1、AN-04-9-4 Efficient Thermal Management of Data Centers-Immediate and Long-Term Research Needs Cullen E. Bash Associate Member ASHRAE Chandrakant D. Patel Member ASHRAE Ratnesh K. Sharma ABSTRACT Power dissipation within computer rooms or data centers has been steadily increasing over the past decade
2、. Eth the spread of CMOS technology into microprocessors and memory in the 1980s and 1990s, water-cooled mainframe systems were lalgely supplanted by lowerpower air-cooledsystems. These systems were typically stacked into 2-m-high racks for ejcient use of expen- sive data center floor space. Data ce
3、nter environmental cooling infrastructures correspondingly evolved into designs that recir- culate hot exhaust airfrom the computer systems into air-conditioning units. The air-conditioning units remove the heat and return the cool air backinto the room in a closed-loop fashion. These air-cooled inf
4、rastructures are largely open, nonductedenvironments where hot and cold airstreams are free to mix. The evolution of microprocessor fabrication technology has enabled the construction of high-power processors. The push by business, academia, and consumers for greater processing speed has motivated t
5、he design of computer systems that enable the greatest number of processors, and, thus, the greatest processing powel; per rack volume. This increase in microprocessor densityplaces a great dealofstrain on current computer room environmental control technology. Furthermore, the rate of increase in p
6、ower density in the data center is outpacing that of HVAC technology improvements. Because of this, computer manufacturers are faced with the choice of either limiting system performance in favor of reducedpower consumption or ofproviding customers with higher performance products that are impractic
7、al to deploy. In this papel; we will highlight some of the primary challenges with cooling high-power density data centers. We will demon- strate that existing environmental infrastructures have inherent ineflciencies that can be very costly, and we will explore alter- natives. Additionally, the use
8、 of numerical modeling to diagnoseproblems with data center design and layout will be demonstrated, and limitations to its efective use will be discussed. Finally, the high-power densities involved have increased the needfor a theo- retical treatment of data center thermophysics. We will discuss thi
9、s need in detail and will suggest ways in which it might be addressed. Throughout the papel; focus will be placed on future directions with the hope of instilling enthusiasm for further research and development by academia and industry in this particular area of HVAC&R that will soon reach a critica
10、l point in its continuing evolution. *The full text of this paper can be found in the International Journal of Heating, Ventilating, Air-conditioning and Refrigerating Research, Volume 9, Number 2, April 2003, pp. 137-152. Responses to questionstcomments to this paper will be published in the Research Journal. Cullen E. Bash is a senior scientist, Chandrakant D. Patel is a principal department scientist, and Ratnesh K. Sharma is a research scientist at Hewlett-Packard Laboratories, Palo Alto, Calif. 580 02004 ASHRAE.
