The Application of Time Series Forecasting Model for Carbon Emissions Prediction in Electrical Grid: A Step Toward Climate Action
Article Sidebar
Main Article Content
Abstract
This study evaluates the forecasting performance of three models of Autoregressive Integrated Moving Average (ARIMA), Prophet, and Bi-directional Long Short-Term Memory (BiLSTM) in predicting CO2 emissions from the electricity grid in the United States. Using a real dataset from the California Independent System Operator (CAISO) that records CO2 emissions at five-minute intervals between 2018 and 2020, the data underwent preprocessing steps including outlier removal, missing value imputation, and feature selection before model training. ARIMA parameters were determined using statistical tests such as ACF, Partial Autocorrelation Function (PACF), and Augmented Dickey Fuller (ADF), while Prophet addressed seasonality and calendar effects. BiLSTM, a deep learning model, was applied to capture complex temporal dependencies and non-linear relationships in the dataset. The models were evaluated using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) metrics. The results show that BiLSTM achieved the lowest error values (MAE: 266.726; RMSE: 429.228), outperforming ARIMA (MAE: 1728.797; RMSE: 2203.464) and Prophet (MAE: 831.346; RMSE: 1102.884). These findings indicate that BiLSTM is more effective in modeling and forecasting highly variable and long-term CO2 emission data. The study provides valuable insights for researchers and energy sector practitioners by demonstrating that machine learning-based forecasting can support carbon reduction initiatives and improve decision-making for electricity grid management. Moreover, the inclusion of a near-real-time alert system and dashboard design enhances the study’s practical relevance. Despite being limited to U.S. grid data, this research underscores the potential of BiLSTM models in achieving environmentally sustainable energy operations through accurate and timely CO2 emission forecasting.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
All articles published in JIWE are licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) License. Readers are allowed to
- Share — copy and redistribute the material in any medium or format under the following conditions:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use;
- NonCommercial — You may not use the material for commercial purposes;
- NoDerivatives — If you remix, transform, or build upon the material, you may not distribute the modified material.
References
[1] H. Ritchie, P. Rosado, and M. Roser, “Greenhouse gas emissions,” *Our World in Data*, Jun. 2020. [Online]. Available: https://ourworldindata.org/greenhouse-gas-emissions
[2] A. Mostafaeipour, A. Bidokhti, M. B. Fakhrzad, A. Sadegheih, and Y. Z. Mehrjerdi, “A new model for the use of renewable electricity to reduce carbon dioxide emissions,” *Energy*, vol. 238, Art. no. 121602, 2022, doi: 10.1016/j.energy.2021.121602.
[3] Y. Huang, L. Shen, and H. Liu, “Grey relational analysis, principal component analysis and forecasting of carbon emissions based on long short-term memory in China,” *J. Clean. Prod.*, vol. 209, pp. 415–423, 2019, doi: 10.1016/j.jclepro.2018.10.128.
[4] J. Luo, W. Zhuo, S. Liu, and B. Xu, “The optimization of carbon emission prediction in low carbon energy economy under big data,” *IEEE Access*, vol. 12, pp. 14690–14702, 2024, doi: 10.1109/ACCESS.2024.3351468.
[5] K. Leerbeck, P. Bacher, R. G. Junker, G. Goranovic, O. Corradi, R. Ebrahimy, A. Tveit, and H. Madsen, “Short-term forecasting of CO2 emission intensity in power grids by machine learning,” *Appl. Energy*, vol. 277, Art. no. 115527, 2020, doi: 10.1016/j.apenergy.2020.115527.
[6] Y. Li, “Forecasting Chinese carbon emissions based on a novel time series prediction method,” *Energy Sci. Eng.*, vol. 8, no. 7, pp. 2274–2285, 2020, doi: 10.1002/ese3.662.
[7] V. Sawant, “Forecasting carbon dioxide emission,” *National College of Ireland Repository*, 2022. [Online]. Available: https://norma.ncirl.ie/id/eprint/6297
[8] S. H. Shin, N. C. Deb, E. Arulmozhi, N. Tamrakar, O. M. Ogundele, J. Kook, D. H. Kim, and H. T. Kim, “Prediction of carbon dioxide concentrations in strawberry greenhouse by using time series models,” *Agriculture*, vol. 14, no. 11, Art. no. 1895, 2024, doi: 10.3390/agriculture14111895.
[9] U. Shafique and H. Qaiser, “A comparative study of data mining process models (KDD, CRISP-DM and SEMMA),” *Int. J. Innov. Sci. Res.*, vol. 12, no. 1, 2014. [Online]. Available: http://www.ijisr.issr-journals.org/
[10] W. Chen, Y. Cai, L. Zhu, J. Xu, R. Yan, J. Guo, and Z. Yang, “A study on carbon emission prediction model in ceramic industry based on CNN-BiLSTM-attention,” in *Proc. 2nd Int. Conf. Cyber-Energy Syst. Intell. Energy (ICCSIE)*, 2024, doi: 10.1109/ICCSIE61360.2024.10698073.
[11] F. Liu and C. Liang, “Short-term power load forecasting based on AC-BiLSTM model,” *Energy Rep.*, vol. 11, pp. 1570–1579, 2024, doi: 10.1016/j.egyr.2024.01.026.
[12] H. Mirshekali, A. Q. Santos, and H. R. Shaker, “A survey of time-series prediction for digitally enabled maintenance of electrical grids,” *Energies*, vol. 16, no. 17, Art. no. 6332, 2023, doi: 10.3390/en16176332.
[13] H. Habbak, M. Mahmoud, K. Metwally, M. M. Fouda, and M. I. Ibrahem, “Load forecasting techniques and their applications in smart grids,” *Energies*, vol. 16, no. 3, Art. no. 1480, 2023, doi: 10.3390/en16031480.
[14] G. Dudek, P. Piotrowski, and D. Baczynski, “Intelligent forecasting and optimization in electrical power systems: Advances in models and applications,” *Energies*, vol. 16, no. 7, Art. no. 3024, 2023, doi: 10.3390/en16073024.
[15] R. Zhang, L. Xu, X. Pan, G. Zhang, Z. Yu, B. Chu, M. Wei, and H. Zhang, “Optimization of LSTM model based on sparrow search algorithm for carbon emission prediction,” in *Proc. 2nd Int. Conf. Cyber-Energy Syst. Intell. Energy (ICCSIE)*, 2024, doi: 10.1109/ICCSIE61360.2024.10698078.
[16] M. Aamir, M. A. Bhatti, S. U. Bazai, S. Marjan, A. M. Mirza, A. Wahid, A. Hasnain, and U. A. Bhatti, “Predicting the environmental change of carbon emission patterns in South Asia: A deep learning approach using BiLSTM,” *Atmosphere*, vol. 13, no. 12, Art. no. 2011, 2022, doi: 10.3390/atmos13122011.
[17] H. Sankaradass, “Predicting CO2 emission from power industry using machine learning,” 2024.
[18] S. C. Patole, “Time series forecasting of methane emissions from livestock using machine learning,” M.Sc. research study, Data Analytics, 2021.
[19] S. Namboori, “Forecasting carbon dioxide emissions in the United States using machine learning,” M.Sc. research study, Data Analytics, 2020.
[20] T. Ozcan, A. K. Konyalioglu, and T. Beldek, “Deep learning based models for the CO2 emission forecasting in Turkey,” in *Proc. 10th Int. Conf. Environmental Management, Engineering, Planning and Economics*, Skiathos Island, Greece, 2023, pp. 5–9.