Designing Energy Efficiency for Traditional Data Center

Abstract Power Management Strategies and the impact of carbon dioxide emissions from data centers across the globe have drawn significant attention worldwide. The rapid growth of energy consumed in data centers has led to 1) huge costs 2) depletion of non-renewable resources such as coal and petroleum, and 3) emission of greenhouse gases like CO2 in the atmosphere. These greenhouse gas significantly contributes to the climate change of the earth. To tackle this challenge, our research deals with modeling the energy resources of data centers, thereby offering insights to reduce the global carbon footprint and energy cost. In our model, we prioritize green energy consumption by eliminating brown energy resources. In this process, we devise an algorithm that can determine the amount of CO2 emission in the atmosphere per hour by different energy resources. We create an energy model for data centers by incorporating the support vector regression algorithm. Our model is adroit at projecting energy consumed in data centers powered by green energy. Our experimental results confirm that our model consistently delivers high prediction accuracy in terms of energy usage in data centers. The model is expected to facilitate data analytic venues to optimize energy efficiency and sustaininability for the development of future data centers.