Data Center Energy Consumption Modeling: A Survey

By Miyuru Dayarathna, Yonggang Wen. IEEE Communications Surveys and Tutorials, 2016

1,034 citations recorded by the source corpus.

Data centers are critical, energy-hungry infrastructures that run large-scale Internet-based services. Energy consumption models are pivotal in designing and optimizing energy-efficient operations to curb excessive energy consumption in data centers. In this paper, we survey the state-of-the-art techniques used for energy consumption modeling and prediction for data centers and their components. We conduct an in-depth study of the existing literature on data center power modeling, covering more than 200 models. We organize these models in a hierarchical structure with two main branches focusing on hardware-centric and software-centric power models. Under hardware-centric approaches we start from the digital circuit level and move on to describe higher-level energy consumption models at the hardware component level, server level, data center level, and finally systems of systems level. Under the software-centric approaches we investigate power models developed for operating systems, virtual machines and software applications. This systematic approach allows us to identify multiple issues prevalent in power modeling of different levels of data center systems, including: i) few modeling efforts targeted at power consumption of the entire data center ii) many state-of-the-art power models are based on a few CPU or server metrics, and iii) the effectiveness and accuracy of these power models remain open questions. Based on these observations, we conclude the survey by describing key challenges for future research on constructing effective and accurate data center power models.

Subfields: Computer Networks and Communications, Hardware and Architecture, Information Systems

View Paper: https://www.semanticscholar.org/paper/381c7853690a0fee6f00d2608a7779737f1365f9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Hardware and Architecture

In Information Systems

Citations in the corpus

Energy efficiency in cloud computing data centers: a survey on software technologies (2022, background): “The authors in [14] discussed the different mechanism and architectures for the design of energy efﬁcient data centers.”
Software-Defined Networking for Internet of Things: A Survey (2017, background): “3) Energy-Efficient Data Center Networking: Data centers are one of the most power-hungry consumers [33], in which most of the power consumption is due to the lack of efficient mechanisms and under-utilization of resources.”
The Internet of Things, Fog and Cloud Continuum: Integration and Challenges (2018, background): “The latter includes the large body of work aiming at minimizing the energy cost of running large-scale infrastructures, data centers in particular [67, 68, 69, 70].”
Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning (2020, background): “See also assorted examinations on carbon accounting, standardized reporting, and policy recommendations (Stechemesser and Guenther, 2012; Dayarathna et al., 2015; IPCC, 2018; Ajani et al., 2013; Bellassen and Stephan, 2015; Andrew and Cortese, 2011; Tang and Demeritt, 2018; Cotter et al., 2011; Tol,”
Usage impact on data center electricity needs: A system dynamic forecasting model (2021, methodology): “An extensive review of data center energy consumption models is from Dayarathna et al [5].”
A Closer Look at Deep Policy Gradients (2018, background): “, 2010) and Kakade (2001). Many recent works document the brittleness of deep RL algorithms (Henderson et al.”
A Scalable Near-Memory Architecture for Training Deep Neural Networks on Large In-Memory Datasets (2018, background): “ess (PUE) [56], the ratio of the power consumed by a data center to the power consumed solely by its compute units: pue= P total P compute Data centers have been reported to have pue = 1:82 [57], [58], and more recently as low as 1.12 [59]. The ﬁgure depends heavily on the local climate and usuall”
Green Internet of Things for Smart World (2015, background): “• DC (data center) [24]: a repository (physical or virtual) for the storage, management, and dissemination of data and information.”
Carbon-Aware Computing for Datacenters (2021, positive): “In response, new methodologies for increasing datacenter power and energy efficiency are required to limit their growing environmental, economic and performance impacts [2], [3].”