IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v16y2023i4p2026-d1072755.html
   My bibliography  Save this article

Developing Feedforward Neural Networks as Benchmark for Load Forecasting: Methodology Presentation and Application to Hospital Heat Load Forecasting

Author

Listed:
  • Malte Stienecker

    (Fraunhofer UMSICHT, Fraunhofer Institute for Environmental, Safety, and Energy Technology, Osterfelder Str.3, 46047 Oberhausen, Germany)

  • Anne Hagemeier

    (Fraunhofer UMSICHT, Fraunhofer Institute for Environmental, Safety, and Energy Technology, Osterfelder Str.3, 46047 Oberhausen, Germany)

Abstract

For load forecasting, numerous machine learning (ML) approaches have been published. Besides fully connected feedforward neural networks (FFNNs), also called multilayer perceptron, more advanced ML approaches like deep, recurrent or convolutional neural networks or ensemble methods have been applied. However, evaluating the added benefit by novel approaches is difficult. Statistical or rule-based methods constitute a too low benchmark. FFNNs need extensive tuning due to their manifold design choices. To address this issue, a structured, comprehensible five-step FFNN model creation methodology is presented, which constitutes of initial model creation, internal parameter selection, feature engineering, architecture tuning and final model creation. The methodology is then applied to forecast real world heat load data of a hospital in Germany. The forecast constitutes of 192 values (upcoming 48 h in 15 min resolution) and is composed of a multi-model univariate forecasting strategy, with three test models developed at first. As a result, the test models show great similarities which simplifies creation of the remaining models. A performance increase of up to 18% between initial and final models points out the importance of model tuning. As a conclusion, comprehensible model tuning is vital to use FFNN models as benchmark. The effort needed can be reduced by the experience gained through repeated application of the presented methodology.

Suggested Citation

  • Malte Stienecker & Anne Hagemeier, 2023. "Developing Feedforward Neural Networks as Benchmark for Load Forecasting: Methodology Presentation and Application to Hospital Heat Load Forecasting," Energies, MDPI, vol. 16(4), pages 1-22, February.
  • Handle: RePEc:gam:jeners:v:16:y:2023:i:4:p:2026-:d:1072755
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/16/4/2026/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1996-1073/16/4/2026/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Andrea Manno & Emanuele Martelli & Edoardo Amaldi, 2022. "A Shallow Neural Network Approach for the Short-Term Forecast of Hourly Energy Consumption," Energies, MDPI, vol. 15(3), pages 1-21, January.
    2. Ma, Deyin & Zhang, Lizhi & Sun, Bo, 2021. "An interval scheduling method for the CCHP system containing renewable energy sources based on model predictive control," Energy, Elsevier, vol. 236(C).
    3. Haben, Stephen & Arora, Siddharth & Giasemidis, Georgios & Voss, Marcus & Vukadinović Greetham, Danica, 2021. "Review of low voltage load forecasting: Methods, applications, and recommendations," Applied Energy, Elsevier, vol. 304(C).
    4. Alfonso González González & Justo García-Sanz-Calcedo & David Rodríguez Salgado, 2018. "Evaluation of Energy Consumption in German Hospitals: Benchmarking in the Public Sector," Energies, MDPI, vol. 11(9), pages 1-14, August.
    5. Amasyali, Kadir & El-Gohary, Nora M., 2018. "A review of data-driven building energy consumption prediction studies," Renewable and Sustainable Energy Reviews, Elsevier, vol. 81(P1), pages 1192-1205.
    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. Binglin Li & Yong Shao & Yufeng Lian & Pai Li & Qiang Lei, 2023. "Bayesian Optimization-Based LSTM for Short-Term Heating Load Forecasting," Energies, MDPI, vol. 16(17), pages 1-14, August.

    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. Fredrik Skaug Fadnes & Reyhaneh Banihabib & Mohsen Assadi, 2023. "Using Artificial Neural Networks to Gather Intelligence on a Fully Operational Heat Pump System in an Existing Building Cluster," Energies, MDPI, vol. 16(9), pages 1-33, May.
    2. Tian, Shen & Shao, Shuangquan & Liu, Bin, 2019. "Investigation on transient energy consumption of cold storages: Modeling and a case study," Energy, Elsevier, vol. 180(C), pages 1-9.
    3. Langevin, J. & Reyna, J.L. & Ebrahimigharehbaghi, S. & Sandberg, N. & Fennell, P. & Nägeli, C. & Laverge, J. & Delghust, M. & Mata, É. & Van Hove, M. & Webster, J. & Federico, F. & Jakob, M. & Camaras, 2020. "Developing a common approach for classifying building stock energy models," Renewable and Sustainable Energy Reviews, Elsevier, vol. 133(C).
    4. Ijaz Ul Haq & Amin Ullah & Samee Ullah Khan & Noman Khan & Mi Young Lee & Seungmin Rho & Sung Wook Baik, 2021. "Sequential Learning-Based Energy Consumption Prediction Model for Residential and Commercial Sectors," Mathematics, MDPI, vol. 9(6), pages 1-17, March.
    5. Luo, X.J. & Oyedele, Lukumon O. & Ajayi, Anuoluwapo O. & Akinade, Olugbenga O. & Owolabi, Hakeem A. & Ahmed, Ashraf, 2020. "Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings," Renewable and Sustainable Energy Reviews, Elsevier, vol. 131(C).
    6. Chou, Jui-Sheng & Tran, Duc-Son, 2018. "Forecasting energy consumption time series using machine learning techniques based on usage patterns of residential householders," Energy, Elsevier, vol. 165(PB), pages 709-726.
    7. Gautham Krishnadas & Aristides Kiprakis, 2020. "A Machine Learning Pipeline for Demand Response Capacity Scheduling," Energies, MDPI, vol. 13(7), pages 1-25, April.
    8. Wang, Lan & Lee, Eric W.M. & Hussian, Syed Asad & Yuen, Anthony Chun Yin & Feng, Wei, 2021. "Quantitative impact analysis of driving factors on annual residential building energy end-use combining machine learning and stochastic methods," Applied Energy, Elsevier, vol. 299(C).
    9. Ahmet Bircan Atmaca & Gülay Zorer Gedik & Andreas Wagner, 2021. "Determination of Optimum Envelope of Religious Buildings in Terms of Thermal Comfort and Energy Consumption: Mosque Cases," Energies, MDPI, vol. 14(20), pages 1-17, October.
    10. Wang, Ran & Lu, Shilei & Feng, Wei, 2020. "A novel improved model for building energy consumption prediction based on model integration," Applied Energy, Elsevier, vol. 262(C).
    11. Sarabia Escriva, Emilio José & Hart, Matthew & Acha, Salvador & Soto Francés, Víctor & Shah, Nilay & Markides, Christos N., 2022. "Techno-economic evaluation of integrated energy systems for heat recovery applications in food retail buildings," Applied Energy, Elsevier, vol. 305(C).
    12. Chun-Wei Chen, 2023. "A Feasibility Discussion: Is ML Suitable for Predicting Sustainable Patterns in Consumer Product Preferences?," Sustainability, MDPI, vol. 15(5), pages 1-21, February.
    13. Zhaocheng Li & Yu Song, 2022. "Energy Consumption Linkages of the Chinese Construction Sector," Energies, MDPI, vol. 15(5), pages 1-13, February.
    14. Michel Noussan & Benedetto Nastasi, 2018. "Data Analysis of Heating Systems for Buildings—A Tool for Energy Planning, Policies and Systems Simulation," Energies, MDPI, vol. 11(1), pages 1-15, January.
    15. Zhu, Jizhong & Dong, Hanjiang & Zheng, Weiye & Li, Shenglin & Huang, Yanting & Xi, Lei, 2022. "Review and prospect of data-driven techniques for load forecasting in integrated energy systems," Applied Energy, Elsevier, vol. 321(C).
    16. Guillaume Guerard & Hugo Pousseur & Ihab Taleb, 2021. "Isolated Areas Consumption Short-Term Forecasting Method," Energies, MDPI, vol. 14(23), pages 1-23, November.
    17. Finck, Christian & Li, Rongling & Zeiler, Wim, 2020. "Optimal control of demand flexibility under real-time pricing for heating systems in buildings: A real-life demonstration," Applied Energy, Elsevier, vol. 263(C).
    18. Anand Krishnan Prakash & Susu Xu & Ram Rajagopal & Hae Young Noh, 2018. "Robust Building Energy Load Forecasting Using Physically-Based Kernel Models," Energies, MDPI, vol. 11(4), pages 1-21, April.
    19. Amasyali, Kadir & El-Gohary, Nora M., 2021. "Real data-driven occupant-behavior optimization for reduced energy consumption and improved comfort," Applied Energy, Elsevier, vol. 302(C).
    20. Mohammad Navid Fekri & Ananda Mohon Ghosh & Katarina Grolinger, 2019. "Generating Energy Data for Machine Learning with Recurrent Generative Adversarial Networks," Energies, MDPI, vol. 13(1), pages 1-23, December.

    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:16:y:2023:i:4:p:2026-:d:1072755. 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.