Uncertainty-Aware Decarbonization for Datacenters

TL;DR

This paper introduces a novel uncertainty quantification framework for carbon intensity forecasting in datacenter decarbonization, demonstrating how accounting for uncertainty can significantly reduce carbon emissions through improved scheduling strategies.

Contribution

It is the first to quantify and incorporate temporal and spatial uncertainty in carbon intensity forecasting for datacenter decarbonization using a conformal prediction approach.

Findings

Robust uncertainty quantification achieves target coverage levels.

Incorporating uncertainty prevents 5% and 14% increases in emissions.

Significant reduction of 2.1 and 10.4 tons of carbon emissions in case studies.

Abstract

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.