Enhanced Energy Prediction of Next-Generation Urban Buildings Optimized with Pyramidal Dilation Attention Convolutional Deep Neural Networks
Received: 1 July 2025 | Revised: 9 August 2025 | Accepted: 20 August 2025 | Online: 6 October 2025
Corresponding author: Suleman Alnatheer
Abstract
Investors, urban designers, and energy policymakers increasingly rely on modeling and analysis of building energy performance to develop long-term sustainable energy strategies that reduce energy consumption and emissions. However, a gap remains between building energy modeling and conventional planning techniques due to inconsistent energy data and the lack of scalable building models. In this work, we propose the Enhanced Energy Prediction of Next-Generation Urban Buildings Optimized with Pyramidal Dilation Attention Convolutional Deep Neural Network and Bitterling Fish Optimization (EEP-UB-PDACN-BFO). The approach begins with input data obtained from the Building Energy Ratings (BER) dataset, which is preprocessed using the Bilinear Double-Order Filter (BDOF) to detect and remove inconsistencies. The preprocessed data are then passed through the Pyramidal Dilation Attention Convolutional Network (PDACN) to forecast the Energy Use Intensity (EUI) of buildings. To further improve accuracy, Bitterling Fish Optimization (BFO) is applied to optimize the weight parameters of the PDACN. The proposed EEP-UB-PDACN-BFO model is implemented in Python and evaluated using performance metrics including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE), and the coefficient of determination (R2). The proposed method achieves an R2 of 0.95, an RMSE of 6.2 kWh/(m2∙year), and an MAE of 3.9 kWh/(m2∙year), outperforming existing approaches. These results demonstrate that the proposed method substantially enhances building performance modelling, providing a more robust tool for the development of sustainable energy policies and industrial regulations.
Keywords:
energy performance, sustainable energy and industry, building energy rating dataset, urban building, residential building, environment, building energy, smart citiesDownloads
References
U. Perwez, Y. Yamaguchi, T. Ma, Y. Dai, and Y. Shimoda, "Multi-scale GIS-synthetic hybrid approach for the development of commercial building stock energy model," Applied Energy, vol. 323, Oct. 2022, Art. no. 119536.
F. Johari, F. Shadram, and J. Widén, "Urban building energy modeling from geo-referenced energy performance certificate data: Development, calibration, and validation," Sustainable Cities and Society, vol. 96, Sep. 2023, Art. no. 104664.
A. Malhotra, M. Shamovich, J. Frisch, and C. Van Treeck, "Urban energy simulations using open CityGML models: A comparative analysis," Energy and Buildings, vol. 255, Jan. 2022, Art. no. 111658.
U. Ali et al., "Urban building energy performance prediction and retrofit analysis using data-driven machine learning approach," Energy and Buildings, vol. 303, Jan. 2024, Art. no. 113768.
S. Wenninger, C. Kaymakci, and C. Wiethe, "Explainable long-term building energy consumption prediction using QLattice," Applied Energy, vol. 308, Feb. 2022, Art. no. 118300.
M. S. Geraldi and E. Ghisi, "Data-driven framework towards realistic bottom-up energy benchmarking using an Artificial Neural Network," Applied Energy, vol. 306, Jan. 2022, Art. no. 117960.
J. Lizana, V. P. López-Cabeza, R. Renaldi, E. Diz-Mellado, C. Rivera-Gómez, and C. Galán-Marín, "Integrating courtyard microclimate in building performance to mitigate extreme urban heat impacts," Sustainable Cities and Society, vol. 78, Mar. 2022, Art. no. 103590.
A. Nakhaee and A. Paydar, "DeepRadiation: An intelligent augmented reality platform for predicting urban energy performance just through 360 panoramic streetscape images utilizing various deep learning models," Building Simulation, vol. 16, no. 3, pp. 499–510, Mar. 2023.
Y. Zhang, A. Schlueter, and C. Waibel, "SolarGAN: Synthetic annual solar irradiance time series on urban building facades via Deep Generative Networks," Energy and AI, vol. 12, Apr. 2023, Art. no. 100223.
X. Jin, F. Xiao, C. Zhang, and A. Li, "GEIN: An interpretable benchmarking framework towards all building types based on machine learning," Energy and Buildings, vol. 260, Apr. 2022, Art. no. 111909.
A. Soni, R. Koner, and V. G. K. Villuri, "Fusion of Dual-Scale Convolution Neural Network for Urban Building Footprints," Ain Shams Engineering Journal, vol. 13, no. 3, May 2022, Art. no. 101622.
D. Shi, Y. Gao, P. Zeng, B. Li, P. Shen, and C. Zhuang, "Climate adaptive optimization of green roofs and natural night ventilation for lifespan energy performance improvement in office buildings," Building and Environment, vol. 223, Sep. 2022, Art. no. 109505.
P. Lin, L. Zhang, and J. Zuo, "Data-driven prediction of building energy consumption using an adaptive multi-model fusion approach," Applied Soft Computing, vol. 129, Nov. 2022, Art. no. 109616.
S. Han, H. Shao, Z. Huo, X. Yang, and J. Cheng, "End-to-end chiller fault diagnosis using fused attention mechanism and dynamic cross-entropy under imbalanced datasets," Building and Environment, vol. 212, Mar. 2022, Art. no. 108821.
Z. Deng, K. Javanroodi, V. M. Nik, and Y. Chen, "Using urban building energy modeling to quantify the energy performance of residential buildings under climate change," Building Simulation, vol. 16, no. 9, pp. 1629–1643, Sep. 2023.
J. An, Y. Wu, C. Gui, and D. Yan, "Chinese prototype building models for simulating the energy performance of the nationwide building stock," Building Simulation, vol. 16, no. 8, pp. 1559–1582, Aug. 2023.
Z. Jalali, A. Y. Shamseldin, and A. Ghaffarianhoseini, "Urban microclimate impacts on residential building energy demand in Auckland, New Zealand: A climate change perspective," Urban Climate, vol. 53, Jan. 2024, Art. no. 101808.
F. Battini, G. Pernigotto, and A. Gasparella, "District-level validation of a shoeboxing simplification algorithm to speed-up Urban Building Energy Modeling simulations," Applied Energy, vol. 349, Nov. 2023, Art. no. 121570.
F. E. Sapnken, M. M. Hamed, B. Soldo, and J. Gaston Tamba, "Modeling energy-efficient building loads using machine-learning algorithms for the design phase," Energy and Buildings, vol. 283, Mar. 2023, Art. no. 112807.
U. Perwez, K. Shono, Y. Yamaguchi, and Y. Shimoda, "Multi-scale UBEM-BIPV coupled approach for the assessment of carbon neutrality of commercial building stock," Energy and Buildings, vol. 291, Jul. 2023, Art. no. 113086.
P. Sutthichaimethee, W. Sa-Ngiamvibool, B. Wattana, J. Luo, and S. Wattana, "A Long-Term Electricity Consumption Model adapted from the MMM-ARCH-M Framework for Strategic Greenhouse Gas Emission Reduction towards Smart City Goals in Thailand," Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 22367–22377, Jun. 2025.
Irish Building Energy Ratings (BER) Dataset. (2023), J. McNeill. [Online]. Available: https://www.kaggle.com/datasets/datajmcn/berpublicdata.
J. Nako, C. Psychalinos, F. Khateb, and A. S. Elwakil, "Bilinear Double-Order Filter Designs and Application Examples," IEEE Access, vol. 12, pp. 14040–14049, 2024.
W. Hou, N. Chen, J. Peng, W. Sun, and Q. Du, "Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image Classification," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 1503–1518, 2023.
L. Zareian, J. Rahebi, and M. J. Shayegan, "Bitterling fish optimization (BFO) algorithm," Multimedia Tools and Applications, vol. 83, no. 31, pp. 75893–75926, Feb. 2024.
K. Elhabyb, A. Baina, M. Bellafkih, and A. F. Deifalla, "Machine Learning Algorithms for Predicting Energy Consumption in Educational Buildings," International Journal of Energy Research, vol. 2024, no. 1, Jan. 2024, Art. no. 6812425.
H. B. Juričić and H. Krstić, "Comparing MLR and ANN models for school building electrical energy prediction in Osijek-Baranja County in Croatia," Energy Reports, vol. 12, pp. 3595–3606, Dec. 2024.
Y. Shen et al., "Utilizing interpretable stacking ensemble learning and NSGA-III for the prediction and optimisation of building photo-thermal environment and energy consumption," Building Simulation, vol. 17, no. 5, pp. 819–838, May 2024.
Downloads
How to Cite
License
Copyright (c) 2025 Suleman Alnatheer, Mohammed Altaf Ahmed
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
