IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v17y2024i20p5183-d1501184.html
   My bibliography  Save this article

Autoencoder-Driven Training Data Selection Based on Hidden Features for Improved Accuracy of ANN Short-Term Load Forecasting in ADMS

Author

Listed:
  • Zoran Pajić

    (Electronic and Telecommunication Engineering, Department of Power, Faculty of Technical Sciences, University of Novi Sad, Trg Dositeja Obradovića 6, 21000 Novi Sad, Serbia)

  • Zoran Janković

    (Electronic and Telecommunication Engineering, Department of Power, Faculty of Technical Sciences, University of Novi Sad, Trg Dositeja Obradovića 6, 21000 Novi Sad, Serbia
    Schneider Electric Novi Sad, Industrijska 3G, 21000 Novi Sad, Serbia)

  • Aleksandar Selakov

    (Electronic and Telecommunication Engineering, Department of Power, Faculty of Technical Sciences, University of Novi Sad, Trg Dositeja Obradovića 6, 21000 Novi Sad, Serbia)

Abstract

This paper presents a novel methodology for short-term load forecasting in the context of significant shifts in the daily load curve due to the rapid and extensive adoption of Distributed Energy Resources (DERs). The proposed solution, built upon the Similar Days Method (SDM) and Artificial Neural Network (ANN), introduces several novelties: (1) selection of similar days based on hidden representations of day data using Autoencoder (AE); (2) enhancement of model generalization by utilizing a broader set of training examples; (3) incorporating the relative importance of training examples derived from the similarity measure during training; and (4) mitigation of the influence of outliers by applying an ensemble of ANN models trained with different data splits. The presented AE configuration and procedure for selecting similar days generated a higher-quality training dataset, which led to more robust predictions by the ANN model for days with unexpected deviations. Experiments were conducted on actual load data from a Serbian electrical power system, and the results were compared to predictions obtained by the field-proven STLF tool. The experiments demonstrated an improved performance of the presented solution on test days when the existing STLF tool had poor predictions over the past year.

Suggested Citation

  • Zoran Pajić & Zoran Janković & Aleksandar Selakov, 2024. "Autoencoder-Driven Training Data Selection Based on Hidden Features for Improved Accuracy of ANN Short-Term Load Forecasting in ADMS," Energies, MDPI, vol. 17(20), pages 1-14, October.
    • Handle: RePEc:gam:jeners:v:17:y:2024:i:20:p:5183-:d:1501184
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/17/20/5183/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/17/20/5183/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Stevan Savić & Aleksandar Selakov & Dragan Milošević, 2014. "Cold and warm air temperature spells during the winter and summer seasons and their impact on energy consumption in urban areas," Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, Springer;International Society for the Prevention and Mitigation of Natural Hazards, vol. 73(2), pages 373-387, September.
    2. Amirhossein Sajadi & Luka Strezoski & Vladimir Strezoski & Marija Prica & Kenneth A. Loparo, 2019. "Integration of renewable energy systems and challenges for dynamics, control, and automation of electrical power systems," Wiley Interdisciplinary Reviews: Energy and Environment, Wiley Blackwell, vol. 8(1), January.
    3. Hany Habbak & Mohamed Mahmoud & Khaled Metwally & Mostafa M. Fouda & Mohamed I. Ibrahem, 2023. "Load Forecasting Techniques and Their Applications in Smart Grids," Energies, MDPI, vol. 16(3), pages 1-33, February.
    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. Manuel S. Alvarez-Alvarado & Johnny Rengifo & Rommel M. Gallegos-Núñez & José G. Rivera-Mora & Holguer H. Noriega & Washington Velasquez & Daniel L. Donaldson & Carlos D. Rodríguez-Gallegos, 2022. "Particle Swarm Optimization for Optimal Frequency Response with High Penetration of Photovoltaic and Wind Generation," Energies, MDPI, vol. 15(22), pages 1-12, November.
    2. Fangzong Wang & Zuhaib Nishtar, 2024. "Real-Time Load Forecasting and Adaptive Control in Smart Grids Using a Hybrid Neuro-Fuzzy Approach," Energies, MDPI, vol. 17(11), pages 1-24, May.
    3. Peng Tian & Zetao Li & Zhenghang Hao, 2019. "A Doubly-Fed Induction Generator Adaptive Control Strategy and Coordination Technology Compatible with Feeder Automation," Energies, MDPI, vol. 12(23), pages 1-21, November.
    4. Doljak, Dejan & Stanojević, Gorica, 2017. "Evaluation of natural conditions for site selection of ground-mounted photovoltaic power plants in Serbia," Energy, Elsevier, vol. 127(C), pages 291-300.
    5. Wadim Strielkowski & Andrey Vlasov & Kirill Selivanov & Konstantin Muraviev & Vadim Shakhnov, 2023. "Prospects and Challenges of the Machine Learning and Data-Driven Methods for the Predictive Analysis of Power Systems: A Review," Energies, MDPI, vol. 16(10), pages 1-31, May.
    6. Stevan Savić & Vladimir Marković & Ivan Šećerov & Dragoslav Pavić & Daniela Arsenović & Dragan Milošević & Dragan Dolinaj & Imre Nagy & Milana Pantelić, 2018. "Heat wave risk assessment and mapping in urban areas: case study for a midsized Central European city, Novi Sad (Serbia)," Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, Springer;International Society for the Prevention and Mitigation of Natural Hazards, vol. 91(3), pages 891-911, April.
    7. Lv, Jiaqing & Zheng, Xiaodong & Pawlak, Mirosław & Mo, Weike & Miśkowicz, Marek, 2021. "Very short-term probabilistic wind power prediction using sparse machine learning and nonparametric density estimation algorithms," Renewable Energy, Elsevier, vol. 177(C), pages 181-192.
    8. Jiakang Wang & Hui Liu & Guangji Zheng & Ye Li & Shi Yin, 2023. "Short-Term Load Forecasting Based on Outlier Correction, Decomposition, and Ensemble Reinforcement Learning," Energies, MDPI, vol. 16(11), pages 1-16, May.
    9. repec:ags:aaea16:235739 is not listed on IDEAS
    10. Eren, Yavuz & Küçükdemiral, İbrahim, 2024. "A comprehensive review on deep learning approaches for short-term load forecasting," Renewable and Sustainable Energy Reviews, Elsevier, vol. 189(PB).
    11. Lee, Gi-Eu, 2016. "Temperature Effects are more Complex than Degrees: A Case Study on Residential Energy Consumption," 2016 Annual Meeting, July 31-August 2, Boston, Massachusetts 242285, Agricultural and Applied Economics Association.
    12. Peter D. Lund & John Byrne, 2020. "Little time left to reverse emissions—Growing hope despite disappointing CO2 trend," Wiley Interdisciplinary Reviews: Energy and Environment, Wiley Blackwell, vol. 9(1), January.
    13. Luka Strezoski, 2023. "Distributed energy resource management systems—DERMS: State of the art and how to move forward," Wiley Interdisciplinary Reviews: Energy and Environment, Wiley Blackwell, vol. 12(1), January.
    14. Zheyu He & Rongheng Lin & Budan Wu & Xin Zhao & Hua Zou, 2023. "Pre-Attention Mechanism and Convolutional Neural Network Based Multivariate Load Prediction for Demand Response," Energies, MDPI, vol. 16(8), pages 1-13, April.
    15. Amirhossein Sajadi & Rick Wallace Kenyon & Bri-Mathias Hodge, 2022. "Synchronization in electric power networks with inherent heterogeneity up to 100% inverter-based renewable generation," Nature Communications, Nature, vol. 13(1), pages 1-12, December.
    16. Alarico Macor & Alberto Benato, 2020. "Regulated Emissions of Biogas Engines—On Site Experimental Measurements and Damage Assessment on Human Health," Energies, MDPI, vol. 13(5), pages 1-38, February.
    17. Kim, Hyunggeun & Park, Sangkyu & Lee, Jongsu, 2021. "Is renewable energy acceptable with power grid expansion? A quantitative study of South Korea's renewable energy acceptance," Renewable and Sustainable Energy Reviews, Elsevier, vol. 139(C).
    18. Aydin Zaboli & Swetha Rani Kasimalla & Kuchan Park & Younggi Hong & Junho Hong, 2024. "A Comprehensive Review of Behind-the-Meter Distributed Energy Resources Load Forecasting: Models, Challenges, and Emerging Technologies," Energies, MDPI, vol. 17(11), pages 1-27, May.
    19. Yanxu Liu & Shuangshuang Li & Yanglin Wang & Tian Zhang & Jian Peng & Tianyi Li, 2015. "Identification of multiple climatic extremes in metropolis: a comparison of Guangzhou and Shenzhen, China," Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, Springer;International Society for the Prevention and Mitigation of Natural Hazards, vol. 79(2), pages 939-953, November.
    20. Hany Habbak & Mohamed Mahmoud & Mostafa M. Fouda & Maazen Alsabaan & Ahmed Mattar & Gouda I. Salama & Khaled Metwally, 2023. "Efficient One-Class False Data Detector Based on Deep SVDD for Smart Grids," Energies, MDPI, vol. 16(20), pages 1-28, October.
    21. Sepideh Radhoush & Bradley M. Whitaker & Hashem Nehrir, 2023. "An Overview of Supervised Machine Learning Approaches for Applications in Active Distribution Networks," Energies, MDPI, vol. 16(16), pages 1-29, 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:17:y:2024:i:20:p:5183-:d:1501184. 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.