Prediksi Konsumsi Energi Listrik untuk Pendingin Bangunan Komersial Menggunakan Gated Recurrent Unit (GRU) dan Kolmogorov-Arnold Networks (KANs)

research
  • 12 Mar
  • 2025

Prediksi Konsumsi Energi Listrik untuk Pendingin Bangunan Komersial Menggunakan Gated Recurrent Unit (GRU) dan Kolmogorov-Arnold Networks (KANs)

Efisiensi pengelolaan energi sangat penting untuk mengurangi biaya operasional dan
dampak lingkungan pada bangunan komersial. Sistem pendingin, yang merupakan
salah satu komponen utama konsumsi energi, menghadirkan tantangan prediksi karena
sifatnya yang kompleks dan non-linear. Penelitian ini mengusulkan model hybrid
GRU-KAN untuk meningkatkan akurasi prediksi konsumsi energi listrik pada sistem
pendingin bangunan komersial. Dataset yang digunakan berasal dari data sistem
pendingin HVAC di Singapura dengan tujuh fitur utama, seperti suhu luar ruangan,
kelembapan, dan beban pendinginan. Hasil eksperimen menunjukkan bahwa model
GRU-KAN memberikan performa terbaik dengan nilai RMSE sebesar 4,168, MAE
sebesar 2,242, dan R² sebesar 0,819. Model ini mengungguli model GRU, LSTM, dan
LSTM-KAN dalam menangkap pola non-linear yang kompleks. Penelitian ini
memberikan kontribusi signifikan dalam optimalisasi pengelolaan energi pada sistem
pendingin bangunan melalui penerapan metode deep learning inovatif berbasis
Kolmogorov-Arnold Networks (KANs).

Unduhan

 

REFERENSI

DAFTAR PUSTAKA

[1]       Nasruddin et al., “Potential of geothermal energy for electricity generation in Indonesia: A review,” Renewable and Sustainable Energy Reviews, vol. 53, pp. 733–740, Jan. 2016, doi: 10.1016/j.rser.2015.09.032.

[2]       Internationale Energieagentur, Ed., World energy outlook 2013. in World Energy Outlook, no. 2013. Paris, 2013.

[3]       B. Poel, G. Van Cruchten, and C. A. Balaras, “Energy performance assessment of existing dwellings,” Energy and Buildings, vol. 39, no. 4, pp. 393–403, Apr. 2007, doi: 10.1016/j.enbuild.2006.08.008.

[4]       M. González-Torres, L. Pérez-Lombard, J. F. Coronel, I. R. Maestre, and D. Yan, “A review on buildings energy information: Trends, end-uses, fuels and drivers,” Energy Reports, vol. 8, pp. 626–637, Nov. 2022, doi: 10.1016/j.egyr.2021.11.280.

[5]       A. M. Reda, A. H. H. Ali, M. G. Morsy, and I. S. Taha, “Design optimization of a residential scale solar driven adsorption cooling system in upper Egypt based,” Energy and Buildings, vol. 130, pp. 843–856, Oct. 2016, doi: 10.1016/j.enbuild.2016.09.011.

[6]       N. I. Zulkafli, M. F. Sukri, M. Mohd Tahir, A. Muhajir, and D. P. Hanak, “Performance analysis and optimisation of the chiller-air handling units system with a wide range of ambient temperature,” Cleaner Engineering and Technology, vol. 14, p. 100643, Jun. 2023, doi: 10.1016/j.clet.2023.100643.

[7]       H. H. Hosamo, H. K. Nielsen, D. Kraniotis, P. R. Svennevig, and K. Svidt, “Improving building occupant comfort through a digital twin approach: A Bayesian network model and predictive maintenance method,” Energy and Buildings, vol. 288, p. 112992, Jun. 2023, doi: 10.1016/j.enbuild.2023.112992.

[8]       P. Pandiyan, S. Saravanan, K. Usha, R. Kannadasan, M. H. Alsharif, and M.-K. Kim, “Technological advancements toward smart energy management in smart cities,” Energy Reports, vol. 10, pp. 648–677, Nov. 2023, doi: 10.1016/j.egyr.2023.07.021.

[9]       Z. Tian and J. A. Love, “Energy performance optimization of radiant slab cooling using building simulation and field measurements,” Energy and Buildings, vol. 41, no. 3, pp. 320–330, Mar. 2009, doi: 10.1016/j.enbuild.2008.10.002.

[10]     E. Bourdakis, O. B. Kazanci, and B. W. Olesen, “Load Calculations of Radiant Cooling Systems for Sizing the Plant,” Energy Procedia, vol. 78, pp. 2639–2644, Nov. 2015, doi: 10.1016/j.egypro.2015.11.333.

[11]     R. A. Memon, S. Chirarattananon, and P. Vangtook, “Thermal comfort assessment and application of radiant cooling: A case study,” Building and Environment, vol. 43, no. 7, pp. 1185–1196, Jul. 2008, doi: 10.1016/j.buildenv.2006.04.025.

[12]     S. H. Park, W. J. Chung, M. S. Yeo, and K. W. Kim, “Evaluation of the thermal performance of a Thermally Activated Building System (TABS) according to the thermal load in a residential building,” Energy and Buildings, vol. 73, pp. 69–82, Apr. 2014, doi: 10.1016/j.enbuild.2014.01.008.

[13]     K. Zhao, X.-H. Liu, and Y. Jiang, “Application of radiant floor cooling in a large open space building with high-intensity solar radiation,” Energy and Buildings, vol. 66, pp. 246–257, Nov. 2013, doi: 10.1016/j.enbuild.2013.07.014.

[14]     N. Nutprasert and P. Chaiwiwatworakul, “Radiant Cooling with Dehumidified Air Ventilation for Thermal Comfort in Buildings in Tropical Climate,” Energy Procedia, vol. 52, pp. 250–259, 2014, doi: 10.1016/j.egypro.2014.07.076.

[15]     A. M. Hamed, “Desorption characteristics of desiccant bed for solar dehumidification/humidification air conditioning systems,” Renewable Energy, vol. 28, no. 13, pp. 2099–2111, Oct. 2003, doi: 10.1016/S0960-1481(03)00075-2.

[16]     C. Stetiu, “Energy and peak power savings potential of radiant cooling systems in US commercial buildings,” 1999.

[17]     L. Jia, S. Wei, and J. Liu, “A review of optimization approaches for controlling water-cooled central cooling systems,” Building and Environment, vol. 203, p. 108100, Oct. 2021, doi: 10.1016/j.buildenv.2021.108100.

[18]     E. Schito, P. Conti, L. Urbanucci, and D. Testi, “Multi-objective optimization of HVAC control in museum environment for artwork preservation, visitors’ thermal comfort and energy efficiency,” Building and Environment, vol. 180, p. 107018, Aug. 2020, doi: 10.1016/j.buildenv.2020.107018.

[19]     W. Valladares et al., “Energy optimization associated with thermal comfort and indoor air control via a deep reinforcement learning algorithm,” Building and Environment, vol. 155, pp. 105–117, May 2019, doi: 10.1016/j.buildenv.2019.03.038.

[20]     M. Soufiane, B. Imane, R. Ikram, B. Fatah, and D. Belkacem, “Modeling and Control Thermal of Building for Improve Comfort Level by Using PID and On/Off Methods in the Case South-West Algeria,” in Artificial Intelligence in Renewable Energetic Systems, vol. 35, M. Hatti, Ed., in Lecture Notes in Networks and Systems, vol. 35. , Cham: Springer International Publishing, 2018, pp. 383–391. doi: 10.1007/978-3-319-73192-6_40.

[21]     F. Oldewurtel et al., “Use of model predictive control and weather forecasts for energy efficient building climate control,” Energy and Buildings, vol. 45, pp. 15–27, Feb. 2012, doi: 10.1016/j.enbuild.2011.09.022.

[22]     Y. Himeur et al., “AI-big data analytics for building automation and management systems: a survey, actual challenges and future perspectives,” Artif Intell Rev, vol. 56, no. 6, pp. 4929–5021, Jun. 2023, doi: 10.1007/s10462-022-10286-2.

[23]     M. H. Sulaiman, Z. Mustaffa, M. S. Saealal, M. M. Saari, and A. Z. Ahmad, “Utilizing the Kolmogorov-Arnold Networks for chiller energy consumption prediction in commercial building,” Journal of Building Engineering, vol. 96, p. 110475, Nov. 2024, doi: 10.1016/j.jobe.2024.110475.

[24]     J. Braun and M. Griebel, “On a Constructive Proof of Kolmogorov’s Superposition Theorem,” Constr Approx, vol. 30, no. 3, pp. 653–675, Dec. 2009, doi: 10.1007/s00365-009-9054-2.

[25]     A. N. Kolmogorov, “On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition,” in American Mathematical Society Translations: Series 2, vol. 28, Providence, Rhode Island: American Mathematical Society, 1963, pp. 55–59. doi: 10.1090/trans2/028/04.

[26]     Z. Liu et al., “KAN: Kolmogorov-Arnold Networks,” Jun. 16, 2024, arXiv: arXiv:2404.19756. Accessed: Aug. 06, 2024. [Online]. Available: http://arxiv.org/abs/2404.19756

[27]     C. J. Vaca-Rubio, L. Blanco, R. Pereira, and M. Caus, “Kolmogorov-Arnold Networks (KANs) for Time Series Analysis,” Sep. 25, 2024, arXiv: arXiv:2405.08790. Accessed: Oct. 05, 2024. [Online]. Available: http://arxiv.org/abs/2405.08790

[28]     S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.

[29]     K. Cho et al., “Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation,” Sep. 02, 2014, arXiv: arXiv:1406.1078. Accessed: Aug. 20, 2024. [Online]. Available: http://arxiv.org/abs/1406.1078

[30]     L. Lei, W. Chen, B. Wu, C. Chen, and W. Liu, “A building energy consumption prediction model based on rough set theory and deep learning algorithms,” Energy and Buildings, vol. 240, p. 110886, Jun. 2021, doi: 10.1016/j.enbuild.2021.110886.

[31]     H. H. Hosamo, M. S. Tingstveit, H. K. Nielsen, P. R. Svennevig, and K. Svidt, “Multiobjective optimization of building energy consumption and thermal comfort based on integrated BIM framework with machine learning-NSGA II,” Energy and Buildings, vol. 277, p. 112479, Dec. 2022, doi: 10.1016/j.enbuild.2022.112479.

[32]     F. G. Ciampi, A. Rega, T. M. L. Diallo, F. Pelella, J.-Y. Choley, and S. Patalano, “Energy consumption prediction of industrial HVAC systems using Bayesian Networks,” Energy and Buildings, vol. 309, p. 114039, Apr. 2024, doi: 10.1016/j.enbuild.2024.114039.

[33]     Y. Zhou and S. Zheng, “Machine-learning based hybrid demand-side controller for high-rise office buildings with high energy flexibilities,” Applied Energy, vol. 262, p. 114416, Mar. 2020, doi: 10.1016/j.apenergy.2019.114416.

[34]     V. J. Mawson and B. R. Hughes, “Deep learning techniques for energy forecasting and condition monitoring in the manufacturing sector,” Energy and Buildings, vol. 217, p. 109966, Jun. 2020, doi: 10.1016/j.enbuild.2020.109966.

[35]     C. Zhang, J. Li, Y. Zhao, T. Li, Q. Chen, and X. Zhang, “A hybrid deep learning-based method for short-term building energy load prediction combined with an interpretation process,” Energy and Buildings, vol. 225, p. 110301, Oct. 2020, doi: 10.1016/j.enbuild.2020.110301.

[36]     D.-K. Bui, T. N. Nguyen, T. D. Ngo, and H. Nguyen-Xuan, “An artificial neural network (ANN) expert system enhanced with the electromagnetism-based firefly algorithm (EFA) for predicting the energy consumption in buildings,” Energy, vol. 190, p. 116370, Jan. 2020, doi: 10.1016/j.energy.2019.116370.

[37]     X. Zhu, S. Zhang, X. Jin, and Z. Du, “Deep learning based reference model for operational risk evaluation of screw chillers for energy efficiency,” Energy, vol. 213, p. 118833, Dec. 2020, doi: 10.1016/j.energy.2020.118833.

[38]     Y. Zhou, J. Wang, Y. Liu, R. Yan, and Y. Ma, “Incorporating deep learning of load predictions to enhance the optimal active energy management of combined cooling, heating and power system,” Energy, vol. 233, p. 121134, Oct. 2021, doi: 10.1016/j.energy.2021.121134.

[39]     W. T. Ho and F. W. Yu, “Predicting chiller system performance using ARIMA-regression models,” Journal of Building Engineering, vol. 33, p. 101871, Jan. 2021, doi: 10.1016/j.jobe.2020.101871.

[40]     C. H. Kim, M. Kim, and Y. J. Song, “Sequence-to-sequence deep learning model for building energy consumption prediction with dynamic simulation modeling,” Journal of Building Engineering, vol. 43, p. 102577, Nov. 2021, doi: 10.1016/j.jobe.2021.102577.

[41]     A. Abida and P. Richter, “HVAC control in buildings using neural network,” Journal of Building Engineering, vol. 65, p. 105558, Apr. 2023, doi: 10.1016/j.jobe.2022.105558.

[42]     Chiller energy data: HVAC system energy data with weather data [Online]. Available: https://www.kaggle.com/datasets/chillerenergy/chiller-energy-data, 24 August 2023.

Cari

Bidang Ilmu

Kategori

Kiriman Terbaru