The Greenly methodology uses "cost & usage" billing files to derive physical data. The study is an activity-based study, which tracks electricity consumption, hardware depreciation, and refrigerant leaks. It even differentiates emissions related to computation, data storage, and data transfer. It is therefore a strict and comprehensive methodology that allows for the best measurement of these emissions and understanding them to better reduce them. In particular, it is the best way to have a representation of cloud emissions per service and per country.
It also allows to give a representation of the countries in which cloud operations are run, and the associated carbon intensity of electricity.
The types of GHG emissions of cloud providers include:
Electricity Consumption: Emissions from generating the electricity used to power servers and data center operations.
Hardware Amortization: Emissions from manufacturing, transporting, and disposing of IT hardware.
Cooling: Emissions from coolant leaks (electricity used for cooling is in the 1st category).
Other Indirect Emissions: Emissions from buildings' amortization and employee commuting. This final category is not taken into account in cloud models, because they are tough to quantify, and represent a small share of overall emissions.
How do we calculate emissions?
In our cloud analysis, these emissions are split between 4 different families of services:
1. Compute
The usage of computation servers and processors (= computing power) to run applications, websites or processes.
The compute power consumed is measured in hours of vCPUs, which represent the usage of a share of one processor during one hour. Basically, each type of CPU has a number of CPUs “cores” - If they have 4 cores, they are theoretically able to run 4 computations at the same time. Each core can be separated in two “threads”, one thread forming one vCPU.
Each vCPU hour used doesn’t consume the same energy, depending on the processor behind it. To estimate the energy consumption, we are using the TDP (thermal design power) and an estimated workload of 40% on average. Note that the power consumption of a processor is high even when it is idle, so running one processor at 100% of its capacity is better than running two processors at 50%.
We also calculate the impact of amortization of servers using data from R740 LCA and the number of vCPU used by the service purchased compared with the total number of vCPU available.
Finally, we calculate the impact of refrigerant gas leaks using a proxy with the electricity consumption and a study from ADEME x ARCEP on European datacenters.
2. Storage
The storage is measured in GB.month. So 1 GB stored during one year is equivalent to 12 GB.month.
To compute the impact of storage linked to electricity and amortization, we base ourself on academical studies, along with the Dell R740 LCA for the impact of storage disks, comparing the electricity consumption of a server with or without the storage disks to estimate the electricity consumption per GB stored. A ratio of 25% of unused storage space is estimated to meet the increase in demand.
Cloud providers offer different types of storage, with more or less availability. To take into account the lower impact of ‘cold’ storage compared to the regular one, Greenly uses a proxy based on the cost of a GB stored for each SKU. The first step is to calculate the cost of storage A for a regular storage solution. Then, we compare it with the cost B of each cold storage SKU. Our conversion factors are then multiplied by the ratio (B/A), the hypothesis being that the cost of a service is almost a linear function of the electricity consumption.
Finally, we calculate the impact of cooling (refrigerant gas leaks) using a proxy with the electricity consumption and a study from ADEME x ARCEP on European datacenters.
3. Transfer
The data transfer is measured in GB, and represents the amount of data transferred either between the datacenter of the client and their users, or data transferred internally between different locations and servers (to duplicate data for example).
We separate 3 types of data transfer :
Internet: For a data transfer using an internet network, linked with the “outside world”. This is the most energy-consuming type of data transfer (40x the electricity consumption of the Inter-region) because it is less optimized (a lot of end-points)
Inter-region: For a data transfer between different countries or regions but using the data center network, well optimized
Intra-region: For a data transfer between two servers located in the same region.
To calculate the network electricity consumption for each type of data transfer, we base ourself on an ARCEP report, giving the energy consumption for the:
Box using FTTx network
Box using xDSL network
Network without box
For the box, this electricity consumption is then compared with the amount of data transferred, so we end-up with an amount of kWh/GB transferred on the network for each of those 3 categories, that are then summed up to arrive to 0.0695 kWh/GB
4. Others services
For all the services that we cannot map in on the 3 first categories (monitoring, support, security, logs, IP addresses…), we use this category that is assessed using an expense-based approach, applying the monetary ratio calculated in the first three categories.
Key figures
Compute:
Server workload used: 40%
Storage:
Regular storage service - Electricity consumption: 0.0065 kWh/GB.month
Regular storage service - Amortization: 0.00056 kgCO2e/GB.month
Transfer:
Internet: 0.0695 kWh/GB
Inter-region: 0.0015 kWh/GB
Intra-region: 0.00075 kWh/GB
These figures have been calculated based on the ARCEP study made in 2022 for the fixed network, itself based on ICT and IEA data (p.71-73). This report calculates an amount of 0.0342 kWh/GB for the fixed network. We also count electricity from the internet box, that makes the electricity consumption raise to 0.0695 kWh/GB transferred (considering Fiber and xDSL networks)
PUE:
AWS: 1.2
GCP: 1.1
Azure: 1.18