2692-4048ISSN (Online)
2770-0070ISSN (Print)
Volume 21 , Issue 2 , PP: 306-326, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Doaa Sami Khafaga 1 *
Doi: https://doi.org/10.54216/FPA.210219
Forecasting the energy consumption of heating, ventilation, and air conditioning (HVAC) chillers is vital for enhancing building efficiency, reducing operating costs, and supporting sustainability goals. However, the task remains challenging due to nonlinear system dynamics, strong dependence on weather conditions, and the scarcity of high-quality real-world datasets. In this work, we employ the Chiller Energy Data from Kaggle, which contains 13,561 cleaned records collected between August 2019 and June 2020, incorporating ten operational and meteorological features. Six baseline models, namely the Evolutionary Attention-based Long Short-Term Memory (EALSTM), Bidirectional LSTM (BILSTM), standard LSTM, Gated Recurrent Unit (GRU), Temporal Convolutional Network (TCN), and Artificial Neural Network (ANN), are first benchmarked to assess their forecasting capability. To further improve predictive accuracy, we integrate EALSTM with ten meta-heuristic optimization algorithms, focusing on the Greylag Goose Optimization Algorithm (GGO) and comparing it with alternatives such as Harris Hawks Optimization (HHO), Artificial Physics Optimization (APO), Simulated Annealing Optimization (SAO), Grey Wolf Optimizer (GWO), and others. The optimized GGO+EALSTM framework achieves state-of-the-art performance with a mean squared error of 6.83×10−6 and an R2 value of 0.98, reflecting a 96% reduction in error relative to simple feedforward models and significant improvements over other recurrent networks and optimizer-enhanced variants. The main contributions of this study include a structured benchmarking of neural architectures for chiller forecasting, the first systematic comparison of ten meta-heuristic optimizers applied to deep learning in this domain, and a visualization-based error analysis that strengthens interpretability and supports practical deployment. These results establish optimization-enhanced EALSTM as a robust and generalizable framework for HVAC energy forecasting, paving the way toward more efficient, reliable, and sustainable building energy management.
HVAC energy forecasting , Chiller energy consumption , Evolutionary attention-based LSTM , Meta-heuristic optimization , Greylag Goose Optimization
[1] R. Saidur, R. Purba, M. Hasanuzzaman, and N. Rahim, “Chillers energy consumption, energy savings and emission analysis in institutional buildings,” Energy Conversion and Management, vol. 52, no. 2, pp. 1479–1489, 2011. DOI: 10.1016/j.enconman.2010.11.032.
[2] X. Deng, Y. Liu, and Z. Liu, “A systematic review of hvac system energy consumption analysis,” Renewable and Sustainable Energy Reviews, 2023, Manuscript under review.
[3] X. Shi et al., “Convolutional lstm network: A machine learning approach for precipitation nowcasting,” in Advances in Neural Information Processing Systems, 2015, 802–810.
[4] F. Liu, Z. Wang, J. Xie, Z. Gao, and Y. Xi, “Deep learning for spatiotemporal sequence forecasting: A survey,” IEEE Transactions on Knowledge and Data Engineering, vol. 31, no. 9, pp. 1865–1886, 2019. DOI: 10.1109/TKDE.2018.2850849.
[5] A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems, 2017, 5998–6008.
[6] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. DOI: 10.1162/neco.1997.9.8.1735.
[7] P. Shaikh, J. Agarwal, and Y. Jaluria, “Short-term load forecasting using deep learning methods: A review,” International Journal of Energy Research, 2022, Review article.
[8] Y. Qin, D. Song, H. Chen, W. Cheng, G. Jiang, and G. Cottrell, “A dual-stage attention-based recurrent neural network for time series prediction,” in Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), 2017, pp. 2627–2633. DOI: 10.24963/ijcai.2017/366.
[9] J. Kennedy and R. Eberhart, Particle Swarm Optimization. IEEE International Conference on Neural Networks, 1995, Proceedings.
[10] J. Holland, Adaptation in Natural and Artificial Systems. University of Michigan Press, 1992.
[11] S. Mirjalili, S. Mirjalili, and A. Lewis, “Grey wolf optimizer,” Advances in Engineering Software, vol. 69, pp. 46–61, 2014. DOI: 10.1016/j.advengsoft.2013.12.007.
[12] S. Mirjalili and A. Lewis, “The whale optimization algorithm,” Advances in Engineering Software, vol. 95, pp. 51–67, 2016. DOI: 10.1016/j.advengsoft.2016.01.008.
[13] E.-S. M. El-kenawy, N. Khodadadi, S. Mirjalili, A. A. Abdelhamid, M. M. Eid, and A. Ibrahim, Greylag goose optimization: Nature-inspired optimization algorithm, 2024. DOI: https://doi.org/10. 1016/j.eswa.2023.122147. [Online]. Available: https://www.sciencedirect.com/ science/article/pii/S0957417423026490.
[14] F. P. S. Almeida, M. Castelli, and N. Cí´rte-Real, “Leveraging Feature Sets and Machine Learning for Enhanced Energy Load Prediction: A Comparative Analysis,” en, Emerging Science Journal, vol. 8, no. 6, pp. 2120–2143, Dec. 2024, ISSN: 2610-9182. DOI: 10.28991/ESJ- 2024- 08- 06- 01. [Online]. Available: https://ijournalse.org/index.php/ESJ/article/view/2563.
[15] R. Heidarykiany and C. Ababei, “Minimalistic LSTM Models for Next Day Hourly Residential HVAC Energy Usage Forecasting,” in 2022 IEEE Electrical Power and Energy Conference (EPEC), ISSN: 2381-2842, Dec. 2022, pp. 129–136. DOI: 10.1109/EPEC56903.2022.10000121. [Online]. Available: https://ieeexplore.ieee.org/document/10000121.
[16] Y. Zhang, “Harnessing Machine Learning and Meta-Heuristic Algorithms for Accurate Cooling Load Prediction,” en, International Journal of Advanced Computer Science and Applications (ijacsa), vol. 15, no. 6, 2024, Publisher: The Science and Information (SAI) Organization Limited, ISSN: 2156-5570. DOI: 10.14569/IJACSA.2024.01506119. [Online]. Available: https://thesai.org/ Publications/ViewPaper?Volume=15&Issue=6&Code=ijacsa&SerialNo=119.
[17] Y. Peng et al., “Energy Consumption Optimization for Heating, Ventilation and Air Conditioning Systems Based on Deep Reinforcement Learning,” IEEE Access, vol. 11, pp. 88 265–88 277, 2023, ISSN: 2169-3536. DOI: 10 . 1109 / ACCESS . 2023 . 3305683. [Online]. Available: https : ieeexplore.ieee.org/document/10220078.
[18] S. Wang, X. Chen, L. Bu, B. Wang, K. Yu, and D. He, “A DQN-Based Coordination Method of HVAC and Energy Storage for Building Energy Management,” in 2023 IEEE 7th Conference on Energy Internet and Energy System Integration (EI2), Dec. 2023, pp. 4891–4896. DOI: 10.1109/ EI259745 . 2023 . 10512933. [Online]. Available: https : / / ieeexplore . ieee . org / document/10512933.
[19] Y.-F. Hsu, C. Mizumoto, K. Matsuda, and M. Matsuoka, “Sustainable Data Center Energy Management Through Server Workload Allocation Optimization and HVAC System,” in 2024 IEEE Cloud Summit, Jun. 2024, pp. 17–23. DOI: 10.1109/Cloud-Summit61220.2024.00010. [Online]. Available: https://ieeexplore.ieee.org/document/10630908.
[20] L. Mengru, R. Yingjun, Q. Fanyue, M. Hua, and M. Jiacheng, “Energy consumption characteristic analysis and multi-source instance transfer prediction based on chiller operational data,” en-US, ser. Building Simulation, vol. 18, IBPSA, 2023, pp. 3820–3826. DOI: 10 . 26868 / 25222708 . 2023.1729. [Online]. Available: https://publications. ibpsa.org/conference/ paper/?id=bs2023_1729.
