This repository holds the source code for all the experiments conducted for the publication "Learning Causality Structures from Electricity Demand Data," featured in the journal Energy Systems in June 2024. The authors of the paper are Mariano Maisonnave, Fernando Delbianco, Fernando Tohmé, Evangelos Milios, and Ana Maguitman.
In this paper, we present an alternative approach to predictive modeling for future energy demands. It is based on the application of causal detection models to create specifications of how this demand might be caused by different environmental and social factors. We proceed by using a dataset generated by the wholesale electricity company of Argentina (CAMMESA) and selecting four prominent causal detection methods identified in the literature. These methods were selected based on their demonstrated effectiveness and widespread adoption. Since these causal detection methods yield different causal graphs, we were able to construct an ensemble model that achieved better performance for recovering the true causal structure when applied to the full dataset. Also, we show that the variables in the causal model can be used to yield more accurate forecasts of future demands, improving over the informal models used by staff in electricity utilities.
For this project, we used real-world data from CAMMESA, the company that manages Argentina's wholesale electricity market. The dataset tracks electricity consumption in the Gran Buenos Aires metropolitan area from 2012 to 2018. You can access the dataset in the Data Mendeley Repository.
The source code in this repository is licensed under the MIT License - see the LICENSE.md file for details
We welcome contributions from the community. Please open an issue or submit a pull request for any improvements or suggestions.
This work was enabled by support provided by CONICET, Universidad Nacional del Sur (PGI-UNS 24/N051), and ANPCyT (PICT 2019-03944). We would also like to express our gratitude to CAMMESA for providing the dataset for this project.