IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v299y2021ics0306261921006760.html
   My bibliography  Save this article

Minimization of natural gas consumption of domestic boilers with convolutional, long-short term memory neural networks and genetic algorithm

Author

Listed:
  • Tsoumalis, Georgios I.
  • Bampos, Zafeirios N.
  • Chatzis, Georgios V.
  • Biskas, Pandelis N.
  • Keranidis, Stratos D.

Abstract

This paper presents a novel approach that aims to minimize the natural gas consumption of domestic boilers for heating purposes, while not compromising the user’s heating needs. The system utilizes gas consumption data, the conditions both inside and outside the house collected via interconnected commercial thermostats, and the heating needs of the users. The architecture of the presented system is divided in two main coordinated processes: (a) the first one consists of two Neural Networks with Convolutional and Long Short-Term Memory layers, used to predict the indoor temperature and the boiler’s modulation (load percentage), whereas (b) the second process includes a Genetic Algorithm used to determine the optimal operation conditions of the boiler, by finding the boiler control instructions that meet the user's heating preferences concerning the target indoor temperature, while minimizing the total gas consumption. One main advantage of the solution is its ability to consider boilers as a black box, since it does not need to be aware of the internal mechanics. In this way, the proposed methodology can be applied to a wide range of domestic gas boilers with minimum adjustments. The overall methodology is applied to four domestic boilers in Greece spanning three cities, to capture different climatic conditions and evaluate the system performance in varying outdoor conditions. The attained results indicate that the proposed system can lead to significant gas consumption reduction through autonomously created optimal control instructions provided to the boiler.

Suggested Citation

  • Tsoumalis, Georgios I. & Bampos, Zafeirios N. & Chatzis, Georgios V. & Biskas, Pandelis N. & Keranidis, Stratos D., 2021. "Minimization of natural gas consumption of domestic boilers with convolutional, long-short term memory neural networks and genetic algorithm," Applied Energy, Elsevier, vol. 299(C).
    • Handle: RePEc:eee:appene:v:299:y:2021:i:c:s0306261921006760
    DOI: 10.1016/j.apenergy.2021.117256
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261921006760
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2021.117256?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Afroz, Zakia & Urmee, Tania & Shafiullah, G.M. & Higgins, Gary, 2018. "Real-time prediction model for indoor temperature in a commercial building," Applied Energy, Elsevier, vol. 231(C), pages 29-53.
    2. Hribar, Rok & Potočnik, Primož & Šilc, Jurij & Papa, Gregor, 2019. "A comparison of models for forecasting the residential natural gas demand of an urban area," Energy, Elsevier, vol. 167(C), pages 511-522.
    3. Jin Woo Moon & Ji-Hyun Lee & Sooyoung Kim, 2014. "Evaluation of Artificial Neural Network-Based Temperature Control for Optimum Operation of Building Envelopes," Energies, MDPI, vol. 7(11), pages 1-21, November.
    4. Smarra, Francesco & Jain, Achin & de Rubeis, Tullio & Ambrosini, Dario & D’Innocenzo, Alessandro & Mangharam, Rahul, 2018. "Data-driven model predictive control using random forests for building energy optimization and climate control," Applied Energy, Elsevier, vol. 226(C), pages 1252-1272.
    5. Petri Hietaharju & Mika Ruusunen & Kauko Leiviskä, 2018. "A Dynamic Model for Indoor Temperature Prediction in Buildings," Energies, MDPI, vol. 11(6), pages 1-20, June.
    6. Hewamalage, Hansika & Bergmeir, Christoph & Bandara, Kasun, 2021. "Recurrent Neural Networks for Time Series Forecasting: Current status and future directions," International Journal of Forecasting, Elsevier, vol. 37(1), pages 388-427.
    7. Reynolds, Jonathan & Rezgui, Yacine & Kwan, Alan & Piriou, Solène, 2018. "A zone-level, building energy optimisation combining an artificial neural network, a genetic algorithm, and model predictive control," Energy, Elsevier, vol. 151(C), pages 729-739.
    8. Wei, Nan & Li, Changjun & Peng, Xiaolong & Li, Yang & Zeng, Fanhua, 2019. "Daily natural gas consumption forecasting via the application of a novel hybrid model," Applied Energy, Elsevier, vol. 250(C), pages 358-368.
    9. Tabares-Velasco, Paulo Cesar & Speake, Andrew & Harris, Maxwell & Newman, Alexandra & Vincent, Tyrone & Lanahan, Michael, 2019. "A modeling framework for optimization-based control of a residential building thermostat for time-of-use pricing," Applied Energy, Elsevier, vol. 242(C), pages 1346-1357.
    10. Özmen, Ayşe & Yılmaz, Yavuz & Weber, Gerhard-Wilhelm, 2018. "Natural gas consumption forecast with MARS and CMARS models for residential users," Energy Economics, Elsevier, vol. 70(C), pages 357-381.
    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. Georgios I. Tsoumalis & Zafeirios N. Bampos & Georgios V. Chatzis & Pandelis N. Biskas, 2022. "Overview of Natural Gas Boiler Optimization Technologies and Potential Applications on Gas Load Balancing Services," Energies, MDPI, vol. 15(22), pages 1-24, November.
    2. Qingyan Zhou & Hao Li & Youhua Zhang & Junhong Zheng, 2023. "Product Evaluation Prediction Model Based on Multi-Level Deep Feature Fusion," Future Internet, MDPI, vol. 15(1), pages 1-16, January.

    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. Kathirgamanathan, Anjukan & De Rosa, Mattia & Mangina, Eleni & Finn, Donal P., 2021. "Data-driven predictive control for unlocking building energy flexibility: A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 135(C).
    2. Wei, Nan & Yin, Lihua & Li, Chao & Li, Changjun & Chan, Christine & Zeng, Fanhua, 2021. "Forecasting the daily natural gas consumption with an accurate white-box model," Energy, Elsevier, vol. 232(C).
    3. Tomasz Cieślik & Piotr Narloch & Adam Szurlej & Krzysztof Kogut, 2022. "Indirect Impact of the COVID-19 Pandemic on Natural Gas Consumption by Commercial Consumers in a Selected City in Poland," Energies, MDPI, vol. 15(4), pages 1-18, February.
    4. Sun, Hongchang & Niu, Yanlei & Li, Chengdong & Zhou, Changgeng & Zhai, Wenwen & Chen, Zhe & Wu, Hao & Niu, Lanqiang, 2022. "Energy consumption optimization of building air conditioning system via combining the parallel temporal convolutional neural network and adaptive opposition-learning chimp algorithm," Energy, Elsevier, vol. 259(C).
    5. Fang, Lei & He, Bin, 2023. "A deep learning framework using multi-feature fusion recurrent neural networks for energy consumption forecasting," Applied Energy, Elsevier, vol. 348(C).
    6. Oleksandr Castello & Marina Resta, 2023. "A Machine-Learning-Based Approach for Natural Gas Futures Curve Modeling," Energies, MDPI, vol. 16(12), pages 1-22, June.
    7. Lu, Hongfang & Ma, Xin & Azimi, Mohammadamin, 2020. "US natural gas consumption prediction using an improved kernel-based nonlinear extension of the Arps decline model," Energy, Elsevier, vol. 194(C).
    8. Ayşe Özmen, 2023. "Sparse regression modeling for short- and long‐term natural gas demand prediction," Annals of Operations Research, Springer, vol. 322(2), pages 921-946, March.
    9. Jason Runge & Radu Zmeureanu, 2021. "A Review of Deep Learning Techniques for Forecasting Energy Use in Buildings," Energies, MDPI, vol. 14(3), pages 1-26, January.
    10. Jahangir Hossain & Aida. F. A. Kadir & Ainain. N. Hanafi & Hussain Shareef & Tamer Khatib & Kyairul. A. Baharin & Mohamad. F. Sulaima, 2023. "A Review on Optimal Energy Management in Commercial Buildings," Energies, MDPI, vol. 16(4), pages 1-40, February.
    11. Finck, Christian & Li, Rongling & Zeiler, Wim, 2019. "Economic model predictive control for demand flexibility of a residential building," Energy, Elsevier, vol. 176(C), pages 365-379.
    12. Ding, Jia & Zhao, Yuxuan & Jin, Junyang, 2023. "Forecasting natural gas consumption with multiple seasonal patterns," Applied Energy, Elsevier, vol. 337(C).
    13. Yang, Shiyu & Wan, Man Pun & Chen, Wanyu & Ng, Bing Feng & Dubey, Swapnil, 2020. "Model predictive control with adaptive machine-learning-based model for building energy efficiency and comfort optimization," Applied Energy, Elsevier, vol. 271(C).
    14. Ali Sadollah & Mohammad Nasir & Zong Woo Geem, 2020. "Sustainability and Optimization: From Conceptual Fundamentals to Applications," Sustainability, MDPI, vol. 12(5), pages 1-34, March.
    15. Yang, Zhaoming & Liu, Zhe & Zhou, Jing & Song, Chaofan & Xiang, Qi & He, Qian & Hu, Jingjing & Faber, Michael H. & Zio, Enrico & Li, Zhenlin & Su, Huai & Zhang, Jinjun, 2023. "A graph neural network (GNN) method for assigning gas calorific values to natural gas pipeline networks," Energy, Elsevier, vol. 278(C).
    16. Germán Campos Gordillo & Germán Ramos Ruiz & Yves Stauffer & Stephan Dasen & Carlos Fernández Bandera, 2020. "EplusLauncher: An API to Perform Complex EnergyPlus Simulations in MATLAB ® and C#," Sustainability, MDPI, vol. 12(2), pages 1-14, January.
    17. Gao, Datong & Zhao, Bin & Kwan, Trevor Hocksun & Hao, Yong & Pei, Gang, 2022. "The spatial and temporal mismatch phenomenon in solar space heating applications: status and solutions," Applied Energy, Elsevier, vol. 321(C).
    18. Beyca, Omer Faruk & Ervural, Beyzanur Cayir & Tatoglu, Ekrem & Ozuyar, Pinar Gokcin & Zaim, Selim, 2019. "Using machine learning tools for forecasting natural gas consumption in the province of Istanbul," Energy Economics, Elsevier, vol. 80(C), pages 937-949.
    19. Ascione, Fabrizio & Bianco, Nicola & Mauro, Gerardo Maria & Vanoli, Giuseppe Peter, 2019. "A new comprehensive framework for the multi-objective optimization of building energy design: Harlequin," Applied Energy, Elsevier, vol. 241(C), pages 331-361.
    20. Bartłomiej Gaweł & Andrzej Paliński, 2021. "Long-Term Natural Gas Consumption Forecasting Based on Analog Method and Fuzzy Decision Tree," Energies, MDPI, vol. 14(16), pages 1-26, 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:eee:appene:v:299:y:2021:i:c:s0306261921006760. 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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    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.