Journal of Korea Artificial Intelligence Association

Korea Distribution Science Association (한국유통과학회)
권호 표지
DOI QR코드

DOI QR Code

Forecasting Energy Consumption of Steel Industry Using Regression Model

회귀 모델을 활용한 철강 기업의 에너지 소비 예측

  • Received : 2023.10.30
  • Accepted : 2023.12.30
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study was to compare the performance using multiple regression models to predict the energy consumption of steel industry. Specific independent variables were selected in consideration of correlation among various attributes such as CO2 concentration, NSM, Week Status, Day of week, and Load Type, and preprocessing was performed to solve the multicollinearity problem. In data preprocessing, we evaluated linear and nonlinear relationships between each attribute through correlation analysis. In particular, we decided to select variables with high correlation and include appropriate variables in the final model to prevent multicollinearity problems. Among the many regression models learned, Boosted Decision Tree Regression showed the best predictive performance. Ensemble learning in this model was able to effectively learn complex patterns while preventing overfitting by combining multiple decision trees. Consequently, these predictive models are expected to provide important information for improving energy efficiency and management decision-making at steel industry. In the future, we plan to improve the performance of the model by collecting more data and extending variables, and the application of the model considering interactions with external factors will also be considered.

Keywords

References

  1. Kim, J., & Hong, J. (2022). "Energy Demand Forecasting and the Relationship between Energy and Economic Growth: A Focus on VECM and ARDL Models." Applied Economics, 24(2), 87-113.
  2. Xiao, L., Shao, W., Liang, T., & Wang, C. (2016). "A Combined Model Based on Multiple Seasonal Patterns and Modified Firefly Algorithm for Electrical Load Forecasting." Applied Energy, 167, 135-153. DOI: 10.1016/j.apenergy.2016.01.050
  3. Simeone, O. (2018). "A Very Brief Introduction to Machine Learning with Applications to Communication Systems." IEEE Transactions on Cognitive Communications and Networking, 4(4), 648-664. DOI: 10.1109/TCCN.2018.2881442.
  4. Sathishkumar, V. E., Shin, C., Cho, Y. (2021). "Efficient Energy Consumption Prediction Model for a Data Analytic-Enabled Industry Building in a Smart City." Building Research & Information, 49(1), 127-143. https://doi.org/10.1080/09613218.2020.1809983
  5. De Cauwer, C., Van Mierlo, J., Coosemans, T. (2015). "Energy Consumption Prediction for Electric Vehicles based on Real-world Data." Energies, 8(8), 8573-8593. https://doi.org/10.3390/en8088573
  6. Xuemei, L., Yuyan, D., Lixing, D., & Liangzhong, J. (2010). Building Cooling Load Forecasting Using Fuzzy Support Vector Machine and Fuzzy C-mean Clustering. In Proceedings of the 2010 International Conference on Computer and Communication Technologies in Agriculture Engineering, Chengdu, pp. 438-441.
  7. Zhao, J., Han, Z., Pedrycz, W., & Wang, W. (2015). Granular model of long-term prediction for energy system in steel industry. IEEE Transactions on Cybernetics, 46(2), 388-400.
  8. Dong, B., Cao, C., & Lee, S. E. (2005). Applying Support Vector Machines to Predict Building Energy Consumption in Tropical Region. Energy Build., 37(5), 545-553. https://doi.org/10.1016/j.enbuild.2004.09.009
  9. Lee, S. H. (2003). "A Study on Multicollinearity." Master's thesis, [Yonsei University Graduate School], Seoul.
  10. Sandels, C., Widen, J., Nordstrom, L., & Andersson, E. (2015). "Day-ahead Predictions of Electricity Consumption in a Swedish Office Building from Weather, Occupancy, and Temporal Data." Energy and Buildings, 108, 279-290. DOI: 10.1016/j.enbuild.2015.08.052.
  11. Bacher, P., Madsen, H., Nielsen, H. A., & Perers, B. (2013). "Short-term Heat Load Forecasting for Single Family Houses." Energy and Buildings, 65, 101-112. DOI: 10.1016/j.enbuild.2013.04.022.