Data Center Energy

Will we ever be able to accurately assess the carbon footprint of IT? Could a relational footprint methodology be more useful? Paper notes on Pasek et al (2023).

The GHG Protocol needs to evolve to better represent the complexity of how energy markets work.

There is a correlation between the training time and energy consumption, but that doesn’t mean there is a correlation between training time and carbon emissions.

Data centers consuming too much energy at peak times - can’t we just turn them off?

With the grid mix constantly changing, what needs to happen to energy systems to reach the goal of 24/7 carbon free energy? Google has funded two studies to find out.

This is a good paper that makes valid points about the possibilities of migrating flexible IT workloads, however it makes classic assumptions I see in most papers that discuss this topic.

Is cryptocurrency / Bitcoin bad for the environment? In 2019 crypto consumed 70-90 TWh of electricity globally, with 60-70 TWh of that from Bitcoin mining. What that means for carbon emissions depends on where the mining happens.

The methodology is invalid, which the authors acknowledge but ignore. This means the results of this article aren’t particularly useful.

Using a marginal emissions-based sustainability score incentivizes migrating workloads to a region with a lower marginal emissions factor. The emissions factor for that workload would reduce, but does it incentivize the deployment of new clean energy?