Uncertainty-Aware Decarbonization for Datacenters
This work addresses decarbonization for datacenters by quantifying uncertainty, offering practical emission reductions, though it is incremental in applying existing methods to a new domain.
This paper tackles the problem of carbon intensity forecasting uncertainty for datacenter decarbonization by introducing a conformal prediction-based framework, resulting in preventing a 5% and 14% increase in carbon emissions in case studies, translating to absolute reductions of 2.1 and 10.4 tons.
This paper represents the first effort to quantify uncertainty in carbon intensity forecasting for datacenter decarbonization. We identify and analyze two types of uncertainty -- temporal and spatial -- and discuss their system implications. To address the temporal dynamics in quantifying uncertainty for carbon intensity forecasting, we introduce a conformal prediction-based framework. Evaluation results show that our technique robustly achieves target coverages in uncertainty quantification across various significance levels. We conduct two case studies using production power traces, focusing on temporal and spatial load shifting respectively. The results show that incorporating uncertainty into scheduling decisions can prevent a 5% and 14% increase in carbon emissions, respectively. These percentages translate to an absolute reduction of 2.1 and 10.4 tons of carbon emissions in a 20 MW datacenter cluster.