Green IT : A 360-Degree Scan of Current Research , Projects and Initiatives
One advantage of edge computing over cloud computing in terms of Green IT is that the decentralized storage and processing of data at the network edge means that large data packets do not need to be sent over a global network and consume bandwidth . In particular , much smaller data that is measured or calculated at short intervals does not need to be stored and processed in larger cloud server facilities . In addition , smaller edge computing devices can be more easily tailored to individual user needs than data centers and servers . This allows organizations to pay more attention to the recyclability and energy efficiency of individual devices , and thus fit into a possible corporate sustainability strategy .
According to Figure 3-1 , the main aspects of a Green Virtual Machine include " cloud computing " and " virtualization ." The topics and research aspects thus essentially coincide with the aspects already mentioned in 3.3.13.3.1 and 3.3.2 . When it comes to data centers , Figure 3-2 shows that the most important topics are cloud computing and energy efficiency , but also virtualization and renewable energy for data center power . The overall topic of ' data centers ’ is also likely to be one of the most important Green IT topics , partly because optimizing data centers involves other important topics such as cloud and edge computing , and partly because the volume of data , the associated computing load and , ultimately , energy requirements will continue to increase in the coming years as global digitization continues . The challenge for data center operators will not only be how to store and process the data , but also how to supply the various components with sufficient energy - a major hurdle in the face of rising electricity prices .
Data centers are therefore a significant factor and there is clearly a great deal of potential for optimization . One problem that arises in this context is how to measure the energy efficiency of a data center . One possible indicator is Power Usage Effectiveness ( PUE ), which is the quotient of the total energy demand of a data center and the separate energy demand of IT . This metric was introduced by The Green Grid in 2006 and is now one of the most widely used metrics for measuring data center energy efficiency .
However , the PUE must be critically analyzed , as it can only be calculated in very general terms and thus ignores specific requirements . For example , it does not take into account the location of the data center or the external climatic conditions . A data center that is located in a very hot place and requires more energy for cooling systems , but is otherwise extremely efficient , could have a lower PUE than a data center that is not particularly efficient but requires less powerful cooling systems because it is located in a cold place , so the overall PUE is lower . Another problem is that PUE only makes sense if the entire IT is running at full capacity , to get a true value for the maximum energy consumption of the IT . In addition , there is no clear definition of which energy sources are included in total data center consumption . Perhaps the biggest criticism of PUE is that it does not take into account IT performance . Only the power consumption is relevant to the PUE , which does not allow any conclusions to be drawn about the actual performance of the data
12 April 2023