Approach that schedules computing workloads based on when and where clean energy is available to minimize carbon emissions. Like running heavy tasks when solar or wind power is abundant.
Machine learning training jobs shift to regions and times when renewable energy is plentiful, reducing carbon footprint by 30-50%.
No major cloud offers a single, universal 'carbon-aware scheduler' service across all workloads. Azure and Google Cloud provide carbon-related data/optimization features that can be combined with schedulers/orchestrators to shift flexible jobs to lower-carbon times/regions. AWS and OCI provide sustainability reporting and general scheduling primitives, but no direct, first-party carbon-aware workload scheduler equivalent.