A Stacking-Based Ensemble Model for Short-Term Load Forecasting

Kecheng Huang; Yidong Yu; Kang Jiang

doi:doi:10.11648/j.ijeee.20251003.12

Research Article |

| Peer-Reviewed

A Stacking-Based Ensemble Model for Short-Term Load Forecasting

Kecheng Huang

, Yidong Yu^*

, Kang Jiang

Published in International Journal of Economy, Energy and Environment (Volume 10, Issue 3)

Received: 14 April 2025 Accepted: 15 May 2025 Published: 11 June 2025

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Short-term load forecasting plays an important and indispensable role in the daily operation planning of power grid because it allows grid operators to predict electricity demand a few hours to one week in advance. Although statistics-based methods and machine learning-based methods have been widely used in short-term load forecasting, a single model may have difficulty capturing all underlying dynamics, causing reduced prediction accuracy. Therefore, a stacking-based ensemble model that improves prediction accuracy by integrating multiple base prediction models is proposed in this study for short-term load forecasting. Firstly, for data preprocessing, data normalization is used to scale the raw load data to a range of 0 to 1. Data imputation is used to ensure data integrity. Secondly, base prediction models including logistic regression, decision tree, random forest, multilayer perceptron, convolutional neural network, and long short-term memory are utilized to train the prediction models. Thirdly, the stacking-based ensemble learning method is utilized to integrate these base prediction models to further predict electric load. The results of comparative experiments and error analysis show that the stacking-based ensemble learning model outperforms the base prediction models for the majority of the evaluation metrics. Additionally, the analysis of curve fitting results demonstrates the high level of agreement between the actual values and the predicted values for the stacking-based ensemble learning model.

Published in	International Journal of Economy, Energy and Environment (Volume 10, Issue 3)
DOI	10.11648/j.ijeee.20251003.12
Page(s)	65-71
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2025. Published by Science Publishing Group

Keywords

Load Forecasting, Stacking, Ensemble Learning Method

References

[1]	Sankalpa, C., Kittipiyakul, S., & Laitrakun, S. (2022). Forecasting short-term electricity load using validated ensemble learning. Energies, 15(22), 8567. https://doi.org/10.3390/en15228567
[2]	Wang, Y., Chen, Q. X., Hong, T., & Kang, C. Q. (2019). Review of smart meter data analytics: Applications, methodologies, and challenges. IEEE Transactions on Smart Grid, 10(3), 3125-3148. https://doi.org/10.1109/TSG.2018.2818167
[3]	Lee, C. M., & Ko, C. N. (2011). Short-term load forecasting using lifting scheme and ARIMA models. Expert Systems with Applications, 38(5), 5902-5911. https://doi.org/10.1016/j.eswa.2010.11.033
[4]	Göb, R., Lurz, K., & Pievatolo, A. (2013). Electrical load forecasting by exponential smoothing with covariates. Applied Stochastic Models in Business and Industry, 29(6), 629-645. https://doi.org/10.1002/asmb.2008
[5]	Fang, T. T., & Lahdelma, R. (2016). Evaluation of a multiple linear regression model and SARIMA model in forecasting heat demand for district heating system. Applied energy, 179, 544-552. https://doi.org/10.1016/j.apenergy.2016.06.133
[6]	Feng, R. H., Xue, Y. B., Wang, W., & Xiao, M. (2022). Saturated load forecasting based on clustering and logistic iterative regression. Electric Power Systems Research, 202, 107604. https://doi.org/10.1016/j.epsr.2021.107604
[7]	Hsu, C. C., & Chen, C. Y. (2003). Regional load forecasting in Taiwan––applications of artificial neural networks. Energy conversion and Management, 44(12), 1941-1949. https://doi.org/10.1016/S0196-8904(02)00225-X
[8]	Dai, X. Q., Sheng, K. C., & Shu, F. Z. (2022). Ship power load forecasting based on PSO-SVM. Mathematical Biosciences and Engineering, 19, 4547-4567. https://doi.org/10.3934/mbe.2022210
[9]	Fan, G. F., Peng, L. L., & Hong, W. C. (2022). Short-term load forecasting based on empirical wavelet transform and random forest. Electrical Engineering, 104(6), 4433-4449. https://doi.org/10.1007/s00202-022-01628-y
[10]	Dietrich, B., Walther, J., Weigold, M., & Abele, E. (2020). Machine learning based very short term load forecasting of machine tools. Applied Energy, 276, 115440. https://doi.org/10.1016/j.apenergy.2020.115440
[11]	Liu, L. Y., Bai, F. F., Su, C. Y., Ma, C. P., Yan, R. F., Li, H. L., Sun, Q., & Wennersten, R. (2022). Forecasting the occurrence of extreme electricity prices using a multivariate logistic regression model. Energy, 247, 123417. https://doi.org/10.1016/j.energy.2022.123417
[12]	Ramos, D., Faria, P., Morais, A., & Vale, Z. (2022). Using decision tree to select forecasting algorithms in distinct electricity consumption context of an office building. Energy Reports, 8, 417-422. https://doi.org/10.1016/j.egyr.2022.01.046
[13]	Moon, J., Kim, Y., Son, M., & Hwang, E. (2018). Hybrid short-term load forecasting scheme using random forest and multilayer perceptron. Energies, 11(12), 3283. https://doi.org/10.3390/en11123283
[14]	Kim, T. Y., & Cho, S. B. (2019). Predicting residential energy consumption using CNN-LSTM neural networks. Energy, 182, 72-81. https://doi.org/10.1016/j.energy.2019.05.230
[15]	Kong, W. C., Dong, Z. Y., Jia, Y. W., Hill, D. J., Xu, Y., & Zhang, Y. (2019). 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
[16]	Shi, J., Qu, X. L., & Zeng, S. T. (2011). Short-term wind power generation forecasting: Direct versus indirect ARIMA-based approaches. International Journal of Green Energy, 8(1), 100-112. https://doi.org/10.1080/15435075.2011.546755
[17]	Raza, M. Q., & Khosravi, A. (2015). A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings. Renewable and Sustainable Energy Reviews, 50, 1352-1372. https://doi.org/10.1016/j.rser.2015.04.065
[18]	Xu, L., Wang, S. W., & Tang, R. (2019). Probabilistic load forecasting for buildings considering weather forecasting uncertainty and uncertain peak load. Applied Energy, 237, 180-195. https://doi.org/10.1016/j.apenergy.2019.01.022
[19]	Qiu, Y. L., He, Z., Zhang, W. Y., Yin, X., & Ni, C. J. (2024). MSGCN-ISTL: A multi-scaled self-attention-enhanced graph convolutional network with improved STL decomposition for probabilistic load forecasting. Expert Systems with Applications, 238, 121737. https://doi.org/10.1016/j.eswa.2023.121737

Cite This Article

Plain Text BibTeX RIS

APA Style

Huang, K., Yu, Y., Jiang, K. (2025). A Stacking-Based Ensemble Model for Short-Term Load Forecasting. International Journal of Economy, Energy and Environment, 10(3), 65-71. https://doi.org/10.11648/j.ijeee.20251003.12

Copy | Download

ACS Style

Huang, K.; Yu, Y.; Jiang, K. A Stacking-Based Ensemble Model for Short-Term Load Forecasting. Int. J. Econ. Energy Environ. 2025, 10(3), 65-71. doi: 10.11648/j.ijeee.20251003.12

Copy | Download

AMA Style

Huang K, Yu Y, Jiang K. A Stacking-Based Ensemble Model for Short-Term Load Forecasting. Int J Econ Energy Environ. 2025;10(3):65-71. doi: 10.11648/j.ijeee.20251003.12

Copy | Download

@article{10.11648/j.ijeee.20251003.12,
  author = {Kecheng Huang and Yidong Yu and Kang Jiang},
  title = {A Stacking-Based Ensemble Model for Short-Term Load Forecasting
},
  journal = {International Journal of Economy, Energy and Environment},
  volume = {10},
  number = {3},
  pages = {65-71},
  doi = {10.11648/j.ijeee.20251003.12},
  url = {https://doi.org/10.11648/j.ijeee.20251003.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijeee.20251003.12},
  abstract = {Short-term load forecasting plays an important and indispensable role in the daily operation planning of power grid because it allows grid operators to predict electricity demand a few hours to one week in advance. Although statistics-based methods and machine learning-based methods have been widely used in short-term load forecasting, a single model may have difficulty capturing all underlying dynamics, causing reduced prediction accuracy. Therefore, a stacking-based ensemble model that improves prediction accuracy by integrating multiple base prediction models is proposed in this study for short-term load forecasting. Firstly, for data preprocessing, data normalization is used to scale the raw load data to a range of 0 to 1. Data imputation is used to ensure data integrity. Secondly, base prediction models including logistic regression, decision tree, random forest, multilayer perceptron, convolutional neural network, and long short-term memory are utilized to train the prediction models. Thirdly, the stacking-based ensemble learning method is utilized to integrate these base prediction models to further predict electric load. The results of comparative experiments and error analysis show that the stacking-based ensemble learning model outperforms the base prediction models for the majority of the evaluation metrics. Additionally, the analysis of curve fitting results demonstrates the high level of agreement between the actual values and the predicted values for the stacking-based ensemble learning model.
},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - A Stacking-Based Ensemble Model for Short-Term Load Forecasting

AU  - Kecheng Huang
AU  - Yidong Yu
AU  - Kang Jiang
Y1  - 2025/06/11
PY  - 2025
N1  - https://doi.org/10.11648/j.ijeee.20251003.12
DO  - 10.11648/j.ijeee.20251003.12
T2  - International Journal of Economy, Energy and Environment
JF  - International Journal of Economy, Energy and Environment
JO  - International Journal of Economy, Energy and Environment
SP  - 65
EP  - 71
PB  - Science Publishing Group
SN  - 2575-5021
UR  - https://doi.org/10.11648/j.ijeee.20251003.12
AB  - Short-term load forecasting plays an important and indispensable role in the daily operation planning of power grid because it allows grid operators to predict electricity demand a few hours to one week in advance. Although statistics-based methods and machine learning-based methods have been widely used in short-term load forecasting, a single model may have difficulty capturing all underlying dynamics, causing reduced prediction accuracy. Therefore, a stacking-based ensemble model that improves prediction accuracy by integrating multiple base prediction models is proposed in this study for short-term load forecasting. Firstly, for data preprocessing, data normalization is used to scale the raw load data to a range of 0 to 1. Data imputation is used to ensure data integrity. Secondly, base prediction models including logistic regression, decision tree, random forest, multilayer perceptron, convolutional neural network, and long short-term memory are utilized to train the prediction models. Thirdly, the stacking-based ensemble learning method is utilized to integrate these base prediction models to further predict electric load. The results of comparative experiments and error analysis show that the stacking-based ensemble learning model outperforms the base prediction models for the majority of the evaluation metrics. Additionally, the analysis of curve fitting results demonstrates the high level of agreement between the actual values and the predicted values for the stacking-based ensemble learning model.

VL  - 10
IS  - 3
ER  -

Copy | Download

Author Information

Kecheng Huang

Emerging AI Technology Co. Ltd., Hangzhou, China

Contact Email

http://orcid.org/0009-0007-3745-1963
Yidong Yu

School of Information Technology and Artificial Intelligence, Zhejiang University of Finance and Economics, Hangzhou, China

Contact Email

http://orcid.org/0009-0004-3026-4864
Kang Jiang

School of Information Technology and Artificial Intelligence, Zhejiang University of Finance and Economics, Hangzhou, China

Contact Email

http://orcid.org/0009-0003-4271-6285

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Huang, K., Yu, Y., Jiang, K. (2025). A Stacking-Based Ensemble Model for Short-Term Load Forecasting. International Journal of Economy, Energy and Environment, 10(3), 65-71. https://doi.org/10.11648/j.ijeee.20251003.12

Copy | Download

ACS Style

Huang, K.; Yu, Y.; Jiang, K. A Stacking-Based Ensemble Model for Short-Term Load Forecasting. Int. J. Econ. Energy Environ. 2025, 10(3), 65-71. doi: 10.11648/j.ijeee.20251003.12

Copy | Download

AMA Style

Huang K, Yu Y, Jiang K. A Stacking-Based Ensemble Model for Short-Term Load Forecasting. Int J Econ Energy Environ. 2025;10(3):65-71. doi: 10.11648/j.ijeee.20251003.12

Copy | Download

@article{10.11648/j.ijeee.20251003.12,
  author = {Kecheng Huang and Yidong Yu and Kang Jiang},
  title = {A Stacking-Based Ensemble Model for Short-Term Load Forecasting
},
  journal = {International Journal of Economy, Energy and Environment},
  volume = {10},
  number = {3},
  pages = {65-71},
  doi = {10.11648/j.ijeee.20251003.12},
  url = {https://doi.org/10.11648/j.ijeee.20251003.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijeee.20251003.12},
  abstract = {Short-term load forecasting plays an important and indispensable role in the daily operation planning of power grid because it allows grid operators to predict electricity demand a few hours to one week in advance. Although statistics-based methods and machine learning-based methods have been widely used in short-term load forecasting, a single model may have difficulty capturing all underlying dynamics, causing reduced prediction accuracy. Therefore, a stacking-based ensemble model that improves prediction accuracy by integrating multiple base prediction models is proposed in this study for short-term load forecasting. Firstly, for data preprocessing, data normalization is used to scale the raw load data to a range of 0 to 1. Data imputation is used to ensure data integrity. Secondly, base prediction models including logistic regression, decision tree, random forest, multilayer perceptron, convolutional neural network, and long short-term memory are utilized to train the prediction models. Thirdly, the stacking-based ensemble learning method is utilized to integrate these base prediction models to further predict electric load. The results of comparative experiments and error analysis show that the stacking-based ensemble learning model outperforms the base prediction models for the majority of the evaluation metrics. Additionally, the analysis of curve fitting results demonstrates the high level of agreement between the actual values and the predicted values for the stacking-based ensemble learning model.
},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - A Stacking-Based Ensemble Model for Short-Term Load Forecasting

AU  - Kecheng Huang
AU  - Yidong Yu
AU  - Kang Jiang
Y1  - 2025/06/11
PY  - 2025
N1  - https://doi.org/10.11648/j.ijeee.20251003.12
DO  - 10.11648/j.ijeee.20251003.12
T2  - International Journal of Economy, Energy and Environment
JF  - International Journal of Economy, Energy and Environment
JO  - International Journal of Economy, Energy and Environment
SP  - 65
EP  - 71
PB  - Science Publishing Group
SN  - 2575-5021
UR  - https://doi.org/10.11648/j.ijeee.20251003.12
AB  - Short-term load forecasting plays an important and indispensable role in the daily operation planning of power grid because it allows grid operators to predict electricity demand a few hours to one week in advance. Although statistics-based methods and machine learning-based methods have been widely used in short-term load forecasting, a single model may have difficulty capturing all underlying dynamics, causing reduced prediction accuracy. Therefore, a stacking-based ensemble model that improves prediction accuracy by integrating multiple base prediction models is proposed in this study for short-term load forecasting. Firstly, for data preprocessing, data normalization is used to scale the raw load data to a range of 0 to 1. Data imputation is used to ensure data integrity. Secondly, base prediction models including logistic regression, decision tree, random forest, multilayer perceptron, convolutional neural network, and long short-term memory are utilized to train the prediction models. Thirdly, the stacking-based ensemble learning method is utilized to integrate these base prediction models to further predict electric load. The results of comparative experiments and error analysis show that the stacking-based ensemble learning model outperforms the base prediction models for the majority of the evaluation metrics. Additionally, the analysis of curve fitting results demonstrates the high level of agreement between the actual values and the predicted values for the stacking-based ensemble learning model.

VL  - 10
IS  - 3
ER  -

Copy | Download