PROJECT TITLE :

Data Center Energy Consumption Modeling: A Survey

ABSTRACT:

Information centers are vital, energy-hungry infrastructures that run giant-scale Net-primarily based services. Energy consumption models are pivotal in designing and optimizing energy-efficient operations to curb excessive energy consumption in information centers. In this paper, we tend to survey the state-of-the-art techniques used for energy consumption modeling and prediction for data centers and their elements. We conduct an in-depth study of the present literature on information center power modeling, covering a lot of than two hundred models. We tend to organize these models in an exceedingly hierarchical structure with two main branches focusing on hardware-centric and software-centric power models. Beneath hardware-centric approaches we begin from the digital circuit level and move on to describe higher-level energy consumption models at the hardware element level, server level, data center level, and at last systems of systems level. Beneath the software-centric approaches we have a tendency to investigate power models developed for operating systems, virtual machines and software applications. This systematic approach allows us to spot multiple problems prevalent in power modeling of different levels of knowledge center systems, as well as: i) few modeling efforts targeted at power consumption of the entire information center ii) many state-of-the-art power models are primarily based on some CPU or server metrics, and iii) the effectiveness and accuracy of these power models stay open questions. Based mostly on these observations, we conclude the survey by describing key challenges for future research on constructing effective and accurate data center power models.