IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v14y2021i18p5873-d637102.html
   My bibliography  Save this article

A Two-Stage Short-Term Load Forecasting Method Using Long Short-Term Memory and Multilayer Perceptron

Author

Listed:
  • Yuhong Xie

    (Research Center for Advanced Science and Technology, School of Engineering, The University of Tokyo, 4-6-1 Komaba Meguro-ku, Tokyo 1538904, Japan)

  • Yuzuru Ueda

    (School of Engineering, Tokyo University of Science, 6-3-1 Niijuku Katsushika-ku, Tokyo 1258585, Japan)

  • Masakazu Sugiyama

    (Research Center for Advanced Science and Technology, School of Engineering, The University of Tokyo, 4-6-1 Komaba Meguro-ku, Tokyo 1538904, Japan)

Abstract

Load forecasting is an essential task in the operation management of a power system. Electric power companies utilize short-term load forecasting (STLF) technology to make reasonable power generation plans. A forecasting model with low prediction errors helps reduce operating costs and risks for the operators. In recent years, machine learning has become one of the most popular technologies for load forecasting. In this paper, a two-stage STLF model based on long short-term memory (LSTM) and multilayer perceptron (MLP), which improves the forecasting accuracy over the entire time horizon, is proposed. In the first stage, a sequence-to-sequence (seq2seq) architecture, which can handle a multi-sequence of input to extract more features of historical data than that of single sequence, is used to make multistep predictions. In the second stage, the MLP is used for residual modification by perceiving other information that the LSTM cannot. To construct the model, we collected the electrical load, calendar, and meteorological records of Kanto region in Japan for four years. Unlike other LSTM-based hybrid architectures, the proposed model uses two independent neural networks instead of making the neural network deeper by concatenating a series of LSTM cells and convolutional neural networks (CNNs). Therefore, the proposed model is easy to be trained and more interpretable. The seq2seq module performs well in the first few hours of the predictions. The MLP inherits the advantage of the seq2seq module and improves the results by feeding artificially selected features both from historical data and information of the target day. Compared to the LSTM-AM model and single MLP model, the mean absolute percentage error (MAPE) of the proposed model decreases from 2.82% and 2.65% to 2%, respectively. The results demonstrate that the MLP helps improve the prediction accuracy of seq2seq module and the proposed model achieves better performance than other popular models. In addition, this paper also reveals the reason why the MLP achieves the improvement.

Suggested Citation

  • Yuhong Xie & Yuzuru Ueda & Masakazu Sugiyama, 2021. "A Two-Stage Short-Term Load Forecasting Method Using Long Short-Term Memory and Multilayer Perceptron," Energies, MDPI, vol. 14(18), pages 1-17, September.
    • Handle: RePEc:gam:jeners:v:14:y:2021:i:18:p:5873-:d:637102
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/14/18/5873/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/14/18/5873/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Jihoon Moon & Yongsung Kim & Minjae Son & Eenjun Hwang, 2018. "Hybrid Short-Term Load Forecasting Scheme Using Random Forest and Multilayer Perceptron," Energies, MDPI, vol. 11(12), pages 1-20, November.
    2. 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.
    3. Chujie Tian & Jian Ma & Chunhong Zhang & Panpan Zhan, 2018. "A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network," Energies, MDPI, vol. 11(12), pages 1-13, December.
    4. Ping-Huan Kuo & Chiou-Jye Huang, 2018. "A High Precision Artificial Neural Networks Model for Short-Term Energy Load Forecasting," Energies, MDPI, vol. 11(1), pages 1-13, January.
    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. Can Ding & Yiyuan Zhou & Qingchang Ding & Kaiming Li, 2022. "Integrated Carbon-Capture-Based Low-Carbon Economic Dispatch of Power Systems Based on EEMD-LSTM-SVR Wind Power Forecasting," Energies, MDPI, vol. 15(5), pages 1-27, February.
    2. Pedro M. R. Bento & Jose A. N. Pombo & Maria R. A. Calado & Silvio J. P. S. Mariano, 2021. "Stacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting," Energies, MDPI, vol. 14(21), pages 1-21, November.
    3. Min Cao & Jinfeng Wang & Xiaochen Sun & Zhengmou Ren & Haokai Chai & Jie Yan & Ning Li, 2022. "Short-Term and Medium-Term Electricity Sales Forecasting Method Based on Deep Spatio-Temporal Residual Network," Energies, MDPI, vol. 15(23), pages 1-15, November.

    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. Myoungsoo Kim & Wonik Choi & Youngjun Jeon & Ling Liu, 2019. "A Hybrid Neural Network Model for Power Demand Forecasting," Energies, MDPI, vol. 12(5), pages 1-17, March.
    2. Odin Foldvik Eikeland & Filippo Maria Bianchi & Harry Apostoleris & Morten Hansen & Yu-Cheng Chiou & Matteo Chiesa, 2021. "Predicting Energy Demand in Semi-Remote Arctic Locations," Energies, MDPI, vol. 14(4), pages 1-17, February.
    3. Bin Li & Mingzhen Lu & Yiyi Zhang & Jia Huang, 2019. "A Weekend Load Forecasting Model Based on Semi-Parametric Regression Analysis Considering Weather and Load Interaction," Energies, MDPI, vol. 12(20), pages 1-19, October.
    4. Seung-Min Jung & Sungwoo Park & Seung-Won Jung & Eenjun Hwang, 2020. "Monthly Electric Load Forecasting Using Transfer Learning for Smart Cities," Sustainability, MDPI, vol. 12(16), pages 1-20, August.
    5. Stanislaw Osowski & Robert Szmurlo & Krzysztof Siwek & Tomasz Ciechulski, 2022. "Neural Approaches to Short-Time Load Forecasting in Power Systems—A Comparative Study," Energies, MDPI, vol. 15(9), pages 1-21, April.
    6. Chujie Tian & Jian Ma & Chunhong Zhang & Panpan Zhan, 2018. "A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network," Energies, MDPI, vol. 11(12), pages 1-13, December.
    7. Sungwoo Park & Jihoon Moon & Seungwon Jung & Seungmin Rho & Sung Wook Baik & Eenjun Hwang, 2020. "A Two-Stage Industrial Load Forecasting Scheme for Day-Ahead Combined Cooling, Heating and Power Scheduling," Energies, MDPI, vol. 13(2), pages 1-23, January.
    8. Jihoon Moon & Sungwoo Park & Seungmin Rho & Eenjun Hwang, 2019. "A comparative analysis of artificial neural network architectures for building energy consumption forecasting," International Journal of Distributed Sensor Networks, , vol. 15(9), pages 15501477198, September.
    9. Fatma Yaprakdal & M. Berkay Yılmaz & Mustafa Baysal & Amjad Anvari-Moghaddam, 2020. "A Deep Neural Network-Assisted Approach to Enhance Short-Term Optimal Operational Scheduling of a Microgrid," Sustainability, MDPI, vol. 12(4), pages 1-27, February.
    10. 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.
    11. Akylas Stratigakos & Athanasios Bachoumis & Vasiliki Vita & Elias Zafiropoulos, 2021. "Short-Term Net Load Forecasting with Singular Spectrum Analysis and LSTM Neural Networks," Energies, MDPI, vol. 14(14), pages 1-13, July.
    12. 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.
    13. Andrea Menapace & Simone Santopietro & Rudy Gargano & Maurizio Righetti, 2021. "Stochastic Generation of District Heat Load," Energies, MDPI, vol. 14(17), pages 1-17, August.
    14. Liu Lu & Wei Wei, 2023. "Influence of Public Sports Services on Residents’ Mental Health at Communities Level: New Insights from China," IJERPH, MDPI, vol. 20(2), pages 1-14, January.
    15. Md. Nazmul Hasan & Rafia Nishat Toma & Abdullah-Al Nahid & M M Manjurul Islam & Jong-Myon Kim, 2019. "Electricity Theft Detection in Smart Grid Systems: A CNN-LSTM Based Approach," Energies, MDPI, vol. 12(17), pages 1-18, August.
    16. Zhang, Jiyuan & Tang, Hailong & Chen, Min, 2019. "Linear substitute model-based uncertainty analysis of complicated non-linear energy system performance (case study of an adaptive cycle engine)," Applied Energy, Elsevier, vol. 249(C), pages 87-108.
    17. Fei Teng & Yafei Song & Xinpeng Guo, 2021. "Attention-TCN-BiGRU: An Air Target Combat Intention Recognition Model," Mathematics, MDPI, vol. 9(19), pages 1-21, September.
    18. Jihoon Moon & Junhong Kim & Pilsung Kang & Eenjun Hwang, 2020. "Solving the Cold-Start Problem in Short-Term Load Forecasting Using Tree-Based Methods," Energies, MDPI, vol. 13(4), pages 1-37, February.
    19. V. Y. Kondaiah & B. Saravanan, 2022. "Short-Term Load Forecasting with a Novel Wavelet-Based Ensemble Method," Energies, MDPI, vol. 15(14), pages 1-17, July.
    20. Umut Ugurlu & Ilkay Oksuz & Oktay Tas, 2018. "Electricity Price Forecasting Using Recurrent Neural Networks," Energies, MDPI, vol. 11(5), pages 1-23, May.

    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:14:y:2021:i:18:p:5873-:d:637102. 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.