Enerji Verimliliğinde Makine Öğrenmesi: Enerji Tahmin Modellerinin Karşılaştırılması

Year 2025, Issue: 103, 196 - 210

Muhammed Akif Yenikaya , Onur Oktaysoy

https://doi.org/10.17753/sosekev.1636999

Abstract

Bu çalışmada endüstriyel üretimde ihtiyaç duyulan enerji tüketimini tahmin etmek amacıyla makine öğrenimi modellerinin işlevselliği belirlenmeye çalışılmış, bu bağlamda Linear Regression, Decision Tree, Random Forest, K-Nearest Neighbors ve Support Vector Machine algoritmaları kullanılabilirlik ve performans değerleri bakımından karşılaştırılarak değerlendirilmiştir. Enerji tüketim tahminlerinin yapılabilmesi için geçmiş üretim verileri, enerji tüketim verileri ve diğer ilgili parametreler giriş verisi olarak kullanılmıştır. Veriler bir açık kaynak platformu olan UCI veri deposundan elde edilmiştir. 80/20 eğitim/test şeklinde yapılandırılan makine öğretim süreci kapsamlı veri parametreleriyle modellerin enerji verimliliği analizi yapabilecekleri forma uyarlanmıştır. Modellerin performanslarını değerlendirmek için determinasyon katsayısı (R²), kök ortalama kare hatası (RMSE), ortalama kare hatası (MSE) ve ortalama mutlak hata (MAE) gibi hata metrikleri kullanılmıştır. Elde edilen bulgulara göre, çalışma kapsamında kullanılan Random Forest modeli diğer modellere oranla daha yüksek doğruluk oranını sağlayarak R² değeri 0.9989 olarak elde edilmiştir. Bu sonuç, enerji tüketimine yönelik tahminlemede makine öğrenmesi modellerinin etkili araçlar olarak kullanılabileceğini ve bu araçların üretimde enerjinin önemi göz önüne alındığında işletmeler için stratejik avantaja dönüşebileceğini ortaya koymaktadır. Araştırma enerji tüketiminde makine öğrenmesi teknolojisinin önemli bir araç olabileceğini ortaya koyması ve dahası farklı modellerin enerji tahminlemede sergiledikleri performansı karşılaştırması bakımından alanyazına önemli kazanım yaratmaktadır.

Keywords

Enerji tüketimi, Kaynak verimliliği, Makine öğrenmesi, Enerji tahmini, Teknoloji

MACHINE LEARNING IN ENERGY EFFICIENCY: COMPARISON OF ENERGY ESTIMATION MODELS

Abstract

In this study, the functionality of machine learning models was tried to be determined in order to estimate the energy consumption needed in industrial production. In this context, Linear Regression, Decision Tree, Random Forest, K-Nearest Neighbors and Support Vector Machine algorithms were compared and evaluated in terms of usability and performance values. In the study, five different machine learning models were compared to estimate energy consumption. In order to make energy consumption estimates, historical production data, energy consumption data and other relevant parameters were used as input data. Data was obtained from UCI data repository, an open-source platform. The machine learning process structured as 80/20 training/testing was adapted to the form where the models can perform energy efficiency analysis with comprehensive data parameters. Error metrics such as coefficient of determination (R²), root mean square error (RMSE), mean square error (MSE) and mean absolute error (MAE) were used to evaluate the performance of the models. According to the findings, the Random Forest model used in the study provided a higher accuracy rate compared to other models, and the R² value was obtained as 0.9989. This result reveals that machine learning models can be used as effective tools in estimating energy consumption and that these tools can turn into a strategic advantage for businesses, considering the importance of energy in production. The research provides significant contributions to literature by revealing that machine learning technology can be an important tool in energy consumption and, moreover, by comparing the performance of different models in energy estimation.

Keywords

Technology, Energy consumption, Resource efficiency, Machine learning, Energy forecasting

References

• Ahmad, T., Chen, H., Huang, R., Yabin, G., Wang, J., Shair, J., ... & Kazim, M. (2018). Supervised based machine learning models for short, medium and long-term energy prediction in distinct building environment. Energy, 158, 17-32. https://doi.org/10.1016/j.energy.2018.05.169
• Ahmad, T., & Chen, H. (2020). A review on machine learning forecasting growth trends and their real-time applications in different energy systems. Sustainable Cities and Society, 54, 102010. https://doi.org/10.1016/j.scs.2019.102010
• Bahij, M., Cherkaoui, M., & Labbadi, M. (2019). Energy consumption forecasting in industrial sector using machine learning approaches. Innovation in Information Systems and Technologies to Support Learning Research (Conference paper), 155-164. https://doi.org/10.1007/978-3-030-36778-7_17
• Berriel, R., Lopes, A., Rodrigues, A., Varejão, F., & Oliveira-Santos, T. (2017). Monthly energy consumption forecast: A deep learning approach. 2017 International Joint Conference on Neural Networks (IJCNN), 4283-4290. https://doi.org/10.1109/IJCNN.2017.7966398
• Breiman, L. (2001). Random forests. Machine learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
• Chahbi, I., Rabah, N., & Tekaya, I. (2022). Towards an efficient and interpretable machine learning approach for energy prediction in industrial buildings: A case study in the steel industry. 2022 IEEE/ACS 19th International Conference on Computer Systems and Applications (AICCSA), 1-8. https://doi.org/10.1109/AICCSA56895.2022.10017816
• Dan, T., & Phuc, P. (2018). Application of machine learning in forecasting energy usage of building design. 2018 4th International Conference on Green Technology and Sustainable Development (GTSD), 53-59. https://doi.org/10.1109/GTSD.2018.8595595
• Devaraj, J., Madurai Elavarasan, R., Shafiullah, G. M., Jamal, T., & Khan, I. (2021). A holistic review on energy forecasting using big data and deep learning models. International journal of energy research, 45(9), 13489-13530. https://doi.org/10.1002/er.6679
• Enerji ve Tabii Kaynaklar Bakanlığı (2022). Türkiye ulusal enerji planı 2022. https://enerji.gov.tr//Media/Dizin/EIGM/tr/Raporlar/TUEP/T%C3%BCrkiye_Ulusal_Enerji_Plan%C4%B1.pdf (Access Date: 08.09.2024).
• Feng, C., & Zhang, J. (2020). Assessment of aggregation strategies for machine-learning based short-term load forecasting. Electric Power Systems Research, 184, 106304. https://doi.org/10.1016/j.epsr.2020.106304
• Gellings, C. W. (2020). The smart grid: Enabling energy efficiency and demand response. River Publishers. https://doi.org/10.1201/9781003151524
• Gellings, C. W., & Parmenter, K. E. (2016). Demand-side management. In Energy management and conservation Handbook, 399-420. CRC. https://doi.org/10.1201/9781315374178-20
• Goodfellow, I., Bengio, Y., & Courville, A. (2016). Regularization for deep learning. Deep learning, 216-261. https://mnassar.github.io/deeplearninghandbook/slides/07_regularization.pdf (Access Date: 23.08.2024).
• Hastie, T., Friedman, J., & Tibshirani, R. (2001). Linear methods for regression. In: The elements of statistical learning. Springer Series in Statistics. Springer. https://doi.org/10.1007/978-0-387-21606-5_3
• Hochreiter, S. (1997). Long short-term memory. Neural Computation MIT-Press. https://doi.org/10.1162/neco.1997.9.8.1735
• Hyndman, R. J. (2018). Forecasting: principles and practice. OTexts. Monash University, Australia, IEA, 2023 - International Energy Agency (2023). World Energy Outlook 2023. International Energy Agency. https://www.iea.org/reports/world-energy-outlook-2023 (Access Date: 10.09.2024).
• IEA, 2021 - International Energy Agency, (2021). Global Energy Review 2021. https://www.iea.org/reports/global-energy-review-2021?utm_source=newsletter&utm_medium=email&utm_campaign=newsletter_axiosgenerate&stream=top (Access Date: 04.09.2024).
• Jahangiri, A., & Rakha, H. (2015). Applying machine learning techniques to transportation mode recognition using mobile phone sensor data. IEEE Transactions on Intelligent Transportation Systems, 16, 2406-2417. https://doi.org/10.1109/TITS.2015.2405759
• Khan, P., Byun, Y., Lee, S., & Park, N. (2020). Machine learning based hybrid system for imputation and efficient energy demand forecasting. Energies, 13(11), 2681. https://doi.org/10.3390/en13112681
• Kong, W., Dong, Z. Y., Jia, Y., Hill, D. J., Xu, Y., & Zhang, Y. (2017). Short-term residential load forecasting based on LSTM recurrent neural network. IEEE transactions on smart grid, 10(1), 841-851. https://doi.org/10.1109/TSG.2017.2753802
• Krahwinkler, P., Roßmann, J., & Sondermann, B. (2011). Support vector machine based decision tree for very high resolution multispectral forest mapping. 2011 IEEE International Geoscience and Remote Sensing Symposium, 43-46. https://doi.org/10.1109/IGARSS.2011.6048893
• Kushwaha, N., & Waoo, A. (2023). Energy consumption prediction by using machine learning. International Journal For Multidisciplinary Research, 5(6), 1-12. https://pdfs.semanticscholar.org/dd9e/5db5ca2529fe92a46c53cb7082ceba01f0d2.pdf
• Makridou, G., Andriosopoulos, K., Doumpos, M., & Zopounidis, C. (2016). Measuring the efficiency of energy-intensive industries across European countries. Energy Policy, 88, 573-583. https://doi.org/10.1016/j.enpol.2015.06.042
• Mathur, S., & Badone, A. (2019). A methodological study and analysis of machine learning al gorithms. International Journal of Advanced Technology and Engineering Exploration, 6(51), 45-9. https://doi.org/10.19101/IJATEE.2019.650020
• Mawson, V. J., & Hughes, B. R. (2020). Deep learning techniques for energy forecasting and condition monitoring in the manufacturing sector. Energy and Buildings, 217, 109966. https://doi.org/10.1016/j.enbuild.2020.109966
• Milićević, M. M., & Marinović, B. R. (2024). Machine learning methods in forecasting solar photovoltaic energy production. Thermal Science, 28(1 Part B), 479-488. https://doi.org/10.2298/TSCI230402150M
• Sathe, S., & Aggarwal, C. (2019). Nearest neighbor classifiers versus random forests and support vector machines. 2019 IEEE International Conference on Data Mining (ICDM), 1300-1305. https://doi.org/10.1109/ICDM.2019.00164
• Sathishkumar, V. E., Lim, J., Lee, M., Cho, K., Park, J., Shin, C., & Cho, Y. (2020). Industry energy consumption prediction using data mining techniques. International Journal of Energy, Information and Communications, 11(1), 7-14. http://dx.doi.org/10.21742/ijeic.2020.11.1.02
• Sathishkumar, V. E., Changsun, S., & Yongyun, C. (2023). Steel industry energy consumption. UCI Machine Learning Repository. https://archive.ics.uci.edu/datasets
• Solyali, D. (2020). A comparative analysis of machine learning approaches for short-/long-term electricity load forecasting in Cyprus. Sustainability, 12(9), 3612. https://doi.org/10.3390/su12093612
• Taylor, S. J., & Letham, B. (2018). Forecasting at scale. The American Statistician, 72(1), 37-45. https://doi.org/10.1080/00031305.2017.1380080
• Topcuoglu, E., Oktaysoy, O., Kaygin, E., Kosa, G., Uygungil-Erdogan, S., Kobanoglu, M. S., & Turan-Torun, B. (2024). The potential of the society 5.0 strategy to be a solution to the political and structural problems of countries: The case of Türkiye. Sustainability, 16(22), 9825. https://doi.org/10.3390/su16229825
• UN, 2023 – United Nations Environment Programme – 2023. https://www.unep.org/resources/global-environment-outlook-6 (Access Date: 10.09.2024).
• Vianna, V., Celeste, W., & Freitas, R. (2019). Energy efficiency in the context of Industry 4.0. International Journal of Advanced Engineering Research and Science, 6(12), 1-16. https://doi.org/10.22161/ijaers.612.1
• Wang, H., Lei, Z., Zhang, X., Zhou, B., & Peng, J. (2019). A review of deep learning for renewable energy forecasting. Energy Conversion and Management. 198, 111799. https://doi.org/10.1016/j.enconman.2019.111799
• Yenikaya, M. A., Kerse, G., & Oktaysoy, O. (2024). Artificial intelligence in the healthcare sector: comparison of deep learning networks using chest X-ray images. Frontiers in Public Health, 12, 1386110. https://doi.org/10.3389/fpubh.2024.1386110
• Zhang, L., Wen, J., Li, Y., Chen, J., Ye, Y., Fu, Y., & Livingood, W. (2021). A review of machine learning in building load prediction. Applied Energy, 285, 116452. https://doi.org/10.1016/j.apenergy.2021.116452
• Zengin, Y., Naktiyok, S., Kaygın, E., Kavak, O., & Topçuoğlu, E. (2021). An investigation upon industry 4.0 and society 5.0 within the context of sustainable development goals. Sustainability, 13(5), 2682. https://doi.org/10.3390/su13052682