ComputingComputer ScienceForecastingMachine LearningPredictive AnalyticsCarbon Emissions ManagementGreenhouse Gas AccountingProduction ForecastingTime Series ForecastingCarbon Emissions DataCarbon Emissions ForecastingCarbon Intensity ReductionDay-ahead ForecastingGridsMachine Learning Forecasting ModelsPredictive Emission Modeling
Electricity usage is a substantial source of carbon emissions worldwide. There has been significant interest in reducing the carbon impact of energy usage through supply-side shifts to cleaner generation sources and through demand-side optimizations to reduce carbon usage. An essential building block for these optimizations is future knowledge of the carbon intensity of the supplied electricity. In this paper, we present a Day-Ahead Carbon Forecasting system (DACF) that predicts the carbon intensity from scope 2 emissions in the power grids using machine learning. DACF first computes production forecasts for all the electricity-generating sources and then combines them with the carbon-emission rate of each source to generate a carbon intensity forecast. DACF provides a general approach that works well across a range of geographically distributed regions. DACF has a mean MAPE of 6.4% across the regions. It also achieves an average decrease of 6.4% and a maximum decrease of 8.6% in MAPE compared to the state-of-the-art. We make DACF publicly available so that it is easily accessible to researchers.
5
US Environmental Protection Agency
Choice Reviews Online · 1998 · 5.9K citations
Public Affairs, Environmental Policy, Environmental Sciences +6
Kenneth Leerbeck, Peder Bacher, Rune Grønborg Junker et al. · Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU) · 2020 · 117 citations · Full text
Applied Energy · 2020 · 71 citations · Full text
Gordon Lowry · Building Services Engineering Research and Technology · 2018 · 30 citations