IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v17y2024i4p902-d1339147.html
   My bibliography  Save this article

Multihousehold Load Forecasting Based on a Convolutional Neural Network Using Moment Information and Data Augmentation

Author

Listed:
  • Shree Krishna Acharya

    (School of Business, University College Dublin, Dublin A94XF34, Ireland)

  • Hwanuk Yu

    (School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea)

  • Young-Min Wi

    (Department of Electrical Engineering, Sangmyung University, Seoul 03016, Republic of Korea)

  • Jaehee Lee

    (Department of Electrical and Control Engineering, Mokpo National University, Muan 58554, Republic of Korea)

Abstract

Deep learning (DL) networks are a popular choice for short-term load forecasting (STLF) in the residential sector. Hybrid DL methodologies based on convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) have a higher forecasting accuracy than conventional statistical STLF techniques for different types of single-household load series. However, existing load forecasting methodologies are often inefficient when a high load demand persists for a few hours in a day. Peak load consumption is explicitly depicted as a tail in the probability distribution function (PDF) of the load series. Due to the diverse and uncertain nature of peak load demands, DL methodologies have difficulty maintaining consistent forecasting results, particularly when the PDF of the load series has a longer tail. This paper proposes a multihousehold load forecasting strategy based on the collective moment measure (CMM) (which is obtained from the PDF of the load series), data augmentation, and a CNN. Each load series was compared and ordered through CMM indexing, which helped maintain a minimum or constant shifting variance in the dataset inputted to the CNN. Data augmentation was used to enlarge the input dataset and solve the existing data requirement issues of the CNN. With the ordered load series and data augmentation strategy, the simulation results demonstrated a significant improvement in the performance of both single-household and multihousehold load forecasting. The proposed method predicts day-ahead multihousehold loads simultaneously and compares the results based on a single household. The forecasting performance of the proposed method for six different household groups with 10, 20, 30, 50, 80, and 100 household load series was evaluated and compared with those of existing methodologies. The mean absolute percentage error of the prediction results for each multihousehold load series could be improved by more than 3%. This study can help advance the application of DL methods for household load prediction under high-load-demand conditions.

Suggested Citation

  • Shree Krishna Acharya & Hwanuk Yu & Young-Min Wi & Jaehee Lee, 2024. "Multihousehold Load Forecasting Based on a Convolutional Neural Network Using Moment Information and Data Augmentation," Energies, MDPI, vol. 17(4), pages 1-18, February.
    • Handle: RePEc:gam:jeners:v:17:y:2024:i:4:p:902-:d:1339147
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/17/4/902/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/17/4/902/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Changqing Cheng & Akkarapol Sa-Ngasoongsong & Omer Beyca & Trung Le & Hui Yang & Zhenyu (James) Kong & Satish T.S. Bukkapatnam, 2015. "Time series forecasting for nonlinear and non-stationary processes: a review and comparative study," IISE Transactions, Taylor & Francis Journals, vol. 47(10), pages 1053-1071, October.
    2. Huang, Qian & Li, Jinghua & Zhu, Mengshu, 2020. "An improved convolutional neural network with load range discretization for probabilistic load forecasting," Energy, Elsevier, vol. 203(C).
    Full references (including those not matched with items on IDEAS)

    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. Jie Fang & Shutao Xia & Jianwu Lin & Yong Jiang, 2019. "Automatic Financial Feature Construction," Papers 1912.06236, arXiv.org, revised Oct 2020.
    2. Lu, Shixiang & Xu, Qifa & Jiang, Cuixia & Liu, Yezheng & Kusiak, Andrew, 2022. "Probabilistic load forecasting with a non-crossing sparse-group Lasso-quantile regression deep neural network," Energy, Elsevier, vol. 242(C).
    3. Hernandez-Matheus, Alejandro & Löschenbrand, Markus & Berg, Kjersti & Fuchs, Ida & Aragüés-Peñalba, Mònica & Bullich-Massagué, Eduard & Sumper, Andreas, 2022. "A systematic review of machine learning techniques related to local energy communities," Renewable and Sustainable Energy Reviews, Elsevier, vol. 170(C).
    4. Kristof Lommers & Ouns El Harzli & Jack Kim, 2021. "Confronting Machine Learning With Financial Research," Papers 2103.00366, arXiv.org, revised Mar 2021.
    5. Mayer, Martin János & Biró, Bence & Szücs, Botond & Aszódi, Attila, 2023. "Probabilistic modeling of future electricity systems with high renewable energy penetration using machine learning," Applied Energy, Elsevier, vol. 336(C).
    6. Navarkar, Abhishek & Hasti, Veeraraghava Raju & Deneke, Elihu & Gore, Jay P., 2020. "A data-driven model for thermodynamic properties of a steam generator under cycling operation," Energy, Elsevier, vol. 211(C).
    7. Jia, Xiongjie & Sang, Yichen & Li, Yanjun & Du, Wei & Zhang, Guolei, 2022. "Short-term forecasting for supercharged boiler safety performance based on advanced data-driven modelling framework," Energy, Elsevier, vol. 239(PE).
    8. Zang, Haixiang & Xu, Ruiqi & Cheng, Lilin & Ding, Tao & Liu, Ling & Wei, Zhinong & Sun, Guoqiang, 2021. "Residential load forecasting based on LSTM fusing self-attention mechanism with pooling," Energy, Elsevier, vol. 229(C).
    9. Du, Pei & Wang, Jianzhou & Yang, Wendong & Niu, Tong, 2020. "Point and interval forecasting for metal prices based on variational mode decomposition and an optimized outlier-robust extreme learning machine," Resources Policy, Elsevier, vol. 69(C).
    10. Wan, Anping & Chang, Qing & AL-Bukhaiti, Khalil & He, Jiabo, 2023. "Short-term power load forecasting for combined heat and power using CNN-LSTM enhanced by attention mechanism," Energy, Elsevier, vol. 282(C).
    11. Ozdemir, Ali Can & Buluş, Kurtuluş & Zor, Kasım, 2022. "Medium- to long-term nickel price forecasting using LSTM and GRU networks," Resources Policy, Elsevier, vol. 78(C).
    12. Vaia I. Kontopoulou & Athanasios D. Panagopoulos & Ioannis Kakkos & George K. Matsopoulos, 2023. "A Review of ARIMA vs. Machine Learning Approaches for Time Series Forecasting in Data Driven Networks," Future Internet, MDPI, vol. 15(8), pages 1-31, July.
    13. Tadeusz A. Grzeszczyk & Michal K. Grzeszczyk, 2022. "Justifying Short-Term Load Forecasts Obtained with the Use of Neural Models," Energies, MDPI, vol. 15(5), pages 1-20, March.
    14. Iraj Daizadeh, 2021. "Leveraging latent persistency in United States patent and trademark applications to gain insight into the evolution of an innovation-driven economy," Papers 2101.02588, arXiv.org, revised May 2021.
    15. George Kosgei Kiptum, 2022. "Relationship between Kenya’s economic growth and inflation," SN Business & Economics, Springer, vol. 2(12), pages 1-16, December.
    16. Hyunsoo Lee, 2019. "Development of Sustainable Recycling Investment Framework Considering Uncertain Demand and Nonlinear Recycling Cost," Sustainability, MDPI, vol. 11(14), pages 1-18, July.
    17. Zhang, Wenyu & Chen, Qian & Yan, Jianyong & Zhang, Shuai & Xu, Jiyuan, 2021. "A novel asynchronous deep reinforcement learning model with adaptive early forecasting method and reward incentive mechanism for short-term load forecasting," Energy, Elsevier, vol. 236(C).
    18. He Jiang & Weihua Zheng, 2022. "Deep learning with regularized robust long‐ and short‐term memory network for probabilistic short‐term load forecasting," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 41(6), pages 1201-1216, September.
    19. Lagomarsino-Oneto, Daniele & Meanti, Giacomo & Pagliana, Nicolò & Verri, Alessandro & Mazzino, Andrea & Rosasco, Lorenzo & Seminara, Agnese, 2023. "Physics informed machine learning for wind speed prediction," Energy, Elsevier, vol. 268(C).
    20. Liu, Luyao & Bai, Feifei & Su, Chenyu & Ma, Cuiping & Yan, Ruifeng & Li, Hailong & Sun, Qie & Wennersten, Ronald, 2022. "Forecasting the occurrence of extreme electricity prices using a multivariate logistic regression model," Energy, Elsevier, vol. 247(C).

    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:17:y:2024:i:4:p:902-:d:1339147. 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.