Network
Telecommunications network carrying traffic between users and the servers — Wi-Fi, fixed broadband, cellular. Modeled by its energy intensity per gigabyte transferred.
Params
name
A human readable description of the object.
bandwidth_energy_intensity
Electricity consumed per gigabyte transferred end-to-end through the network. Multiplied by the data transferred by jobs to obtain hourly energy use.
Unit: kilowatt_hour / gigabyte.
Backwards links
Calculated attributes
energy_footprint_per_job
Hourly carbon emissions caused by network traffic, broken down by job. Equal to data transferred times bandwidth energy intensity times the country's grid carbon intensity.
Example value: {
EcoLogitsGenAIExternalAPIJob Generative AI model job (37b623a4-7bc): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00: first=0.191 mg, last=0.127 mg, mean=0.105 mg, min=0.0213 mg, max=0.191 mg, std=0.0548 mg,
EcoLogitsVideoGenExternalAPIJob Generative AI video model job (2b5435a6-6b3): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00: first=84.6 mg, last=56.4 mg, mean=46.6 mg, min=9.4 mg, max=84.6 mg, std=24.2 mg,
VideoStreamingJob Video streaming job (8e2f10b8-db0): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00: first=35.7 g, last=23.8 g, mean=19.7 g, min=3.97 g, max=35.7 g, std=10.2 g,
Job Manually defined job (a18ee205-e24): 105192 values from 2025-01-01 00:00:00+00:00 to 2037-01-01 00:00:00+00:00: first=12.2 mg, last=0.387 mg, mean=6.59 kg, min=0.387 mg, max=13.2 kg, std=3.8 kg,
GPUJob Manually defined GPU job (93077a91-895): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00: first=5.74 mg, last=3.83 mg, mean=3.16 mg, min=0.638 mg, max=5.74 mg, std=1.64 mg,
}
Depends directly on:
through the following calculations:
You can also visit the link to Generative AI model job network energy footprint’s full calculation graph.
instances_fabrication_footprint
Network fabrication footprint, currently always empty: e-footprint does not account for the embodied carbon of network infrastructure since it is shared across countless services.
Example value: no value
Depends directly on:
through the following calculations:
You can also visit the link to no value’s full calculation graph.
energy_footprint
Total hourly carbon emissions caused by network traffic, summed across all jobs that route through this network.
Example value: 105192 values from 2025-01-01 00:00:00+00:00 to 2037-01-01 00:00:00+00:00: first=35.8 g, last=0.387 mg, mean=6.59 kg, min=0.387 mg, max=13.2 kg, std=3.8 kg
Depends directly on:
- Generative AI model job network energy footprint
- Generative AI video model job network energy footprint
- Video streaming job network energy footprint
- Manually defined job network energy footprint
- Manually defined GPU job network energy footprint
through the following calculations:
You can also visit the link to Hourly energy footprint’s full calculation graph.