case study-iscs1

profileTtnsK8Kb
CaseStudy1.pdf

Read the Case Study information and Watch the 3 videos below. As you watch the videos, consider the impact of "big data" on the environment and the responsibility of large online businesses to be socially responsible in terms of controlling both pollution and global warming. Using what you've learned, do the following:

1. Craft an argument identifying the 2 best techniques employed (by any of the 3 companies) to enhance environmental responsibility. The 2 best techniques do not have to be from the same company.

2. Additionally, identify the technique from the case study narrative or videos that you believe to be the LEAST effective in having a positive impact on the environment and explain why.

3. Identify the company (of the 3 in this case study) that you believe to be most environmentally responsible and briefly explain why.

Be sure to support your positions (in parts 1 & 2) with at least 2 external sources - these sources can be used to support either your "best techniques" argument or your "least effective" argument, but the textbook is not considered an external source.

Videos:

Facebook (Note that this video starts at a specific time where the data center is discussed. You're welcome to watch the entire video if you'd like.):

https://www.youtube.com/watch?v=_r97qdyQtIk&t=332sLinks to an external site.

Google:

http://www.youtube.com/watch?v=voOK-1DLr00Links to an external site.

eBay:

https://www.youtube.com/watch?v=HcD47Y-TQQw&t=9sLinks to an external site.

Case:

Consumers of technology constantly demand devices that are smaller, more efficient, and more powerful than the ones they have. But most consumers don’t understand the massive back-end infrastructure that powers their “front end” devices, like mobile phones, smartphones, tablets, and desktop computers.

Take, for example, smartphones and tablet computers. iPhones, Androids, iPads, and other tablets represent a trend in all forms of mobile technology towards smaller devices that perform an increasingly large number of functions. But every time a smartphone or tablet user connects to the Internet, places a call, or sends an instant message, it uses power not only on their phone, but at every step of the infrastructure used to perform

that function. More often than not, data centers are intimately involved in any Internet- based communication.

In 2022, there were over 7 million data centers of all sizes worldwide. IDC estimates that the number of data centers will eventually decline due to the growth of very large cloud mega-data centers. Because most data centers use air conditioning of one sort or another to keep operating temperatures of microprocessor chips within a safe range, they are significant contributors to pollution and global warming. Many data centers do not practice effective energy management and waste billions of kilowatt hours annually. The growth of cloud computing, in particular streaming of music, television, and movies, is expected to accelerate data center power consumption in the next ten years even as the number of data centers declines.

Data centers are growing not only in number, but also in sheer size. For instance, Facebook has a data center which covers approximately 1.1 million square feet and contains thousands of servers. The cost of running large data centers is a significant component of the overall IT budget of firms. There are two components to the energy cost of data centers: the cost of running the computers, and the cost of cooling them. For this reason, large-scale data center operators are seeking a variety of new ways to cool their servers.

Of all the websites in the world, Google and YouTube may get the most hits per day, but no site can top Facebook as far as raw traffic. Facebook is by far the “stickiest” of the top sites, meaning its users spend more time per visit there, so it’s reasonable to argue that no site has a greater need for a robust infrastructure than the social networking giant. With a mind-boggling 2.9 billion monthly active users as of 2022, Facebook faces computing demands that no other company has ever faced. Not only is their site traffic unparalleled, but users are contributing 100s of petabytes of photos and videos on Facebook each day, and that data requires storage.

To manage this demand, Facebook has 18 data centers around the world. They also lease server space across the United States and worldwide. Facebook has chosen locations that allow them to use environmental factors (such as cooling water from rivers, and cooler northern climates) to reduce the costs of cooling computers, and to minimize their carbon footprint. Each location consumes roughly 30 megawatts of electricity. To ensure 100 percent uptime of the flagship Facebook site, each site has backup power. For example, the Oregon location has 14 diesel generators capable of 3 megawatts apiece in case of a power generation failure.

A widely used method for assessing data center efficiency is Power Usage Effectiveness (PUE). PUE measures the ratio of total facility energy divided by IT equipment energy in watts. IT equipment refers to the computers and hard drives used in the facility. Total facility power would include lighting, and cooling the computer equipment, a major cost. PUE measures the energy used to power and cool a data center. In 2012, a typical data center consumed 2 watts of total facility power to support 1 watt of IT equipment. Today the number is much closer to 1.5 because of changes in IT equipment, and

changes in facility power management. The ideal is a PUE of 1, in which case all power was being used to simply operate the IT equipment and no other significant support power for cooling is being used.

Other large tech companies like eBay are developing their own techniques and methods to better evaluate the business impact of their power consumption. The auction giant has revamped the way it views its infrastructure efficiency, using the concept of Digital Service Efficiency (DSE). DSE is like a miles-per-gallon metric used to measure how effectively its power consumption is driving its business. Instead of miles, eBay charts revenue (or other business measure), and instead of gallons, eBay charts kilowatt hours. For instance, eBay is able to understand how many kilowatts it takes to process customer transactions, and what is the carbon emission impact of its data centers. eBay managers chart the efficiency of its data center operations using a dashboard.

Digital Service Efficiency (DSE) helps eBay to see the full cost, business impact, power efficiency (PUE), and environmental impact of customer buy and sell transactions. The dashboard combines PUE with other DSE measures of data center performance. Today, many data centers use both PUE and DSE.

eBay operates one of the largest data center networks in the world, and it has begun to shift from air to water for its data center cooling needs using a cooling technology from Dell called Triton. In large data centers, temperatures can reach 120 degrees in just two minutes if the cooling system became disabled. At this temperature, processors and hard drives begin to malfunction. The traditional method of using air cooling has become increasingly expensive as data centers continue to grow. eBay has begun reconfiguring its server cooling from air to liquid cooling using water which is a more expensive, but also a far more effective process for removing heat. The company already boasts some of the best power usage effectiveness (PUE) ratings in the industry.