<iframe src="//www.googletagmanager.com/ns.html?id=GTM-WHST8N" height="0" width="0" style="display:none;visibility:hidden">

Stay Powered Blog

What comes first, the network or the application?

Posted by Marc Cram on May 3, 2017 11:05:22 AM

Businessman hand working with a Cloud Computing diagram on the new computer interface as concept.jpeg

If you believe many of today’s publications, sensor-laden driverless cars look to become a part of everyday life over the next decade. The processing power needed to handle the flood of data for driving, along with vehicle to vehicle, vehicle to highway, and vehicle to dispatch/management communications is likely to be huge. Edge computing, putting compute infrastructure close to the point of use (beside or over the highway, for example) will likely be called for along with deploying 5G wireless communications for transporting the data.

Here are a few questions to ponder:

  • Will the car companies (Ford, GM, Toyota, Hyundai, Tesla) build their own wireless networks to move that data?
  • Will the city and state governments who manage the roads and highways move that data?
  • Will the wireless network owners be responsible for transport?
  • Will a cloud provider such as Amazon or Google build the network that enables Uber and Lyft to function?


I’d like to hear your inputs on where we are going and how we get there. Email me at marc.cram@servertech.com and @mcram01 on twitter.

Download the White Paper on Edge Computing to Learn More

What’s Better Than Control?  Complete Control.  Get It With SPM.

Posted by RJ Tee on May 1, 2017 11:36:52 AM


Imagine Lennon without McCartney. Steak without potatoes. The Giants without Buster Posey. Sometimes, things just pair together so well you can’t fathom them ever being separated. We like to think the same is true for our rack mount PDUs and our award-winning Sentry Power Manager Software. Separately, they’re still pretty incredible, but when you bring the power of these two elements together, the greatness compounds exponentially.

Let’s explore how.

Alone, our rack PDUs are powerful right out of the box. With options from metered to smart, to switched, with and without POPS, Server Technology’s PDUs are designed to maximize your uptime while keeping efficiency high, as well. Many offer individual outlet control, expansion modules, environmental monitoring, current monitoring and branch circuit protection. When you bring SPM into the mix, however, you can suddenly roll all your PDUs across all your data centers into a single bird's eye view.

Sentry Power Manager is also a time saver. Its built-in SNAP feature allows you to create templates which can push down vital system, IP and security settings to the PDU. Setting up multiple PDUs? Push settings all at once to each of your PDUs, saving countless hours of frustration and headaches. Configuration is simple with SPM.

Reporting is also a key differentiator with Sentry Power Manager. Looking for an “at-a-glance” view of everything going on in your data center? See overall system statuses, including a programmable slide show of all NOC views and open tabs. Schedule system reports for critical data on billing, carbon footprint, cabinet redundancy and total energy expenditure for a high-level view of all your cabinets and servers. Predictive trending reports will estimate temperature and power usage so you’re never caught off guard.

And, when you combine Server Technology rack mount PDUs with Sentry Power Manager, you’ll enjoy seamless integration via an API that shares power and environmental information with third-party systems such as BMS and DCIM solutions. Get details on system, location, cabinet, outlet, PDU, phase, branch and sensor information in a single pane of glass.

Ready to give SPM a shot? Check out our 120-day free configuration tool and monitoring trial here. For four months, you can put SPM through its paces at no cost to see if it’s the right fit for your data center power monitoring needs. For more details, see the Sentry Power Manager version 6.0 data sheet here and watch our YouTube videos to discover just how easy and efficient Sentry Power Manager really is.

Learn More about Sentry Power Manager

Topics: SPM

Smart Cities Need Fog Computing with Intelligent Power

Posted by Marc Cram on Apr 26, 2017 11:02:06 AM

Businessperson holding media image of city in palm. New technologies-1.jpeg

Mainframes and Moore’s law led to personal computers.  Client-server applications became possible with the first local area networks. Cellular radio systems and Wi-Fi, along with Moore’s law (again) combined with improved battery technology have made laptops, tablets, cell phones, and augmented reality headsets key drivers of internet activity today. Tomorrow’s applications will be more widespread, and possibly less visible. Think smart cities, where the lamp posts and the sidewalks work together to guide you to your destination so you don’t have to watch your progress on a map application on your phone. The solar powered talking trash bin on the corner can call a driverless Lyft for you. Need to make a phone call? Put your hand on the glass of the bus stop shelter and you can have a video call for a few micro-cents.

These distributed “fog” applications need local compute support, and that requires reliable electrical sources to power them along with remote management tools to monitor and report issues to the appropriate companies and agencies.

Are you tasked with enabling these projects?

Would you use this infrastructure if it was available?

I’d like your vision and feedback on this. Drop me a line at marc.cram@servertech.com or @mcram01 on twitter.

Learn More About What We Can Do For Your Edge Computing Application

Topics: intelligent PDUs, smart, fog computing

Living on the Edge? You Need Remote Power Management

Posted by RJ Tee on Apr 24, 2017 10:59:22 AM


Your business is currently in the process of decentralizing its core network and migrating to the “edge” of the network. The goal is to push your servers closer to key markets, in order to eliminate long-haul data transmissions. In doing so, you hope to reduce operating costs and minimize latency for your customers.  

Rest assured, your business isn’t the only one doing it. Edge computing has quickly emerged as one of the top data center trends, and we only see this pattern accelerating as the need for high-speed connectivity increases over the next 10 years.

So, here at Server Technology we support your initiative. But here is one thing to keep in mind:

If you’re not careful about power management, you could be in for a rude awakening once your edge facilities are up and running. We have seen many businesses decentralize their networks intending to save money and improve performance, only to learn the hard way that it can lead to massive spikes in electricity consumption — and unexpected outages.

Here are some challenges you will face while migrating to the edge of the network:

Regional complexities:  Decentralizing your network and opening small hubs in areas like New York City, Los Angeles or Houston means you will have to navigate new electricity markets — with varying rates, energy choices and regional constraints. Cities and towns will also have diverse environmental regulations that you will need to be aware of. For instance, you may have water restrictions that you need to adhere to.

Costs and regulations aside, you may also have to overcome new environmental challenges. For example, opening an edge data center in a place like south Florida or Nevada will subject your facility to higher temperatures. Your servers will be at increased risk of overheating.

Repairs: Servers require periodic maintenance, and they will occasionally need to be shut down. This means that you will have to hire new technicians. Do you have the extra resources to hire data center power maintenance crews in every region that you move to?

Server utilization: You’ll want to beware of “zombie” servers that run in the background unnoticed, silently eating into your monthly budget. It can be very difficult tracking electricity consumption across multiple facilities. It’s important to collect real-time and historical power usage data at the rack level if you want to keep operating costs at manageable level.

Server Technology offers a powerful line of intelligent, horizontal data center power distribution units. Server Technology also offers the Sentry Power Manager, which provides real-time power usage and environmental metrics directly from a centralized, Web –based console.

To learn more about how Server Technology can make your migration to the edge successful, click here.

Learn More About What We Can Do For Your Edge Computing Application

Three Questions for Your Edge Application

Posted by Marc Cram on Apr 19, 2017 10:44:22 AM


Your centralized hyperscale data center is up and running in a stable fashion. Now the software team has come up with applications that are so bandwidth intensive that you are going to have to do some extensive pre-processing in every major locale to reduce network traffic and latency times. Sounds like some form of edge computing is needed, whether that is edge, mobile edge or even fog computing.  And wherever distributed/edge computing is called for, intelligent remote power management is a requisite. 

Here are three questions that should accompany every edge computing deployment:

  • How are you going to avoid a truck roll when hardware is locked up?
  • How are you going to know if you are consuming more power in one location than is typical?
  • How are you going to know if the site is having a thermal issue?

Your Power Strategy Experts are standing by to help you answer these questions and more. 

But I’d like to hear from you – what do consider to be the most important factors when designing an edge computing application?

Email me at marc.cram@servertech.com, or @mcram01 on twitter.

Learn More About What We Can Do For Your Edge Computing Application


Picking the Right Rack Mount PDU For Your Data Center

Posted by RJ Tee on Apr 12, 2017 10:40:19 AM


Decisions, decisions. We often stress over relatively easy decisions more than we reasonably should. One decision that shouldn’t be all that difficult – once you’re armed with the proper knowledge – revolves around which type of rack mount PDU you’ll need to help power your data center for the foreseeable future.

When picking a rack mount PDU for your data center, pinpointing your exact needs before shopping will save you a lot of time and energy in the long run. Perhaps density is your primary concern. Or maybe uptime is on the top of your checklist, along with capacity planning. That’s where Server Technology comes in. We offer smart, switched and other intelligent rack PDU options ranging from ready-made units with super-fast shipping to PDUs precisely customized to meet your every need.

Let’s explore some of those options here. 

Build Your Own

It’s the ultimate in customization. Server Technology’s Build Your Own PDU tool starts with a blank canvas and lets you paint in your power needs – everything from rack mount PDU type to power options, number and types of plugs/outlets and even unit color. Begin by selecting from metered, smart or switched units and construct your own PDU from there. Once you’ve built your virtual PDU, you’ll see it on the screen along with a datasheet and quote for your units. If your needs are very exacting, this is the place to begin. Start building your own rack PDU here.

Fast Movers

Designed to minimize the time between order and delivery, our line of Fast Movers represents some of the most popular PDU configurations based on customer feedback. These rack PDUs can be quickly assembled and shipped, usually within three to five days of your order, meaning reliable power is only days away when you need it in a hurry. This is perfect for those considering a move to a colocation. Often, in a colo setup, your SLA begins the minute you sign the contract, so it’s imperative to move quickly on your power needs. Each of our Fast Movers is fully compatible with our award-winning  Sentry Power Manager software for remote monitoring and management from anywhere in the world.

Smart and Switched Family

Maybe your needs are somewhere in between a fully customized rack PDU and our Fast Movers. For that, check out Server Technology’s Product Selector, which gives you the best of both worlds – quite a few customization options along with some of the fastest shipping in the industry. Here, you’ll find everything from basic to metered, smart and switched PDUs with POPS and PIPs options. These units provide options including individual outlet control, temperature and humidity monitoring, input current monitoring, branch circuit protection and more.

Whatever your needs, Server Technology’s commitment to our customers translates into some of the most dependable, powerful rack mount PDUs on the market. Start shopping PDUs today.  

Topics: rack PDU

Top Reasons Your DCIM Strategy Isn’t Working

Posted by RJ Tee on Apr 10, 2017 10:31:26 AM


Awhile back, you and your team implemented a data center infrastructure management (DCIM) strategy to help control your rapidly-growing department. At the time, your thinking was that DCIM would streamline operations, aid in knowledge-based decision making and help your business respond to changing workloads. The whole point was to make life easier for you and your team members, while also making the data center more efficient and cost-effective for your business (which is now riding almost entirely its network infrastructure).

Let’s face it, though: Things aren’t going exactly as they planned. Your data center is still wasting vast amounts of power on a daily basis, and it’s still suffering from sporadic bouts of downtime. And on top of it, you’re continuously operating in the red zone and upper management is not happy about it.

So, why are your DCIM tools failing to get the job done? Just recently, our Product Manager Robert Faulkner sounded off in The Stack about why so many IT administrators are having trouble with their strategies.

Here are some of the main issues that administrators are having with DCIM:  

  1. A lack of manpower: One thing Faulkner pointed out in the article was that IT teams are being asked to do more and more in their data centers but with fewer resources — including manpower. “This brings up a catch-22 scenario where data center managers have to account for the time it takes to install, implement, integrate, and continually manage and monitor a massive system, while still fighting the seemingly never-ending battles associated with overall business growth,” Faulkner explained. Small IT teams, therefore, require tools that help them work smarter.
  1. Human error: Between 40 to 90 percent of data center downtime can be attributed to human error. So according to Faulkner, the main priority from a power delivery perspective should be to keep workers out of the data center whenever possible. Remote monitoring and management is, therefore, critical for success.
  1. A lack of actionable data: Many DCIM strategies will attempt to monitor and measure every part of the data center. However, they’re not getting much value out of the data they’re collecting because it’s typically all over the place and unrefined. As a result, many data center administrators are making decisions based on assumptions instead of using cold, hard data. This can lead to all sorts of capacity planning issues.

Ultimately, the root cause of the problem comes down to a lack of specific, purpose-build monitoring tools in the data center. Any business looking to improve its power management strategy, in other words, needs to collect real-time intelligence from the PDUs which are powering servers, storage, and network gear.

How Server Technology Can Help Your DCIM Strategy

Server Technology’s Sentry Power Manager (SPM) platform comes with access to an open API that can be used to share critical power and environmental data with other systems like BMS and DCIM. It allows users to see critical information related location, system, outlet, cabinet, PDU, branch, sensor, and phase.

To learn more, click here.

Topics: SPM, DCIM

Hyperscale Demands...

Posted by Marc Cram on Apr 7, 2017 11:29:07 AM

Utility power should just be there. Always on. Never failing. Today’s hyperscale data center designs frequently count on the electric utility to supply them with a stable source of clean renewable energy. Alternatively, some use locally generated power with the utility as a backup.  Combining robust software stacks that incorporate either virtual machine or container technologies in a rack with in-rack UPS solutions ensures a high degree of uptime and failover capability. Your hyperscale data center can’t tolerate a PDU as the weakest link in the power distribution chain. You need the best PDU solution in the business. You need Server Technology.

What are the most important things you look for in choosing a power solution?

  1. Price?
  2. Availability?
  3. Technology?
  4. Reliability?
  5. Support?

I’d like to hear from you. Email me at Marc.Cram@servertech.com or on twitter @mcram01

Topics: Hyperscale

FITARA - Data Center Consolidation Deadline Could Be Pushed Back

Posted by RJ Tee on Apr 3, 2017 11:11:30 AM


Since 2014, federal data centers have been optimizing their facilities under the Federal Information Technology Acquisition Reform Act (FITARA), a money-saving initiative imposed by the federal government that will force certain data centers to close by 2018.

As of right now, the project is moving much too slow. According to MeriTalk, the most recent FITARA scorecard — released on Dec. 6 — shows that federal data centers are far behind where they need to be in their optimization efforts.

How poorly is the project progressing? Twelve out of 24 graded scores generated a C or worse for their efforts. At this pace, it’s unlikely that the majority will meet their goals by 2018.

Fortunately, Uncle Sam is feeling a bit generous right now and may extend the deadline beyond 2018. But he’s not happy about it.

Director of IT issues for the Government Accountability Office Dave Powner recently sounded off about the pace of the project.

 “2018 probably isn’t enough time to get this done. A key recommendation moving forward is extending the sunset provision in FITARA,” Powner stated. “The question is how long to extend it. If an agency really can’t optimize by 2020, should they be in the business of managing a data center? They need to ask themselves that. If agencies can’t operate these things, they need to think long and hard about getting out of the business.”

So, why are federal agencies having such a hard time consolidating their facilities? According to Powner, a major reason is that only a few agencies have tools for server utilization. Right now, there are 4,400 remaining data centers and just 1200 have server utilization tools.

Server Technology is an obvious choice for federal data centers in need of energy utilization tools.

First and foremost, Server Technology’s products are Trade Agreements Act (TAA) compliant, meaning they are made here in the U.S. So federal agencies will have no problem in using Server Technology as a vendor. And plus, since products are made domestically Server Technology can offer fast shipment times for products and accessories. Most products ship between three and 10 days.

The products that can help federal data centers the most are Server Technology’s Web-based power management console, the Sentry Power Manager (SPM), as well as Server Technology’s intelligent power distribution units (PDUs). Federal data center administrators can use these products to gain a clear understanding of power usage and server utilization at the cabinet, zone and location levels.

It should also be noted that Server Technology offers a wide range of products under the umbrella of intelligent PDUs. There is even a “Build Your Own PDU” feature, for custom builds with up to 42 C13 outlets.

To learn more about how Server Technology’s power management solutions for government agencies, click here.

Topics: federal government, government data center, fitara

Educational Efficiency - Rethinking Your Current Strategy

Posted by RJ Tee on Mar 31, 2017 11:33:06 AM



If you were in the position to start from scratch with power distribution, what would you do? For many of our education customers looking at planning a new facility, the answer is to completely rethink the norms.  Many data center managers are making do with the power distribution that came with the building, and for most, the system is not current.  No pun intended. 

Given a new-build situation in which all ideas are on the table, more and more users are looking for better efficiencies and going to higher voltages to support their IT loads.  “We were fortunate to be able to explore all of the options that are out there,” states Dave Fahey, North America Sales Director for Server Technology about a recent campus project.  “The first thought when we sat down with the engineering team was to go with what they knew.  Fortunately, they approached the project with an open mind and looked different distribution voltages.”

Here are a few things to help keep your mind open as you head down this road:

Avoid transformation.  The most typical scenario is to begin with a 480/277 service, commonly delivered to large commercial buildings in the US.  Instead of dialing the service down to 208/120V, either at the UPS or PDU level by way of a step-down transformer, users are specifying an autotransformer in their UPS or PDU that delivers 415/240V to the rack level, and 240 to the appliance.  This method not only saves on equipment cost but also generates a 2% energy savings that would be assigned to the transformer loss.

Mind the gap.  By going to 415/240V, users understand that they will be delivering much higher voltages to the rack, which must be accommodated in the design.  It is important for staff to be educated on working near higher voltages, and to update company change management processes to reflect this accommodation.  Additionally, temperature monitoring and PDU-level controls will be essential.  And don’t forget the plug – electronic equipment operating at 240V will need IEC-based cords!     

Efficiency up, cost down.  The procedural changes are worth their weight in increased efficiencies and energy savings.  On top of the 2% gain realized by eliminating the transformer, most server and storage equipment operates more efficiently at 240V than either 208V or 120V.  Add in savings from avoiding line losses, and users can expect savings in the 4 to 5% range.  According to a Server Technology white paper on the topic, even at a modest 750 kW load, this energy savings translates to $32,850 per year assuming a $.10 kW/h rate.  Over the lifespan of the facility, say 10 years, this equates to $328,500 in savings at the given load.  And the higher the load, the higher the efficiency, and the higher the total savings.

While there may be a learning curve involved with working with new voltages, the reward from higher efficiency is certain.  “It is mostly a matter of rethinking what you know,” comments Fahey.  “Our customer was able to learn about a different side of the power world, and I’m glad they did because the cost savings helped fund the program.”

To see if rethinking your current strategy is right for you, take a look at our white paper on power efficiency gains, or ask us a question in the form on the right.

Topics: education