Hybrid Machine Learning for Electricity Load Forecasting: Integration of CatBoost and HGBoost with Optimization Techniques
Abstract
Electricity load consumption stands at the heart of energetic webs, being one of those main building blocks on which the very concept of power consumption in industry and regions originally relies. That includes measures and analyses of electricity consumption from single residential consumers up to large territorial levels, as well as interrelations among human activities, dependencies on technologies, and social development. It has huge implications for energy policy, planning, and environmental sustainability to gain insight into the dynamics of load consumption. Some state-of-the-art machine learning techniques, including the Cat Boost and HG Boost algorithms, are put to work in this work for forecasting electricity consumption levels. Moreover, three metaheuristic optimization algorithms—Sparrow Search Algorithm (SSA), Archimedes Optimization Algorithm (ArchOA), and Chaos Game Optimization (CGO)—were employed to fine-tune model parameters and improve forecasting outcomes. After carefully tuning hyperparameters in detail and performing broad model evaluations, six different predictive models were developed and examined. The best-performing hybrid configuration (CatBoost-CGO) achieved an R² of 0.999 and RMSE of 6.41 on training data, while HGBoost-SSA achieved an R² of 0.979 and RMSE of 37.23 on test data. These results demonstrate significant improvements over the standalone models, emphasizing the effectiveness of optimization in enhancing model convergence and prediction accuracy. The findings are discussed in detail about energy policy formulation, infrastructure planning, and sustainable development. This research is expected to further add to the contributions related to enhancing the understanding of electricity load consumption dynamics and informing better decision-making in energy.
Full Text:
PDFReferences
S. S. Aung, “Electric power is the main driving force for industrialization,” 2018. https://doi.org/10.1016/j.egyr.2019.09.041
A. Dedinec, S. Filiposka, A. Dedinec, and L. Kocarev, “Deep belief network-based electricity load forecasting: An analysis of Macedonian case,” Energy, 115, 1688–1700, 2016. https://doi.org/10.1016/j.energy.2016.07.090
A. Hussain, M. Rahman, and J. A. Memon, “Forecasting electricity consumption in Pakistan: The way forward,” Energy Policy, 90, 73–80, 2016. https://doi.org/10.1016/j.enpol.2015.11.028
M. Uz Zaman, A. Islam, and N. Sultana, “Short term load forecasting based on internet of things (IoT),” 2018, BRAC University. DOI:10.1109/GreenTech.2017.34
C. H. J. Kumar and M. Veerakumari, “Load forecasting of Andhra Pradesh grid using PSO, DE algorithms,” Int J Adv Res Comput Eng Technol, 2012. DOI:10.1186/s43067-020-00021-8
T. Van de Graaf, “International energy agency,” in Handbook of governance and security, Edward Elgar Publishing, 2014, 489–503. DOI:
https://doi.org/10.4337/9781781953174.00038
A. Vergnol, “Intégration dans le réseau électrique et le marché de l’électricité de production décentralisée d’origine renouvelable: gestion des congestions locales,” 2010, Ecole centrale de Lille. https://doi.org/10.4000/rei.4053
H. Doukas, K. D. Patlitzianas, K. Iatropoulos, and J. Psarras, “Intelligent building energy management system using rule sets,” Build Environ, 42(10): 3562–3569, 2007. https://doi.org/10.1016/j.buildenv.2006.10.024
R. Missaoui, H. Joumaa, S. Ploix, and S. Bacha, “Managing energy smart homes according to energy prices: analysis of a building energy management system,” Energy Build, 71, 155–167, 2014. https://doi.org/10.1016/j.enbuild.2013.12.018
R. E. Abdel-Aal, “Short-term hourly load forecasting using abductive networks,” IEEE Transactions on Power Systems, 19(1): 164–173, 2004. DOI: 10.1109/TPWRS.2003.820695
Y. Chen et al., “Short-term load forecasting: Similar day-based wavelet neural networks,” IEEE Transactions on Power Systems, 25(1):322–330, 2009. DOI: 10.1109/TPWRS.2009.2030426
N. Amjady, F. Keynia, and H. Zareipour, “Short-term load forecast of microgrids by a new bilevel prediction strategyfile:///E:/Article/New Project/222/samplle/scholar (11). ris,” IEEE Trans Smart Grid, 1(3):286–294, 2010. DOI:10.1109/TSG.2010.2078842
H. Krstić, Ž. Koški, I. I. Otković, and M. Španić, “Application of neural networks in predicting airtightness of residential units,” Energy Build, 84, 160–168, 2014. https://doi.org/10.1016/j.enbuild.2014.08.007
S. Grillo, M. Marinelli, S. Massucco, and F. Silvestro, “Optimal management strategy of a battery-based storage system to improve renewable energy integration in distribution networks,” IEEE Trans Smart Grid, 3(2): 950–958, 2012. DOI:10.1109/TSG.2012.2189984
I. S. Candanedo, E. H. Nieves, S. R. González, M. T. S. Martín, and A. G. Briones, “Machine learning predictive model for industry 4.0,” in Knowledge Management in Organizations: 13th International Conference, KMO 2018, Žilina, Slovakia, August 6–10, 2018, Proceedings 13, Springer, 2018, 501–510. https://doi.org/10.1007/978-3-319-95204-8_61
A. G. Briones, P. Chamoso, and A. Barriuso, “Review of the main security problems with multi-agent systems used in e-commerce applications,” ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, 5(3): 55, 2016. DOI:10.14201/ADCAIJ2016535561
J. A. Morente-Molinera, G. Kou, R. González-Crespo, J. M. Corchado, and E. Herrera-Viedma, “Solving multi-criteria group decision making problems under environments with a high number of alternatives using fuzzy ontologies and multi-granular linguistic modelling methods,” Knowl Based Syst, 137, 54–64, 2017. https://doi.org/10.1016/j.knosys.2017.09.010
T. Li, S. Sun, M. Bolić, and J. M. Corchado, “Algorithm design for parallel implementation of the SMC-PHD filter,” Signal Processing, 119, 115–127, 2016. https://doi.org/10.1016/j.sigpro.2015.07.013
J. A. G. Coria, J. A. Castellanos-Garzón, and J. M. Corchado, “Intelligent business processes composition based on multi-agent systems,” Expert Syst Appl, 41(4):1189–1205, 2014. https://doi.org/10.1016/j.eswa.2013.08.003
A. González-Briones, J. Prieto, F. De La Prieta, E. Herrera-Viedma, and J. M. Corchado, “Energy optimization using a case-based reasoning strategy,” Sensors, 18(3): 865, 2018. https://doi.org/10.3390/s18030865
A. González-Briones, P. Chamoso, H. Yoe, and J. M. Corchado, “GreenVMAS: Virtual organization-based platform for heating greenhouses using waste energy from power plants,” Sensors, 18(3): 861, 2018. https://doi.org/10.3390/s18030861
A. González-Briones, P. Chamoso, S. Rodríguez, H. Yoe, and J. M. Corchado, “Reuse of waste energy from power plants in greenhouses through MAS-based architecture,” Wirel Commun Mob Comput, 2018, 2018. https://doi.org/10.3390/s18030861
T. Ahmad and H. Chen, “Utility companies’ strategy for short-term energy demand forecasting using machine learning based models,” Sustain Cities Soc, 39, 401–417, 2018. https://doi.org/10.1016/j.scs.2018.03.002
T. Ahmad and H. Chen, “Nonlinear autoregressive and random forest approaches to forecasting electricity load for utility energy management systems,” Sustain Cities Soc, 45, 460–473, 2019. https://doi.org/10.1016/j.scs.2018.12.013
T. Saksornchai, W.-J. Lee, K. Methaprayoon, J. R. Liao, and R. J. Ross, “Improve the unit commitment scheduling by using the neural-network-based short-term load forecasting,” IEEE Trans Ind Appl, 41(1): 169–179, 2005. DOI: 10.1109/TIA.2004.841029
C. Kuster, Y. Rezgui, and M. Mourshed, “Electrical load forecasting models: A critical systematic review,” Sustain Cities Soc, 35, 257–270, 2017. https://doi.org/10.1016/j.scs.2017.08.009
D. Liu et al., “Electricity consumption and economic growth nexus in Beijing: A causal analysis of quarterly sectoral data,” Renewable and Sustainable Energy Reviews, 82, 2498–2503, 2018. https://doi.org/10.1016/j.rser.2017.09.016
M. Q. Raza, M. Nadarajah, D. Q. Hung, and Z. Baharudin, “An intelligent hybrid short-term load forecasting model for smart power grids,” Sustain Cities Soc, 31, 264–275, 2017. https://doi.org/10.1016/j.scs.2016.12.006
L. Xiao, W. Shao, T. Liang, and C. Wang, “A combined model based on multiple seasonal patterns and modified firefly algorithm for electrical load forecasting,” Appl Energy, 167, 135–153, 2016. https://doi.org/10.1016/j.apenergy.2016.01.050
J. Massana, C. Pous, L. Burgas, J. Melendez, and J. Colomer, “Identifying services for short-term load forecasting using data driven models in a Smart City platform,” Sustain Cities Soc, 28, 108–117, 2017. https://doi.org/10.1016/j.scs.2016.09.001
P. Pinson and H. Madsen, “Benefits and challenges of electrical demand response: A critical review,” Renewable and Sustainable Energy Reviews, 39, 686–699, 2014. https://doi.org/10.1016/j.rser.2014.07.098
W.-C. Hong, Hybrid intelligent technologies in energy demand forecasting. Springer, 2020. https://doi.org/10.1007/978-3-030-36529-5
M. A. AlKhars, “Survey and analysis of the quantitative methods used in electricity research on GCC countries: 1983–2018,” Heliyon, 5(10):2019. https://doi.org/10.1016/j.heliyon.2019.e02634
X. JIN, “Energy Station Data,” 2024, doi: 10.6084/m9.figshare. 24978645.v1.
Y. Zhang, Z. Zhao, and J. Zheng, “CatBoost: A new approach for estimating daily reference crop evapotranspiration in arid and semi-arid regions of Northern China,” J Hydrol (Amst), 588, 125087, 2020. https://doi.org/10.1016/j.jhydrol.2020.125087
J. Jiang, B. Cui, C. Zhang, and F. Fu, “DimBoost: Boosting gradient boosting decision tree to higher dimensions,” Proceedings of the ACM SIGMOD International Conference on Management of Data,1363–1376, 2018, doi: 10.1145/3183713.3196892.
J. Xue and B. Shen, “A novel swarm intelligence optimization approach: sparrow search algorithm,” Systems Science and Control Engineering,8(1): 22–34, 2020, doi: 10.1080/21642583.2019.1708830.
L. Zhang, Y. Chen, and Z. Yan, “Predicting the short-term electricity demand based on the weather variables using a hybrid CatBoost-PPSO model,” Journal of Building Engineering, 71, 106432, Jul. 2023, doi: 10.1016/J.JOBE.2023.106432.
E. Dogan and N. Yorukeren, “Enhancement of Transmission System Security with Archimedes Optimization Algorithm,” Turkish Journal of Electrical Power and Energy Systems, 2(2): 115–123, 2022, doi: 10.5152/tepes.2022.22015.
I. Alsaidan, M. A. M. Shaheen, H. M. Hasanien, M. Alaraj, and A. S. Alnafisah, “Proton exchange membrane fuel cells modeling using chaos game optimization technique,” Sustainability (Switzerland), 13(14): 1–24, 2021, doi: 10.3390/su13147911.
A. Rastgoo and H. Khajavi, “A novel study on forecasting the Airfoil self-noise, using a hybrid model based on the combination of CatBoost and Arithmetic Optimization Algorithm,” Expert Syst Appl, p. 120576, 2023. https://doi.org/10.1016/j.eswa.2023.120576
DOI: https://doi.org/10.31449/inf.v49i23.7716
This work is licensed under a Creative Commons Attribution 3.0 License.