Short-Term Forecasting of CO2 Emission Intensity in Power Grids by Machine Learning

A machine learning algorithm is developed to forecast the CO2 emission intensities in electrical power grids in the Danish bidding zone DK2, distinguishing between average and marginal emissions. The analysis was done on data set comprised of a large number (473) of explanatory variables such as power production, demand, import, weather conditions etc. collected from selected neighboring zones. The number was reduced to less than 50 using both LASSO (a penalized linear regression analysis) and a forward feature selection algorithm. Three linear regression models that capture different aspects of the data (non-linearities and coupling of variables etc.) were created and combined into a final model using Softmax weighted average. Cross-validation is performed for debiasing and autoregressive moving average model (ARIMA) implemented to correct the residuals, making the final model the variant with exogenous inputs (ARIMAX). The forecasts with the corresponding uncertainties are given for two time horizons, below and above six hours. Marginal emissions came up independent of any conditions in the DK2 zone, suggesting that the marginal generators are located in the neighbouring zones. The developed methodology can be applied to any bidding zone in the European electricity network without requiring detailed knowledge about the zone.

[1]  Jianzhou Wang,et al.  An analysis-forecast system for uncertainty modeling of wind speed: A case study of large-scale wind farms , 2018 .

[2]  Urbano Nunes,et al.  Novel Maximum-Margin Training Algorithms for Supervised Neural Networks , 2010, IEEE Transactions on Neural Networks.

[3]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986, Encyclopedia of Big Data.

[4]  Janusz Bialek,et al.  Tracing the flow of electricity , 1996 .

[5]  Jstor.  Journal of the Royal Statistical Society. Series D, (The statistician) , 1993 .

[6]  Goran Strbac,et al.  Contributions of individual generators to loads and flows , 1997 .

[8]  Henrik Madsen,et al.  Evaluation Method for the Hourly Average CO2eq. Intensity of the Electricity Mix and Its Application to the Demand Response of Residential Heating , 2019, Energies.

[9]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[10]  Vladimir Ceperic,et al.  Short-term forecasting of natural gas prices using machine learning and feature selection algorithms , 2017 .

[11]  Larry E. Toothaker,et al.  Multiple Regression: Testing and Interpreting Interactions , 1991 .

[12]  A. Hawkes.  Estimating marginal CO2 emissions rates for national electricity systems , 2010 .

[13]  L. D. Monache,et al.  An analog ensemble for short-term probabilistic solar power forecast , 2015 .

[14]  Zhang Yang,et al.  Electricity price forecasting by a hybrid model, combining wavelet transform, ARMA and kernel-based extreme learning machine methods , 2017 .

[15]  William D'haeseleer,et al.  An evaluation method for calculating the emission-responsibility of specific electric applications , 2000 .

[16]  Anika Regett,et al.  Emission Assessment of Electricity: Mix vs. Marginal Power Plant Method , 2018, 2018 15th International Conference on the European Energy Market (EEM).

[17]  Michael Y. Hu,et al.  A Cross‐Validation Analysis of Neural Network Out‐of‐Sample Performance in Exchange Rate Forecasting , 1999 .

[18]  E. R. Hitchin,et al.  Interactions between electricity-saving measures and carbon emissions from power generation in England and Wales , 2006 .

[19]  William D'haeseleer,et al.  The influence of the instantaneous fuel mix for electricity generation on the corresponding emissions , 2000 .

[20]  S. West,et al.  Multiple Regression: Testing and Interpreting Interactions. , 1994 .

[21]  Jun Liang,et al.  Short-term wind power combined forecasting based on error forecast correction , 2016 .

[22]  C. Marnay,et al.  Estimating carbon dioxide emission factors for the California electric power sector , 2002 .

[23]  James D. Hamilton.  Time Series Analysis , 1994 .

[24]  R. Tibshirani.  Regression shrinkage and selection via the lasso: a retrospective , 2011 .

[25]  Florentina Paraschiv,et al.  Extended forecast methods for day-ahead electricity spot prices applying artificial neural networks , 2016 .

[26]  Azim Heydari,et al.  Renewable Energies Generation and Carbon Dioxide Emission Forecasting in Microgrids and National Grids using GRNN-GWO Methodology , 2019, Energy Procedia.