MODSIM 2024, Seattle, USA, August 14-16, 2024
Data centers significantly contribute to the global carbon foot- print [2], accounting for 1% of global greenhouse gas emissions in 2021 [3]. As a result of demands from governments and users, and financial, ethical, and other considerations, data center operators have been working to reduce their carbon footprint. The recent energy price crisis and verious sustainability efforts (e.g., through green bond emissions) have made operational expenses a primary cost factor for data centers [6].
For data center service providers to become aware of and accountable for the sustainability impact of their design and operational choices, new carbon-aware design and evaluation capabilities, and guidelines for carbon-aware optimization, are needed. In this work, we consider how the OpenDC datacenter simulator [4] and its energy-aware extension FootPrinter [5], and its extensions for exploring evolving computer ecosystems built around data centers (e.g., Capelin [1]), can support data center designers and operators in exploring various what-if scenarios and assess the environmental impact of their data center. How can OpenDC become a digital twin for large-scale ICT infrastructure, supporting essential scenarios offline and online?
OpenDC currently uses coarse-grained operational data and grid
energy mix information as inputs into a discrete event simulation,
to determine the data center’s operational carbon footprint and
evaluate the impact of infrastructural or operational changes. With
FootPrinter, OpenDC can simulate days of operations of a regional
data center on a commodity laptop in a few seconds, returning the
estimated footprint with marginal error. With Capelin, OpenDC can
simulate long-term scenarios, e.g., the impact of CO2-emission
and energy-related costs over months to years.
We hope to engage the community in the development of method-
ologies and tools for systematically assessing and exploring the
sustainability of data centers and, further, the digital continuum.
The OpenDC project and its extensions are available open source,
open access: https://github.com/atlarge-research/opendc
[1] G. Andreadis et al. 2022. Capelin: Data-Driven Compute Capacity Procurement for Cloud Datacenters Using Portfolios of Scenarios. IEEE TPDS 33, 1 (2022), 26–39.
[2] ACM Technology Council. 2021. Computing and climate change.
https://doi.org/
doi/pdf/10.1145/3483410
[3] IEA. 2022. Data Centres and Data Transmission Networks.
[4] F. Mastenbroek et al. 2021. OpenDC 2.0: Convenient Modeling and Simulation of Emerging Technologies in Cloud Datacenters. In IEEE/ACM CCGrid. 455–464.
[5] D. Niewenhuis and Others. 2024. FootPrinter: Quantifying Data Center Carbon Footprint. In ACM/SPEC ICPE. 189–195.
[6] April Roach and Ewa Krukowska. 2022. Recalibrating global data center energy- use estimates. https://www.bnnbloomberg.ca/big-tech-gets-caught-up-in-europe-s-energy-politics-1.1782670