APPLYING EXPLAINABLE AI TO TRADITIONAL MACHINE LEARNING MODELS FOR SUSTAINABLE ECONOMIC CONSUMPTION
Main Article Content
Abstract
This study addresses the challenge of predicting solar power generation for Enefit by utilizing Explainable AI (XAI) in conjunction with traditional machine learning models to identify key factors. Accurate prediction is essential for the seamless integration of photovoltaic (PV) systems into the national grid. The research also proposes various machine learning methodologies to improve forecasting accuracy. By combining historical weather data, gas and electricity prices, and projected weather attributes, we developed a range of traditional models, such as linear, nonlinear, and LightGBM (LGBM) models. Experiments were carried out to determine the most effective models, allowing us to elucidate and investigate the factors influencing the issue across different models. The findings contribute to reducing power grid imbalance and improving the efficiency and reliability of renewable energy integration. Future research should focus on integrating real-time data and deep learning techniques to further refine the accuracy and effectiveness of predictions.
Keywords
hotovoltaic system (PV), renewable energy, traditional method, XAI
Article Details
References
Allal, Z., Noura, H. N., Salman, O., & Chahine, K. (2024). Leveraging the power of machine learning and data balancing techniques to evaluate stability in smart grids. Engineering Applications of Artificial Intelligence, 133, 108304.
Bhuiyan, M. A., Zhang, Q., Khare, V., Mikhaylov, A., Pinter, G., & Huang, X. (2022). Renewable Energy Consumption and Economic Growth Nexus—A Systematic Literature Review. Frontiers in Environmental Science, 10. https://doi.org/10.3389/fenvs.2022.878394
Frederiks, E., Stenner, K., & Hobman, E. (2015). The Socio-Demographic and Psychological Predictors of Residential Energy Consumption: A Comprehensive Review. Energies, 8(1), 573–609.
Enefit. (2023). Enefit – Predict energy behavior of prosumers. Kaggle. https://www.kaggle.com/competitions/predict-energy-behavior-of-prosumers
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T. (2017). LightGBM: a highly efficient gradient boosting decision tree. In Proceedings of the 31st Conference on Neural Information Processing Systems (NeurIPS 2017).
Kuzlu, M., Cali, U., Sharma, V., & Güler, Ö. (2020). Gaining insight into solar photovoltaic power generation forecasting utilizing explainable artificial intelligence tools. Ieee Access, 8, 187814-187823. https://doi.org/10.1109/ACCESS.2020.3031477
Machlev, R., Heistrene, L., Perl, M., Levy, K. Y., Belikov, J., Mannor, S., & Levron, Y. (2022). Explainable Artificial Intelligence (XAI) techniques for energy and power systems: Review, challenges and opportunities. Energy and AI, 9, 100169. https://doi.org/10.1016/j.egyai.2022.100169
Marcílio, W. E., & Eler, D. M. (2020, November). From explanations to feature selection: assessing SHAP values as feature selection mechanism. In 2020 33rd SIBGRAPI conference on Graphics, Patterns and Images (SIBGRAPI) (pp. 340-347). Ieee.
Molnar, C. (2024, July 31). Interpretable Machine learning.
Peñasco, C., & Anadón, L. D. (2023). Assessing the effectiveness of energy efficiency measures in the residential sector gas consumption through dynamic treatment effects: Evidence from England and Wales. Energy Economics, 117, 106435.
Sadorsky, P. (2010). The impact of financial development on energy consumption in emerging economies. Energy policy, 38(5), 2528-2535.
Tolliver, C., Fujii, H., Keeley, A. R., & Managi, S. (2021). Green Innovation and Finance in Asia. Asian Economic Policy Review, 16(1), 67–87. https://doi.org/10.1111/aepr.12320
Van den Broeck, G., Lykov, A., Schleich, M., & Suciu, D. (2022). On the tractability of SHAP explanations. Journal of Artificial Intelligence Research, 74, 851-886.
Zhao, H., & Magoulès, F. (2012). A review on the prediction of building energy consumption. Renewable and Sustainable Energy Reviews, 16(6), 3586–3592.