Harnessing Deep Learning and Reinforcement Learning Synergy as a Form of Strategic Energy Optimization in Architectural Design: A Case Study in Famagusta, North Cyprus
Abstract
:1. Introduction
1.1. Background
1.1.1. Deep Learning in Architectural Design
1.1.2. Reinforcement Learning in Architectural Design
1.1.3. Synergistic Integration of Deep Learning and Reinforcement Learning
1.1.4. Challenges and Limitations
- Data availability and quality: deep learning models require large amounts of diverse and representative data for training, which may not always be readily available in the architectural domain. The lack of standardized data formats and the heterogeneity of building designs and energy consumption patterns can exacerbate this challenge [27,69,101];
- Model complexity and generalization: the complexity of architectural design and the wide range of interacting factors that influence energy performance can make it challenging to develop accurate and reliable deep learning models that generalize well across diverse building types and climatic regions [27,46,88,91];
- Reinforcement learning optimization: training and optimizing reinforcement learning agents in complex environments with high-dimensional state and action spaces, such as architectural design, can be computationally intensive and sensitive to the choice of reward function and exploration strategy [32,42,52,64,78];
- Computational resources: the computational complexity and resource requirements of deep learning and reinforcement learning models can pose practical challenges for their integration into architectural design workflows, potentially requiring specialized hardware and computational resources [55,68,90];
1.1.5. Addressing the Gap and Proposed Approach
2. Methodology
2.1. Research Design
AI Models
- A variational autoencoder (VAE) was trained on a dataset of architectural layouts to generate optimized building designs. The VAE architecture was adapted from previous work but retrained specifically for energy-efficient design;
- A model-free reinforcement learning (RL) agent using Q-learning aimed to further optimize the generated designs by maximizing energy efficiency. A multi-objective reward function balanced priorities like energy usage, occupant comfort, construction costs, and alignment with urban policies.
2.2. Data Collection
- A dataset of 200 architectural layouts from energy-efficient office buildings, represented as graphs with nodes (rooms/spaces) and edges (connections);
- A comprehensive review of policy documents related to building regulations, urban planning, and energy goals for Famagusta. Relevant priorities were extracted to shape the RL reward function.
2.3. Data Analysis
- Changes in reward between episodes;
- Percentage of nodes connected;
- Average path lengths in the optimized network layouts.
2.4. AI Model Architecture
- Variational autoencoder (VAE);
- Reinforcement learning (RL) agent.
- is graph reconstruction loss;
- are regularization penalties for constraint violations;
- β is a weighting hyperparameter.
- E is the predicted energy demand for the layout;
- C is the estimated construction cost;
- T represents occupant thermal comfort metrics;
- P measures alignment with urban policies/regulations;
- , , , are weights summing to 1.
2.5. Optimization Process
2.6. Computational Environment
2.7. Ethical Considerations
3. Result
3.1. Reconstruction Accuracy
3.2. Pedestrian Network Generation
- Qualitative results: Extensive iterations were included in our experiments, whereby a diverse array of energy-efficient architectural configurations were generated by the VAE. Through several visualization techniques, it could be observed that the generated layouts resonated well with contemporary design sensibilities while reflecting the nuances of historical design data. These visual outputs, when reviewed by a panel of expert architects, were commended for embodying practical viability and creative ingenuity (see Table 2);
- Quantitative results: The VAE model was also scrutinized against objective quantitative performance metrics. The statistical analysis extended beyond mere accuracy, delving into aspects such as diversity of designs, adherence to energy consumption limits, and alignment with pre-set aesthetic parameters. The generated designs not only showcased variety but also maintained a consistent focus on energy optimization, underpinned by the model’s learned representations.
3.3. Reinforcement Learning Optimization Results
3.4. Convergence and Stability Analysis
3.5. Comparison with Traditional Optimization Techniques
3.6. Performance Graphs
Solution Quality and Computational Efficiency
3.7. Case Study Results
3.7.1. Real-World Application
3.7.2. Adaptation to Various Scenarios
3.8. Scenario Visualizations
3.8.1. Case Study on Office Building Energy Optimization
3.8.2. Recommendations for Future Work
- A deeper analysis of the specific energy consumption drivers in the office building should be conducted to target the energy-saving measures more accurately;
- The potential impact of additional climatic factors, such as humidity and precipitation, on energy consumption should be explored;
- Extending the RL model to incorporate predictive maintenance of the building’s systems, thus minimizing downtime and unexpected spikes in energy usage, should be considered.
4. Discussion
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- U.S. United Nations. Revision of World Urbanization Prospects; United Nations Department of Economic and Social Affairs: New York, NY, USA, 2018.
- Arabi, R.; Shahidan, M.; Kamal, M.S.; Jaafar, M.; Rakhshandehroo, M. Mitigating Urban Heat Island Through Green Roofs. Curr. World Environ. 2015, 10, 918–927. [Google Scholar] [CrossRef]
- Koch, K.; Ysebaert, T.; Denys, S.; Samson, R. Urban heat stress mitigation potential of green walls: A review. Urban For. Urban Green. 2020, 55, 126843. [Google Scholar] [CrossRef]
- Block, A.H.; Livesley, S.J.; Williams, N.S.G. Responding to the Urban Heat Island: A Review of the Potential of Green Infrastructure; Victorian Centre for Climate Change Adaptation Research (VCCCAR): Melbourne, Australia, 2012. [Google Scholar]
- Gago, E.J.; Roldan, J.; Pacheco-Torres, R.; Ordóñez, J. The city and urban heat islands: A review of strategies to mitigate adverse effects. Renew. Sustain. Energy Rev. 2013, 25, 749–758. [Google Scholar] [CrossRef]
- Singh, N.; Singh, S.; Mall, R.K. Urban ecology and human health: Implications of urban heat island, air pollution and climate change nexus. In Urban Ecology: Emerging Patterns and Social-Ecological Systems; Elsevier: Amsterdam, The Netherlands, 2020. [Google Scholar] [CrossRef]
- Irfeey, A.M.M.; Chau, H.W.; Sumaiya, M.M.F.; Wai, C.Y.; Muttil, N.; Jamei, E. Sustainable Mitigation Strategies for Urban Heat Island Effects in Urban Areas. Sustainability 2023, 15, 10767. [Google Scholar] [CrossRef]
- Elhabodi, T.S.; Yang, S.; Parker, J.; Khattak, S.; He, B.J.; Attia, S. A review on BIPV-induced temperature effects on urban heat islands. Urban Clim. 2023, 50, 101592. [Google Scholar] [CrossRef]
- Yin, Z.; Liu, Z.; Liu, X.; Zheng, W.; Yin, L. Urban heat islands and their effects on thermal comfort in the US: New York and New Jersey. Ecol. Indic. 2023, 154, 110765. [Google Scholar] [CrossRef]
- Yadav, N.; Rajendra, K.; Awasthi, A.; Singh, C. Systematic exploration of heat wave impact on mortality and urban heat island: A review from 2000 to 2022. Urban Clim. 2023, 51, 101622. [Google Scholar] [CrossRef]
- Rajagopal, P.; Priya, R.S.; Senthil, R. A review of recent developments in the impact of environmental measures on urban heat island. Sustain. Cities Soc. 2023, 88, 104279. [Google Scholar] [CrossRef]
- Fanelli, C.; Pomponi, J. DeepRICH: Learning deeply Cherenkov detectors. Mach. Learn. Sci. Technol. 2020, 1, 015010. [Google Scholar] [CrossRef]
- Chang, S.; Jun, H. Hybrid deep-learning model to recognise emotional responses of users towards architectural design alternatives. J. Asian Archit. Build. Eng. 2019, 18, 381–391. [Google Scholar] [CrossRef]
- Li, Z.; Su, S.; Jin, X.; Xia, M.; Chen, Q.; Yamashita, K. Stochastic and distributed optimal energy management of active distribution network with integrated office buildings. CSEE J. Power Energy Syst. 2022, 10, 504–517. [Google Scholar] [CrossRef]
- Li, J.; Yang, B.; Yu, T. Distributed deep reinforcement learning-based coordination performance optimization method for proton exchange membrane fuel cell system. Sustain. Energy Technol. Assess. 2022, 50, 101814. [Google Scholar] [CrossRef]
- Sutton, R.; Barto, A. Reinforcement Learning: An Introduction. 2018. Available online: https://books.google.com/books?hl=en&lr=&id=uWV0DwAAQBAJ&oi=fnd&pg=PR7&dq=Reinforcement+Learning,+second+edition:+An+Introduction&ots=miuKr30Ym6&sig=5TAVLNn7NVuqhFzrLDBu3UXQ6lg (accessed on 15 February 2023).
- Wiering, M.; Otterlo, M. Adaptation, undefined learning, and optimization, and undefined. In Reinforcement Learning; Springer: Berlin/Heidelberg, Germany, 2012; Available online: https://link.springer.com/content/pdf/10.1007/978-3-642-27645-3.pdf (accessed on 15 February 2023).
- Kellogg, K.A.; La Cumbre-Gibbs, N. The impact of state level residential building code stringency on energy consumption in the United States. Energy Build. 2023, 278, 112607. [Google Scholar] [CrossRef]
- Mansourimajoumerd, P.; Bazazzadeh, H.; Mahdavinejad, M.; Nia, S.N. Energy Efficiency and Building’s Envelope: An Integrated Approach to High-Performance Architecture. In Advances in Science, Technology and Innovation; Springer: Cham, Switzerland, 2023. [Google Scholar] [CrossRef]
- Fakhr, B.V.; Mahdavinejad, M.; Rahbar, M.; Dabaj, B. Design Optimization of the Skylight for Daylighting and Energy Performance Using NSGA-II. J. Daylighting 2023, 10, 72–86. [Google Scholar] [CrossRef]
- Zhang, J.; Zhu, X.; Khan, A.M.; Houda, M.; Rehman, S.K.; Jameel, M.; Javed, M.F.; Alrowais, R. BIM-based architectural analysis and optimization for construction 4.0 concept (a comparison). Ain Shams Eng. J. 2023, 14, 102110. [Google Scholar] [CrossRef]
- Assareh, E.; Meshkinnezhad, S.; Agarwal, N.; Baheri, A.; Ahmadinejad, M.; Behrang, M.; Sohani, A.; Fathi, A.; Jafarinejad, T.; Lee, M. Performance evaluation and multi-objective optimization of an innovative double-stage thermoelectric heat storage system for electricity generation. Energy Nexus 2024, 13, 100260. [Google Scholar] [CrossRef]
- Assareh, E.; Keykhah, A.; Hoseinzadeh, S.; Garcia, D.A. Application of PCM in a Zero-Energy Building and Using a CCHP System Based on Geothermal Energy in Canada and the UAE. Buildings 2024, 14, 477. [Google Scholar] [CrossRef]
- Sohani, A.; Rezapour, S.; Sayyaadi, H. Comprehensive performance evaluation and demands’ sensitivity analysis of different optimum sizing strategies for a combined cooling, heating, and power system. J. Clean. Prod. 2021, 279, 123225. [Google Scholar] [CrossRef]
- Amirhaeri, Y.; Pourfayaz, F.; Hadavi, H.; Kasaeian, A. Energy and exergy analysis-based monthly co-optimization of a poly-generation system for power, heating, cooling, and hydrogen production. J. Therm. Anal. Calorim. 2023, 148, 8195–8221. [Google Scholar] [CrossRef]
- YMaleki; Pourfayaz, F.; Mehrpooya, M. Transient optimization of annual performance of a photovoltaic thermal system based on accurate estimation of coolant water temperature: A comparison with conventional methods. Case Stud. Therm. Eng. 2021, 28, 101395. [Google Scholar] [CrossRef]
- Fourie, C.M. Deep learning? What deep learning? S. Afr. J. High. Educ. 2003, 17, 123–131. [Google Scholar] [CrossRef]
- Yaman, M.Y.; Kalinin, S.V.; Guye, K.N.; Ginger, D.S.; Ziatdinov, M. Learning and Predicting Photonic Responses of Plasmonic Nanoparticle Assemblies via Dual Variational Autoencoders. Small 2023, 19, 2205893. [Google Scholar] [CrossRef] [PubMed]
- Barto, A.G. Reinforcement Learning: An Introduction. By Richard’s Sutton. SIAM Rev. 2021, 6, 423. [Google Scholar]
- Wang, Z.; Hong, T. Reinforcement learning for building controls: The opportunities and challenges. Appl. Energy 2020, 269, 115036. [Google Scholar] [CrossRef]
- Li, C.; Zheng, P.; Yin, Y.; Wang, B.; Wang, L. Deep reinforcement learning in smart manufacturing: A review and prospects. CIRP J. Manuf. Sci. Technol. 2023, 40, 75–101. [Google Scholar] [CrossRef]
- Han, Z.; Yan, W.; Liu, G. A Performance-Based Urban Block Generative Design Using Deep Reinforcement Learning and Computer Vision. In Proceedings of the 2020 DigitalFUTURES; Springer: Singapore, 2021. [Google Scholar] [CrossRef]
- Liu, R.; Nageotte, F.; Zanne, P.; de Mathelin, M.; Dresp-Langley, B. Deep reinforcement learning for the control of robotic manipulation: A focussed mini-review. Robotics 2021, 10, 22. [Google Scholar] [CrossRef]
- Yu, Y.; Zhang, P.; Zhao, K.; Zheng, Y.; Hao, J. Accelerating deep reinforcement learning via knowledge-guided policy network. Auton. Agents Multi Agent Syst. 2023, 37, 17. [Google Scholar] [CrossRef]
- Wang, Z.; Schaul, T.; Hessel, M.; Van Hasselt, H.; Lanctot, M.; De Frcitas, N. Dueling Network Architectures for Deep Reinforcement Learning. In Proceedings of the 33rd International Conference on Machine Learning, ICML, New York, NY, USA, 19–24 June 2016. [Google Scholar]
- Quevedo, T.C.; Geraldi, M.S.; Melo, A.P. Applying machine learning to develop energy benchmarking for university buildings in Brazil. J. Build. Eng. 2023, 63, 105468. [Google Scholar] [CrossRef]
- Coraci, D.; Brandi, S.; Hong, T.; Capozzoli, A. Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings. Appl. Energy 2023, 333, 120598. [Google Scholar] [CrossRef]
- Kreuzberger, D.; Kuhl, N.; Hirschl, S. Machine Learning Operations (MLOps): Overview, Definition, and Architecture. IEEE Access 2023, 11, 31866–31879. [Google Scholar] [CrossRef]
- Arroyo, D.M.; Postels, J.; Tombari, F. Variational transformer networks for layout generation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20–25 June 2021. [Google Scholar] [CrossRef]
- Chang, S.; Saha, N.; Castro-Lacouture, D.; Yang, P.P.J. Multivariate relationships between campus design parameters and energy performance using reinforcement learning and parametric modeling. Appl. Energy 2019, 249, 253–264. [Google Scholar] [CrossRef]
- Liu, X.; Li, P.; Meng, F.; Zhou, H.; Zhong, H.; Zhou, J.; Mou, L.; Song, S. Simulated annealing for optimization of graphs and sequences. Neurocomputing 2021, 465, 310–324. [Google Scholar] [CrossRef]
- Kingma, D.P.; Welling, M. An Introduction to Variational Autoencoders. Found. Trends® Mach. Learn. 2019, 12, 307–392. [Google Scholar] [CrossRef]
- Liang, D.; Krishnan, R.G.; Hoffman, M.D.; Jebara, T. Variational autoencoders for collaborative filtering. In Proceedings of the World Wide Web Conference, WWW 2018, Lyon, France, 23–27 April 2018. [Google Scholar] [CrossRef]
- Botvinick, M.; Ritter, S.; Wang, J.X.; Kurth-Nelson, Z.; Blundell, C.; Hassabis, D. Reinforcement Learning, Fast and Slow. Trends Cogn. Sci. 2019, 23, 408–422. [Google Scholar] [CrossRef]
- Wang, Y.; Zeng, Z.; Li, Q.; Deng, Y. A Complete Reinforcement-Learning-Based Framework for Urban-Safety Perception. ISPRS Int. J. Geo Inf. 2022, 11, 465. [Google Scholar] [CrossRef]
- Dey, S.; Marzullo, T.; Zhang, X.; Henze, G. Reinforcement learning building control approach harnessing imitation learning. Energy AI 2023, 14, 100255. [Google Scholar] [CrossRef]
- Wu, M.; Guo, K.; Li, X.; Lin, Z.; Wu, Y.; Tsiftsis, T.A.; Song, H. Deep Reinforcement Learning-based Energy Efficiency Optimization for RIS-aided Integrated Satellite-Aerial-Terrestrial Relay Networks. IEEE Trans. Commun. 2024. [Google Scholar] [CrossRef]
- Sarkar, S.; Naug, A.; Guillen, A.; Luna, R.; Gundecha, V.; Babu, A.R.; Mousavi, S. Sustainability of Data Center Digital Twins with Reinforcement Learning. Proc. AAAI Conf. Artif. Intell. 2024, 38, 23832–23834. [Google Scholar] [CrossRef]
- Sebestyen, A.; Tyc, J. Machine Learning Methods in Energy Simulations for Architects and Designers The implementation of supervised machine learning in the context of the computational design process. In Proceedings of the International Conference on Education and Research in Computer Aided Architectural Design in Europe, Berlin, Germany, 16–18 September 2020. [Google Scholar] [CrossRef]
- Sanaei, R.; Otto, K.; Hölttä-Otto, K.; Wood, K. A reinforcement learning approach to system modularization under constraints. Syst. Eng. 2023, 26, 408–424. [Google Scholar] [CrossRef]
- Gilan, S.S.; Dilkina, B. Sustainable building design: A challenge at the intersection of machine learning and design optimization. In Proceedings of the Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, TX, USA, 25–30 January 2015. [Google Scholar]
- Tao, F.; Sui, F.; Liu, A.; Qi, Q.; Zhang, M.; Song, B.; Guo, Z.; Lu, S.C.-Y.; Nee, A.Y.C. Digital twin-driven product design framework. Int. J. Prod. Res. 2019, 57, 3935–3953. [Google Scholar] [CrossRef]
- Tracking Clean Energy Progress 2023—Analysis—IEA. Available online: https://www.iea.org/reports/tracking-clean-energy-progress-2023 (accessed on 30 March 2024).
- Dezfouli, M.M.S.; Dehghani-Sanij, A.R.; Kadir, K.; Sopian, K. Development and life cycle cost analysis of a solar hybrid HVAC system for use in buildings in tropical climates. Sustain. Energy Technol. Assess. 2023, 57, 103143. [Google Scholar] [CrossRef]
- Rahman, S.; Issa, S.; Assad, M.E.H.; Shah, S.K.; Abdelkareem, M.A.; Hoque, E.; Olabi, A. Performance enhancement and life cycle analysis of a novel solar HVAC system using underground water and energy recovery technique. Therm. Sci. Eng. Prog. 2022, 36, 101515. [Google Scholar] [CrossRef]
- Etemad, A.; Abdalisousan, A.; Aliehyaei, M. Design and Feasibility Analysis of a HVAC System based on CCHP, Solar Heating and Ice Thermal Storage for Residential Buildings. Modares Mech. Eng. 2022, 22, 81–92. Available online: https://mme.modares.ac.ir/article-15-46591-en.html (accessed on 25 February 2024).
- Mehrpooya, M.; Bahnamiri, F.K.; Moosavian, S.M.A. Energy analysis and economic evaluation of a new developed integrated process configuration to produce power, hydrogen, and heat. J. Clean. Prod. 2019, 239, 118042. [Google Scholar] [CrossRef]
- Ascione, F.; Bianco, N.; De Masi, R.F.; de Rossi, F.; De Stasio, C.; Vanoli, G.P. Energy audit of health care facilities: Dynamic simulation of energy performances and energy-oriented refurbishment of system and equipment for microclimatic control. Am. J. Eng. Appl. Sci. 2016, 9, 814–834. [Google Scholar] [CrossRef]
- Wan, Y.; Zhai, Y.; Wang, X.; Cui, C. Evaluation of Indoor Energy-Saving Optimization Design of Green Buildings Based on the Intelligent GANN-BIM Model. Math. Probl. Eng. 2022, 2022, 3130512. [Google Scholar] [CrossRef]
- Alhuyi-Nazari, M.; Mukhtar, A.; Yasir, A.S.H.M.; Ahmadi, M.H.; Kumar, R.; Luong, T.N.L. Applications of geothermal sources for absorption chillers as efficient and clean cooling technologies for buildings: A comprehensive review. J. Build. Eng. 2024, 82, 108340. [Google Scholar] [CrossRef]
- Nguyen, A.T.; Reiter, S.; Rigo, P. A review on simulation-based optimization methods applied to building performance analysis. Appl. Energy 2014, 113, 1043–1058. [Google Scholar] [CrossRef]
- Ramage, M.H.; McRobie, F.A.; Thomas, R. Architectural engineering: Collaborating to deliver energy-efficient buildings. In Oxford Conference: A Re-Evaluation of Education in Architecture; Roaf, S., Bairstow, A., Eds.; WIT Press: Southampton, UK, 2008; pp. 207–210. [Google Scholar]
- An, Y.; Chen, C. Energy-efficient control of indoor PM2. 5 and thermal comfort in a real room using deep reinforcement learning. Energy Build. 2023, 295, 113340. [Google Scholar] [CrossRef]
- Kabir, E.; Kumar, P.; Kumar, S.; Adelodun, A.A.; Kim, K.H. Solar energy: Potential and future prospects. Renew. Sustain. Energy Rev. 2018, 82, 894–900. [Google Scholar] [CrossRef]
- Dezfouli, M.M.S.; Dehghani-Sanij, A.; Kadir, K.A. Modelling and Energy Analysis of a Solar Cooling System Powered by a Photovoltaic (PV) System for a Net-Zero Energy Building (NZEB) Using TRNSYS-PVsyst. In Reducing the Effects of Climate Change Using Building-Integrated and Building-Applied Photovoltaics in the Power Supply; Springer: Cham, Switzerland, 2024; pp. 315–350. [Google Scholar] [CrossRef]
- Mahmoudan, A.; Samadof, P.; Sadeghzadeh, M.; Jalili, M.; Sharifpur, M.; Kumar, R. Thermodynamic and exergoeconomic analyses and performance assessment of a new configuration of a combined cooling and power generation system based on ORC–VCR. J. Therm. Anal. Calorim. 2021, 145, 1163–1189. [Google Scholar] [CrossRef]
- Hoseinzadeh, S.; Azadi, R. Simulation and optimization of a solar-assisted heating and cooling system for a house in Northern of Iran. J. Renew. Sustain. Energy 2017, 9, 045101. [Google Scholar] [CrossRef]
- Kariman, H.; Hoseinzadeh, S.; Heyns, P.S. Energetic and exergetic analysis of evaporation desalination system integrated with mechanical vapor recompression circulation. Case Stud. Therm. Eng. 2019, 16, 100548. [Google Scholar] [CrossRef]
- Said, Z.; Rahman, S.M.; Sohail, M.A.; Bibin, B.S. Analysis of thermophysical properties and performance of nanorefrigerants and nanolubricant-refrigerant mixtures in refrigeration systems. Case Stud. Therm. Eng. 2023, 49, 103274. [Google Scholar] [CrossRef]
- Chen, M.-Y.; Chiang, P.-R. COVID-19 Diagnosis System Based on Chest X-ray Images Using Optimized Convolutional Neural Network. ACM Trans. Sens. Netw. 2023, 19, 1–22. [Google Scholar] [CrossRef]
- Kumar, R.L.; Khan, F.; Din, S.; Band, S.S.; Mosavi, A.; Ibeke, E. Recurrent Neural Network and Reinforcement Learning Model for COVID-19 Prediction. Front. Public Health 2021, 9, 744100. [Google Scholar] [CrossRef] [PubMed]
- Newton, D. Generative Deep Learning in Architectural Design. Technol. Archit. + Des. 2019, 3, 176–189. [Google Scholar] [CrossRef]
- Jaenal, A.; Ruiz-Sarmiento, J.R.; Gonzalez-Jimenez, J. MachNet, a general Deep Learning architecture for Predictive Maintenance within the industry 4.0 paradigm. Eng. Appl. Artif. Intell. 2024, 127, 107365. [Google Scholar] [CrossRef]
- Wang, Y.; Zhao, J.W.; Zheng, M.Y.; Li, M.Y.; Sun, X.; Liu, H.; Liu, Z. Applications of a Deep Neural Network to Illustration Art Style Design of City Architectural. J. Inf. Process. Syst. 2024, 20, 53. [Google Scholar] [CrossRef]
- Dikshit, S.V.; Chavali, S.; Malwe, P.D.; Kulkarni, S.; Panchal, H.; Alrubaie, A.J.; Mohamed, M.A.; Jaber, M.M. A comprehensive review on dehumidification system using solid desiccant for thermal comfort in HVAC applications. Proc. Inst. Mech. Eng. Part E J. Process Mech. Eng. 2023. [Google Scholar] [CrossRef]
- Rahman, A.; Srikumar, V.; Smith, A.D. Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks. Appl. Energy 2018, 212, 372–385. [Google Scholar] [CrossRef]
- Dinmohammadi, F.; Han, Y.; Shafiee, M. Predicting energy consumption in residential buildings using advanced machine learning algorithms. Energies 2023, 16, 3748. [Google Scholar] [CrossRef]
- Nabavi, S.A.; Motlagh, N.H.; Zaidan, M.A.; Aslani, A.; Zakeri, B. Deep Learning in Energy Modeling: Application in Smart Buildings with Distributed Energy Generation. IEEE Access 2021, 9, 125439–125461. [Google Scholar] [CrossRef]
- Hafeez, G.; Alimgeer, K.S.; Khan, I. Electric load forecasting based on deep learning and optimized by heuristic algorithm in smart grid. Appl. Energy 2020, 269, 114915. [Google Scholar] [CrossRef]
- Wazirali, R.; Yaghoubi, E.; Abujazar, M.S.S.; Ahmad, R.; Vakili, A.H. State-of-the-art review on energy and load forecasting in microgrids using artificial neural networks, machine learning, and deep learning techniques. Electr. Power Syst. Res. 2023, 225, 109792. [Google Scholar] [CrossRef]
- Sendra-Arranz, R.; Gutiérrez, A. A long short-term memory artificial neural network to predict daily HVAC consumption in buildings. Energy Build. 2020, 216, 109952. [Google Scholar] [CrossRef]
- Rahbar, M.; Mahdavinejad, M.; Markazi, A.H.D.; Bemanian, M. Architectural layout design through deep learning and agent-based modeling: A hybrid approach. J. Build. Eng. 2022, 47, 103822. [Google Scholar] [CrossRef]
- Ferreiro-Cabello, J.; Fraile-Garcia, E.; de Pison Ascacibar, E.M.; de Pison Ascacibar, F.J.M. Metamodel-based design optimization of structural one-way slabs based on deep learning neural networks to reduce environmental impact. Eng. Struct. 2018, 155, 91–101. [Google Scholar] [CrossRef]
- Ferrara, M.; Della Santa, F.; Bilardo, M.; De Gregorio, A.; Mastropietro, A.; Fugacci, U.; Vaccarino, F.; Fabrizio, E. Design optimization of renewable energy systems for NZEBs based on deep residual learning. Renew. Energy 2021, 176, 590–605. [Google Scholar] [CrossRef]
- Kallioras, N.A.; Lagaros, N.D. DzAIℕ: Deep learning based generative design. Procedia Manuf. 2020, 44, 591–598. [Google Scholar] [CrossRef]
- Zhang, W.; Wang, Y.; Du, Z.; Liu, C.; Youn, S.K.; Guo, X. Machine-learning assisted topology optimization for architectural design with artistic flavor. Comput. Methods Appl. Mech. Eng. 2023, 413, 116041. [Google Scholar] [CrossRef]
- Zhang, H. 3D Model Generation on Architectural Plan and Section Training through Machine Learning. Technologies 2019, 7, 82. [Google Scholar] [CrossRef]
- Asperti, A.; Evangelista, D.; Piccolomini, E.L. A Survey on Variational Autoencoders from a Green AI Perspective. SN Comput. Sci. 2021, 2, 301. [Google Scholar] [CrossRef]
- Cai, C.; Li, B. Training deep convolution network with synthetic data for architectural morphological prototype classification. Front. Archit. Res. 2021, 10, 304–316. [Google Scholar] [CrossRef]
- As, I.; Pal, S.; Basu, P. Artificial intelligence in architecture: Generating conceptual design via deep learning. Int. J. Archit. Comput. 2018, 16, 306–327. [Google Scholar] [CrossRef]
- Yoo, S.; Lee, S.; Kim, S.; Hwang, K.H.; Park, J.H.; Kang, N. Integrating deep learning into CAD/CAE system: Generative design and evaluation of 3D conceptual wheel. Struct. Multidiscip. Optim. 2021, 64, 2725–2747. [Google Scholar] [CrossRef]
- Oh, S.; Jung, Y.; Kim, S.; Lee, I.; Kang, N. Deep generative design: Integration of topology optimization and generative models. J. Mech. Des. 2019, 141, 111405. [Google Scholar] [CrossRef]
- Adibhesami, M.A.; Karimi, H.; Sharifi, A.; Sepehri, B.; Bazazzadeh, H.; Berardi, U. Optimization of Urban-Scale Sustainable Energy Strategies to Improve Citizens’ Health. Energies 2023, 16, 119. [Google Scholar] [CrossRef]
- Wei, P.; Xia, S.; Chen, R.; Qian, J.; Li, C.; Jiang, X. A Deep-Reinforcement-Learning-Based Recommender System for Occupant-Driven Energy Optimization in Commercial Buildings. IEEE Internet Things J. 2020, 7, 6402–6413. [Google Scholar] [CrossRef]
- Gómez-Romero, J.; Molina-Solana, M. Towards self-adaptive building energy control in smart grids. In Proceedings of the NeurIPS 2019 Workshop on Tackling Climate Change with Machine Learning, Vancouver, BC, Canada, 13–14 December 2019. [Google Scholar]
- Zhang, Z.; Chong, A.; Pan, Y.; Zhang, C.; Lu, S.; Lam, K.P. A deep reinforcement learning approach to using whole building energy model for HVAC optimal control. In Proceedings of the ASHRAE and IBPSA-USA Building Simulation Conference, Chicago, IL, USA, 26–28 September 2018. [Google Scholar]
- Gao, Y.; Matsunami, Y.; Miyata, S.; Akashi, Y. Operational optimization for off-grid renewable building energy system using deep reinforcement learning. Appl. Energy 2022, 325, 119783. [Google Scholar] [CrossRef]
- Gao, Y.; Matsunami, Y.; Miyata, S.; Akashi, Y. Multi-agent reinforcement learning dealing with hybrid action spaces: A case study for off-grid oriented renewable building energy system. Appl. Energy 2022, 326, 120021. [Google Scholar] [CrossRef]
- Shen, R.; Zhong, S.; Wen, X.; An, Q.; Zheng, R.; Li, Y.; Zhao, J. Multi-agent deep reinforcement learning optimization framework for building energy system with renewable energy. Appl. Energy 2022, 312, 118724. [Google Scholar] [CrossRef]
- Mocanu, E.; Mocanu, D.C.; Nguyen, P.H.; Liotta, A.; Webber, M.E.; Gibescu, M.; Slootweg, J.G. On-Line Building Energy Optimization Using Deep Reinforcement Learning. IEEE Trans. Smart Grid 2019, 10, 3698–3708. [Google Scholar] [CrossRef]
- Zhang, Z.; Chong, A.; Pan, Y.; Zhang, C.; Lam, K.P. Whole building energy model for HVAC optimal control: A practical framework based on deep reinforcement learning. Energy Build. 2019, 199, 472–490. [Google Scholar] [CrossRef]
- Elbeltagi, E.; Wefki, H. Predicting energy consumption for residential buildings using ANN through parametric modeling. Energy Rep. 2021, 7, 2534–2545. [Google Scholar] [CrossRef]
- Chen, S.; Zhao, L.; Zheng, L.; Bi, G. A rapid evaluation method for design strategies of high-rise office buildings achieving nearly zero energy in Guangzhou. J. Build. Eng. 2021, 44, 103297. [Google Scholar] [CrossRef]
- Amiri, S.S.; Mottahedi, M.; Asadi, S. Using multiple regression analysis to develop energy consumption indicators for commercial buildings in the U.S. Energy Build. 2015, 109, 209–216. [Google Scholar] [CrossRef]
- Elbeltagi, E.; Wefki, H.; Abdrabou, S. Dawood, and A. Ramzy. Visualized strategy for predicting buildings energy consumption during early design stage using parametric analysis. J. Build. Eng. 2017, 13, 127–136. [Google Scholar] [CrossRef]
- Chegari, B.; Tabaa, M.; Simeu, E.; Moutaouakkil, F.; Medromi, H. Multi-objective optimization of building energy performance and indoor thermal comfort by combining artificial neural networks and metaheuristic algorithms. Energy Build. 2021, 239, 110839. [Google Scholar] [CrossRef]
- Gossard, D.; Lartigue, B.; Thellier, F. Multi-objective optimization of a building envelope for thermal performance using genetic algorithms and artificial neural network. Energy Build. 2013, 67, 253–260. [Google Scholar] [CrossRef]
- Yu, W.; Li, B.; Jia, H.; Zhang, M.; Wang, D. Application of multi-objective genetic algorithm to optimize energy efficiency and thermal comfort in building design. Energy Build. 2015, 88, 135–143. Available online: https://www.sciencedirect.com/science/article/pii/S0378778814010305 (accessed on 18 March 2023). [CrossRef]
- Taye, M.M. Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions. Computers 2023, 12, 91. [Google Scholar] [CrossRef]
- Ahmad, S.; Shakeel, I.; Mehfuz, S.; Ahmad, J. Deep learning models for cloud, edge, fog, and IoT computing paradigms: Survey, recent advances, and future directions. Comput. Sci. Rev. 2023, 49, 100568. [Google Scholar] [CrossRef]
- Sapnken, F.E.; Hamed, M.M.; Soldo, B.; Tamba, J.G. Modeling energy-efficient building loads using machine-learning algorithms for the design phase. Energy Build. 2023, 283, 112807. [Google Scholar] [CrossRef]
- Shen, Y.; Pan, Y. BIM-supported automatic energy performance analysis for green building design using explainable machine learning and multi-objective optimization. Appl. Energy 2023, 333, 120575. [Google Scholar] [CrossRef]
- Hemmerling, M.; Cocchiarella, L. Informed Architecture: Computational Strategies in Architectural Design; Cologne University of Applied Sciences; Springer International Publishing: Cologne, Germany, 2017. [Google Scholar] [CrossRef]
- Senske, N. Confronting the challenges of computational design instruction. In Proceedings of the 19th International Conference on Computer-Aided Architectural Design Research in Asia—Rethinking Comprehensive Design: Speculative Counterculture, CAADRIA 2014, Kyoto, Japan, 14–16 May 2014; The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA). University of North Carolina at Charlotte: Charlotte, NC, USA, 2014; pp. 821–830. [Google Scholar]
- Cao, X.; Dai, X.; Liu, J. Building energy-consumption status worldwide and the state-of-the-art technologies for zero-energy buildings during the past decade. Energy Build. 2016, 128, 198–213. [Google Scholar] [CrossRef]
- Pérez-Lombard, L.; Ortiz, J.; Pout, C. A review on buildings energy consumption information. Energy Build. 2008, 40, 394–398. [Google Scholar] [CrossRef]
- Gilani, H.A.; Hoseinzadeh, S.; Karimi, H.; Karimi, A.; Hassanzadeh, A.; Garcia, D.A. Performance analysis of integrated solar heat pump VRF system for the low energy building in Mediterranean island. Renew. Energy 2021, 174, 1006–1019. [Google Scholar] [CrossRef]
- McHugh, J.; Burns, P.J.; Hittle, D.C. The energy impact of daylighting. ASHRAE J. 1998, 40, 31–35. [Google Scholar]
- ASHRAE Terminology. Available online: https://xp20.ashrae.org/terminology/ (accessed on 28 July 2022).
- Nassif, N.; Kajl, S.; Sabourin, R. Optimization of HVAC control system strategy using two-objective genetic algorithm. HVAC&R Res. 2005, 11, 459–486. [Google Scholar] [CrossRef]
- Ding, X. A Brief Analysis of Energy Conservation Ways by Building Materials for Ecological Architecture. J. Power Energy Eng. 2020, 8, 13–22. [Google Scholar] [CrossRef]
- Alahmad, M.; Wheeler, P.; Schwer, A.; Tiller, D.; Wilkerson, A.; Eiden, J. Collaboration with industry to promote energy conservation and education. In Proceedings of the 2009 ASEE Annual Conference and Exposition, Austin, TX, USA, 14–17 June 2009; American Society for Engineering Education, University of Nebraska: Lincoln, NE, USA, 2009. [Google Scholar]
- Gao, G.; Li, J.; Wen, Y. DeepComfort: Energy-efficient thermal comfort control in buildings via reinforcement learning. IEEE Internet Things J. 2020, 7, 8472–8484. Available online: https://ieeexplore.ieee.org/abstract/document/9085925/ (accessed on 15 February 2023). [CrossRef]
- Gao, G.; Li, J.; Wen, Y. Energy-efficient thermal comfort control in smart buildings via deep reinforcement learning. arXiv 2019, arXiv:1901.04693. [Google Scholar]
- Luo, X.J.; Oyedele, L.O.; Ajayi, A.O.; Akinade, O.O. Comparative study of machine learning-based multi-objective prediction framework for multiple building energy loads. Sustain. Cities Soc. 2020, 61, 102283. Available online: https://www.sciencedirect.com/science/article/pii/S2210670720305047 (accessed on 15 February 2023). [CrossRef]
- Li, M.; Dai, L.; Hu, Y. Machine Learning for Harnessing Thermal Energy: From Materials Discovery to System Optimization. ACS Energy Lett. 2022, 7, 3204–3226. [Google Scholar] [CrossRef] [PubMed]
- Brna, P.; Burton, M. Modelling students collaborating while learning about energy. J. Comput. Assist. Learn. 1997, 13, 194–205. [Google Scholar] [CrossRef]
- Ardabili, S.; Abdolalizadeh, L.; Mako, C.; Torok, B.; Mosavi, A. Systematic review of deep learning and machine learning for building energy. arXiv 2022, arXiv:2202.12269. [Google Scholar] [CrossRef]
- Qin, Y.; Ke, J.; Wang, B.; Filaretov, G.F. Energy optimization for regional buildings based on distributed reinforcement learning. Sustain. Cities Soc. 2022, 78, 103625. [Google Scholar] [CrossRef]
- Olu-Ajayi, R.; Alaka, H.; Sulaimon, I.; Sunmola, F.; Ajayi, S. Building energy consumption prediction for residential buildings using deep learning and other machine learning techniques. J. Build. Eng. 2022, 45, 103406. [Google Scholar] [CrossRef]
- Ghoshchi, A.; Zahedi, R.; Pour, Z.M.; Ahmadi, A. Machine learning theory in building energy modeling and optimization: A bibliometric analysis. J. Mod. Green Energy 2022, 1, 4. Available online: https://www.researchgate.net/profile/Abolfazl-Ahmadi-4/publication/363300127_Machine_Learning_Theory_in_Building_Energy_Modeling_and_Optimization_A_Bibliometric_nalysis/links/63173ae7acd814437f0a0eca/Machine-Learning-Theory-in-Building-Energy-Modeling-and-Optimization-A-Bibliometric-Analysis.pdf (accessed on 15 February 2023).
Metric | Our VAE | Benchmark |
---|---|---|
MSE | 0.023 | 0.050 |
Design ID | SSIM with Reference Design | Diversity |
---|---|---|
1 | 0.85 | High |
2 | 0.82 | Medium |
3 | 0.87 | High |
Episode | Old Discount Factor | New Discount Factor |
---|---|---|
20 | 0.9 | 0.95 |
40 | 0.9 | 0.95 |
60 | 0.9 | 0.93 |
80 | 0.9 | 0.93 |
Episode | Old Reward | New Reward |
---|---|---|
10 | 76.55205 | 270.6377 |
30 | 50.50446 | 219.1624 |
50 | 20.25485 | 229.7900 |
70 | 71.71387 | 232.5131 |
90 | 76.80770 | 257.1876 |
Metric | RL | GA | SA |
---|---|---|---|
Convergence Rate | 1.20 | 1.00 | 1.10 |
Solution Quality | 0.95 | 0.85 | 0.90 |
Computational Efficiency | 0.85 | 0.80 | 0.75 |
Scalability | 0.90 | 0.85 | 0.80 |
Robustness | 0.92 | 0.88 | 0.85 |
Adaptability | 0.95 | 0.80 | 0.78 |
Metrics | RL | GA | SA |
---|---|---|---|
Convergence Rate | 1.20 | 1.00 | 1.10 |
Solution Quality | 0.95 | 0.85 | 0.90 |
Computational Efficiency | 0.80 | 0.70 | 0.60 |
Scalability | 0.90 | 0.70 | 0.75 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Karimi, H.; Adibhesami, M.A.; Hoseinzadeh, S.; Salehi, A.; Groppi, D.; Astiaso Garcia, D. Harnessing Deep Learning and Reinforcement Learning Synergy as a Form of Strategic Energy Optimization in Architectural Design: A Case Study in Famagusta, North Cyprus. Buildings 2024, 14, 1342. https://doi.org/10.3390/buildings14051342
Karimi H, Adibhesami MA, Hoseinzadeh S, Salehi A, Groppi D, Astiaso Garcia D. Harnessing Deep Learning and Reinforcement Learning Synergy as a Form of Strategic Energy Optimization in Architectural Design: A Case Study in Famagusta, North Cyprus. Buildings. 2024; 14(5):1342. https://doi.org/10.3390/buildings14051342
Chicago/Turabian StyleKarimi, Hirou, Mohammad Anvar Adibhesami, Siamak Hoseinzadeh, Ali Salehi, Daniele Groppi, and Davide Astiaso Garcia. 2024. "Harnessing Deep Learning and Reinforcement Learning Synergy as a Form of Strategic Energy Optimization in Architectural Design: A Case Study in Famagusta, North Cyprus" Buildings 14, no. 5: 1342. https://doi.org/10.3390/buildings14051342
APA StyleKarimi, H., Adibhesami, M. A., Hoseinzadeh, S., Salehi, A., Groppi, D., & Astiaso Garcia, D. (2024). Harnessing Deep Learning and Reinforcement Learning Synergy as a Form of Strategic Energy Optimization in Architectural Design: A Case Study in Famagusta, North Cyprus. Buildings, 14(5), 1342. https://doi.org/10.3390/buildings14051342