IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v9y2016i10p767-d78664.html
   My bibliography  Save this article

A Permutation Importance-Based Feature Selection Method for Short-Term Electricity Load Forecasting Using Random Forest

Author

Listed:
  • Nantian Huang

    (School of Electrical Engineering, Northeast Dianli University, Jilin 132012, China)

  • Guobo Lu

    (School of Electrical Engineering, Northeast Dianli University, Jilin 132012, China)

  • Dianguo Xu

    (Department of Electrical Engineering, Harbin Institute of Technology, Harbin 150001, China)

Abstract

The prediction accuracy of short-term load forecast (STLF) depends on prediction model choice and feature selection result. In this paper, a novel random forest (RF)-based feature selection method for STLF is proposed. First, 243 related features were extracted from historical load data and the time information of prediction points to form the original feature set. Subsequently, the original feature set was used to train an RF as the original model. After the training process, the prediction error of the original model on the test set was recorded and the permutation importance (PI) value of each feature was obtained. Then, an improved sequential backward search method was used to select the optimal forecasting feature subset based on the PI value of each feature. Finally, the optimal forecasting feature subset was used to train a new RF model as the final prediction model. Experiments showed that the prediction accuracy of RF trained by the optimal forecasting feature subset was higher than that of the original model and comparative models based on support vector regression and artificial neural network.

Suggested Citation

  • Nantian Huang & Guobo Lu & Dianguo Xu, 2016. "A Permutation Importance-Based Feature Selection Method for Short-Term Electricity Load Forecasting Using Random Forest," Energies, MDPI, vol. 9(10), pages 1-24, September.
    • Handle: RePEc:gam:jeners:v:9:y:2016:i:10:p:767-:d:78664
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/9/10/767/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/9/10/767/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Yu, Feng & Xu, Xiaozhong, 2014. "A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network," Applied Energy, Elsevier, vol. 134(C), pages 102-113.
    2. Hernández, Luis & Baladrón, Carlos & Aguiar, Javier M. & Carro, Belén & Sánchez-Esguevillas, Antonio & Lloret, Jaime, 2014. "Artificial neural networks for short-term load forecasting in microgrids environment," Energy, Elsevier, vol. 75(C), pages 252-264.
    3. Jurado, Sergio & Nebot, Àngela & Mugica, Fransisco & Avellana, Narcís, 2015. "Hybrid methodologies for electricity load forecasting: Entropy-based feature selection with machine learning and soft computing techniques," Energy, Elsevier, vol. 86(C), pages 276-291.
    4. Luis Hernández & Carlos Baladrón & Javier M. Aguiar & Lorena Calavia & Belén Carro & Antonio Sánchez-Esguevillas & Francisco Pérez & Ángel Fernández & Jaime Lloret, 2014. "Artificial Neural Network for Short-Term Load Forecasting in Distribution Systems," Energies, MDPI, vol. 7(3), pages 1-23, March.
    5. Ghofrani, M. & Ghayekhloo, M. & Arabali, A. & Ghayekhloo, A., 2015. "A hybrid short-term load forecasting with a new input selection framework," Energy, Elsevier, vol. 81(C), pages 777-786.
    6. Wang, Jianjun & Li, Li & Niu, Dongxiao & Tan, Zhongfu, 2012. "An annual load forecasting model based on support vector regression with differential evolution algorithm," Applied Energy, Elsevier, vol. 94(C), pages 65-70.
    7. Mamlook, Rustum & Badran, Omar & Abdulhadi, Emad, 2009. "A fuzzy inference model for short-term load forecasting," Energy Policy, Elsevier, vol. 37(4), pages 1239-1248, April.
    8. Troncoso, A. & Salcedo-Sanz, S. & Casanova-Mateo, C. & Riquelme, J.C. & Prieto, L., 2015. "Local models-based regression trees for very short-term wind speed prediction," Renewable Energy, Elsevier, vol. 81(C), pages 589-598.
    9. Che, JinXing & Wang, JianZhou, 2014. "Short-term load forecasting using a kernel-based support vector regression combination model," Applied Energy, Elsevier, vol. 132(C), pages 602-609.
    10. Khan, Ahsan Raza & Mahmood, Anzar & Safdar, Awais & Khan, Zafar A. & Khan, Naveed Ahmed, 2016. "Load forecasting, dynamic pricing and DSM in smart grid: A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 54(C), pages 1311-1322.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Yundong Gu & Dongfen Ma & Jiawei Cui & Zhenhua Li & Yaqi Chen, 2022. "Variable-Weighted Ensemble Forecasting of Short-Term Power Load Based on Factor Space Theory," Annals of Data Science, Springer, vol. 9(3), pages 485-501, June.
    2. Sangwan Lee, 2022. "Exploring Associations between Multimodality and Built Environment Characteristics in the U.S," Sustainability, MDPI, vol. 14(11), pages 1-16, May.
    3. Thi-Minh-Trang Huynh & Chuen-Fa Ni & Yu-Sheng Su & Vo-Chau-Ngan Nguyen & I-Hsien Lee & Chi-Ping Lin & Hoang-Hiep Nguyen, 2022. "Predicting Heavy Metal Concentrations in Shallow Aquifer Systems Based on Low-Cost Physiochemical Parameters Using Machine Learning Techniques," IJERPH, MDPI, vol. 19(19), pages 1-21, September.
    4. Kaneko, Nanae & Fujimoto, Yu & Hayashi, Yasuhiro, 2022. "Sensitivity analysis of factors relevant to extreme imbalance between procurement plans and actual demand: Case study of the Japanese electricity market," Applied Energy, Elsevier, vol. 313(C).
    5. Jiabao Du & Changxi Yue & Ying Shi & Jicheng Yu & Fan Sun & Changjun Xie & Tao Su, 2021. "A Frequency Decomposition-Based Hybrid Forecasting Algorithm for Short-Term Reactive Power," Energies, MDPI, vol. 14(20), pages 1-18, October.
    6. Peng Liu & Peijun Zheng & Ziyu Chen, 2019. "Deep Learning with Stacked Denoising Auto-Encoder for Short-Term Electric Load Forecasting," Energies, MDPI, vol. 12(12), pages 1-15, June.
    7. Chan-Uk Yeom & Keun-Chang Kwak, 2017. "Short-Term Electricity-Load Forecasting Using a TSK-Based Extreme Learning Machine with Knowledge Representation," Energies, MDPI, vol. 10(10), pages 1-18, October.
    8. Sangwan Lee, 2022. "Satisfaction with the Pedestrian Environment and Its Relationship to Neighborhood Satisfaction in Seoul, South Korea," Sustainability, MDPI, vol. 14(15), pages 1-15, July.
    9. Chiou-Jye Huang & Ping-Huan Kuo, 2018. "A Short-Term Wind Speed Forecasting Model by Using Artificial Neural Networks with Stochastic Optimization for Renewable Energy Systems," Energies, MDPI, vol. 11(10), pages 1-20, October.
    10. Dongkyu Lee & Jinhwa Jeong & Sung Hoon Yoon & Young Tae Chae, 2019. "Improvement of Short-Term BIPV Power Predictions Using Feature Engineering and a Recurrent Neural Network," Energies, MDPI, vol. 12(17), pages 1-17, August.
    11. Tomasz Ciechulski & Stanisław Osowski, 2020. "Deep Learning Approach to Power Demand Forecasting in Polish Power System," Energies, MDPI, vol. 13(22), pages 1-13, November.
    12. Marta Kłosok & Marcin Chlebus, 2020. "Towards better understanding of complex machine learning models using Explainable Artificial Intelligence (XAI) - case of Credit Scoring modelling," Working Papers 2020-18, Faculty of Economic Sciences, University of Warsaw.
    13. Francisco Martínez-Álvarez & Alicia Troncoso & José C. Riquelme, 2017. "Recent Advances in Energy Time Series Forecasting," Energies, MDPI, vol. 10(6), pages 1-3, June.
    14. Kaneko, Nanae & Fujimoto, Yu & Kabe, Satoshi & Hayashida, Motonari & Hayashi, Yasuhiro, 2020. "Sparse modeling approach for identifying the dominant factors affecting situation-dependent hourly electricity demand," Applied Energy, Elsevier, vol. 265(C).
    15. Paul Anton Verwiebe & Stephan Seim & Simon Burges & Lennart Schulz & Joachim Müller-Kirchenbauer, 2021. "Modeling Energy Demand—A Systematic Literature Review," Energies, MDPI, vol. 14(23), pages 1-58, November.
    16. Ricardo Vazquez & Hortensia Amaris & Monica Alonso & Gregorio Lopez & Jose Ignacio Moreno & Daniel Olmeda & Javier Coca, 2017. "Assessment of an Adaptive Load Forecasting Methodology in a Smart Grid Demonstration Project," Energies, MDPI, vol. 10(2), pages 1-23, February.
    17. Li, Chuan & Tao, Ying & Ao, Wengang & Yang, Shuai & Bai, Yun, 2018. "Improving forecasting accuracy of daily enterprise electricity consumption using a random forest based on ensemble empirical mode decomposition," Energy, Elsevier, vol. 165(PB), pages 1220-1227.
    18. Feras Alasali & Husam Foudeh & Esraa Mousa Ali & Khaled Nusair & William Holderbaum, 2021. "Forecasting and Modelling the Uncertainty of Low Voltage Network Demand and the Effect of Renewable Energy Sources," Energies, MDPI, vol. 14(8), pages 1-31, April.
    19. Ping-Huan Kuo & Chiou-Jye Huang, 2018. "An Electricity Price Forecasting Model by Hybrid Structured Deep Neural Networks," Sustainability, MDPI, vol. 10(4), pages 1-17, April.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Fan, Guo-Feng & Peng, Li-Ling & Hong, Wei-Chiang, 2018. "Short term load forecasting based on phase space reconstruction algorithm and bi-square kernel regression model," Applied Energy, Elsevier, vol. 224(C), pages 13-33.
    2. Tu, Chunming & He, Xi & Shuai, Zhikang & Jiang, Fei, 2017. "Big data issues in smart grid – A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 79(C), pages 1099-1107.
    3. Alobaidi, Mohammad H. & Chebana, Fateh & Meguid, Mohamed A., 2018. "Robust ensemble learning framework for day-ahead forecasting of household based energy consumption," Applied Energy, Elsevier, vol. 212(C), pages 997-1012.
    4. Singh, Priyanka & Dwivedi, Pragya, 2018. "Integration of new evolutionary approach with artificial neural network for solving short term load forecast problem," Applied Energy, Elsevier, vol. 217(C), pages 537-549.
    5. Barman, Mayur & Dev Choudhury, N.B. & Sutradhar, Suman, 2018. "A regional hybrid GOA-SVM model based on similar day approach for short-term load forecasting in Assam, India," Energy, Elsevier, vol. 145(C), pages 710-720.
    6. Yuchun Li & Yinghua Han & Jinkuan Wang & Qiang Zhao, 2018. "A MBCRF Algorithm Based on Ensemble Learning for Building Demand Response Considering the Thermal Comfort," Energies, MDPI, vol. 11(12), pages 1-20, December.
    7. He, Yaoyao & Xu, Qifa & Wan, Jinhong & Yang, Shanlin, 2016. "Short-term power load probability density forecasting based on quantile regression neural network and triangle kernel function," Energy, Elsevier, vol. 114(C), pages 498-512.
    8. Ma, Weiwu & Fang, Song & Liu, Gang & Zhou, Ruoyu, 2017. "Modeling of district load forecasting for distributed energy system," Applied Energy, Elsevier, vol. 204(C), pages 181-205.
    9. Xiao, Liye & Shao, Wei & Yu, Mengxia & Ma, Jing & Jin, Congjun, 2017. "Research and application of a combined model based on multi-objective optimization for electrical load forecasting," Energy, Elsevier, vol. 119(C), pages 1057-1074.
    10. Tomasz Szul & Sylwester Tabor & Krzysztof Pancerz, 2021. "Application of the BORUTA Algorithm to Input Data Selection for a Model Based on Rough Set Theory (RST) to Prediction Energy Consumption for Building Heating," Energies, MDPI, vol. 14(10), pages 1-13, May.
    11. Wu, Zhuochun & Zhao, Xiaochen & Ma, Yuqing & Zhao, Xinyan, 2019. "A hybrid model based on modified multi-objective cuckoo search algorithm for short-term load forecasting," Applied Energy, Elsevier, vol. 237(C), pages 896-909.
    12. Dedinec, Aleksandra & Filiposka, Sonja & Dedinec, Aleksandar & Kocarev, Ljupco, 2016. "Deep belief network based electricity load forecasting: An analysis of Macedonian case," Energy, Elsevier, vol. 115(P3), pages 1688-1700.
    13. Yoldaş, Yeliz & Önen, Ahmet & Muyeen, S.M. & Vasilakos, Athanasios V. & Alan, İrfan, 2017. "Enhancing smart grid with microgrids: Challenges and opportunities," Renewable and Sustainable Energy Reviews, Elsevier, vol. 72(C), pages 205-214.
    14. Zhang, Liang & Wen, Jin & Li, Yanfei & Chen, Jianli & Ye, Yunyang & Fu, Yangyang & Livingood, William, 2021. "A review of machine learning in building load prediction," Applied Energy, Elsevier, vol. 285(C).
    15. Lin Lin & Lin Xue & Zhiqiang Hu & Nantian Huang, 2018. "Modular Predictor for Day-Ahead Load Forecasting and Feature Selection for Different Hours," Energies, MDPI, vol. 11(7), pages 1-30, July.
    16. He, Yaoyao & Liu, Rui & Li, Haiyan & Wang, Shuo & Lu, Xiaofen, 2017. "Short-term power load probability density forecasting method using kernel-based support vector quantile regression and Copula theory," Applied Energy, Elsevier, vol. 185(P1), pages 254-266.
    17. Karimi, M. & Karami, H. & Gholami, M. & Khatibzadehazad, H. & Moslemi, N., 2018. "Priority index considering temperature and date proximity for selection of similar days in knowledge-based short term load forecasting method," Energy, Elsevier, vol. 144(C), pages 928-940.
    18. Kaur, Amanpreet & Nonnenmacher, Lukas & Coimbra, Carlos F.M., 2016. "Net load forecasting for high renewable energy penetration grids," Energy, Elsevier, vol. 114(C), pages 1073-1084.
    19. Debnath, Kumar Biswajit & Mourshed, Monjur, 2018. "Forecasting methods in energy planning models," Renewable and Sustainable Energy Reviews, Elsevier, vol. 88(C), pages 297-325.
    20. Huiting Zheng & Jiabin Yuan & Long Chen, 2017. "Short-Term Load Forecasting Using EMD-LSTM Neural Networks with a Xgboost Algorithm for Feature Importance Evaluation," Energies, MDPI, vol. 10(8), pages 1-20, August.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:9:y:2016:i:10:p:767-:d:78664. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.