Yığılmış Topluluk Makine Öğrenmesi Modeli ile Enerji Tüketim Tahmini

Öz

Hızlı kentleşme, aşırı enerji tüketimi ve nüfus artışı sonucunda son yıllarda enerji ihtiyacı önemli ölçüde artmıştır. Bu durum iklim değişikliği, su ve hava kirliliği gibi çevresel sorunlara yol açmaktadır. Enerji tüketimini tahmin etmek bu sorunları azaltabilir ve enerji yönetimine ve etkinliğine yardımcı olabilir. Bu makalede, Fas'taki Tetouan şehrinde enerji tüketimini tahmin etmek için doğrusal regresyon, K-En Yakın Komşu, destek vektör regresörü, rastgele orman, gradyan artırma ve istifleme gibi çeşitli makine öğrenimi yöntemlerinin performansını araştırılmıştır. Bu modellerin performansını değerlendirmek için MAE, RMSE ve R2 gibi değerlendirme ölçütleri kullanılmıştır. Yığınlama yöntemi, 1., 2. ve 3. bölgelerde sırasıyla %98,13, %98,11 ve %99,05 doğrulukla olağanüstü performans ve en iyi sonucu sağlamaktadır.

Anahtar Kelimeler

• Makine Öğrenmesi
• Topluluk Modeli
• Enerji Tüketimi
• Tahmin

Stacked Ensemble Machine Learning Model of Energy Consumption Prediction

Abstract

The need for energy has significantly increased in recent decades as a result of rapid urbanization, excessive energy consumption and population growth. This leads to environmental problems such as climate change, water and air pollution. Predicting energy consumption can reduce these problems and helps energy management and efficacity. In this paper, we investigate the performance of several machine learning methods, such as linear regression, K-Nearest neighbor, support vector regressor, random forest, gradient boosting, and stacking to predict energy consumption in Tetouan city, in Morocco. To evaluate the performance of these models, evaluation metrics such as MAE, RMSE, and R2 were used. Stacking method provided outstanding performance and the best result with accuracy of 98.13%, 98.11% and 99.05% in zone 1, 2, 3, respectively.

Keywords

• Machine Learning
• Ensemble Model
• Energy Consumption
• Prediction

References

1. P. Chujai, N. Kerdprasop, and K. Kerdprasop, “Time Series Analysis of Household Electric Consumption with ARIMA and ARMA Models,” Hong Kong, 2013.
2. “Forecasting Electricity Consumption using ARIMA Model | IEEE Conference Publication | IEEE Xplore,” accessed May 04, 2025.
3. E. Erdogdu, “Electricity demand analysis using cointegration and ARIMA modelling: A case study of Turkey,” Energy Policy, vol. 35, no. 2, pp. 1129–1146, Feb. 2007, doi: 10.1016/j.enpol.2006.02.013.
4. C. Lee and C. Ko, “Short-term load forecasting using lifting scheme and ARIMA models,” Expert Syst. Appl., vol. 38, no. 5, pp. 5339–5349, May 2011, doi: 10.1016/j.eswa.2010.11.033.
5. T. O. Benli, “A Comparison of Nineteen Various Electricity Consumption Forecasting Approaches and Practicing to Five Different Households in Turkey,” arXiv preprint arXiv:1607.05660, Jul. 2016.
6. J. Che and H. Zhai, “WT-ARIMA Combination Modelling for Short-term Load Forecasting,” IAENG Int. J. Comput. Sci., vol. 49, no. 2, pp. 542–549, Jun. 2022.
7. A. S. Ahmad, M. Y. Hassan, M. P. Abdullah, H. A. Rahman, F. Hussin, H. Abdullah, and R. Saidur, “A review on applications of ANN and SVM for building electrical energy consumption forecasting,” Renew. Sustain. Energy Rev., vol. 33, pp. 102–109, May 2014, doi: 10.1016/j.rser.2014.01.069.
8. A. H. Neto and F. A. S. Fiorelli, “Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption,” Energy Build., vol. 40, no. 12, pp. 2169–2176, Jan. 2008, doi: 10.1016/j.enbuild.2008.06.013.

9. M. Q. Raza and A. Khosravi, “A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings,” Renew. Sustain. Energy Rev., vol. 50, pp. 1352–1372, Oct. 2015, doi: 10.1016/j.rser.2015.04.065.
10. A.-D. Pham, N.-T. Ngo, T. T. Ha Truong, N.-T. Huynh, and N.-S. Truong, “Predicting energy consumption in multiple buildings using machine learning for improving energy efficiency and sustainability,” J. Clean. Prod., vol. 260, p. 121082, Jul. 2020, doi: 10.1016/j.jclepro.2020.121082.
11. S. Ben Taieb and R. J. Hyndman, “A gradient boosting approach to the Kaggle load forecasting competition,” Int. J. Forecast., vol. 30, no. 2, pp. 382–394, Apr. 2014, doi: 10.1016/j.ijforecast.2013.07.005.
12. A. Salam and A. El Hibaoui, “Energy consumption prediction model with deep inception residual network inspiration and LSTM,” Math. Comput. Simul., vol. 190, pp. 97–109, Dec. 2021, doi: 10.1016/j.matcom.2021.05.006.
13. L. Wang, S. Mao, B. M. Wilamowski, and R. M. Nelms, “Ensemble learning for load forecasting,” IEEE Trans. Green Commun. Netw., vol. 4, no. 2, pp. 616–627, Jun. 2020, doi: 10.1109/TGCN.2020.2992521.
14. L. Liu, F. H. Juwono, W. K. Wong, and H. Liu, “Building Energy Consumption Prediction: A Machine Learning Approach with Feature Selection,” Proc. ICSCC, Jul. 2024, doi:10.1109/icscc62041.2024.10690314.
15. M. Ou, X. Zhang, Y. Li, and H. Wang, “Prediction of Energy Consumption Based on Discrete Fourier Transform and BiLSTM,” Proc. BigDIA, Oct. 2024, doi:10.1109/bigdia63733.2024.10808753.
16. N. Yoon, H. Kim, J. Park, and S. Lee, “Energy Consumption Prediction Using CNN-LSTM Models: A Time Series Big Data Analysis,” Proc. ICCE-Asia, Nov. 2024, doi:10.1109/icce-asia63397.2024.10774020.
17. S. Munir, M. Pradhan, S. Abbas, and M. A. Khan, “Energy Consumption Prediction Based on LightGBM empowered with eXplainable AI,” IEEE Access, vol. 12, Jan. 2024, doi:10.1109/access.2024.3418967.
18. Y. Chen, Z. Song, and R. Chen, “Energy Consumption Prediction of PEVs Incorporating Traffic Flow Information,” Preprint, Jan. 2025, doi:10.21203/rs.3.rs-5850009/v1.
19. Z. Yang, Z. Xie, and Z. Huang, “Electricity Consumption Prediction Based On Autoregressive Kalman Filtering,” Preprint, Sep. 2024, doi:10.21203/rs.3.rs-4878573/v1.
20. A. R. Salam and A. El Hibaoui, “Comparison of Machine Learning Algorithms for the Power Consumption Prediction: Case Study of Tetouan City,” in Proc. 6th Int. Renewable and Sustainable Energy Conf. (IRSEC), 2018, pp. 1–5.
21. A. Salam and A. El Hibaoui, “Power Consumption of Tetouan City” [Dataset], UCI Machine Learning Repository, 2018. doi: 10.24432/C5B034