Cloud Carbon Footprint
Purpose:: Measure & analyze carbon emissions of cloud environments
Website:: https://www.cloudcarbonfootprint.org/
Docs:: https://www.cloudcarbonfootprint.org/docs/
Source Code:: https://github.com/cloud-carbon-footprint/cloud-carbon-footprint
Community:: https://groups.google.com/g/cloud-carbon-footprint
Description
Cloud Carbon Footprint is an open source tool that provides visibility and tooling to measure, monitor and reduce your cloud carbon emissions. We use best practice methodologies to convert cloud utilization into estimated energy usage and carbon emissions, producing metrics and carbon savings estimates that can be shared with employees, investors, and other stakeholders.
Technology Radar (ThoughtWorks)
Cloud Carbon Footprint | Technology Radar | Thoughtworks
Trial as of 2023-09-27
In our experiments, the estimates between different tools have varied, which is not a huge surprise given that all tools in this space make estimates and multiply estimated numbers. However, settling on one tool, taking a baseline and improving from that baseline is the key usage scenario we've come across, and tools like Kepler may reduce the need for estimates in the future.
Methodology
https://www.cloudcarbonfootprint.org/docs/methodology/
The tool uses mainly the costs as a proxy measure of carbon emissions.
Data sources
- Cloud provider API's for billing and usage
- SPECpower database: data about power consumption at various points of utilization for a wide range of servers
- United States Data Center Energy Usage Report: Average utilization of the servers in hyperscale data centers in 2020 is 50%. This value is used, if the actual vCPU utilization is not available.
- Carbon estimates from different sources (USA: EPA)
- โฆ
Networking
Source: https://www.cloudcarbonfootprint.org/docs/methodology/#networking (accessed on 2024-01-29)
Currently, our application takes into account only the data exchanged between different geographical data centers.
For networking, it is safe to assume that the electricity used to power the internal network is close to 0, or at least negligible compared to the electricity required to power servers.[โฆ]
There have not been many studies that deal specifically with estimating the electricity impact of exchanging data across data-centers. Most studies focus on estimating the impact of end-user traffic from the data center to the mobile phone; integrating the scope of the core network (what we are interested in), the local access to internet (optical fiber, copper, or 3G/4G/5G) and eventually the connection to the phone (WiFi or 4G).
[โฆ]
It is safe to assume hyper-scale cloud providers have a very energy efficient network between their data centers with their own optical fiber networks and submarine cable. Data exchanges between data-centers are also done with a very high bitrate (~100 GbE -> 100 Gbps), thus being the most efficient use-case. Given these assumptions, we have decided to use the smallest coefficient available to date: 0.001 kWh/Gb.
Appendix IV: Recent Networking studies
Discussions:
- Include estimate of bandwidth leaving a data centre ยท cloud-carbon-footprint/cloud-carbon-footprint
- Research coefficient for networking of data leaving a data center ยท Issue #379 ยท cloud-carbon-footprint/cloud-carbon-footprint
- Intra-Region network energy/data transfer coefficient is unclear in the documentation ยท Issue #951 ยท cloud-carbon-footprint/cloud-carbon-footprint
- Networking for traffic leaving a data center ยท Issue #723 ยท cloud-carbon-footprint/cloud-carbon-footprint
Coefficients
Cloud Carbon Coefficients (ccfcoef) is the tool to calculate the coefficients used by CCF.
Usage Coefficients (Energy)
Docs: https://www.cloudcarbonfootprint.org/docs/methodology#appendix-i-energy-coefficients
AWS
- Average Minimum Watts (0% CPU Utilization): 0.74
- Average Maximum Watts (100% CPU Utilization): 3.5
- Average CPU Utilization for hyperscale data centers: 50%
- HDD Storage Watt Hours / Terabyte: 0.65
- SSD Storage Watt Hours / Terabyte: 1.2
- Networking Kilowatt Hours / Gigabyte: 0.001
- Memory Kilowatt Hours / Gigabyte: 0.000392
- Average PUE: 1.135
CSV: https://github.com/cloud-carbon-footprint/ccf-coefficients/blob/main/data/aws-instances.csv
GCP
- Median Minimum Watts (0% CPU Utilization): 0.71
- Median Maximum Watts (100% CPU Utilization): 4.26
- Average CPU Utilization for hyperscale data centers: 50%
- HDD Storage Watt Hours / Terabyte: 0.65
- SSD Storage Watt Hours / Terabyte: 1.2
- Networking Kilowatt Hours / Gigabyte: 0.001
- Memory Kilowatt Hours / Gigabyte: 0.000392
- Average PUE: 1.1
Azure
- Average Minimum Watts (0% CPU Utilization): 0.78
- Average Maximum Watts (100% CPU Utilization): 3.76
- Average CPU Utilization for hyperscale data centers: 50%
- HDD Storage Watt Hours / Terabyte: 0.65
- SSD Storage Watt Hours / Terabyte: 1.2
- Networking Kilowatt Hours / Gigabyte: 0.001
- Memory Kilowatt Hours / Gigabyte: 0.000392
- Average PUE: 1.125
Embodied Emissions Coefficients
Docs: https://www.cloudcarbonfootprint.org/docs/embodied-emissions/
At this moment, we only include Embodied Emissions for the Compute usage types for all the cloud providers we support.
AWS
Usage
On-Premise
Using Cloud Carbon Footprint to estimate On-Premise emissions