THERMAL SCIENCE

International Scientific Journal

Xuwei Liu

,

Lisha Si

,

Wenting Tang

,

Yongde Li

BUILDING ENERGY MANAGEMENT: INTEGRATING K-MEANS WITH SPARROW SEARCH ALGORITHM OPTIMIZED BILSTM FOR ANOMALY DETECTION AND PREDICTION

ABSTRACT
Currently, building energy conservation and emission reduction are crucial for environmental protection and sustainable development. In response to the difficulty in accurately quantifying building energy consumption and the low efficiency of existing management, this study develops a building energy management system that integrates hybrid anomaly detection and intelligent prediction algorithms. The outcomes indicate that the highest determination coefficient of the prediction model reaches 0.96, and the mean absolute error of energy consumption prediction in spring is 3.33%, with a mean absolute percentage error of 1.01%. Compared with benchmark models such as sparrow search algorithm and particle swarm optimization algorithm, this method reduces the number of convergence iterations by 40.8%, further reduces the average absolute error by 14.2%, saves training time by 44.7%, and reduces memory usage by 18.5%. This method has significant advantages in building energy consumption prediction and anomaly detection, which can effectively improve the efficiency of building energy management and provide data support for energy efficiency enhancement and pollutant reduction. This provides new solutions for energy efficiency optimization of university buildings, promoting the realization of green buildings and energy efficiency enhancement and pollutant reduction.
KEYWORDS
Building energy, Anomaly detection, BiLSTM, K-means, DBSCAN
PAPER SUBMITTED: 2025-08-06
PAPER REVISED: 2025-09-10
PAPER ACCEPTED: 2025-10-21
PUBLISHED ONLINE: 2026-01-17
DOI REFERENCE: https://doi.org/10.2298/TSCI250806226L
REFERENCES
[1] R. K. T., "Energy Efficiency and Integration of Renewable Energy Sources in Architectural Design: Techno-Economic Possibilities of Azerbaijan," The American Journal of Applied Sciences, vol. 7, no. 3, pp. 27-44, Mar. 2025, 10.37547/tajas/Volume07Issue03-05A
[2] P. Bouquet, I. Jackson, M. Nick, and A. Kaboli, "AI-based forecasting for optimised solar energy management and smart grid efficiency," Int. J. Prod. Res., vol. 62, no. 13, pp. 4623-4644, Sep. 2024, 10.1080/00207543.2023.2269565
[3] A. Heidari, Y. Peyvastehgar, and M. Amanzadegan, "A systematic review of the BIM in construction: From smart building management to interoperability of BIM & AI," Archit. Sci. Rev., vol. 67, no. 3, pp. 237-254, Aug. 2024, 10.1080/00038628.2023.2243247
[4] L. Y. Rock, F. P. Tajudeen, and Y. W. Chung, "Usage and impact of the internet-of-things-based smart home technology: a quality-of-life perspective," Univ. Access Inf. Soc., vol. 23, no. 1, pp. 345-364, Nov. 2024, 10.1007/s10209-022-00937-0
[5] H. Youssef, S. Kamel, M. H. Hassan, L. Nasrat, and F. Jurado, "An improved bald eagle search optimization algorithm for optimal home energy management systems," Soft Comput., vol. 28, no. 2, pp. 1367-1390, May. 2024, 10.1007/s00500-023-09471-4
[6] M. U. Shoukat, L. Yan, J. Zhang, Y. Cheng, M. U. Raza, and A. Niaz, "Smart home for enhanced healthcare: exploring human machine interface oriented digital twin model," Multimed. Tools Appl., vol. 83, no. 11, pp. 31297-31315, Sep. 2024, 10.1007/s11042-023-16875-9
[7] A. Polyanska, Y. Pazynich, K. Mykhailyshyn, D. Babets, and P. Toś, "Aspects of energy efficiency management for rational energy resource utilization," Rud.-Geolo.-Naft. Zb., vol. 39, no. 3, pp. 13-26, Apr. 2024, 10.17794/rgn.2024.3.2
[8] L. Maier, D. Jansen, F. Wüllhorst, M. Kremer, A. Kümpel, T. Blacha, and D. Mü ller, "AixLib: an open-source Modelica library for compound building energy systems from component to district level with automated quality management," J. Build. Perform. Simul., vol. 17, no. 2, pp. 196-219, Aug. 2024, 10.1080/19401493.2023.2250521
[9] E. Tabaku, E. Vyshka, R. Kapç iu, A. Shehi, and E. Smajli, "Utilizing artificial intelligence in energy management systems to improve carbon emission reduction and sustainability," J. Ilm. Ilmu Terap. Univ. Jambi, vol. 9, no. 1, pp. 393-405, Mar. 2025, 10.22437/jiituj.v9i1.38665
[10] K. Sharma, Y. K. Dwivedi, and B. Metri, "Incorporating causality in energy consumption forecasting using deep neural networks," Ann. Oper. Res., vol. 339, no. 1, pp. 537-572, Jul. 2024, 10.1007/s10479-022-04857-3
[11] A. Kristian, T. S. Goh, A. Ramadan, A. Erica, and S. V. Sihotang, "Application of AI in optimizing energy and resource management: Effectiveness of deep learning models," Int. Trans. Artif. Intell., vol. 2, no. 2, pp. 99-105, Jun. 2024, 10.33050/italic.v2i2.530
[12] B. Mehdizadeh Khorrami, A. Soleimani, A. Pinnarelli, G. Brusco, and P. Vizza, "Forecasting heating and cooling loads in residential buildings using machine learning: a comparative study of techniques and influential indicators," Asian J. Civ. Eng., vol. 25, no. 2, pp. 1163-1177, Jul. 2024, 10.1007/s42107-023-00834-8
[13] A. M. Usman and M. K. Abdullah, "An assessment of building energy consumption characteristics using analytical energy and carbon footprint assessment model," Green Low-Carbon Econ., vol. 1, no. 1, pp. 28-40, Mar. 2023, 10.47852/bonviewGLCE3202545
[14] W. N. Digitemie and I. O. Ekemezie, "A comprehensive review of Building Energy Management Systems BEMS) for improved efficiency," World J. Adv. Res. Rev., vol. 21, no. 3, pp. 829-841, Mar. 2024, 10.30574/wjarr.2024.21.3.0746
[15] H. Zhang, C. Yu, M. Zeng, T. Ye, D. Yue and C. Dou, "Homomorphic encryption-based resilient distributed energy management under cyber-attack of micro-grid with event-triggered mechanism," IEEE Trans. Smart Grid, vol. 15, no. 5, pp. 5115-5126, April, 2024, 10.1109/TSG.2024.3390108
[16] X. Wang, H. Wang, B. Bhandari, and L. Cheng, "AI-empowered methods for smart energy consumption: A review of load forecasting, anomaly detection and demand response," Int. J. Precis. Eng. Manuf.-Green Technol., vol. 11, no. 3, pp. 963-993, Sep. 2024, 10.1007/s40684-023-00537-0
[17] C. N. Egwim, H. Alaka, O. O. Egunjobi, A. Gomes, and I. Mporas, "Comparison of machine learning algorithms for evaluating building energy efficiency using big data analytics," J. Eng. Des. Technol., vol. 22, no. 4, pp. 1325-1350, Sep. 2024, 10.1108/JEDT-05-2022-0238
[18] Y. K. Ahranjani, M. Beiraghi, and R. Ghanizadeh, "Short time load forecasting for Urmia city using the novel CNN-LTSM deep learning structure," Electr. Eng., vol. 107, no. 1, pp. 1253-1264, May. 2025, 10.1007/s00202-024-02361-4
[19] A. A. Nasser and A. S. A. Alghawli, "Evaluation and clustering of health security performance in Africa: A comparative analysis through the entropy-TOPSIS-K-means approach," Afr. Secur. Rev., vol. 33, no. 3, pp. 330-348, Jun. 2024, 10.1080/10246029.2024.2367967
[20] S. Jia, H. Yuan, L. Zhang, Z. Liang, and Z. Yinfei, "Detecting outliers in crowdsourced bathymetric data based on intelligently optimized 3D-DBSCAN algorithm," Mar. Geod., vol. 47, no. 1, pp. 41-58, Oct. 2024, 10.1080/01490419.2023.2279086
[21] A. Bhattacharya and P. Majumdar, "Artificial intelligence-machine learning algorithms for the simulation of combustion thermal analysis," Heat Transf. Eng., vol. 45, no. 2, pp. 176-193, Feb. 2024, 10.1080/01457632.2023.2178282
[22] D. Hu, H. Sun, P. Mehrabi, Y. A. Ali, and M. Al-Razgan, "Application of artificial intelligence technique in optimization and prediction of the stability of the walls against wind loads in building design," Mech. Adv. Mater. Struct., vol. 31, no. 19, pp. 4755-4772, May. 2024, 10.1080/15376494.2023.2206208
[23] P. Kumar and P. Samui, "Reliability-based load and resistance factor design of an energy pile with CPT data using machine learning techniques," Arab. J. Sci. Eng., vol. 49, no. 4, pp. 4831-4860, Sep. 2024, 10.1007/s13369-023-08253-2
[24] M. Ordouei, A. Broumandnia, T. Banirostam, and A. Gilani, "Optimization of energy consumption in smart city using reinforcement learning algorithm," Int. J. Nonlin. Anal. Appl., vol. 15, no. 1, pp. 277-290, Jul. 2024, 10.22075/IJNAA.2022.29258.4102
[25] M. E. Ramachandran, R. R. Singh, G. B. Balachandran, D. P. Mohan, P. W. David, M. Anantharaman, and N. Ganesan, "Energy monitoring for renewable energy system using machine learning algorithms," Recent Adv. Electr. Electron. Eng., vol. 17, no. 10, pp. 966-975, Oct. 2024, 10.2174/0123520965258879231011182850
[26] M. A. Alghamdi, S. Abdullah, and M. Ragab, "Predicting energy consumption using stacked LSTM snapshot ensemble," Big Data Min. Anal., vol. 7, no. 2, pp. 247-270, Jun. 2024, 10.26599/BDMA.2023.9020030
PDF VERSION [DOWNLOAD]
Building energy management: Integrating k-means with sparrow search algorithm optimized BiLSTM for anomaly detection and prediction

© 2026 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence