Power Usage Effectiveness In Data Centers

PUE is defined as ratio of total facility power to the total power delivered to the IT equipment. Based on some short comings and uncertainty in measuring the power of facility and IT other metrics were proposed to represent the energy efficiency more accurately. Power Usage Effectiveness (PUETM) has been proposed by The Green Grid (TGG) about a decade ago and it became a popular indicator of data center energy efficiency performance.The Green Grid has published two metrics to evaluate the energy efficiency of data centers – Power Usage Effectiveness (PUE), and it is inverse data center infrastructure efficiency (DCiE).

PUE has been adopted by the data center community and has been employed frequently to represent a data center energy efficiency. Although, the definition of PUE is simple and straight forward, it can be misleading because it only considers the effectiveness of energy delivery rather that the resulting cooling performance or IT productivity that results .PUE can be used to understand the overall energy efficiency trend of a data center over time and measuring the effect of different IT and cooling arrangements in an operational planning.In addition, the measurement has fundamental limitations such as the inclusion of IT fan power in IT equipment power rather than cooling power and so the results can be skewed.

The concept of the need to measure cooling effectiveness as well as energy delivery effectiveness has been well received and some have started to use this approach to gain a balanced view. However, there is little data yet for owner operators to review so it difficult for them to understand what are reasonable or appropriate performance targets for their facility. The problem stems from the fact that the performance is affected by the data center location, construction and usage. This paper starts from performance data collected from operating data center facilities. This base data set not only provides the first set of data to learn from but it is also used to confirm simulated performance in calibrated models that are then used with confidence to extend the data set for other conditions.The concept of the need to measure cooling effectiveness as well as energy delivery effectiveness has been well received and some have started to use this approach to gain a balanced view. However, there is little data yet for owner operators to review so it difficult for them to understand what are reasonable or appropriate performance targets for their facility. The problem stems from the fact that the performance is affected by the data center location, construction and usage. This paper starts from performance data collected from operating data center facilities. This base data set not only provides the first set of data to learn from but it is also used to confirm simulated performance in calibrated models that are then used with confidence to extend the data set for other conditions.

Representing the thermal performance of a data center by a single PUE number is incomplete and a more holistic metric is required. The Green Grid (TGG) has developed a new view of multiple metrics (TGG Performance Indicator (PI) that beside energy efficiency evaluate facility cooling performance based on IT thermal standards during normal and redundant cooling system failure. TGG PI defines the thermal conformance and resilience of IT as measures of cooling effectiveness along with PUE as a measure of cooling efficiency and displays them in a single view. This view allows the business, not just the technical teams, to observe the trade-off between adjusting thermal performance based on standards and striving energy efficiency and choose the balance that best fits the business need.The data center community is becoming increasingly aware of the need to provide efficient and effective data center. However, beside the publicized PUE figures for high profile hyperscale data centers what cooling performance can a data center operator realistically expect? The introduction of TGG PI offers a view to evaluate not just energy efficiency but the effectiveness of cooling delivery as well. However, does the view of the metrics tell us whether the data center performance is good or bad? This paper shows the PI values for a number of existing data centers and discusses the need for performance data to understand what performance might be expected for different data center types, cooling infrastructures, locations and associated climates.