | Comments Off

Comprehensive Data Center Spring Cleaning Checklist

Spring Cleaning Checklist

There are numerous mission critical elements to all data centers, and regular maintenance is integral to minimizing downtime and keeping all mission critical systems running.  Arguably, it is best to take a top-down approach when itemizing which data center components are most integral to successful operations.  The redundancies and numerous automated facility support systems as well as interdependent operations need to be addressed for viability before downtime, or in some instances permanent data loss occurs.

It is also important to note that optimal data center construction and maintenance can provide some of the top results for data center owners.  Recent research by technology research firm Gartner suggests that most current data centers will be obsolete in less than 10 years. Others argue that the lifespan of the average fully-functional data center may be as little five years. Maintenance, testing, and general spring cleaning can help increase the lifespan of almost any data center substantially.

Spring Cleaning Checklist For Data Centers

Below is a simple, itemized checklist for what items should be addressed when maintaining data centers.

ü  Specialized Testing of the Facility

It is almost always more cost-effective to invest in specialized testing of data center systems in order to adequately repair or maintain mechanical devices and hardware that is integrated with critical operations than to wait until several operations have been damaged or failed.

Specialized testing can also help identify if additional redundancies are necessary due to data center growth or potential overuse of the larger power grid the data center is connected to. In addition, facility roll-over testing can accurately identify if all backup systems will be fully functional in the event of a power surge or full power outage.

Generators and Power Supply – Power surges and power outages can be adequately addressed with redundancies. However, all automated generators that provide an alternative power source need to be fully-functional and work in conjunction with alarm systems. In addition, load bank testing can ensure that all generators are functioning at a normal capacity.

Infrared Thermography Testing and Troubleshooting – Infrared thermography testing can identify atypically warm or cool areas throughout a data center. The cause of the temperature change can be traced back to components that were not properly installed, electrical issues, or overloads, or loose circuits.

Specialized HVAC Testing and Installation – HVAC testing and design for data centers is integral to supporting basic functions and extending the lifespan of all mechanical components. Optimal temperatures ensure that hardware does not melt or crack, and optimal humidity reduces the risk of corrosion as well as other types of damage.

Testing and troubleshooting is the first step to identifying which data center components need to be repaired or replaced.  Other components can be replaced or removed for increased space.

ü  Replacements and Installations

Routine replacements of inadequate or semi-functional components and installation of new components can help extend the lifespan of data centers as well as offer increased security.  In addition,  routine replacement and installations by data center experts can further ensure that downtime due to various types of interruption is less likely.

Battery Replacement – Battery failure is the leading cause of system downtime due to UPS load loss. A single bad battery in an entire string can cause system failure during a power surge or power outage. Low quality batteries can have substantial consequences for data centers, and they are one of the most important elements to regularly replace.

Additional Power Redundancies – Large data centers located away from main power grids may experience the need for new generators and other sources for power redundancies.  New developments can put strain on an existing power grid, or planned infrastructure could jeopardize the viability of current power plans for data centers. Utility companies often need to be contacted by data centers that consume a notable amount of electricity in order to continually and accurately assess available resources.

ü  Optimizing Usable Space

Secure data disposal is necessary after a certain point in time. Data racks should not be cleared haphazardly due to potential ramifications with interruption of optimal airflow or other concerns associated with physically altering the design of the data center. One of the easiest ways to increase usable space is to get rid of trays that are no longer in use. It is of the utmost importance to dispose of data securely and properly in order to protect the integrity of the data center as well as personal information stored that is no longer in use.

Different Needs For Tier 1 Data Centers and Tier 4 Data Centers

Spring cleaning for data centers can be highly dependent on the type of data center as the consequences of downtime can vary substantially. Similarly, the consequences of a breach can also vary substantially.  A Tier 4 data center on a military base is a prime example of a data center that would likely need extensive testing and maintenance for optimal security and function.

However, a small municipality might have a Tier 1 data center due to limited needs and limited funds. Downtime for a Tier 1 data center may not be especially detrimental, and off-site servers can be used as a form of redundancy to ensure that critical operations are not interrupted, such as emergency response for citizens.

How to Approach Data Center Spring Cleaning

Work with a team of experts to best approach data center spring cleaning from all necessary angles. Instead of guessing what might be fine for another year, be confident that all systems are fully-functional.  Optimize space, install necessary new components, and maintain existing components to prolong the lifespan of data centers.

Posted in computer room maintenance, data center maintenance | Comments Off

Making Sense of Data Hosting Solutions

Data hosting is a serious concern for businesses everywhere. Choosing the right service can hold back your organization or give it a push in the right direction. Without data hosting services adequate to your current needs and adaptable enough to offer you solutions for future growth, the technology your organization relies on will not be up to the challenges posed by a rapidly changing industry.


Today there is a wide range of hosting services available for organizations of all sizes. Each type of data hosting has particular advantages as well as potential drawbacks. Understanding the unique features of each of these hosting options allows you to maximize the advantages of the hosting service you ultimately select. This information will help you zero in on the hosting solution that is the best fit for your organization.


In-House Server


In-house server options are arguably the most straightforward server solutions that an organization can select. All the equipment is purchased, maintained, and upgraded by the organization using it. The server equipment is kept somewhere on site. There is typically a team or department tasked with maintaining the server function and keeping the system running smoothly.


This server option gives you the ultimate flexibility in terms of structure and resource deployment. Members of your organization have the final say with regards to what equipment is selected and how it is taken care of. Security is also under the direct control of the organization. Though this element of control is highly attractive to some businesses, in-house servers require a considerable investment. Physical space has to be dedicated to server storage; improved cooling and ventilation solutions may have to be added to this space to create a climate optimal for computer function. This can be a problem for organizations with limited available space.


Dedicated Hosting Service and Shared Servers


Dedicated hosting service lets clients lease a server that is dedicated to their needs alone. It is not shared with any other client served by the data hosting company. This allows the lease holder to exercise full control over hardware, operating system, and other technical aspects. The hosting company is responsible for physical security, system maintenance, and even IT support services. Though an organization would give up some degree of control, this hosting option offsets many of the necessary investments that an organization would have to make in order to accommodate in-house servers. Though organizations can comparison shop for the most competitive price, clients are typically locked into a contract for a certain period of time.


Shared server solutions have many of the same qualities as dedicated hosting. The difference is that instead of leasing an entire server, the client leases space on a server shared by other clients. Each client is allotted a certain amount of server space which can then be used for website hosting or other data storage.


Managed Dedicated Server


This option is tailored to organizations that do not have the space to house complex server equipment or the means to develop their own server management team. Managed dedicated server hosting services bundle together everything necessary for hosting and then offer these bundled products to their clients. This hosting solution can cost more than other options but makes many specialized services available to clients. Technical services such as the following are offered by many managed dedicated server host companies:


  • Database management
  • Server monitoring
  • Firewall, backup, and recovery
  • Virus and spam protection
  • Software updates
  • Security audits


Virtual Private Server


This is similar to dedicated and shared server hosting except that in this case, a virtual machine is used instead of a physical one. These virtual machines provide many of the same benefits as a physical hosting service, though may not be able to deliver the same kind of performance power since host-end processing has to be shared among numerous virtual private servers. Virtual private servers are quite cost competitive compared to other hosting solutions. This is a popular choice among organizations looking for website hosting services; in fact, many web hosts offer virtual private server space for their clients to use.


Cloud Hosting


Cloud hosting services are a relatively new innovation that has seen divisive opinions regarding its usefulness and ease of application. However, cloud-based solutions have certain characteristics that are an excellent fit for some businesses.


Cloud hosting is made possible by cloud computing. Computers in a cloud configuration work together to provide the services essential for modern business function. This collective effort means that a single machine can fail without compromising the overall function of the cloud; the services can continue uninterrupted while the broken element is addressed. Cloud hosting therefore can provide highly reliable server functions; this has significant advantages in terms of security and stability.


Some businesses are hesitant to adopt cloud hosting solutions for their server needs because this approach is relatively new. There are concerns about the long-term usefulness of this server solution as well as overall data security. Because cloud hosting has received so much industry attention since its introduction, it is fairly easy for business owners to find authoritative analyses of the viability of cloud hosting. Though cloud hosting offers a great deal of flexibility and a number of useful features, the concerns particular to each individual organization have to be considered before selecting this, or any other, data hosting option.


Selecting a hosting solution for your organization is a very important decision and should be made only after a thorough examination of all available options. With a little effort you can narrow down your options to the ones that make the most sense for your organization.



Posted in Technology Industry | Comments Off

Planning for a Data Center Infrastructure Management Solution

Traditional organization separates data center functionality into two groups:

  • Physical assets controlled by facility management
  • IT domains maintained by the information technology (IT) department












Analysts discovered that this scheme ignores many opportunities for increased efficiency by supporting overlapping functions between the two groups. Data center infrastructure management (DCIM) combines the two groups into a single system. In OSI (Open Systems Interconnection) terms, the management of the physical layer 1 is included in the supervision of the remaining six layers for a “full stack” solution. Complete management systems include the ability to centralize monitoring, maintenance, and expansion activities.

Components of DCIM

The components of a DCIM system include hardware, specialized software, and sensors. The hardware specifications remain the same as for a traditional implementation. The sensors provide a bridge between the hardware and software. These sensors convert physical information such as ambient temperature, humidity, and power supply integrity into digital signals suitable for a computer interface. DCIM software integrates traditional functionality with sensor monitoring capability, in order to allow the software to supervise the hardware.

As companies shop the DCIM marketplace, they will find that providers fall into two categories:

  • Suite vendors – sell complete DCIM solutions
  • Specialists – sell enhancements to suite solutions that are often viable stand-alone products

Performance of DCIM Systems

Performance metrics for DCIM are evolving as quickly as the systems themselves. Some metrics derive from existing industry standards, including the following:

  • PUE (power usage effectiveness) – a metric for energy efficiency for a data center
  • CUE (carbon usage effectiveness) – measures efficient use of water and tracks limits on carbon emissions
  • DCeP (Data Center Energy Productivity) – relates the net value of the data center service to the consumption of energy resources
  • PAR4 – Server Power Usage – tracks server power during four states: system off, idle, loaded, peak
  • DCPM (Data Center Predictive Modeling) – a model to predict future performance, including energy use, energy efficiency, and cost

Many companies contract an industry expert to come into the firm, analyze the existing systems, and compile the business requirements. This exercise often concludes with a serious of seminars to educate management and the IT department. Armed with this knowledge, the company is ready to work with the contractor to choose the appropriate DCIM solution.

DCIM Tracking Parameters

DCIM systems manage resources through the following capabilities:

  • Visual representation of the physical structure – some advanced systems offer a 3D virtual fly-through of the data center
  • Capacity planning
  • Modeling and Simulation – allows managers to model proposed changes in order to analyze performance and cost impact
  • Change management – controls the change order process
  • IP camera management – captures motion alarms and coordinates physical access control
  • Environment monitoring
  • Power management – monitors the entire power chain, from the server chip sets to the data center power generators
  • Asset management (cost containment)
  • Monitoring – the system monitors all electrical, mechanical, and power equipment, including servers, routers, switches, and virtual machines (VM).
  • Dashboards – quick-view screens display a summary of system integrity
  • Reports – systems record data to document tracking, identify trending, and perform predictive analysis

Two of these capabilities, capacity planning and cost containment, are examined in more depth.

Capacity Planning

Capacity planning for DCIM allows managers to allocate resources against present and future needs. Following is a suggested outline of steps to generate an effective capacity plan:

  • Step 1: Compile a complete inventory of the data center resources. Identify which are the critical infrastructure assets. List the mission interdependencies for each.
  • Step 2: Generate a comprehensive monitoring report for each of the critical assets in the data center. Perform an analysis of the critical performance parameters. Use the analysis to identify bottlenecks in the system.
  • Step 3: Ensure the DCIM solution will include data for all of the space, power, and cooling attributes of the environment. Verify that snapshot data is readily available to the supervisor in real-time, and that alarms are in place to indicate out-of-spec conditions.
  • Step 4: Monitor daily workloads for a month or other suitable period. Make sure the system provides the flexibility to deal with on-demand needs as they arrive.
  • Step 5: Validate system performance against service level agreements (SLAs).
  • Step 6: Use DCIM trend analysis to complete capacity planning against future needs.

These steps will provide the current state of the system, and allow scenario planning for future expected expansions.

Cost Containment

As part of a critical business analysis, companies use a DCIM system to provide the information necessary to generate an ROI (return on investment) on the data center performance. This ROI is based on a careful analysis of all cost contributors. Cost monitoring starts by analyzing the power and other resource consumption of all key assets from the capacity plan. It continues by monitoring dynamic use on a real-time basis.

One of the strategies of cost containment is to avoid chasing up time. This pursuit can be a very expensive undertaking. Like many business processes, the cost sensitivity of up time tends to show decreasing returns on investment at high levels. Companies should perform a marginal cost analysis to find the optimal operating point.

To perform a marginal analysis, the company can start by considering price points for each of a Tier-1, Tier-2, Tier-3, and Tier-4 solution. These points would be calculated for a fixed power budget (in megawatts) and an available data center floor space (in square feet). This will generate four cost values for each of the performance tiers. Then, the company should complete pro forma calculations of these values over a suitable period, perhaps 30 years. This will yield a marginal cost per year for each tier. These four values, as a ratio to marginal uptime for each tier, will yield the four values for marginal cost per hour of uptime. These values will climb exponentially as performance increases. This analysis presents a clear cost vs. benefits result to the company.

The Power of DCIM

Data center infrastructure management solutions offer powerful control to data center enterprises. DCIM allows demonstrable improvements in efficiency, performance, and cost control.

Posted in Data Center Design | Comments Off

Energy-Efficient Big Data Businesses See a Better Bottom Line



Green Building Data CenterOne of the biggest costs for a big data center is power. In fact, according to Greenpeace, data centers typically require close to 100 megawatts of energy. Put in simpler terms, that’s enough energy to power 80,000 homes. While high-capacity systems are inevitable, there are ways for these businesses to reduce their energy consumption and improve their bottom line.


The Cold, Hard Facts


The Internet is energy-intensive. One of the biggest areas where data centers stand to improve their carbon footprint, according to Greenpeace, is where that energy comes from. Some companies are working on just that, branching out to solar power options or using air from the great outdoors to cool data centers.


There is still much that can be done. For example, there are still states in which Internet companies largely rely on fossil fuels for energy. The Greenpeace report noted in North Carolina, only 4 percent of the energy powering the state’s data centers comes from renewable resources. When looking at the big picture, data centers account for more than 2 percent of all of the power that is generated in the U.S. Therefore, improvements in data centers can actually have a ripple effect, boosting efforts across the country.


Why It Matters


How does that 100 megawatts of energy translate into dollars? Think millions. These centers can consume millions of dollars’ worth of energy every year. It makes sense, as there are servers that need to be running around the clock. Therefore, simply powering down every night is not an option for most companies. The fact remains that preserving fossil fuels and utilizing cleaner sources can actually help grow revenue by minimizing expenses. It goes without saying that when you can maximize efficiencies in terms of power, utility bills shrink.


Where Issues Arise


The ideal power use effectiveness (called PUE) for a data center is measured at 1.0, which would indicate that all of the power the center is using goes toward processing and storing data with no energy being used to cool any servers. For smaller companies, the ideal PUE is not out of reach. In fact, most start with stellar ratings.


What happens is the business starts to grow, increasing the number of computers they need and adding more racks. To keep things cool, they increase air conditioning to accommodate for the additional equipment. They grow again, they cool more intensely. The cycle continues and can easily spiral out of control, especially if no one is keeping tabs on how the power is (or is not) being used efficiently. So what can be done?


  1. 1.     Take Stock


Experts note that the companies that succeed in reducing expenses are the ones that view power as more than just a cost; it is something that can be controlled. The first step any data center should take is to do an audit of how energy is put to use. Most utility companies can provide this service, and some will even do it for free. The trick is to balance reducing power needs with still maintaining the quality output you need. There are energy-efficiency firms that will partner with companies to piggy-back on top of what a utility company can do.


Depending on the result of the audit, big data centers may note that making small changes can produce big results. For example, in 2013, Forbes Magazine reported on one retailer that was consuming $7 million of power annually and wanted to make a change. They brought in experts and made changes to things like the racks they used and determined a smart back-up power supply that would keep them afloat if something happened.


  1. 2.     Give Air Conditioning the Boot


Many data centers rely on a traditional method of cooling servers, which involves air conditioning. These units typically run around the clock to ensure equipment does not get over-heated. There is an alternative way to generate cool air inside the center, however, and it is known as evaporative cooling. The process involves installing a rooftop tower that will cool the water that keeps servers at a safe temperature. The aforementioned retailer now only uses air conditioning a very small fraction of the time, reducing the power they needed to cool the center by 93 percent.


  1. 3.     Rethink the Configuration


One of the most compelling aspects of what the retailer did was to put the focus on the equipment itself. Typically, a data center utilizes a universal energy supply. An inefficient system will actually produce wasted heat, which means energy is being used to generate unnecessary warmth that in turn needs more cool air to prevent overheating.


The solution? Combine racks to actually shrink the amount of space that is used. The universal power supply is then reduced, thus minimizing the energy that is used and the bill that hits the doorstep every month.


The Cost of Energy Efficiency


Upgrading equipment and software comes with a cost. Depending on the size and scope of the center, that figure could exceed six or seven figures. However, the savings can kick in almost instantly. In the Forbes report, the retailer noticed a return on its energy investment in less than a year, now operating at the energy levels they were using half a decade ago despite having added more than 30 stores.


Big data centers will inevitably devote a decent part of their budgets toward power, but the kind of power they use and the cost are flexible. By taking the right steps, companies that make the investment can notice a return on their investment in a short period of time, thus improving their bottom line for years to come.

Posted in Data Center Construction | Comments Off

Helping Data Centers Survive a Cold Snap



cold-serverFor all of their power and capabilities, data centers are still susceptible to the disastrous effects of water, fire, lightning, earthquakes and extreme winter cold. It seems that winter has received an upgrade, which means that it’s more important than ever to make sure that data is being well-protected while it’s being housed in a data center.


The Frigid Fallout


Should a data center succumb to an arctic chill, it can cause problems with cooling and fuel while making it more difficult for equipment to work at peak efficiency. There’s also the fact that data center employees might have difficulty getting to work on time if they’re able to make it there at all, which can create an all new set of problems and setbacks.


It’s beneficial to have contingency plans in place that can mitigate any damage and make sure that operations proceed as normally as possible should something go wrong with the data center. It’s always better to be acting in these situations as opposed to reacting.


Know Your Enemy


In order to properly prepare a data center for the cold, you need to understand how the cold can affect a data center. The cold can add undue stress on the data system, and that’s especially true if the frigid air outside is being used to keep the center warm. The center’s drain lines can freeze over in addition to heating coils, fuel systems, humidification units and cooling towers. You never realize how much effort goes into keeping data centers at the proper temperature and setting until a cold snap blows through town.


Frozen air conditioning units might spring leaks, and snow might find its ways into the intake vents, which can make it all but impossible for air to properly circulate and lead to a system wide shut down. One of the best ways to prevent these mishaps from occurring or at least keep them from completely crippling a data center is to be diligent when it comes to maintenance and upkeep. Make sure all battery warmers, block heaters and engine oil heaters are in working condition.


Location, Location, Location


Prevention and contingency plans will also depend on where the data center is located. If the data center is located in an area that receives especially bitter winters, it might be necessary to set aside the funds necessary to make sure that the center is always being well-heated. It’s a good idea to start saving this money up as soon as possible beforehand so that finances don’t take a bigger blow than necessary. You know that winter is coming, so you might as well prepare for it in the spring.


Generators should be insulated and heated, and you’ll want to keep humidity in mind whenever you’re dealing with electricity and cold.


It’s not unusual for anti-static wrist straps to be used in order to make sure that equipment is properly protected during the winter. The use of ultrasonic humidification can result in much better energy savings when compared to the use of conventional humidification methods.


The weather forecast should also be monitored so that there’s ample time to call in extra employees and help if necessary and so that there’s enough time to gather any necessary extra supplies.


Consider Employees


Employees should be just as well-protected from the extreme winter cold as the data center itself. Even if a data center is being built in an area that isn’t known for its punishing winters, there should still be plenty of room in storage for salt in case things take a turn for the worst. It’s also a good idea for there to be stairs instead of ladders for employees to use to move between levels since ladders can be a huge hazard if they ever ice over.


The areas employees frequent for extended periods of time should be kept warm so that employees remain comfortable enough to be able to focus on their jobs. Snow drifts are something else that should be taken into account whenever a data center is being built since they can damage the structure of the center and lead to numerous other complications.


Aside from keeping employees comfortable, there’s also the fact that employees might not be able to make it in to work due to road closings. Individuals who are at the data center when inclement weather hits need to well-supplied so that they can continue working as normal and so that productivity doesn’t dip.


There should also be proper employee protection, such as gloves and heavy coats, for when maintenance needs to be done on outside equipment. Even with the right winter protection, there’s still a chance that maintenance might take longer than it usually does since employees might need more breaks and have to deal with equipment that could be iced over.


Proper Preparation


In order to protect a data center from inclement winter weather, certain steps need to be taken, including:


  • Making sure that all alarms and remote monitoring panels are operational
  • Keeping a close and constant eye on outside equipment
  • Stocking up on all necessary parts in case they should fail
  • Ensuring that there are plenty of de-icing products on hand and that temperature probes have been calibrated
  • Keeping an eye on the forecast in order that maintenance can be postponed if necessary


The worst case scenario always needs to be taken into account when it comes to preparing data centers for a cold snap. Be proactive and make sure that employees are fully aware of what they should do if the weather takes a frigid turn.

Posted in Mission Critical Industry | Comments Off