IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v11y2018i9p2460-d170187.html
   My bibliography  Save this article

Implementation Strategy of Convolution Neural Networks on Field Programmable Gate Arrays for Appliance Classification Using the Voltage and Current (V-I) Trajectory

Author

Listed:
  • Darío Baptista

    (Instituto Superior Tecnico, Universidade de Lisboa, 1649-001 Lisbon, Portugal
    M-ITI—Madeira Interactive Technologies Institute, 9020-105 Funchal, Portugal
    INESC-ID Instituto de Engenharia de Sistemas e Computadores—Investigação e Desenvolvimento, DEEC, 1000-029 Lisbon, Portugal)

  • Sheikh Shanawaz Mostafa

    (Instituto Superior Tecnico, Universidade de Lisboa, 1649-001 Lisbon, Portugal
    M-ITI—Madeira Interactive Technologies Institute, 9020-105 Funchal, Portugal)

  • Lucas Pereira

    (M-ITI—Madeira Interactive Technologies Institute, 9020-105 Funchal, Portugal)

  • Leonel Sousa

    (Instituto Superior Tecnico, Universidade de Lisboa, 1649-001 Lisbon, Portugal
    INESC-ID Instituto de Engenharia de Sistemas e Computadores—Investigação e Desenvolvimento, DEEC, 1000-029 Lisbon, Portugal)

  • Fernando Morgado-Dias

    (M-ITI—Madeira Interactive Technologies Institute, 9020-105 Funchal, Portugal
    Ciências Exatas e Engenharia, UMa-University of Madeira, 9020-105 Funchal, Portugal)

Abstract

Specific information about types of appliances and their use in a specific time window could help determining in details the electrical energy consumption information. However, conventional main power meters fail to provide any specific information. One of the best ways to solve these problems is through non-intrusive load monitoring, which is cheaper and easier to implement than other methods. However, developing a classifier for deducing what kind of appliances are used at home is a difficult assignment, because the system should identify the appliance as fast as possible with a higher degree of certainty. To achieve all these requirements, a convolution neural network implemented on hardware was used to identify the appliance through the voltage and current (V-I) trajectory. For the implementation on hardware, a field programmable gate array (FPGA) was used to exploit processing parallelism in order to achieve optimal performance. To validate the design, a publicly available Plug Load Appliance Identification Dataset (PLAID), constituted by 11 different appliances, has been used. The overall average F-score achieved using this classifier is 78.16% for the PLAID 1 dataset. The convolution neural network implemented on hardware has a processing time of approximately 5.7 ms and a power consumption of 1.868 W.

Suggested Citation

  • Darío Baptista & Sheikh Shanawaz Mostafa & Lucas Pereira & Leonel Sousa & Fernando Morgado-Dias, 2018. "Implementation Strategy of Convolution Neural Networks on Field Programmable Gate Arrays for Appliance Classification Using the Voltage and Current (V-I) Trajectory," Energies, MDPI, vol. 11(9), pages 1-18, September.
  • Handle: RePEc:gam:jeners:v:11:y:2018:i:9:p:2460-:d:170187
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/11/9/2460/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1996-1073/11/9/2460/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Carrie Armel, K. & Gupta, Abhay & Shrimali, Gireesh & Albert, Adrian, 2013. "Is disaggregation the holy grail of energy efficiency? The case of electricity," Energy Policy, Elsevier, vol. 52(C), pages 213-234.
    2. Esa, Nur Farahin & Abdullah, Md Pauzi & Hassan, Mohammad Yusri, 2016. "A review disaggregation method in Non-intrusive Appliance Load Monitoring," Renewable and Sustainable Energy Reviews, Elsevier, vol. 66(C), pages 163-173.
    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. Xizheng Guo & Jiaqi Yuan & Yiguo Tang & Xiaojie You, 2018. "Hardware in the Loop Real-time Simulation for the Associated Discrete Circuit Modeling Optimization Method of Power Converters," Energies, MDPI, vol. 11(11), pages 1-14, November.
    2. 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.
    3. Dadiana-Valeria Căiman & Toma-Leonida Dragomir, 2020. "A Novel Method for Obtaining the Signature of Household Consumer Pairs," Energies, MDPI, vol. 13(22), pages 1-20, November.
    4. Anthony Faustine & Lucas Pereira, 2020. "Multi-Label Learning for Appliance Recognition in NILM Using Fryze-Current Decomposition and Convolutional Neural Network," Energies, MDPI, vol. 13(16), pages 1-17, August.
    5. Anthony Faustine & Lucas Pereira, 2020. "Improved Appliance Classification in Non-Intrusive Load Monitoring Using Weighted Recurrence Graph and Convolutional Neural Networks," Energies, MDPI, vol. 13(13), pages 1-15, July.

    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. Hasan Rafiq & Xiaohan Shi & Hengxu Zhang & Huimin Li & Manesh Kumar Ochani, 2020. "A Deep Recurrent Neural Network for Non-Intrusive Load Monitoring Based on Multi-Feature Input Space and Post-Processing," Energies, MDPI, vol. 13(9), pages 1-26, May.
    2. Enríquez, R. & Jiménez, M.J. & Heras, M.R., 2017. "Towards non-intrusive thermal load Monitoring of buildings: BES calibration," Applied Energy, Elsevier, vol. 191(C), pages 44-54.
    3. Sara Tavakoli & Kaveh Khalilpour, 2021. "A Practical Load Disaggregation Approach for Monitoring Industrial Users Demand with Limited Data Availability," Energies, MDPI, vol. 14(16), pages 1-27, August.
    4. Shimoda, Yoshiyuki & Yamaguchi, Yohei & Iwafune, Yumiko & Hidaka, Kazuyoshi & Meier, Alan & Yagita, Yoshie & Kawamoto, Hisaki & Nishikiori, Soichi, 2020. "Energy demand science for a decarbonized society in the context of the residential sector," Renewable and Sustainable Energy Reviews, Elsevier, vol. 132(C).
    5. Augustyn Wójcik & Piotr Bilski & Robert Łukaszewski & Krzysztof Dowalla & Ryszard Kowalik, 2021. "Identification of the State of Electrical Appliances with the Use of a Pulse Signal Generator," Energies, MDPI, vol. 14(3), pages 1-26, January.
    6. Wu, Junqi & Niu, Zhibin & Li, Xiang & Huang, Lizhen & Nielsen, Per Sieverts & Liu, Xiufeng, 2023. "Understanding multi-scale spatiotemporal energy consumption data: A visual analysis approach," Energy, Elsevier, vol. 263(PD).
    7. Chatzigeorgiou, I.M. & Andreou, G.T., 2021. "A systematic review on feedback research for residential energy behavior change through mobile and web interfaces," Renewable and Sustainable Energy Reviews, Elsevier, vol. 135(C).
    8. Y, Kiguchi & Y, Heo & M, Weeks & R, Choudhary, 2019. "Predicting intra-day load profiles under time-of-use tariffs using smart meter data," Energy, Elsevier, vol. 173(C), pages 959-970.
    9. Zhou, Yang & Shi, Zhixiong & Shi, Zhengyu & Gao, Qing & Wu, Libo, 2019. "Disaggregating power consumption of commercial buildings based on the finite mixture model," Applied Energy, Elsevier, vol. 243(C), pages 35-46.
    10. Lang, Corey & Okwelum, Edson, 2015. "The mitigating effect of strategic behavior on the net benefits of a direct load control program," Energy Economics, Elsevier, vol. 49(C), pages 141-148.
    11. Coelho, Igor M. & Coelho, Vitor N. & Luz, Eduardo J. da S. & Ochi, Luiz S. & Guimarães, Frederico G. & Rios, Eyder, 2017. "A GPU deep learning metaheuristic based model for time series forecasting," Applied Energy, Elsevier, vol. 201(C), pages 412-418.
    12. Iana Vassileva & Javier Campillo, 2016. "Consumers’ Perspective on Full-Scale Adoption of Smart Meters: A Case Study in Västerås, Sweden," Resources, MDPI, vol. 5(1), pages 1-18, January.
    13. Schultz, P. Wesley & Estrada, Mica & Schmitt, Joseph & Sokoloski, Rebecca & Silva-Send, Nilmini, 2015. "Using in-home displays to provide smart meter feedback about household electricity consumption: A randomized control trial comparing kilowatts, cost, and social norms," Energy, Elsevier, vol. 90(P1), pages 351-358.
    14. Benjamin Völker & Marc Pfeifer & Philipp M. Scholl & Bernd Becker, 2020. "A Framework to Generate and Label Datasets for Non-Intrusive Load Monitoring," Energies, MDPI, vol. 14(1), pages 1-26, December.
    15. Astier, Nicolas, 2018. "Comparative feedbacks under incomplete information," Resource and Energy Economics, Elsevier, vol. 54(C), pages 90-108.
    16. Cristina Puente & Rafael Palacios & Yolanda González-Arechavala & Eugenio Francisco Sánchez-Úbeda, 2020. "Non-Intrusive Load Monitoring (NILM) for Energy Disaggregation Using Soft Computing Techniques," Energies, MDPI, vol. 13(12), pages 1-20, June.
    17. Yildiz, B. & Bilbao, J.I. & Dore, J. & Sproul, A.B., 2017. "Recent advances in the analysis of residential electricity consumption and applications of smart meter data," Applied Energy, Elsevier, vol. 208(C), pages 402-427.
    18. Liu, Bo & Luan, Wenpeng & Yu, Yixin, 2017. "Dynamic time warping based non-intrusive load transient identification," Applied Energy, Elsevier, vol. 195(C), pages 634-645.
    19. Nicolas Astier, 2016. "Comparative Feedbacks under Incomplete Information," Working Papers hal-01465189, HAL.
    20. Mohamed Aymane Ahajjam & Daniel Bonilla Licea & Chaimaa Essayeh & Mounir Ghogho & Abdellatif Kobbane, 2020. "MORED: A Moroccan Buildings’ Electricity Consumption Dataset," Energies, MDPI, vol. 13(24), pages 1-22, 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:11:y:2018:i:9:p:2460-:d:170187. 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.