IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v14y2021i15p4649-d605767.html
   My bibliography  Save this article

Efficient Design of Energy Disaggregation Model with BERT-NILM Trained by AdaX Optimization Method for Smart Grid

Author

Listed:
  • İsmail Hakkı Çavdar

    (Department of Electrical and Electronic Engineering, Karadeniz Technical University, Trabzon 61080, Turkey)

  • Vahit Feryad

    (Department of Electrical and Electronic Engineering, Karadeniz Technical University, Trabzon 61080, Turkey)

Abstract

One of the basic conditions for the successful implementation of energy demand-side management (EDM) in smart grids is the monitoring of different loads with an electrical load monitoring system. Energy and sustainability concerns present a multitude of issues that can be addressed using approaches of data mining and machine learning. However, resolving such problems due to the lack of publicly available datasets is cumbersome. In this study, we first designed an efficient energy disaggregation (ED) model and evaluated it on the basis of publicly available benchmark data from the Residential Energy Disaggregation Dataset (REDD), and then we aimed to advance ED research in smart grids using the Turkey Electrical Appliances Dataset (TEAD) containing household electricity usage data. In addition, the TEAD was evaluated using the proposed ED model tested with benchmark REDD data. The Internet of things (IoT) architecture with sensors and Node-Red software installations were established to collect data in the research. In the context of smart metering, a nonintrusive load monitoring (NILM) model was designed to classify household appliances according to TEAD data. A highly accurate supervised ED is introduced, which was designed to raise awareness to customers and generate feedback by demand without the need for smart sensors. It is also cost-effective, maintainable, and easy to install, it does not require much space, and it can be trained to monitor multiple devices. We propose an efficient BERT-NILM tuned by new adaptive gradient descent with exponential long-term memory (Adax), using a deep learning (DL) architecture based on bidirectional encoder representations from transformers (BERT). In this paper, an improved training function was designed specifically for tuning of NILM neural networks. We adapted the Adax optimization technique to the ED field and learned the sequence-to-sequence patterns. With the updated training function, BERT-NILM outperformed state-of-the-art adaptive moment estimation (Adam) optimization across various metrics on REDD datasets; lastly, we evaluated the TEAD dataset using BERT-NILM training.

Suggested Citation

  • İsmail Hakkı Çavdar & Vahit Feryad, 2021. "Efficient Design of Energy Disaggregation Model with BERT-NILM Trained by AdaX Optimization Method for Smart Grid," Energies, MDPI, vol. 14(15), pages 1-21, July.
    • Handle: RePEc:gam:jeners:v:14:y:2021:i:15:p:4649-:d:605767
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/14/15/4649/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/14/15/4649/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Wesley Angelino de Souza & Fernando Deluno Garcia & Fernando Pinhabel Marafão & Luiz Carlos Pereira da Silva & Marcelo Godoy Simões, 2019. "Load Disaggregation Using Microscopic Power Features and Pattern Recognition," Energies, MDPI, vol. 12(14), pages 1-18, July.
    2. Behrangrad, Mahdi, 2015. "A review of demand side management business models in the electricity market," Renewable and Sustainable Energy Reviews, Elsevier, vol. 47(C), pages 270-283.
    3. Christos Athanasiadis & Dimitrios Doukas & Theofilos Papadopoulos & Antonios Chrysopoulos, 2021. "A Scalable Real-Time Non-Intrusive Load Monitoring System for the Estimation of Household Appliance Power Consumption," Energies, MDPI, vol. 14(3), pages 1-23, February.
    4. İsmail Hakkı ÇAVDAR & Vahid FARYAD, 2019. "New Design of a Supervised Energy Disaggregation Model Based on the Deep Neural Network for a Smart Grid," Energies, MDPI, vol. 12(7), pages 1-18, March.
    5. Yang, Zaoli & Ghadamyari, Mojtaba & Khorramdel, Hossein & Seyed Alizadeh, Seyed Mehdi & Pirouzi, Sasan & Milani, Muhammed & Banihashemi, Farzad & Ghadimi, Noradin, 2021. "Robust multi-objective optimal design of islanded hybrid system with renewable and diesel sources/stationary and mobile energy storage systems," Renewable and Sustainable Energy Reviews, Elsevier, vol. 148(C).
    6. Moreno Jaramillo, Andres F. & Laverty, David M. & Morrow, D. John & Martinez del Rincon, Jesús & Foley, Aoife M., 2021. "Load modelling and non-intrusive load monitoring to integrate distributed energy resources in low and medium voltage networks," Renewable Energy, Elsevier, vol. 179(C), pages 445-466.
    7. Patrick Huber & Alberto Calatroni & Andreas Rumsch & Andrew Paice, 2021. "Review on Deep Neural Networks Applied to Low-Frequency NILM," Energies, MDPI, vol. 14(9), pages 1-34, April.
    8. Antonio Ruano & Alvaro Hernandez & Jesus Ureña & Maria Ruano & Juan Garcia, 2019. "NILM Techniques for Intelligent Home Energy Management and Ambient Assisted Living: A Review," Energies, MDPI, vol. 12(11), pages 1-29, June.
    9. Arash Moradzadeh & Omid Sadeghian & Kazem Pourhossein & Behnam Mohammadi-Ivatloo & Amjad Anvari-Moghaddam, 2020. "Improving Residential Load Disaggregation for Sustainable Development of Energy via Principal Component Analysis," Sustainability, MDPI, vol. 12(8), pages 1-14, April.
    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. Krzysztof Dowalla & Piotr Bilski & Robert Łukaszewski & Augustyn Wójcik & Ryszard Kowalik, 2022. "Application of the Time-Domain Signal Analysis for Electrical Appliances Identification in the Non-Intrusive Load Monitoring," Energies, MDPI, vol. 15(9), pages 1-20, May.
    2. Everton Luiz de Aguiar & André Eugenio Lazzaretti & Bruna Machado Mulinari & Daniel Rodrigues Pipa, 2021. "Scattering Transform for Classification in Non-Intrusive Load Monitoring," Energies, MDPI, vol. 14(20), pages 1-20, October.
    3. Hari Prasad Devarapalli & V. S. S. Siva Sarma Dhanikonda & Sitarama Brahmam Gunturi, 2020. "Non-Intrusive Identification of Load Patterns in Smart Homes Using Percentage Total Harmonic Distortion," Energies, MDPI, vol. 13(18), pages 1-15, September.
    4. Inoussa Laouali & Antonio Ruano & Maria da Graça Ruano & Saad Dosse Bennani & Hakim El Fadili, 2022. "Non-Intrusive Load Monitoring of Household Devices Using a Hybrid Deep Learning Model through Convex Hull-Based Data Selection," Energies, MDPI, vol. 15(3), pages 1-22, February.
    5. Veronica Piccialli & Antonio M. Sudoso, 2021. "Improving Non-Intrusive Load Disaggregation through an Attention-Based Deep Neural Network," Energies, MDPI, vol. 14(4), pages 1-16, February.
    6. Todic, Tamara & Stankovic, Vladimir & Stankovic, Lina, 2023. "An active learning framework for the low-frequency Non-Intrusive Load Monitoring problem," Applied Energy, Elsevier, vol. 341(C).
    7. Andreas Reinhardt & Lucas Pereira, 2021. "Special Issue: “Energy Data Analytics for Smart Meter Data”," Energies, MDPI, vol. 14(17), pages 1-3, August.
    8. Petros Papageorgiou & Dimitra Mylona & Konstantinos Stergiou & Aggelos S. Bouhouras, 2023. "A Time-Driven Deep Learning NILM Framework Based on Novel Current Harmonic Distortion Images," Sustainability, MDPI, vol. 15(17), pages 1-14, August.
    9. Mingzhi Yang & Yue Liu & Quanlong Liu, 2021. "Nonintrusive Residential Electricity Load Decomposition Based on Transfer Learning," Sustainability, MDPI, vol. 13(12), pages 1-11, June.
    10. Hao Ma & Juncheng Jia & Xinhao Yang & Weipeng Zhu & Hong Zhang, 2021. "MC-NILM: A Multi-Chain Disaggregation Method for NILM," Energies, MDPI, vol. 14(14), pages 1-14, July.
    11. Muhammad Asif Ali Rehmani & Saad Aslam & Shafiqur Rahman Tito & Snjezana Soltic & Pieter Nieuwoudt & Neel Pandey & Mollah Daud Ahmed, 2021. "Power Profile and Thresholding Assisted Multi-Label NILM Classification," Energies, MDPI, vol. 14(22), pages 1-18, November.
    12. Cheng, Meng & Sami, Saif Sabah & Wu, Jianzhong, 2017. "Benefits of using virtual energy storage system for power system frequency response," Applied Energy, Elsevier, vol. 194(C), pages 376-385.
    13. Christos N. Dimitriadis & Evangelos G. Tsimopoulos & Michael C. Georgiadis, 2021. "A Review on the Complementarity Modelling in Competitive Electricity Markets," Energies, MDPI, vol. 14(21), pages 1-27, November.
    14. Meyabadi, A. Fattahi & Deihimi, M.H., 2017. "A review of demand-side management: Reconsidering theoretical framework," Renewable and Sustainable Energy Reviews, Elsevier, vol. 80(C), pages 367-379.
    15. Abdul Conteh & Mohammed Elsayed Lotfy & Kiptoo Mark Kipngetich & Tomonobu Senjyu & Paras Mandal & Shantanu Chakraborty, 2019. "An Economic Analysis of Demand Side Management Considering Interruptible Load and Renewable Energy Integration: A Case Study of Freetown Sierra Leone," Sustainability, MDPI, vol. 11(10), pages 1-19, May.
    16. Pascal A. Schirmer & Iosif Mporas, 2019. "Statistical and Electrical Features Evaluation for Electrical Appliances Energy Disaggregation," Sustainability, MDPI, vol. 11(11), pages 1-14, June.
    17. Saima Akhtar & Sulman Shahzad & Asad Zaheer & Hafiz Sami Ullah & Heybet Kilic & Radomir Gono & Michał Jasiński & Zbigniew Leonowicz, 2023. "Short-Term Load Forecasting Models: A Review of Challenges, Progress, and the Road Ahead," Energies, MDPI, vol. 16(10), pages 1-29, May.
    18. Jurasz, Jakub & Ciapała, Bartłomiej, 2017. "Integrating photovoltaics into energy systems by using a run-off-river power plant with pondage to smooth energy exchange with the power gird," Applied Energy, Elsevier, vol. 198(C), pages 21-35.
    19. Shaik, Saboor & Maduru, Venkata Ramana & Kirankumar, Gorantla & Arıcı, Müslüm & Ghosh, Aritra & Kontoleon, Karolos J. & Afzal, Asif, 2022. "Space-age energy saving, carbon emission mitigation and color rendering perspective of architectural antique stained glass windows," Energy, Elsevier, vol. 259(C).
    20. Nong, Duy & Nguyen, Duong Binh & Nguyen, Trung H. & Wang, Can & Siriwardana, Mahinda, 2020. "A stronger energy strategy for a new era of economic development in Vietnam: A quantitative assessment," Energy Policy, Elsevier, vol. 144(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:14:y:2021:i:15:p:4649-:d:605767. 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.