WSU Energy Program Logo
Bonneville Power Administration Logo
  • Home
  • About
  • Database
      • Browse
      • Energy Systems
        • Building Envelope
        • Electronics
        • HVAC
        • Irrigation
        • Lighting
        • Motors & Drives
        • Multiple Energy Systems
        • Power Systems
        • Process Loads & Appliances
        • Refrigeration
        • Transportation
        • Water Heating
      • Sector
        • Agricultural
        • Commercial
        • Industrial
        • Residential
        • Utility
  • TAG Portal
      • 2017 Residential Lighting TAG (#14)
      • 2016 Multifamily Building TAG (#13)
      • 2015-1 Commercial HVAC TAG (#11)
      • 2014 Residential Building TAG (#10)
      • 2014 Commercial Building TAG (#9)
      • 2013 Information Technology TAG (#8)
      • 2013 ALCS TAG (#7)
      • 2012 Smart Thermostat TAG (#6)
      • 2012 LED Lighting TAG (#5)
      • 2011 Energy Management TAG (#4)
      • 2010 HVAC TAG (#3)
      • 2009 HVAC TAG (#2)
      • 2009 Lighting TAG (#1)
  • Webinars
    • Webinar Archives
  • Glossary
>

Summary

Server Virtualization

Data Management: Virtual Servers vs. Physical Servers

Consolidating the data and processing from a number of partially loaded servers into a single server to cut power use and heat production.

Synopsis:

Without virtualization, most servers use only 6-12% of their capacity but still use most of the power needed for full operation (Glanz, 2012). A virtualized server consolidates compatible sets of data, possibly from different customers' companies, so one physical server may now handle the tasks previously performed by as many as 20 unvirtualized servers. Virtualization can raise utilization rates as high as 96% (Glanz, 2012) and cut energy use in half, as well as offer attractive non-energy benefits. Data center managers likely are motivated less by utilization rates or energy savings than by the prospect of unplugging most of their servers and saving on maintenance and software licenses. 

Most big data centers now use virtualization to some degree, but it is often underutilized. However, only about a third of small businesses, which comprise half of data center servers, have started to virtualize and less than a quarter plan to do more (Bennett, 2012 Pg 3). This is primarily due to misaligned incentives and lack of awareness. Utility programs can raise general awareness, promote the many non-energy benefits of virtualization, and encourage virtualization software and service providers to target this market as well as help larger data centers to virtualize more deeply (Lester, 2011 Pg 14), (Bennett, 2012). 

Until small businesses are willing to outsource to large data centers through cloud computing, virtualization is an opportunity for them to generate substantial, persistent, and cost-effective energy savings. Virtualization also helps prepare businesses to transition to cloud computing.

Energy Savings: 40%
Energy Savings Rating: Comprehensive Analysis  What's this?
LevelStatusDescription
1Concept not validatedClaims of energy savings may not be credible due to lack of documentation or validation by unbiased experts.
2Concept validated:An unbiased expert has validated efficiency concepts through technical review and calculations based on engineering principles.
3Limited assessmentAn unbiased expert has measured technology characteristics and factors of energy use through one or more tests in typical applications with a clear baseline.
4Extensive assessmentAdditional testing in relevant applications and environments has increased knowledge of performance across a broad range of products, applications, and system conditions.
5Comprehensive analysisResults of lab and field tests have been used to develop methods for reliable prediction of performance across the range of intended applications.
6Approved measureProtocols for technology application are established and approved.
Simple Payback, New Construction (years): 1.3   What's this?
Simple Payback, Retrofit (years): 1.3   What's this?

Simple Payback is one tool used to estimate the cost-effectiveness of a proposed investment, such as the investment in an energy efficient technology. Simple payback indicates how many years it will take for the initial investment to "pay itself back." The basic formula for calculating a simple payback is:

Simple Payback = Incremental First Cost / Annual Savings

The Incremental Cost is determined by subtracting the Baseline First Cost from the Measure First Cost.

For New Construction, the Baseline First Cost is the cost to purchase the standard practice technology. The Measure First Cost is the cost of the alternative, more energy efficienct technology. Installation costs are not included, as it is assumed that installation costs are approximately the same for the Baseline and the Emerging Technology.

For Retrofit scenarios, the Baseline First Cost is $0, since the baseline scenario is to leave the existing equipment in place. The Emerging Technology First Cost is the Measure First Cost plus Installation Cost (the cost of the replacement technology, plus the labor cost to install it). Retrofit scenarios generally have a higher First Cost and longer Simple Paybacks than New Construction scenarios.

Simple Paybacks are called "simple" because they do not include details such as the time value of money or inflation, and often do not include operations and maintenance (O&M) costs or end-of-life disposal costs. However, they can still provide a powerful tool for a quick assessment of a proposed measure. These paybacks are rough estimates based upon best available data, and should be treated with caution. For major financial decisions, it is suggested that a full Lifecycle Cost Analysis be performed which includes the unique details of your situation.

The energy savings estimates are based upon an electric rate of $.09/kWh, and are calculated by comparing the range of estimated energy savings to the baseline energy use. For most technologies, this results in "Typical," "Fast" and "Slow" payback estimates, corresponding with the "Typical," "High" and "Low" estimates of energy savings, respectively.

TAG Technical Score:  4.14

Status:

Details

Server Virtualization

Data Management: Virtual Servers vs. Physical Servers

Consolidating the data and processing from a number of partially loaded servers into a single server to cut power use and heat production.
Item ID: 164
Sector: Commercial
Energy System: Electronics--Information Technology
Technical Advisory Group: 2013 Information Technology TAG (#8)
Average TAG Rating: 3.85 out of 5
TAG Ranking Date: 10/25/2013
TAG Rating Commentary:
  1. Solid, well-established technology with significant energy savings. SHOULD NOT receive any utility incentives. VMware is market leader and has over $1 billion in annual revenue - there is no reason to use utility dollars to support what is already a financial no-brainer.
  2. I strongly support this technology. I've observed that it is generally standard practice for most enterprise and large-scale IT departments to use virtualization in new deployments of servers and applications. Utility incentives may still be able to accelerate virtualization in smaller organizations that need additional resources to expand their level of virtualization to older applications that were already running in their data center.
  3. Critical measure for small facilities; not a free ridership issue for smaller DCs (data centers).
  4. It remains to be seen whether this is really an emerging technology in the PNW.
  5. This is not an ET. The market is almost transformed to virtualization and we can only claim savings but not offer incentives.

Synopsis:

Without virtualization, most servers use only 6-12% of their capacity but still use most of the power needed for full operation (Glanz, 2012). A virtualized server consolidates compatible sets of data, possibly from different customers' companies, so one physical server may now handle the tasks previously performed by as many as 20 unvirtualized servers. Virtualization can raise utilization rates as high as 96% (Glanz, 2012) and cut energy use in half, as well as offer attractive non-energy benefits. Data center managers likely are motivated less by utilization rates or energy savings than by the prospect of unplugging most of their servers and saving on maintenance and software licenses. 

Most big data centers now use virtualization to some degree, but it is often underutilized. However, only about a third of small businesses, which comprise half of data center servers, have started to virtualize and less than a quarter plan to do more (Bennett, 2012 Pg 3). This is primarily due to misaligned incentives and lack of awareness. Utility programs can raise general awareness, promote the many non-energy benefits of virtualization, and encourage virtualization software and service providers to target this market as well as help larger data centers to virtualize more deeply (Lester, 2011 Pg 14), (Bennett, 2012). 

Until small businesses are willing to outsource to large data centers through cloud computing, virtualization is an opportunity for them to generate substantial, persistent, and cost-effective energy savings. Virtualization also helps prepare businesses to transition to cloud computing.

Baseline Example:

Baseline Description: Dedicated servers
Baseline Energy Use: 1500 kWh per year per square foot

Comments:

The baseline for virtualization could be defined as a certain number of servers or a certain size of data centers, but the best definition seems to be the total energy use of one square foot of a typical data center. This takes into account the infrastructure (cooling and power distribution systems) energy savings that result from server energy savings and allows the results to be extrapolated to data centers of various sizes.

ENERGY STAR®, in their latest presentation of data center efficiency, estimates that typical data centers use about 400 kBtu/sf/month.  That translates to 1406 kWh/sf/year. Given that smaller data centers are inherently less efficient than larger data centers, this was rounded up to 1500 kWh/sf/year as a reasonable estimation (Sullivan, 2010 Pg 22).

Manufacturer's Energy Savings Claims:

"Typical" Savings: 70%
Savings Range: From 60% to 80%

Comments:

VMware, a market leader providing virtualization software and services, states that data center energy costs can be reduced by 60% to 80% (VMware, 2013) (VMWare, 2011 Pg 2). 

Best Estimate of Energy Savings:

"Typical" Savings: 40%
Low and High Energy Savings: 10% to 70%
Energy Savings Reliability: 5 - Comprehensive Analysis

Comments:

EPA’s ENERGY STAR® training presentation slides from September 2013 note that virtualization reduces energy use by 10% to 40% (Sullivan, 2010 Pg 15).
VMware estimates energy savings at 60% to 80% (VMware, 2013). A regional data center expert estimates 40% to 70% energy savings, with an average of approximately 50%. Most case studies fail to provide enough information to calculate a percentage. The actual amount will vary widely with how deeply the virtualization process is implemented.  Many companies first virtualize their "tier one" applications, and then virtualize their more complex and critical applications and network later. 

Energy can be saved by eliminating unused servers and replacing older servers (even before virtualization). These equipment upgrades could be accomplished any time, so the resulting energy savings do not need to be counted as part of virtualization energy savings; however, those energy savings could be counted as part of the virtualization savings because equipment is typically replaced during the virtualization process. 

Published case studies show a high virtualization rate, but they may have been picked for publication because of that fact, so it is hard to tell what is typical. Additionally, and importantly, translating the consolidation of servers to reductions in overall data center energy use depends on the infrastructure. If the power distribution system and cooling system are already quite oversized, which is not uncommon if central rather than modular systems are used, further reductions in server load can make that equipment less efficient, especially if the cooling system lacks variable speed drives that improve low-load efficiency. 

The energy savings noted in the fields above assume some reasonable average level of effort to further virtualize a medium-sized data center based on the information above.  As indicated by the baseline, these savings reflect the overall data center energy use and include the impact of server energy use reductions on the energy use of infrastructure--cooling and power systems. 

Energy savings reliability was determined to be a level 5 because, as of 2011, 55 utilities in 20 states offered financial incentives for virtualization projects, including the Energy Trust of Oregon (Lester, 2011), however BPA doesn't currently have server virtualization as an incentivized measure.


Finally, note that if a data center consolidates its data through virtualization and then takes on more clients to fill up the remaining servers at that same data density, the data center will now have more energy use per square foot because each server is busier than it was previously. However, that energy use would still be just a fraction of what the energy use would be to accomplish that increased amount of computing without virtualization. Also note that idle servers that are just put to sleep or powered down are still considered part of the data center capacity used to calculate utilization rates if they have not been physically unplugged or removed.

Energy Use of Emerging Technology:
900 kWh per square foot per year What's this?

Energy Use of an Emerging Technology is based upon the following algorithm.

Baseline Energy Use - (Baseline Energy Use * Best Estimate of Energy Savings (either Typical savings OR the high range of savings.))

Technical Potential:
Units: square foot
Currently no data available.
First Cost:

Installed first cost per: square foot
Emerging Technology Unit Cost (Equipment Only): $70.00
Emerging Technology Installation Cost (Labor, Disposal, Etc.): $0.00
Baseline Technology Unit Cost (Equipment Only): $0.00

Comments:

Assuming a small/mid-sized data center uses VMware vSphere standard software, which seems to be the current market leader, the initial cost would be about $10,000. The total cost would depend on what servers, switches, etc. need replacing and how much data center staff time is involved.  This can vary enormously and the process may take months to implement.  It depends on the level of understanding of the data center staff of the complexities of virtualization and thus how much they can do in-house versus hiring a consultant.  A ballpark figure is about $70,000. If the data center is 1,000 square feet, that's about $70 per square foot for the software and for services. These are very rough estimates based largely on discussions with data center experts. In the fields above, these values are modified to result in a more accurate economic payback, which assumes that installation costs are attributable to both the new technology and the baseline technology. Specifically, the full cost of virtualization is input as equipment costs, assuming that existing servers do not need to be replaced except as part of virtualization.  This is an impactful assumption, and the economics would be quite different--and the payback period much shorter--if it were assumed that all the servers needed to be replaced regardless of virtualization.  But for the purposes of this analysis, more conservative assumptions were made.

Because virtualization is primarily a strategy, the cost of implementation is difficult to estimate. The main cost is for the purchase of virtualization "hypervisor" software. International Data Corp. studied virtualization at a Landmark Healthcare facility in 2009. In this study, 63 servers were consolidated onto just three physical servers. Virtualization software cost $3,600 (Energy Star, 2012). 

A storage area network (SAN) will be needed if one is not already in place. Server connections may need to change to match the change in communications that result from server virtualization and to ensure customers can adequately access the new servers. Although there are significant savings in operation and maintenance costs after a virtualization project is completed, some consulting service may be required to accomplish the project. Also, some training of existing IT staff will be needed to help them operate and maintain the virtualized system. The old servers will need to be disposed of or (preferably) recycled. Finally, the infrastructure should be tuned to match the cooling and power needs of the virtualized servers.

Cost Effectiveness:

Simple payback, new construction (years): 1.3

Simple payback, retrofit (years): 1.3

What's this?

Cost Effectiveness is calculated using baseline energy use, best estimate of typical energy savings, and first cost. It does not account for factors such as impacts on O&M costs (which could be significant if product life is greatly extended) or savings of non-electric fuels such as natural gas. Actual overall cost effectiveness could be significantly different based on these other factors.

Detailed Description:

Servers are essentially large computers. However, the full extent of their capacity may be unused, largely because data center managers focus on reliability and not energy efficiency. Until recently, it was fairly common to have a separate physical server for each application. Additional servers were used for testing, staging, and in case of disaster, so there could be multiple servers per application (Energy Star, 2012). In 2012, the McKinsey and Company found the average server utilization rate to be 6% to 12%, and other studies have reached similar conclusions (Glanz, 2012).  

A virtualized server consolidates applications and sets of data, possibly from different customers' companies, so one server may now handle the tasks previously performed by multiple servers. Instead of running many servers with low utilization rates, you can run fewer servers with higher utilization rates. A New York Times article stated that one company has been able to operate at over 96% virtualization by queuing up large jobs and another company shrunk their server space by 60% after virtualization and server replacement (Glanz, 2012). The University of California in Santa Cruz had servers operating at a 5% utilization rate; using virtualization, these servers now operate at 70% utilization rate (LBNL, 2007, page 2).

In addition to a one-time or periodic virtualization, workloads can be orchestrated among servers to maximize the concentration of computing activity on active servers while maximizing the opportunity to power down idle servers for a longer time. Some strategies to accomplish this include: 

  • MAID (massive array of idle disks) concentrates popular data on a new “cache” disk (Colarelli, 2013).
  • PDC (popular data concentration) uses a subset of the server for the most popular data (Pinheiro, 2004).
  • Power-aware caches are used to house the data of spun-down servers to increase their idle time (Francis, 2004).
  • Write-offloading diverts write-access from spun-down disks to active disks, localizing write access (Narayanan, 2008).
  • SRCMap (Sample-Replicate-Consolidate Mapping) is similar to MAID and PDC and uses write-offloading (Verma, 2010).
Not all servers are good candidates for virtualization. Virtualization generally works well with X86 servers, which are currently the most common type. As for minimum appropriate server room size, the National Resources Defense Council (NRDC) estimates that virtualization can be cost-effective for businesses with at least five servers (Bennett, 2012).  VMware has a version of their vSphere virtualization kit that costs only $500, so even small server rooms can take advantage of virtualization (VMware, 2013). Servers with privacy, security, or regulatory restrictions may do best with dedicated servers. 

Servers that are good candidates for virtualization and have similar workload types are grouped and then moved to as many physical servers as are needed to accommodate them in virtual form. It is important to observe server loading for a month to see when computing activity is busiest and combine servers with complementary workloads (e.g., one is busy during the day and another is busy at night) (Energy Star, 2012). Servers that are selected must have adequate memory for the task, as this can be more of a limiting factor than processor speed. An Information Week survey of large data centers found that the median memory (RAM) capacity was 48 GB per server and almost a fourth of these data centers used servers with 128 GB of memory (Marko, 2012). Consolidating servers also consolidates the cooling load. If the virtualization process continues, total data center use may become considerably higher. Therefore, check that the existing cooling system is up to the task (Energy Star, 2012).

Virtualization may be done in phases, as suggested by the Green Grid. The first phase is virtualizing non-critical workloads. The second phase includes critical workloads, which usually involves a need for additional storage and network reconfiguration. The third phase is implementing a “virtual first” policy for future servers. The final phase is to out-source computing to the cloud (Talabar, 2009).

As of 2011, 55 utilities in 20 states offered financial incentives for virtualization projects. Most of these provide a simple prescriptive incentive: $X per server removed. Calculated or customized incentives are more accurate but may be less applicable for small- and medium-sized businesses. Some utilities offer $/kWh for any documented data center savings. The Sacramento Municipal Utility District (SMUD), for example, offers $.04 per kWh saved up to 30% of the project cost or $150,000. Some utilities may want to consider a hybrid model that offers options of prescriptive, calculated, and customized incentives. Utilities should encourage recycling of old servers and work to ensure that those that are not recycled are at least removed from the grid. Utilities may want to skip inspections of smaller projects to help control administrative costs. Finally, larger utilities may do well to assign utility staff to learn about virtualization so they can advise customers.

A side benefit of virtualization incentive programs for utilities is they provide an opportunity to develop a relationship with IT managers who may be willing to consider infrastructure efficiency upgrades after the virtualization project (Lester, 2011). NRDC suggests that these companies’ use of virtualization can be expanded through utility programs with robust marketing and outreach, training, and education programs for IT managers of small server rooms and the IT service provider firms that support them. This would ideally be at a time when IT managers are preparing for a major server room upgrade anyway. Utilities can also articulate the non-energy benefits of virtualization that would apply to small businesses that might lack utility bill incentives. Utilities could also act as aggregators for manufacturers and providers of virtualization services that have not targeted the small business market (Bennett, 2012).

Because large data centers have more readily embraced virtualization than smaller data centers, utilities may be concerned about free-ridership in justifying their incentives to rate-payers. The Green Grid has found that, while many companies may have adopted virtualization, it is typically only at a shallow level with very small consolidation rates. Therefore, utilities still stand to gain substantial energy savings by incentivizing and encouraging customers to get beyond the “low hanging fruit” ("innovation" servers) into deeper savings ("mission-critical" servers) (Talabar, 2009).

Virtualization products and services are provided by VMware, Citrix, Oracle, Red Hat, and Microsoft with costs ranging from $200 (on sale) to tens of thousands of dollars.  Most require or at least encourage annual subscription and support fees. 

Product Information:
VMWare, VSphere Citrix, XenServer Red Hat, Enterprise Virtualization Oracle, VM VirtualBox Microsoft, Hyper-V

Standard Practice:

Over the past five years, virtualization has become fairly common among large, dedicated data centers, but is still less common among smaller server rooms in businesses. In a 2012 study, the NRDC reported that of 30 small businesses (ranging from 3 to 750 employees) surveyed, only a third used virtualization at all, only a quarter of their server stock has been virtualized, and less than a quarter of these businesses planned to increase their adoption of virtualization. NRDC writes, “Unless something is done to encourage small businesses to adopt virtualization, we may see virtualization penetration rates continue to remain low in that segment" (Energy Star, 2012) (Bennett, 2012 Pg 3-5).

Low adoption rates of virtualization is primarily due to unaligned incentives. Over half of the small businesses have leases with a fixed fee for utilities and, therefore, do not stand to benefit directly from cutting energy use. Furthermore, over 90% of small businesses lack the ability to determine server room electrical energy use even if they do pay energy bills directly (Bennett, 2012 Pg 6). However, server rooms can account for 30% to 70% of these organizations' energy costs. Half of these small businesses plan to upgrade their server rooms in the coming year, but with these disconnects and barriers to encourage efficiency improvement projects, these projects are unlikely. 

Of those IT managers who are interested in improving energy efficiency, many have trouble convincing their managers that it is worth their time and effort to learn about the new technologies and strategies that could help them achieve those goals. The IT managers also have trouble reassuring their management about data security concerns. A smaller subset of these business use cloud services for off-site computing or rent their servers so they are not in a position to implement virtualization (Talabar, 2009).

Development Status:

Server virtualization has been discussed at numerous conferences over the past 5 to 10 years. Most large data centers have adopted this strategy to some degree. Software firewalls and data management tools required to accomplish this safely have been developed and consulting firms can help with implementation.

According to InfoWorld, sales of virtual machine and cloud system software grew 17.8% in the first half of 2013. "Virtual machine software unit shipments still remain healthy and growing, but have seen some slowdown in mature markets that have high virtualization rates," IDC analyst Gary Chen said. "Business models are shifting as well, with the hypervisor drawing less direct revenue and increasingly becoming an embedded feature of operating systems and cloud system software." Other factors impacting the virtualization market include stiffer competition for VMware from companies such as Red Hat and Microsoft, as well as the rise of open-source cloud software such as OpenStack, according to Chen (Kanaracus, 2012).

Non-Energy Benefits:

Non-energy benefits include reducing the number of servers needed, thus reducing the resources needed to purchase, set up, and maintain the servers, as well as reducing the number of software licenses needed. 

Virtualization improves a data center’s availability, flexibility, and disaster recovery ability by allowing virtual servers to quickly be moved from one physical server to another, even from one site to another (Bailey, 2009 Pg 5). It also helps that virtual servers can restart applications after a disaster much faster than physical servers (Energy Star, 2012). Virtualization allows data centers to be more responsive to customers’ needs by reducing the time required to deploy a new server (hours instead of days or even weeks required with a physical server deployment) (Bailey, 2009 Pg 5). Virtualization allows data center operators to move entire systems from one physical server to another within seconds to optimize workloads and to allow them to perform maintenance without disrupting work processing. 

The Uptime Institute estimates that decommissioning a single rack of servers generates annual savings of $500 in energy, $500 in operating licenses, and $1,500 in hardware maintenance costs (Energy Star, 2012) (Mstanberry, 2012). VMware estimates that virtualization can cut capital expenditures by 60% and operations expenditures by 30% while providing added monitoring and analytical capability for improved troubleshooting and performance (VMware, 2013). Virtualization is also excellent preparation for transferring computer services off-site to a cloud service.

Virtualization can also reduce real estate costs. The University of California in Santa Cruz had 188 physical servers and was nearly at their maximum capacity. Since virtualization, their number of servers increased to 240, but they still have available capacity and did not need a bigger building (LBNL, 2007 Pg 1).

Southwest Illinois College performed an economic analysis of upgrading their 35 servers in 2011, both without virtualization and using virtualization to consolidate to four physical servers. This generated $280,000 in savings over three years; $150,000 of that was for direct savings on server hardware and networking minus the cost of virtualization software and $130,000 was for indirect savings on cooling costs, server provisioning, and procurement.

IDC studied virtualization at a Landmark Healthcare facility in 2009. There, 63 servers were consolidated onto just three physical servers. Virtualization software cost $3,600 but they saved $60,000 annually for server hardware, backup system software, and operating system licenses (Energy Star, 2012 Pg 16).

End User Drawbacks:

According to Gartner, a multi-national information technology research and advisory company, 30% to 60% of virtualized servers installed between 2010 and 2015 may be less secure than the physical servers they replace. Virtualization is not inherently insecure, but it needs to be done properly to maintain security, and that process is improving. Gartner has identified six contributing factors to this rising vulnerability. One is not involving the information security team in the initial architecture and planning stages.  Another is the possible risks of the hypervisor and virtual machine monitor from hackers. To address this, virtualization vendors should provide a means for detecting when the hypervisor/VMM (virtual machine monitors) layer has been compromised (GlanzGartner, 2012). 

Obtaining per­mission to virtualize servers may be challeng­ing. Ownership of servers may be unclear, and efforts to locate the appropriate parties can delay a virtualization project. Internally, the relationship between IT staff and building management staff may need to change to take full advantage of virtualization opportunities (LBNL, 2007 Pg 2). According to the Uptime Institute, only 20% of data center departments pay their own power bill. For the rest, their facilities or corporate offices take care of it, so IT managers are less aware of the impact of their actions on energy use and may have less incentive to work hard to reduce energy use (Mstanberry, 2012 Pg 2). 

Operations and Maintenance Costs:

Comments:

O&M cost estimates for data centers are not yet available. However, given that virtualized data centers have 50% to 95% fewer servers, O&M costs should not increase once the virtualization project has been completed and the data center staff are trained in O&M duties with the new equipment and software. VMware estimates that operation expenses typically drop 30% while capital expenditures drop 60%. 

The Uptime Institute estimates that decommissioning a single rack of servers generates annual savings of $500 in energy, $500 in operating licenses, and $1,500 in hardware maintenance costs (Energy Star, 2012) (Mstanberry, 2012). VMware estimates that virtualization can cut capital expenditures by 60% and operations expenditures by 30% while providing added monitoring and analytical capability for improved troubleshooting and performance (VMware, 2013).

Effective Life:

Comments:

Virtualized servers have an expected life commensurate with conventional servers, but due to the aggressive development of IT hardware and software, all servers are typically replaced every two or three years.

Competing Technologies:

The primary competing technology (or strategy) for virtualization is out-sourcing IT services to huge data centers operating in the cloud. While these large data centers are likely much more energy efficient than small server rooms, many small businesses are uncomfortable with cloud computing and do not trust cloud services with their private information (NRELBennett, 2011). Virtualization will help small businesses prepare for transitioning to cloud computing in the future. 

The other competing strategy is avoiding virtualization, avoiding the costs and complexities, and maximizing data security.

Reference and Citations:

Energy Star, 01/01/2012. Server Virtualization
Energy Star

NREL, 08/16/2011. Leadership in Green IT
National Renewable Energy Laboratory

Corban Lester, 03/01/2011. An Analysis of Server Virtualization utility Incentives - 2011
The Green Grid

Stratus Technologies, 10/29/2010. Best Practices for Server Virtualization in Mission-Critical Healthcare IT
Stratus Technologies

VMware, 10/15/2013. Automate IT Management
VMware , 1

Sullivan, 2/4/2010. Energy Star for Data Centers
Energy Star , 1

James Glanz, 09/22/2012. Power, Pollution, and the Internet
New York Times

Michelle Bailey, 11/01/2009. The Economics of Virtualization: Moving Toward an Application-Based Cost Model
IDC Software
Special Notes: Sponsored by VMware

Drew Bennett, 02/01/2012. Small Server Rooms, Big Energy Savings: Opportunities and Barriers to Energy Efficiency on the Small Server Room Market
Natural Resource Defense Council
Special Notes: Coauthor is Pierre Delforge. This publication features the results of a survey of small business data centers.

Gartner, 03/15/2010. Gartner Says 60 Percent of Virtualized Servers Will Be Less Secure Than the Physical Servers They Replace Through 2012
Gartner

Kurt Marko, 11/08/2012. Research: State of Servers: Full, Fast, and Diverse
Information Week

LBNL, 1/1/2007. University of California, Santa Cruz Server Virtualization Best Practices Case Study
Lawrence Berkeley National Laboratory

Matt Stansberry, 09/25/2012. Important to recognize the dramatic improvement in data center efficiency
Uptime Institute
Special Notes: This post on the Uptime Institute blog is the first in a series, a conversation about the NY Times articles on the data center industry, particularly Power, Pollution, and the Internet, which is also referenced on this assessment.

VMware, 1/1/2011. How VMware Virtualization Right-sizes Infrastructure to Reduce Power Consumption
VMware

Dennis Colarelli, 11/07/2013. The Case for Massive Arrays of Idle Disks (MAID)”, File and Storage Technologies (FAST)
USENIX: The Advanced Computing Systems Association

Eduardo Pinheiro, 01/01/2004. Energy Conservation Techniques for Disk Array-Based Servers
Rutgers University

Qingbo Zhu Francis, 02/01/2004. Reducing Energy Consumption of Disk Storage Using Power-Aware Cache Management
Operating Systems Research Group
Special Notes: Presented at Symposium on High-Performance Computer Architecture (HPCA), February 2004

Dushyanth Narayanan, 01/01/2008. Write Off-Loading: Practical Power Management for Enterprise Storage
Microsoft
Special Notes: From File, Storage Technologies (FAST), 2008

Akshat Verma, 01/01/2010. Energy Proportional Storage Using Dynamic Consolidation
USENIX: The Advanced Computing Association
Special Notes: Presented at File, Storage Technologies (FAST), 2010

Richard Talabar, 01/01/2009. Using Virtualization to Improve Data Center Efficiency
The Green Grid

Chris Kanaracus, 11/07/2012. IDC: In software market, CRM, virtualization, and collaboration show strongest growth
InfoWorld

Rank & Scores

Server Virtualization

2013 Information Technology TAG (#8)


Technical Advisory Group: 2013 Information Technology TAG (#8)
TAG Ranking: 3 out of 57
Average TAG Rating: 3.85 out of 5
TAG Ranking Date: 10/25/2013
TAG Rating Commentary:

  1. Solid, well-established technology with significant energy savings. SHOULD NOT receive any utility incentives. VMware is market leader and has over $1 billion in annual revenue - there is no reason to use utility dollars to support what is already a financial no-brainer.
  2. I strongly support this technology. I've observed that it is generally standard practice for most enterprise and large-scale IT departments to use virtualization in new deployments of servers and applications. Utility incentives may still be able to accelerate virtualization in smaller organizations that need additional resources to expand their level of virtualization to older applications that were already running in their data center.
  3. Critical measure for small facilities; not a free ridership issue for smaller DCs (data centers).
  4. It remains to be seen whether this is really an emerging technology in the PNW.
  5. This is not an ET. The market is almost transformed to virtualization and we can only claim savings but not offer incentives.


Technical Score Details

TAG Technical Score: 4.1 out of 5

How significant and reliable are the energy savings?
Energy Savings Score: 4.1 Comments:

  • This should not be considered as the market is already moving this direction - Free rider
  • Seems like existing programs have come up with some good, tested savings estimates for the measure.
  • Market may soon be saturated. We no longer give incentives due to free ridership.
  • Many older datacenters especially aren't tapping into the full power of their existing servers. A smaller energy footprint can be achieved by increasing the density of server functions on current hardware.
  • Standard practice/free rider issues
  • Savings per unit are very good but I am concerned about he reliability. If the under utilized servers are actually removed from the racks, the reliability goes up but given the short life of server equipment, 1 to 3 years, the savings could be lost if the new servers are not properly sized based on IT needs.
  • Depends on level of consolidation
  • The energy savings that can be attributed to server virtualization are well known and quantifiable, and can be generalized for a prescriptive rebate program model.
  • Energy savings estimates should be updated. many estimates based on 2005 - 2007 EPA study data. Most servers tend to operate with fairly stable energy consumption, which provides a good degree of certainty for base line, proposed, and kWh savings calculations.
  • "Very reliableEspecially for small in building DCs, very few are virtualized and there is a huge opportunity for this.As we discussed, ideally this would be paired with the consolidation and removal of old servers and purchase a few much smaller ones to do the work."
  • Energy savings is very good to great depending on server consolidation ratios, whether or not new, more efficient servers were installed as part of the project.

How great are the non-energy advantages for adopting this technology?
Non-Energy Benefits Score: 4.1
Comments:

  • This change is happening as we speak and is driven by business needs beyond energy savings.
  • Reducing all the space required adds a lot of value to these projects.
  • Performance, space and power constraints drive this measure
  • "Centralized managementReliability opportunities"
  • This is by far the best measure for an IT manager who is facing capacity constraints in an existing facility. Also, the technology allows for the provisioning of new compute resources in minutes, avoiding the delays in procuring new physical assets to meet IT needs.
  • Non-Energy benefits are significant for the end user in terms of maximizing data center space and power utilization.
  • Reduce hardware and space (capital costs), more processing capacity

How ready are product and provider to scale up for widespread use in the Pacific Northwest?
Technology Readiness Score: 4.3
Comments:

  • Technology is ready, but energy savings wouldn't drive these projects, documenting projects is very labor-intensive and E,M&V path isn't well defined.
  • There is a competitive OEM market (VMware and Microsoft) and a robust IT server provider community that will support utility incentive program delivery.
  • This technology is already mature and widely used in most data centers, especially for deployment of new servers
  • This isn't really "emerging" and is well proven - just hasn't achieved market adoption for small in building DCs
  • It does seem that saturation can be reached quickly. Also, because the replacement efforts around this technology has been around a while, so understanding the opportunities that are left in the market.

How easy is it to change to the proposed technology?
Ease of Adoption Score: 4.3
Comments:

  • It takes lots of engineering and design work, as well as lots of IT upgrades.
  • One project took over a year and was very labor intensive.
  • Difficulty in convincing IT personnel to shift part of their operations to a different data center or convincing them to remove servers that they normally view as installed back-up equipment. I expect pushback from IT personnel based on actual or perceived reliability.
  • It is in many ways harder for an IT manager to implement virtualization in house than to migrate to cloud services. Project implementation times are fairly long (often over six months).
  • Use of this technology is very easy and should be considered standard practice for new server deployments. Migrating existing servers to virtual servers is more difficult. Physical to virtual (P2V) migration requires significant labor for IT personnel to establish that the existing application can be moved to a virtual server, and requires additional coordination to move a "live" production application from a physical to virtual server.
  • IT managers might have reservations that need to be overcome with information/education. Its not a "quick fix", but its not overly complicated either.
  • This is not swapping out the servers for applicable servers, there will be creation of space and removal of racks and wiring

Considering all costs and all benefits, how good a purchase is this technology for the owner?
Value Score: 3.9
Comments:

  • Performance, space and power constraints drive this measure
  • Good value with significant long term benefits for utilities. The utility opportunity with virtualization is to accelerate adoption of virtualization in existing applications and equipment in smaller to mid size data centers.
  • Great return on investment, but does require a some up front capital for new servers - reduce maintenance and energy costs will quickly pay back though



Completed:
12/4/2013 3:56:42 PM
Last Edited:
12/4/2013 3:56:42 PM
Contact
Copyright 2023 Washington State University
disclaimer and privacy policies

Bonneville Power Administration Logo