Contact Us

Subscribe via E-mail

Your email:

Follow Me

Data Center Power Blog

Current Articles | RSS Feed RSS Feed

Study Shows Data Center PUE Not Improving

 

PUE

Your company invests time and resources measuring its data center power usage effectiveness (PUE). But is it actually using that information to drive change and create a more efficient data center? According to the results of a recent Uptime Institute study, it might not be.

As the study shows, the majority of data center operators who were asked indicated that they do measure PUE, which can be found by dividing total facility energy by IT equipment energy. Since the point of a PUE reading is to measure how well a facility uses its total computing power, an ideal score would be 1.0. Unfortunately, the average data center PUE has not changed much in over four years from an uninspiring 1.89 in 2011, for instance, to an only slightly better 1.7 in 2014. 

So, what’s the reason for such high levels of inefficiency across the data center industry? While idle servers have a lot to do with the problem, it can also be attributed to the fact that not everyone is using a robust data center power-monitoring solution that can report power-related data in real time. Actively monitoring data center power levels means taking a deep dive across a power distribution unit (PDU) network and analyzing server usage as it occurs. When such information is made readily available, managers are notified about idle servers and can take appropriate action to better conserve energy and lower PUE scores.

Are you looking to lower PUE in your facility? To see how Server Technology can provision your data center with the necessary technology for understanding exactly how your facility uses power, click here

EIA Predicts Rising Electricity Prices

 

 

 

 

 

 

 

 

 

 

 

describe the image

Summer is almost here, and that means one thing for power users: Prices are on the rise across the country. New data from the U.S. Energy Information Administration’s (EIA’s) latest report shows that energy prices will be higher this year than last summer in just about all areas of the U.S. As the report explains, the East South Central states will experience the highest surge in electricity with an increase of 8.7 percent.

This information, as well as reports that U.S. energy prices might not be coming down any time soon, should, therefore, be a call to arms for executives to start investing in data center power monitoring solutions before power prices really surge. After all, some data centers can suck up as much energy as a small city, so price increases could have a dramatic effect on a company’s bottom line. As energy prices continue to increase, managers will need a way to measure each and every ampere of electricity to ensure efficiency and keep bills at a workable level.

Server Technology’s Sentry Power Manager (SPM) will enable managers to keep a close watch on power consumption. Using SPM, executives can analyze real-time data from across the power distribution unit (PDU) network. This information, which works in conjunction with smart and metered PDUs, is accessible either through an on-site appliance or over a virtualized mobile interface.

Are you looking for a way to control energy usage and create a greener, more efficient data center? Click here to learn how Server Technology can help your business with its SPM system.

Best Practices for Maximizing Data Center Cabinet Density

 

datacentercabinet

Data center power cabinets can get pretty crowded. A fully loaded cabinet will contain upward of 40 1U servers, multiple network switches and inlets for power sources. On top of that, there still needs to be room for cables and air flow, as well as the most important parts: the power distribution units (PDUs).

Since cabinet space comes at a premium, here are some tips to consider for maximizing space safely:

There’s no “one size fits all” approach: Every data center has its own unique demands—from the amount of volts needed to the type of connection that will be established, such as Ethernet or meter. Don’t settle for a solution that “almost” matches your needs. Server Technology’s customizable PDU creator lets you build the device that matches your organization’s needs—right down to the color you want.

Be proactive about fire prevention: There’s no reason to sacrifice air flow for increased productivity. Cramming more equipment inside of a cabinet will run temperatures higher, which could damage sensitive hardware. One of the best ways of being proactive about fire prevention is to invest in a high-density PDU from Server Technology, which fits conveniently on the side of the cabinet to save space. These PDUs are also built to function at high temperatures, which means fire will not be an issue.

Always monitor your cabinet: Don’t let your power consumption get out of control. A smart or metered PDU will let you know exactly how much power your system is using, as well as identify the power source. This will allow you to be proactive and recognize issues before they arise in your data center.

For more information about how Server Technology can help you maximize space in your data center, click here

A Little Power Visibility in Your Data Center Can Go a Long Way During Emergencies

 

Picture this: A major hurricane hits your data center and your facility floods. In the process, your main power feed is knocked out of commission, which means your primary power supply is cut. Now, the only thing keeping your data center up and running is a backup fuel source and power generators. In this case, the huricane is preventing any chances for refueling, thus your servers can only run for about 12 hours before your fuel runs out.

During an emergency situation like this, you need the ability to understand exactly how much power capacity you have as well as your current power usage. The only way you would have access to this information is with an accurate power monitoring and distribution solution that can provide real-time reporting and analysis. You will need this to help you make informed decisions about your power situation so you can keep your facility up and running as long as possible.

Data center operators—especially those near coastal areas—are well-advised to plan for emergency scenarios ahead of time. According to the new “2014 Atlantic Hurricane Season: One Never Truly Knows” report issued by Guy Carpenter & Co. L.L.C., hurricane landfalls are a very real possibility this year. So, as we move into the heart of hurricane season 2014, take a good look at your data center and assess whether you are impervious to foul weather.

Click here for more information about how Server Technology can help keep your data center up and runining longer during this coming hurricane season.

Plan Ahead Before the Power Runs Out in Your Data Center

 

There are a few things your data center should be well-equipped to handle at the last minute, like a new server or router, or an unexpected spike in the number of end users in your company.

But what happens when your data center physically can’t handle these basic additions when you try to implement them? You could wind up having to outsource to a third-party company for additional resources or storage capacity at the last minute—which could mean high costs and potential lapses in service. After all, you can’t turn away customers due to a lack of data center storage capacity.  Data centers are complex entities, and like any storage system, they do come with limitations—the two biggest being processing power and memory.

To prevent a power shortage, it’s critical that you track your resource consumption in real time to avoid set limits. Through the use of smart and metered power distribution units, equipment utilization is easily trackable, enabling redistribution of data load in your network when necessary.

Server Technology can provide your company with utilization visibility through its robust line of data center power management solutions. Server Technology’s Sentry Power Manager is a plug and play dashboard that gives data center managers the ability to auto-discover devices and manage, configure and upgrade the entire power distribution network.

Are you ready to transform the way your data center manages its power usage? For more information about how we can help you prevent a power outage before it happens, click here.

Uptime Is Critical for Data Centers in the Education Sector

 

Most students have put down their pencils and their books by now for their summer break. The IT managers at their institutions of learning, however, are hard at work assessing data center needs in anticipation of September’s first class bell. By the time school resumes, networks will have to be in place for a seamless start to the new academic year.

Like any organization, the success of a school system depends heavily on the health and operational efficiency of its core network. Not only does the network store critical information related to student and faculty records, but it also controls alarm and security systems as well as environmental systems.

Unfortunately, network downtime is a big problem for many school systems. Many school systems are already struggling to make ends meet.  With budgets stretched to the max, there is no allotment for network downtime.

A perfect example of the need for advanced power and environmental monitoring can be seen in the Davis, California, school district, which last year experienced prolonged network failure when its data center’s air conditioning unit failed. The failure caused its servers to overheat, as the room temperature rose to 120 degrees. As a result, the school system experienced lost data and damaged hardware.

To prevent such an undesirable scenario from occurring, IT managers are encouraged to plan ahead to prevent network outages. A great way to accomplish this is to install a data center power monitoring solution that can provide both real-time power consumption statistics as well as reports that can accurately predict and report power usage trends. Data center managers need the ability to oversee how each network component is performing in order to understand where issues are arising on the network.

Click here for more information about how Server Technology can help you plan ahead for the coming school year. 

Avoid IoT-Related Power Constraints With a Power Monitoring and Distribution Solution

 

The era of the Internet of Things (IoT) is officially upon us, as businesses become increasingly connected to the Web. From smart light bulbs and thermostats to automated appliances, machine-to-machine communication applications are spreading quickly amongst cutting-edge companies across all verticals. By 2020, we will see five to 10 times the amount of devices, such as smartphones and computers, with native Internet connectivity, according to benchmark research by Ponemon.

As the IoT grows in popularity, companies will be faced with many new challenges related to powering connected devices as well as storing and managing the data they collect. Connected devices could wreak havoc on a company’s power supply and servers if left unchecked, and could lead to skyrocketing power bills, unsustainable practices and power outages.

So, what’s the key to staying on top of your company’s energy consumption as businesses move forward at full speed into the connected era? You need to invest in a power monitoring and distribution solution that can analyze your power usage in real time. A reliable power monitoring solution will also make it possible to plan ahead for future power capacity issues so your business doesn’t get caught in an unexpected power pinch. Monitoring your power consumption will give data center managers peace of mind knowing that uptime will cease to be an issue.

With Server Technology’s power distribution solution, keeping track of your energy usage has never been easier. Our smart power distribution units are capable of providing real-time power data to mobile devices and Sentry Power Manager (SPM), so business leaders can analyze power consumption from the executive suite instead of in the data center. Click here for more information about how Server Technology can help your business meet the demands that the IoT will bring. 

Don’t Let Unexpected Data Center Capacity Changes Knock Your Business for a Loop

 

Suppose your business needs to rapidly scale and onboard thousands of new customers in a short amount of time. Will you have the storage capacity to accommodate such a spike in customer volume?

Capacity planning is often overlooked by data center technicians, a mistake which results in reactionary managerial decisions like having to redistribute workloads amongst servers or outsource to another company for more capacity. Here are some tips for making sure this doesn’t happen in your data center:  

Monitor your power usage over time: You don’t want to exceed your data center’s power capacity. Keep in mind that equipment will increase its power consumption drastically over time. Therefore, the data center you are building will have a much different power draw in one, three, or five years from now.

Understand how your environment impacts your equipment: Don’t forget to factor in temperature and humidity levels when capacity planning. Your cooling techniques can have a dire impact on power consumption levels, overall equipment performance and the longevity of your hardware.

Optimize your racks: The last thing you want to do when scaling your data center is run out of rack space. For this reason, you should strongly consider optimizing your racks to increase storage capacity. Try increasing the density of your servers to free servers and make more room for new customers.

Remember, capacity planning should be an ongoing process. The key to creating a sustainable and efficient data center is understanding what is happening on a day-to-day basis. You should never be in the dark about information related to your servers’ power levels, environmental conditions or rack space. An intelligent power distribution and monitoring solution can provide this information as it occurs and distribute it directly to a mobile device.

For more information on how Server Technology can help provide you with the technology to make power monitoring a breeze, click here.

Is Your Data Center Ready to Handle the Blazing Summer Heat?

 

The U.S. has already seen its share of stormy weather this year. California, for instance, is enduring its hottest year on record and the worst drought in 40 years. And according to AccuWeather, the rest of the summer will be equally as oppressive throughout most of the country.

Unfortunately, extreme weather can wreak havoc on data centers. Storms can cause power outages and fires, which can lead to costly downtime. Additionally, rising temperatures cause data centers to use more water for cooling purposes, which will increase overall energy usage. Here are some vital tools that data center operators will need to ensure uptime in the coming months:

Environmental monitoring: An air conditioning unit or water cooling system is ideal for keeping temperatures from fluctuating in a data center, but it’s not enough to ensure constant uptime. Invest in a robust environmental monitoring suite that will provide valuable metrics related to power, temperature and humidity in server racks.

Real-time alerts: When something goes wrong in your data center, you need to be in the know right away. Look for a solution that will distribute key power-related metrics right to your mobile device. This will prevent you from having to manually check your data center for errors.

Power monitoring: Keeping your data center cool during the warmer months can cost a fortune. Therefore, you want to make sure your data center is not hemorrhaging money to support idle servers or other unused equipment. A data center power monitoring solution will give you the visibility to understand power usage so you can keep a close watch on those expenses.

Click here to learn more about how Server Tech can help your data center make it through summer without a hitch.

SPM Guides You Forward : Part Four - How do I prove redundancy?

 

Redundancy resized 600

 

This is the fourth in a series of blog posts providing tips and tricks for answering common data center questions with the use of SPM. Last month, I gave some guidance on answering, “How do I find candidates for efficiency improvements?” Another major concern is finding losses in redundancy before a power fault causes downtime.

Speak with a Power Expert

Get a Free Trial Version Today

 

Question: How do I prove power system redundancy?

With uptime being of prime importance for most data centers, the redundancy of the power system from power plant to IT device must be sufficiently monitored. Of course, the design of the power system including its redundancy level is based on the cost of downtime; but once this system is in operation, it is critical to monitor based on the expectations set out by that design.

  1. SPM is designed with both the Data Center Manager and the Facilities Manager in mind. Understanding of the infrastructure design is critical to determining if redundancy is being
    maintained.
    1. Power paths should be outlined, and each power distribution device that has SNMP monitoring capability can be polled for critical values using SPM’s Custom Device Template. For those points in the power distribution chain that don’t have SNMP monitoring capability, the SPM Circuits feature can be used to aggregate rack power up to the level of those devices.
    2. As an alternative to monitoring all the way back to the building input, it may be “good enough” to simply monitor up to the nearest ATS. Many times, this is the furthest up the power chain that the administrator of a monitoring system like SPM has access to.
    3. Single points of failure are the bane of the redundancy goal. Whether this be a single-cord IT device or any device up the power distribution chain back to the building source, these are key points for monitoring.
  2. After identification of the key points available within the power distribution chain, monitoring parameters must be determined.
    1. Current is key. Breakers trip due to over-current, thus monitoring of current flow in all legs of the power distribution chain is of critical importance. After setting up the SPM Circuits and Custom Devices, alert level should be set for the safety rated amperages for each leg. Pay special attention to how redundancy is setup in N+1 and N+N configurations at the particular devices being monitored.
    2. 3-phase balancing helps maximize the availability of the power distribution chain. SPM helps keep tabs on this balancing through use of the Circuits feature.
    3. Sometimes each and every device is not intended to be redundant, but rather systems of devices are setup such that a secondary system can pick up the functional load when the other goes down. In these cases SPM monitoring can be applied to clusters of devices with current and power alerts to be sure that they don’t draw more than allowed, putting functional redundancy at risk.
  3. With the monitoring parameters in place, the logistics of alerting and responding should be understood by all personnel involved.
    1. SPM will send email alerts for numerous conditions, including CDU faults, over-current conditions at all monitored levels, and communication problems.
    2. Nuisance alerts should be avoided whenever possible. When unnecessary alerts are sent to personnel, the level of attention diminishes. Be sure to set SPM to only send alerts of particular importance and to send those alerts to particular personnel.
    3. Proactive monitoring will always trump the “fire drill”. SPM allows key power reports and data trends to be run on a user-set schedule and then sends them to specified personnel for review. Identifying potential redundancy issues before they happen will save a lot of downtime in the long run.

Maintaining redundant status at all stages in the power chain in order to withstand single-point faults is of prime concern in the data center. For more information on methods for improving redundant status and monitoring of your data center, contact our technical staff at support@servertech.com.

All Posts