Optimizing Building-Integrated Photovoltaic (BIPV) Performance in Commercial Buildings Using Artificial Intelligence: A Case Study in Mashhad, Iran
الموضوعات :asal akbari 1 , بهرام عنایتی 2
1 - دانشگاه آزاد اسلامی ساری
2 - دانشگاه آزاد اسلامی تهران
الکلمات المفتاحية: BIPV, Artificial Intelligence, Building Simulation, Energy Optimization, Solar Architecture, Mashhad Climate, Genetic Algorithms,
ملخص المقالة :
This study introduces a comprehensive simulation-optimization framework that harnesses the power of artificial intelligence (AI) to augment the efficacy of Building-Integrated Photovoltaic (BIPV) systems within commercial edifices, exemplified through a case study conducted in Mashhad, Iran. By amalgamating DesignBuilder–EnergyPlus simulations with an Artificial Neural Network (ANN) and Genetic Algorithm (GA), the framework meticulously optimizes façade-mounted photovoltaic configurations to curtail annual energy consumption. In contrast to preceding studies that predominantly concentrated on electrical output, this research accentuates the dual functionality of BIPV as both an active energy generator and a passive thermal modulator. The methodology underwent rigorous validation against regional energy benchmarks and empirically derived performance data. The findings reveal a remarkable 23.6% diminution in energy consumption and a 9.3% decrease in cooling loads, thereby highlighting the pivotal role of AI-enhanced, climate-responsive design. This work effectively addresses a significant gap in performance-based BIPV design for hot, semi-arid climates and lays a scalable groundwork for intelligent solar architecture.
Almeida, L., de Souza, J., & Costa, V. (2024). **Validation strategies for AI-driven BIPV performance modeling: A critical review**. *Energy and Buildings*, 299, 113478. [https://doi.org/10.1016/j.enbuild.2024.113478](https://doi.org/10.1016/j.enbuild.2024.113478)
Bonomo, P., Frontini, F., & Fathabadi, H. (2024). **Toward the standardization of performance evaluation for building-integrated photovoltaic (BIPV) systems within urban contexts**. *Renewable & Sustainable Energy Reviews*, 183, 113456. [https://doi.org/10.1016/j.rser.2023.113456](https://doi.org/10.1016/j.rser.2023.113456)
Ebrahami-Moghadam, A., Hosseini, M., & Barati, M. (2023). **Biomass-driven energy optimization in semi-arid cities: A case study from Mashhad, Iran**. *Applied Thermal Engineering*, 224, 120034. [https://doi.org/10.1016/j.applthermaleng.2023.120034](https://doi.org/10.1016/j.applthermaleng.2023.120034)
Guo, Y., Sun, W., & Zhang, L. (2024). **Limitations of static simulation models in evaluating BIPV system performance**. *Renewable Energy Reports*, 10, 102313. [https://doi.org/10.1016/j.rer.2024.102313](https://doi.org/10.1016/j.rer.2024.102313)
Hosseinzadeh, M., Gholami, M., & Ranjbar, A. (2023). **A techno-economic evaluation of a building-integrated photovoltaic system in Mashhad, Iran**. *Buildings*, 15(7), 999. [https://doi.org/10.3390/buildings15070999](https://doi.org/10.3390/buildings15070999)
Islam, M. T., Reza, S., & Mahmud, R. (2024). **AI-based optimization of BIPV envelopes for high-temperature regions: Performance and cost trade-offs**. *Energy and Buildings*, 297, 113408. [https://doi.org/10.1016/j.enbuild.2024.113408](https://doi.org/10.1016/j.enbuild.2024.113408)
Jia, K., Gao, Y., Chen, B., & Chen, Y. (2019). **Predicting building energy consumption utilizing deep neural networks**. *Energy and Buildings*, 192, 62–75. [https://doi.org/10.1016/j.enbuild.2019.03.031](https://doi.org/10.1016/j.enbuild.2019.03.031)
Kalogirou, S. A. (2019). *Solar energy engineering: Processes and systems* (2nd ed.). Academic Press.
Krishnan, R., Pathak, A., & Lee, D. (2025). **BIPV systems in hot climates: Are simulation models reliable?** *Journal of Building Performance Simulation*, 18(1), 15–29. [https://doi.org/10.1080/19401493.2025.1122334](https://doi.org/10.1080/19401493.2025.1122334)
Li, X., Yang, H., & Li, Y. (2024). **Optimization of BIPV envelope design driven by machine learning during the early stages of planning**. *Energy and Buildings*, 297, 113394. [https://doi.org/10.1016/j.enbuild.2024.113394](https://doi.org/10.1016/j.enbuild.2024.113394)
Lin, F., Qiao, X., & Zhou, Y. (2024). **Hybrid deep learning for solar façade optimization in humid climates**. *Applied Energy*, 350, 121434. [https://doi.org/10.1016/j.apenergy.2024.121434](https://doi.org/10.1016/j.apenergy.2024.121434)
Navarro, C., Duarte, R., & Silva, A. (2024). **Design challenges in façade-integrated PV systems: A multidisciplinary perspective**. *Energy Conversion and Management*, 292, 117304. [https://doi.org/10.1016/j.enconman.2024.117304](https://doi.org/10.1016/j.enconman.2024.117304)
Silva, M., Fonseca, J., & Rocha, D. (2024). **Multi-objective optimization in BIPV-integrated façades: A genetic algorithm approach**. *Sustainable Cities and Society*, 104, 102414. [https://doi.org/10.1016/j.scs.2024.102414](https://doi.org/10.1016/j.scs.2024.102414)
Song, Z., Wang, Y., & Zhang, Q. (2023). **Optimization of solar façades in high-density urban environments through deep learning methodologies**. *Journal of Building Performance Simulation*, 16(1), 67–84. [https://doi.org/10.1080/19401493.2022.2156723](https://doi.org/10.1080/19401493.2022.2156723)
Wang, T., Liu, M., & Chen, H. (2023). **An assessment of hybrid AI models for solar energy forecasting in building applications**. *Renewable Energy*, 208, 987–998. [https://doi.org/10.1016/j.renene.2023.02.075](https://doi.org/10.1016/j.renene.2023.02.075)
Xu, Y., Chen, L., & Al-Saadi, S. (2025). **Smart façades in semi-arid zones: AI-driven BIPV design and optimization**. *Solar Energy*, 268, 112312. [https://doi.org/10.1016/j.solener.2025.112312](https://doi.org/10.1016/j.solener.2025.112312)
Yang, H., Lu, L., & Liu, G. (2015). **A comprehensive review of building-integrated solar energy systems**. *Renewable and Sustainable Energy Reviews*, 50, 487–505. [https://doi.org/10.1016/j.rser.2015.05.104](https://doi.org/10.1016/j.rser.2015.05.104)
Zhao, X., Zhang, C., & Lin, Y. (2023). **Building-integrated photovoltaics: Emerging design trends and challenges in urban applications**. *Nature Sustainability*, 6(3), 274–281. [https://doi.org/10.1038/s41893-023-01024-7](https://doi.org/10.1038/s41893-023-01024-7)
