Analysis of Energy Utilization Metrics as a Measure of Energy Efficiency in Data Centres: Case Study of Wananchi Group (Kenya) Limited Data Centre

Abstract

As society undergoes digital transformation, global demand for Internet services, data storage and network communications increases, leading to increased size and number of data centres (DCs) and the associated energy consumption. Some 1.3% of the world’s electricity is consumed by the data centre (DC) industry and about 2% of the CO <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> emissions across the globe come from the information technology (IT) sector. Because energy is a significant cost to DC operators, metrics have been developed to analyze its utilization. Power Usage Effectiveness (PUE) and Data Center Infrastructure Efficiency (DCIE) are among the globally accepted standard metrics. This work applies PUE and DC <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IE</inf> metrics to evaluate energy utilization at Wananchi Group (Kenya) Limited DC, Nairobi, Kenya. Using monthly electricity bills from the local utility company, results show that the 2021 average annual PUE and DC <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IE</inf> metrics for the DC were 1.8 and 56% respectively. The values compare favorably with those from DCs in Europe (1.8 and 55.6 % respectively). Further, analysis shows that the case study DC facility mainly operates within the American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) allowable envelope-class Al with minimal operation in the recommended envelope.