Posts Tagged breakfast and learn series

Don’s Corner: “Is Perimeter Cooling Dead?”

Posted by on March 6, 2012  |  No Comments

Don Melchert, Critical Facility Specialist

“IS PERIMETER COOLING DEAD?”

Traditional data center “room” cooling is unable to accommodate the latest generation of high and variable density IT equipment resulting in cooling systems that are inefficient, unpredictable, and low in power density.  To address these problems row-oriented and rack-oriented cooling architectures have been developed.  Our presentation, “Is Perimeter Cooling Dead” examines and contrasts the 3 basic cooling approaches: room, row, and rack architectures. Each approach has an appropriate application but row-orientated cooling is emerging as the solution of choice for most next generation data centers. Next generation data centers demand the flexibility, predicability, scalability, reduced electrical power consumption, reduced TCO, and optimum availability that row and rack-oriented cooling architectures can provide. Additionally, the factors that gave rise to the establishment and use of the raised floor in the data center environment are presented.  For many applications the use of the raised floor is no longer justified or desirable. To learn more about this topic, “Is Perimeter Cooling Dead” is available for your organization via our unique “Breakfast and Learn” Educational Series For Data Center Professionals.  This series provides the education that will lay the critical found for your organization to run an efficient data center.  Please feel free to contact me for further information at d.melchert@apcdistributors.com or 918-760-8236.

The Advantages of Row and Rack-Oriented Cooling Architectures for Data Centers (White Paper #30) Overview:

Executive Summary:

Latest generation high density and variable density IT equipment create conditions that traditional data center room cooling was never intended to address, resulting in cooling systems that are inefficient, unpredictable, and low in power density. Row-oriented and rack-oriented cooling architectures have been developed to address these problems. This paper contrasts room, row, and rack architectures and shows why row- oriented cooling will emerge as the preferred solution for most next generation data centers.

Highlights:

  • Discuss the following cooling approaches:  room, row and rack-based cooling architectures.
  • Benefit comparison of cooling architectures:  challenges in agility, availability, lifecycle costs, serviceability, and manageability
  • Special issues:  capacity utilization, humidification, electrical efficiency, water near IT equipment, location and redundancy.
  • Elements of the raised floor and problems associated with using a raised floor.
  • Hurdles to eliminating the raised floor
  • Designing without a raised floor.

Conclusion:

The conventional legacy approach to data center cooling using room-oriented architecture has technical and practical limitations in next generation data centers. The need of next generation data centers to adapt to changing requirements, to reliably support high and variable power density, and to reduce electrical power consumption and other operating costs have directly led to the development of row and rack-oriented cooling architectures. These two architectures are more successful at addressing these needs, particularly at operating densities of 3 kW per rack or greater. The legacy room-oriented approach has served the industry well, and remains an effective and practical alternative for lower density installations and those applications where IT technology changes are minimal.

Row and rack-oriented cooling architecture provides the flexibility, predictability, scalability, reduced electrical power consumption, reduced TCO, and optimum availability that next- generations data centers require. Users should expect that many new product offerings from suppliers will utilize these approaches.

It is expected that many data centers will utilize a mixture of the three cooling architectures. Rack-oriented cooling will find application in situations where extreme densities, high granularity of deployment, or unstructured layout are the key drivers. Room-oriented cooling will remain an effective approach for low density applications and applications where change is infrequent. For most users with newer high density server technologies, row-oriented cooling will provide the best balance of high predictability, high power density, and adaptability, at the best overall TCO.

References:

Avoidable Mistakes that Compromise Cooling Performance in Data Centers and Network Rooms (White Paper#49) Overview:

Executive Summary:

Avoidable mistakes that are routinely made when installing cooling systems and racks in data centers or network rooms compromise availability and increase costs. These unintentional flaws create hot-spots, decrease fault tolerance, decrease efficiency, and reduce cooling capacity. Although facilities operators are often held accountable for cooling problems, many problems are actually caused by improper deployment of IT equipment outside of their control. This paper examines these typical mistakes, explains their principles, quantifies their impacts, and describes simple remedies.

Conclusion:

The air distribution system is a part of the data center that is not well understood, and facility operators and IT personnel often take actions involving airflow that have unintentional and adverse consequences to both availability and cost.

Flawed airflow implementation has not been a serious problem in the past, due to low power density in the data center. However, recent increases in power density are beginning to test the capacity of cooling systems and give rise to hot-spots and unexpected limitations of cooling capacity

Decisions such as facing all racks in the same direction are often made for cosmetic reasons to project image; but as users and customers become more educated they will conclude that people who do not implement airflow correctly are inexperienced, which is the opposite of the original intent.

Adopting a number of simple policies and providing a simple justification for them can achieve alignment between IT and Facilities staff resulting in maximum availability and optimized TCO.

References:

Don’s Corner: “Right-Sizing Versus Over-Sizing: Efficiency In The Data Center”

Posted by on February 29, 2012  |  No Comments

Don Melchert, Critical Facility Specialist

“RIGHT-SIZING VERSUS OVER-SIZING: EFFICIENCY IN THE DATA CENTER”

Forecasting and measuring the total cost of ownership (TCO) for Data Center Physical Infrastructure (DCPI) is essential for return-on-investment (ROI) analysis. Oversizing is the main contributor to excess TCO. Oversizing creates inefficiencies in the data center including excess capital cost, operating cost, and specifically energy cost. The average data center operator can achieve the highest return investment in relation to DCPI through rightsizing.  Right-sizing the DCPI system to the load is the key to optimizing TCO and has the most impact on DCPI electrical consumption.  Right-sizing can potentially eliminate up to 50% of the electrical bill in real-world scenarios.  For example, potential electricity cost savings for a typical 1 MW data center  has been shown to be $2,000,000 to $4,000,000 over a typical 10-year life of the facility.  Data center efficiency is key to controlling your energy costs  and should be a topic of significant importance to all data center operators.

The single largest avoidable cost associated with typical data center and network room infrastructure is oversizing.  To learn more about how you can prevent this unnecessary cost, “Right-Sizing Versus Over-Sizing: Efficiency In The Data Center” is available for your organization via our unique “Breakfast and Learn” Educational Series For Data Center Professionals.  This series provides the education that will lay the critical foundation for your organization to run an efficient data center. Please feel free to contact me for further information at d.melchert@apcdistributors.com or 918-760-8236. Additional resources pertaining to this topic are presented below for your reference.

Avoiding Costs from Oversizing Data Center and Network Room Infrastructure (White Paper #37) Overview:

Executive Summary:

The physical and power infrastructure of data centers and network rooms is typically oversized by more than 100%. Statistics related to oversizing are presented. The costs associated with oversizing are quantified. The fundamental reasons why oversizing occurs are discussed. An architecture and method for avoiding oversizing is described.

Highlights:

  • TCO cost drivers and opportunities to control TCO.
  • Information and statistics related to over-sizing.
  • Practical advantages of right-sizing.
  • Energy consumption reduction in DCPI equipment.
  • Examine key reasons why the industry is moving toward modular, scalable DCPI solutions.

Conclusion:

Data centers and network rooms are routinely oversized to three times their required capacity. Oversizing drives excessive capital and maintenance expenses, which are a substantial fraction of the overall lifecycle cost. Most of this excess cost can be recovered by implementing a method and architecture that can adapt to changing requirements in a cost- effective manner while at the same time providing high availability.

References:

Implementing Energy Efficient Data Centers (White Paper #114) Overview:

Executive Summary:

Electricity usage costs have become an increasing fraction of the total cost of ownership (TCO) for data centers. It is possible to dramatically reduce the electrical consumption of typical data centers through appropriate design of the data center physical infra- structure and through the design of the IT architecture. This paper explains how to quantify the electricity savings and provides examples of methods that can greatly reduce electrical power consumption.

Conclusion:

The cost of electricity for data centers is a substantial operating cost that can and should be managed. A data center designed for reduced power consumption also saves other costs such as capital and operating costs associated with power and cooling systems, as well as saving space.

Electrical consumption of existing data centers can be reduced through various low cost methods but primarily via migration to more energy efficient computing platforms. For new data centers, there are additional options both in the IT architecture and in the DCPI architec- ture that can gain much greater savings.

The electrical power consumption is typically shared evenly between the IT loads and DCPI devices. Any rational approach to reduction in electrical usage must treat the combined IT / DCPI design as a system in order to maximize the benefit.

Some equipment providers offer complete standardized data center designs specifically engineered for efficiency, and energy efficiency audit services are available for users desiring to reduce power consumption in existing data centers.

The cost savings opportunities have been shown to be very large yet the investment required to achieve them is small or even zero in some cases, when compared with legacy approaches to data center design.

References:

Determining Total Cost of Ownership for Data Center and Network Room Infrastructure (White Paper #6) Overview:

Executive Summary:

An improved method for measuring total cost of ownership (TCO) of data center and network room physical infrastructure and relating these costs to the overall Information Technology infrastructure is described, with examples. The cost drivers of TCO are quantified. The largest cost driver is shown to be unnecessary unabsorbed costs resulting from the oversizing of the infrastructure.

Conclusion:

Expressing TCO for data center and network room physical infrastructure on a per-rack basis normalizes the measurement of TCO, providing a metric that can be used to compare data centers/ network rooms and to compare different approaches to design.

The use of a TCO calculation tool and method was described. This tool permits the evaluation of cost control strategies, and can estimate TCO for specific installations.

The per rack lifetime TCO of a high availability data center is approximately $120K. The oversizing of infrastructure is a major contributor to this cost, and on average 30% cost savings can be obtained by implementing practical design techniques using modular scalable data center infrastructure.

References: