Pregled metoda mašinskog učenja u sistemima klimatizacije, grijanja i hlađenja
##plugins.themes.bootstrap3.article.main##
Apstrakt
Potrošnja energije u sektoru zgradarstva predstavlja značajan procenat ukupne primarne energije koja se u većini zemalja troši zbog potrošnje sistema klimatizacije, grijanja i hlađenja. Smanjenje povezane potrošnje energije uz održavanje ugodnih uslova u zgradama konfliktni su ciljevi i predstavljaju tipičan problem optimizacije koji zahtjeva inteligentno projektovanje sistema. Takođe, potrebne su i preciznije i brže metode za otkrivanje i dijagnostiku kvarova tih sistema. Metode vještačke inteligencije i mašinskog učenja imaju veliki potencijal u tom pogledu, posebno sa razvojem informacionih tehnologija i senzorske opreme, omogućavajući pristup velikim količinama visokokvalitetnih podataka. Bez obzira na to, mašinsko učenje još nije potpuno prihvaćeno u industriji. U radu je dat prikaz nekih metoda mašinskog učenja koje se mogu koristiti u sistemima klimatizacije, grijanja i hlađenja, a te metode se klasifikuju na nadgledano, nenadgledano i podržano učenje. U nastavku je dat literaturni pregled metoda i modela zasnovanih na mašinskom učenju za poboljšanje optimizacije i kontrole u pomenutim sistemima, kao i mogućnosti primjene u oblasti otkrivanja i dijagnostike kvarova. Prikazane su prednosti i nedostaci metoda mašinskog učenja i date neke smjernice za dalji tok istraživanja u ovoj oblasti.
##plugins.themes.bootstrap3.article.details##
Reference
Zhou, S. L., A. A. Shah, P. K. Leung, X. Zhu, Q. Liao, A comprehensive review of the applications of machine learning for HVAC, DeCarbon, 2 (2023), 100023, https://doi.org/10.1016/j.decarb.2023.100023.
Carreras, J., J. Higuera, M. P. Alvarez, W. Hertog, Hybrid smart lighting and climate control system for buildings, IET Conference on Future Intelligent Cities, Proceedings, 2014, https://doi.org/10.1049/ic.2014.0047.
Merabet, G. H., M. Essaaidi, M. B. Haddou, B. Qolomany, J. Qadir, M. Anan, A. Al-Fuqaha, M. R. Abid, D. Benhaddou, Intelligent building control systems for thermal comfort and energy-efficiency: A systematic review of artificial intelligence-assisted techniques, Renewable and Sustainable Energy Reviews, 144, 2021, 110969, https://doi.org/10.1016/j.rser.2021.110969.
Hong, T., Z. Wang, X. Luo, W. Zhang, State-of-the-Art on research and applications of machine learning in the building life cycle, Energy Build. 212, 2020, 109831, https://doi.org/10.1016/j.enbuild.2020.109831
Najafabadi, M. E., F. Haghighat, Occupancy-based hvac control systems in buildings: a state-of-the-art review, Build. Environ. 197, 2021, https://doi.org/10.1016/j.buildenv.2021.107810.
Moradzadeh, A., B. M. Ivatloo, M. Abapour, A. A. Moghaddam, S. S. Roy, Heating and cooling loads forecasting for residential buildings based on hybrid machine learning applications: a comprehensive review and comparative analysis, IEEE Access 10, 2196–2215, 2022, 107810, https://doi.org/10.1109/access.2021.3136091.
Maddalena, E. T., Y. Lian, C. N. Jones, Data-driven methods for building control a review and promising future directions, Control Eng. Pract. 95, 2020, 104211, https://doi.org/10.1016/j.conengprac.2019.104211.
Ghahramani, A., P. Galicia, D. Lehrer, Z. Varghese, Z. Wang, Y. Pandit, Artificial intelligence for efficient thermal comfort systems: requirements, current applications and future directions, Frontiers in Built Environment 6, 2020, 6, https://doi.org/10.3389/fbuil.2020.00049.
Han, M., R. Ross May, X. Zhang, X. Wang, S. Pan, D. Yan, Y. Jin, L. Xu, A review of reinforcement learning methodologies for controlling occupant comfort in buildings, Sustain. Cities Soc. 51, 2019, 101748, https://doi.org/10.1016/j.scs.2019.101748.
Yao, Y., D. K. Shekhar, State of the art review on model predictive control (MPC) in Heating Ventilation and Air-conditioning (HVAC) field, Building and Environment, 200, 2021, 107952, https://doi:10.1016/j.buildenv.2021.107952
Gomariz, M. P., A. L. Gómez, F. C. Cartagena, Artificial neural networks as artificial intelligence technique for energy saving in refrigeration systems – A review, Clean Technologies 5, 2023, 1, pp. 116-136, https://doi.org/10.3390/cleantechnol5010007
Salehi, H., R. Burgueño, Emerging artificial intelligence methods in structural engineering, Engineering Structures, 171, 2018, pp. 170-189, https://doi:10.1016/j.engstruct.2018.05.084
Yuan, X., Y. Pan, J. Yang, W. Wang, Z. Huang, Study on the application of reinforcement learning in the operation optimization of HVAC system, Building Simulation 14, 201, 1, pp. 75–87, 2021, https://doi.org/10.1007/s12273-020-0602-9
Chen, B., Z. Cai, M. Berges, Gnu-rl: a practical and scalable reinforcement learning solution for building hvac control using a differentiable MPC policy, Frontiers in Built Environment 6, 2020, https://doi.org/10.3389/fbuil.2020.562239
Solinas, F. M., A. Macii, E. Patti, L. Bottaccioli, An online reinforcement learning approach for HVAC control, Expert Systems with Applications, 238 2024, Part A, 121749, https://doi.org/10.1016/j.eswa.2023.121749.
Deng, Z., Q. Chen, Reinforcement learning of occupant behavior model for cross-building transfer learning to various hvac control systems, Energy and Buildings, 238, 2021, 110860, https://doi.org/10.1016/j.enbuild.2021.110860.
Chen, Y., L. K. Norford, H. W. Samuelson, A. Malkawi, Optimal control of HVAC and window systems for natural ventilation through reinforcement learning, Energy and Buildings, 169, 2018, pp 195–205, https://doi.org/10.1016/ j.enbuild.2018.03.051.
Nasruddin, Sholahudin, P. Satrio, T. M. I. Mahlia, N. Giannetti, K. Saito, K., Optimization of HVAC system energy consumption in a building using artificial neural network and multi-objective genetic algorithm, Sustainable Energy and Technologies Assessments, 35, 2019, pp. 48–57, https://doi.org/10.1016/j.seta.2019.06.002.
Arranz R. S., A. Gutiérrez, A long short-term memory artificial neural network to predict daily HVAC consumption in buildings, Energy and Buildings, 216, 2020, 109952, https://doi.org/10.1016/j.enbuild.2020.109952
Abida, A., P. Richter, HVAC control in buildings using neural network, Journal of Building Engineering, 65, 2023, 105558, https://doi.org/10.1016/j.jobe.2022.105558
Ikeda, S., T. Nagai, A novel optimization method combining metaheuristics and machine learning for daily optimal operations in building energy and storage systems, Applied Energy, 289, 2021, 116716, https://doi.org/10.1016/j.apenergy.2021.116716.
Wei, T., Y. Wang, Q. Zhu, Deep reinforcement learning for building HVAC control, Proceedings, 54th ACM/EDAC/IEEE Design Automation Conference (DAC), 2017, Art. No. 22, https://doi.org/10.1145/3061639.3062224
Gupta, A., Y. Badr, A. Negahban, G. Robin, Qiu, Energy-efficient heating control for smart buildings with deep reinforcement learning, Journal of Building Engineering, 34, 2021, 101739, https://doi.org/10.1016/j.jobe.2020.101739.
Nguyen, A. T., D. H. Pham, B. L. Oo, M. Santamouris, Y. Ahn, B. T. H., Modelling building HVAC control strategies using a deep reinforcement learning approach, Energy and Buildings, 310, 2023, 114065, https://doi.org/10.1016/j.enbuild.2024.114065.
Deng, X., Y. Zhang, H. Qi, Towards optimal hvac control in non-stationary building environments combining active change detection and deep reinforcement learning, Building and Environment, 211, 2022, 108680, https://doi.org/10.1016/ j.buildenv.2021.108680.
Fard, Z. Q., Z. S. Zomorodian, S. S. Korsavi, Application of machine learning in thermal comfort studies: A review of methods, performance and challenges, Energy and Buildings, 256, 2022, 111771, https://doi.org/10.1016/j.enbuild.2021.111771.
Wang, Z., J. Liu, Y. Zhang, H. Yuan, R. Zhang, R. S. Srinivasan, Practical issues in implementing machine-learning models for building energy efficiency: Moving beyond obstacles, Renewable and Sustainable Energy Reviews, 143, 2021, 110929, https://doi.org/10.1016/j.rser.2021.110929.
Luo, M., J. J. Xie. Y. Yan, Z. Ke, P. Yu, Z. Wang, J. Zhang, Comparing machine learning algorithms in predicting thermal sensation using ASHRAE Comfort Database II, Energy and Buildings, 210, 2020, 109776, https://doi.org/10.1016/j.enbuild.2020.109776
Ngarambe, J., G. Y. Yun, M. Santamouris, The use of artificial intelligence (AI) methods in the prediction of thermal comfort in buildings: energy implications of AI-based thermal comfort controls, Energy and Buildings, 211, 2020, 109807, https://doi.org/10.1016/j.enbuild.2020.109807
Zhou, Y., Y. Su, Z. Xu, X. Wang, X. Guan, A hybrid physics-based/data-driven model for personalized dynamic thermal comfort in ordinary office environment, Energy and Buildings 2021, 110790, https://doi.org/10.1016/j.enbuild.2021.110790.
Chen, Z., Z. O’Neill, J. Wen, O. Pradhan, T. Yang, X. Lu, G. Lin, S. Miyata, S. Lee, C. Shen, R. Chiosa, M. S. Piscitelli, A. Capozzoli, F. Hengel, A. Kührer, M. Pritoni, W. Wei Liu, J. Clauß, Y. Chen, T. Herr, A review of data-driven fault detection and diagnostics for building HVAC systems, Applied Energy, 339, 2023, 121030, https://doi.org/10.1016/j.apenergy.2023.121030
Viol, V. M., E. M. Urbano, J. E. T. Rangel, M. D. Prieto, L. Romeral, Semi-supervised transfer learning methodology for fault detection and diagnosis in air-handling units, Applied Science, 12, 2022, 8837, https:// doi.org/10.3390/app12178837.