This page contains a Flash digital edition of a book.
FOCUS INDICES


Issue 5, Aug/Sep 2009


WUF AT THE DOOR?: WATER AND THE DATACENTER


“The Green Grid’s PUE and DCiE metrics have done a lot of good to bring attention to the issue of energy efficiency … However, I find that they have totally ignored a very basic element in their calculations: Water !!” [from DatacenterDyanmics LinkedIn discussion March 2009]


Most debates on the efficiency of the datacenter touch at some point on water. As a resource – pressed by increasing demand, some local scarcity and with strong environmental and geo-political implications – water still has a lower status than power because while the fossil fuel basis of most power generation is not renewable or recyclable, water can be. While news on improved energy efficiency cascades regularly through datacenter media, those focused on water efficiency (such as Microsoft’s initiatives in San Antonio and GE’s in Ohio) are rare.


X‐Values Y‐Values Size 45 34 37 49 46 50 49 32 34 41 42 39 52 39


44 9


27 36 38 23 17 17 21 33 11 54 7


16


1.26 0.99 0.64 0.45 0.52 0.71 0.94 0.92 0.78 0.75 1.49 0.61 0.15 0.94


Even if added as an addendum to the efficiency debate, water is now on the edge of the datacenter radar. This peripheral status is perhaps at variance with the quantum (if not the cost) of waste that is possible. Ramzi Namek, Director of engineering at Total Site Solutions has calculated the annual volume of water needed by a Maryland datacenter at about 61 million gallons. If every person in the New York metropolitan area were to drink the recommended daily amount of water, this quantity of water would keep them going for a week. Datacenter owners and operators have expressed less concern over water costs than they have towards the costs and availability of power, its financial constraint and the skills shortage. However, the worries are there.


50 45 40 35 30 25 20 15 10 5 0


Key Concerns: San Francisco (July 2009) 45.2


Any mention Most major


37.1 32.3 25.8 19.4 12.9 1.6 11.3 1.6


Reduce upf Reduce on Improve eff Improve co Cater for IT Meet CSR Maintain av


14.5 12.9 4.8


Negative ImNo Impact Positive Impact 31.5 35.5 46.3 37.8 36.4 43


60.2 58.1 45


39.4


55.7 58.1 49.9 55


8.4 6.4 8.7 6.4 6.5 7.1 5.6


Maintain availability Meet CSR needs


Throughout 2008 and 2009, the percentage of datacenter owners and operators that believe water costs will have some impact on their operations is between 30% to 55%, while the strength of the negative impact is recognised by 10% to 55% (where the higher the score the worse the perceived outlook). There is little apparent correlation with the average amount of annual precipitation (indicated by the size of each sphere) since the market with the highest annual rainfall (Florida) occurs in the same quadrant as that with the lowest (United Arab Emirates).


There is however a statistical relation between the overall size of a market and the perception of the negative impact that water costs will have over the next 12 to 18 months. The upper half of the chart (green and red) are, with the exception of Madrid, the largest markets studied in terms of facilities, while those where the impact is expected to be less serious are the smaller and regional markets. A further element needs to be hypothesised here – that organisations operating across those markets in the upper half of the chart tend to have a greater proportion of ‘remote’ facilities, where ‘remote’ may also mean


36 www.datacenterdynamics.com Cater for IT growth Improve control Improve efficiency Reduce ongoing costs Reduce upfront costs 0% 10% 32 20% 30% 40% 50% 36 60 60% 70% 80% 90% 36 38 46 58 8 100% 14.5 8.1 40.3


a location away from municipal water supply and therefore more exposed to the availability and costs of static water sources.


Strength of Impact 60


50


Concern about the Issue of Water 2008‐9 Sphere size = average annual rainfall


London New York


40 Paris 30 Amsterdam Chicago 20 Miami 10 Washington 0 30 35 40 Likelihood of Happening 45 50 55 Dubai Seattle Dallas Frankfurt Johannesburg San Francisco Madrid


Concern about the impact of water costs upon operations is highest among those owners and operators of larger portfolios of 5,000 or more racks. These sets of facilities also tend to be run slightly cooler, with a higher power demand and with a slightly higher rate of deploying water-based cooling systems.


There is also evidence that those owners and operators concerned about water are less worried by cost than by environmental and responsibility issues. This impacts upon the selection of equipment for their datacenters (as indicated by the chart below) and also upon their higher than average unprompted concern for issues of facility efficiency and power availability.


Motivations towards Adoption by Attitudinal Group Negative Impact


No Impact 39 43 58 56 45 9 6 55 50 Positive Impact 6 7 7 6


In conclusion, there is strong variance between prompted and unprompted levels of concern about water availability and costs. This suggests that, aside from specific localised problem areas, the main focus of the industry is largely directed to other challenges. Yet the profile of those organisations which indicate greatest concern about water suggests that its current status as a ‘green/ good corporate citizen’ may be undergoing a similar process to other resources towards bottom line and availability concerns. By that time the confluence of other related factors may demand of industry operators nothing less than a total resource strategy. 


Water shortage


Water costs


Power shortage


Power costs


Skills shortage


Reduced investment funding


Increasing legislation


Budget reduction


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56