Sentilla is excited to win the American Business Award for Best Software Product of the Year for Sentilla Energy Manager for Data Centers.

There are essentially two ways to solve the global warming problem: find alternative sources of energy or reduce the energy you're currently using. Wind, solar, and tide power are great. They've come a long way in a short amount of time. But it's going to take a lot more than that to solve this problem because the world's appetite for energy is so immense. In addition to using alternative energy sources, we need to take a closer look at how we use today's energy and find ways to cut back. Improving energy efficiency can be tremendously valuable because the cheapest power plant ever built is the one you don't have to build.

This has never been more profound than in the case of data centers, whose energy consumption, globally, is greater than the country of Israel. This is clearly an area where much can be done and Sentilla Energy Manager for Data Centers is directly addressing this issue.

We appreciate the award and consider it validation that this market segment is not only in need of a solution, but that we are well positioned to provide an answer to this growing problem.

Digital Realty Trust (DRT) announced this week that one of their Santa Clara data centers has been awarded LEED-gold certification. There has been much debate over LEED certification and its role in the data center -- many LEED-platinum buildings have received an exemption from the USGBC to ignore data center energy in the LEED-platinum certification procedure.

DRT's new data center at 1500 Space Park in Santa Clara (located in a building previously occupied by Analog Devices) has also received incentives from Silicon Valley Power for verifiable steps they've taken to reduce the energy consumed by their data centers compared to industry averages. These rebates are estimated between $750,000 and $1,000,000 for the Santa Clara location. In a discussion I had with Mark Bramfitt at PG&E, he confirmed that they too are offering significant incentives for data centers that come to PG&E with verifiable kilowatt-hour savings. Incentive rates for 2009 are typically $0.05 to $0.15 per kwh saved, according to PG&E.

Let's break down DRT's incentive to understand how much energy they've really saved over a traditional data center. First, let's figure out the total amount of energy that may have been saved, based on the $750,000 incentive. On average, incentives are offered at $0.10 per kwh saved and offered on your annualized kwh reduction. Thus, DRT reduced their consumption over a typical data center by 7.5 million kwh over a 1 year period. Put another way, that's a reduction of 856,000 Watts of constant power draw.

That's certainly a lot of power, but to put it in perspective, we need to look at what the entire facility consumed. While DRT has the option to build out over 343,000 square feet of data center space, the initial use of the facility is centered on 34,000 square feet of existing space. According to data from Intel and Nova, a low density data center has a median power usage of 125 Watts per square foot, and we'll give DRT the benefit of the doubt rather than assume their DC is packed with high density equipment and blades. That means the 34,000 square foot facility consumes 4.25MW of power. In fact, this is probably a low estimate, as 1500 Space Park has capacity for 9MW, with expansion on a third feed to 13.5MW.

If you add all this up, it means that 1500 Space Park uses 856,000 Watts less than a traditional datacenter. This is a savings of 16.7% on their energy bills in the best case (plus a nice check from the utility company for $750,000). Not too bad, but there's an opportunity to do better. Savings between 20% and 30% have been seen (for reference, Sentilla has reduced our IT consumption by 24%). But don't take our word for it, Intel touts 23-30% savings for one of their server strategies and VMWare quotes the completely unrealistic number of 80%.

Last month, I noticed an article in Wired, giving us yet another reason to despise spam email (as if we needed more). In addition to stealing our time, energy, and sanity, the article brings to light a study commissioned by McAfee and published by ICF International has quantized the environmental effects of spam. Since spam is largely unwanted, the energy that goes into sending, queuing, delivering, filtering, viewing, and deleting these emails is a complete waste. Yet another reason spammers should be ashamed of themselves.

Of course, the report is really a disguised advertisement for end-user spam filtering tools that McAffee sells, so perhaps it should be taken with a grain of salt. But it got my mind turning, and this focus on the environmental impact of spam really evokes a discussion about a more general question: what are we getting for the energy we spend? In addition to the user-side energy, there's tons of waste at the infrastructure and data-center level, too.

The spam waste is really just the tip of the iceberg of a larger problem: there are very few studies that evaluate the energy spent on networking and computing needs, in the context of useful work done. This is, of course, a difficult problem. The definition of useful work can vary from person to person. In the example above, it's arguable that from a spammer's point of view, the work that these computers is doing is useful, because it gets the advertisement message in front of a large number of eyes. Unfortunately, in a global sense, within some context of social responsibility, the energy used to distribute spam is almost certainly a net loss. Unfortunately the discussion quickly turns into a philosophical debate, which is perhaps why the issue doesn't come up very often.

Consider another example: social networking. The energy devoted to the serving and viewing of social networking websites like Facebook is almost certainly very significant. But how do we assess the global social gain of these sorts of things? They certainly serve well for vanity, and for enabling phatic communication. But is there really a valuable gain that comes from the energy spent on these endeavors? Perhaps this is an argument best left to sociologists.

As our planet moves forward with energy awareness, we must not mask our vision and only look at numbers like kgCO2, kWh, and dollars. We need to consider the value and utility that comes as a result of the expenditure of these things. Since dollars drive the economy, casting the global utility of an action into a dollar amount might be a good starting point. We can also consider some studies that have been done recently to quantize happiness and success, as these take a stab a quantizing abstract sociological qualities in a comparable way.

Recently, there's been a slew of articles about how IT managers have identified that standardized access to power information over SNMP is one of the top ten problems that they face when managing energy.

We were listening. And today we announced the release of Sentilla Energy Manager for Data Centers version 2.1 which integrates all the great things in the original release like the ability to analyze your energy profile at each piece of equipment and we extended that to include third party equipment. That means that, within an hour of installation, you can get a high level overview of what's going on across the entire data center.  

What that gives you is, a single repository of all your energy information in the data center allowing you to begin a process for energy reduction.  That's right, begin a process.  Energy reduction is an ongoing process.  By having a birds-eye view of the entire data center's energy profile, you get an idea of where to start.  This will bring you to an interesting point where you'll need more information to clarify how to reduce your energy consumption.  And that's where the Sentilla Power Analysis Units come in--when you want more information, a more granular view of energy use at each piece of equipment that will lead to specific energy-saving actions.

Listen to Sentilla CEO, Bob Davis discuss the new integration in this audio clip.

Pardon the shameless promotion, but there’s been such great news for Sentilla lately, we just had to share it with you. Sentilla Energy Manager for Data Centers was named a finalist in the American Business Awards last week in the category Best New Software Product of the Year. As part of this award, there’s a subset, the People’s Choice Stevie Awards. People can vote for their favorites here. If interested, there’s still time to cast your vote. Click here to vote. The polls close June 1. Stevie Award winners for both categories will be announced during the annual gala on Monday, June 22, in New York City and on the radio.

This was a pretty big honor, especially coming right on the heels of Sentilla CTO, Joe Polastre, being selected as one of BusinessWeek’s Best Young Tech Entrepreneurs for 2009 and his recognition as one of the Silicon Valley/San Jose Business Journal’s 40 young professionals under the age of 40.

I want to take this opportunity to congratulate Dr. Joe Polastre on his selection to the Silicon Valley/San Jose Business Journal 40 under 40. In the words of the Business Journal, they “looked for people who were not only successful in their professional lives but gave back to the community in their personal lives.” It is an impressive list of 40 people to watch and we are pleased to see Joe honored. This comes on the heels of his selection as one of BusinessWeek’s Best Young Tech Entrepreneurs of 2009 so it has been a very eventful 2009 already.

These awards celebrate Joe’s accomplishments as well as highlight the impact of the work that Sentilla is doing. The release of the Sentilla Energy Manager for Data Centers has generated significant interest and highlights the need for solutions that address the expanding appetite for energy by data centers. We’re excited to see the recognition! Watch this space as we are just getting started!

Congratulations Joe!

Hello, I'm Spence Murray, a member of the Sentilla Server Engineering team. My responsibilities include design and development of core networking and data management technologies for Sentilla Energy Manager. Having been involved in the project since its inception, I've had the pleasure of seeing it evolve into a very useful tool for both energy and network management.

First off, I'd like to congratulate our CTO, Joe Polastre, on his recent selection as a one of BusinessWeek's Best Young Tech Entrepreneurs of 2009. This award is indicative of the growing buzz Sentilla Energy Manager is generating.

During development of Sentilla Energy Manager (SEM), the engineering team often found interesting behaviors among laptops, desktops, servers and other hardware within our offices. Describing some of this information as merely "insightful" just scratches the surface; we're discovering that "awareness" of energy consumption is half the battle. Once we knew more about energy utilization, we were able to do something about it. Replacing less efficient equipment, simply turning off devices, and even changing network configurations can make a significant contribution to energy savings. At the data center scale, these savings can be quite significant, to say the least.

SEM not only provides the display of energy utilization, it also analyzes collected data. Thus, it becomes possible to instruct SEM to detect particular behaviors throughout the data center. Data center operators may decide to be notified when various power usage tolerances are exceeded, or when power distribution changes in undesired ways. Utilization can be tracked over a period of minutes, days weeks or months. All these metrics can be applied to any subset of the data center's various networks. Or even grouped by customer within the data center. Further, SEM's administrative interface can be accessed from a web browser, and configured to give different users specific views of the collected data -- allowing data center operators to provide the value-add of customer-specific views of power usage to their customers.

As an engineer involved in the development of SEM, the usefulness of increased awareness of energy utilization has become extremely apparent. Sentilla's own offices are instrumented with Sentilla smart power meters, which wirelessly send power usage measurements to SEM. In addition, SEM manages off-the-shelf, SNMP-enabled PDU's to provide a comprehensive view of our complete intranet.

BNP Media put on the Green Intelligent Buildings conference in Arlington, VA this spring. I was there, and gave a talk on what sustainability means to green buildings. Utlimately the message was this: There are 3 steps to maintaining a sustainable building -- measure, analyze, and act. While most think they can measure once and expect the result months later to be the same, the collective view was that people are the most disruptive force to a green building. Continually measuring, analyzing, and acting is what differentiates an audit from sustainability.

There were a number of sophisticated companies there, and it was great to learn the different ways that they keep buildings running efficiently. Tridium was quite impressive -- they are wrestling the large Honeywell, Johnson Controls, and Schneider Electric of the world and attacking the SMB market (and, it appears, winning). Many people I talked to had either used Tridium or considered using Tridium. With their appliances, they've connected lots of legacy systems (H/VACs, economizers, etc) to an IP infrastructure, whereby it can be managed remotely. Building infrastructure is becoming more and more sophisticated, and it was great to see BacNet/IP, Modbus, and LonWorks tying back into a larger infrastructure.

Once the data gets back to a management location, Quality Attributes showed a demo of their impressive dashboard. They've tapped into anything with a pulse -- lighting, H/VAC, occupancy, you name it. With this information, they have a series of sophisticated dashboards that allow you to set targets, budgets, and cost provisions. They even have touchscreens you can install in your building to let occupants see their usage and compete against each other.

The important trend is that making buildings more efficient is not just about the data -- sure the data is important but its a means to an end. To make a building more efficient you have to know what to do and how to act on the data. People are a primary contributor to building inefficiency -- by tapping into all the existing information, centralizing it, and knowing the right actions to take -- buildings are adjusted to maintain sustainability every day.

I had the privilege of being one of the only -- and possibly the only -- startup person attending Google's Green Data Center Summit held at their Mountain View campus. While there were a wide variety of talks (which I'll cover with some analysis in a subsequent post), the gadget hacker in me loved how Google unveiled and described their servers.

Completely custom designed and built in Google-style, here's what they did:

• Instead of having a centralized UPS, Google integrated a battery into every server with a charge controller and test circuit. The battery is sealed lead-acid. Basically, it is a car battery. The goal is to keep the server running for "about a minute" until the generator turns on or the A/C power source is switched.
• The power supply ONLY provides 12VDC (notice the yellow 12V wires coming out of the power supply), and the power only goes to the motherboard. The motherboard then directly supplies power to the disks (at 5VDC) and no other voltage conversions occur (with the exception of 1.2-1.8V for the processor). As such, the AC feed of either 208VAC or 230VAC flow directly to the server with no UPS in the middle. The battery backup directly supplies 12VDC during power outages, so no more inverters.
• The power supply is about 92% efficient according to Google.
• The "distributed UPS" solution is estimated by Google to be "99.9%" efficient since there's no power distribution losses by operating directly at the DC voltage of the server.

I fully applaud Google's efforts to reduce the power distribution losses on the way to the server. Check out a picture that I took, and some better high res pics are on the GreenM3 data center blog. You can even see my shirt (elbow) on the right of the 3rd picture. :)

In so many ways, the Cisco announcement was a throwback to the last century. Yes, it was BIG. Satellite uplinks, worldwide audience, a parade of Cisco executives and a roomful of attendees in a world-class venue. John Chambers is extremely compelling and I always enjoy his presentations. I have tremendous respect for him, and for what Cisco has done and is doing for the industry.

The announcement itself was the official unveiling of The Unified Computing System. It is Cisco’s vision for a computing world where the “network is the platform” for all computing needs. The integration of Computing, Virtualization, and Network and Storage access is the central message. It is a platform for innovation, a strategy for execution, and the basis for a partnering strategy that was discussed at great length. The event was short on details about what the new Cisco system actually does; the customer and partner testimonials generally focused on the value of virtualization in the data center, and the resulting advantages this provides for capital and operational efficiencies along with business agility (there was no shortage of high tech speak at this event, too much if you ask me). One of the contentions is that virtualization reduces the requirement for hardware expansion – which I can believe. And this means there is less “stuff” in the data center. Management is simplified, because there is less stuff. Deployment is simplified, because there is less stuff. And, energy is reduced, because there is less stuff.

My information technology background left me wanting additional information about how these benefits would be achieved, wondering how the integration with legacy systems would actually be accomplished (the answer given was “services”), and imagining that the benefit of this would be most pertinent to new installations where the Cisco architecture and implementation would be rolled out from scratch.

I was particularly interested in how this strategy addresses the goal of energy efficiency. The answer is, only indirectly. Energy efficiency is the consequence of the promised benefit of virtualization and equipment optimization. While this makes intuitive and theoretical sense, I don’t feel comforted that this approach will yield any significant energy efficiency gains any time soon. The challenge facing us with respect to reducing the world’s energy use is a massive one. Reading Joe Polastre’s blog on President Obama’s new energy agenda, will remind you of the enormity of the problem and the need for us to move quickly. To do so, energy management needs to be a focus. It needs to be a strategy. Energy information needs to be treated with the same priority and management attention as asset information, network performance or application efficiency. Only then will we have the ability to effect positive change on this problem. The gap between what is really happening with the equipment and infrastructure and the software and management tools that are used in the data center must be closed.

Cisco’s strategy holds great promise, and could well be a game changer as cited in the announcement. But it isn’t enough. Make Energy Management a strategy; make it a priority.