Recent Advances in Machine Learning for Building Envelopes: From Prediction to Optimization

Published: Jan. 1, 2025

Nowadays, advanced building envelopes not only need to meet traditional design requirements but also address emerging demands, such as achieving low-carbon transition of buildings and mitigating the urban heat island (UHI) effect. Given intricacy indoor conditions complexity variables, approaches can hardly keep pace with evolving demands. Therefore, integrating Artificial Intelligence (AI) into envelope is trending in recent years. This paper provides a holistic review research on machine learning (ML) design. Popular ML algorithms, data input requirements, output generation are first elucidated, aiming shed light selection appropriate algorithms for specific datasets achieve optimal outcomes. ML-involved studies related types (e.g., building-integrated photovoltaic (BIPV), green roofs, PCM-integrated walls, glazing systems, etc.) discussed. The further highlights capabilities AI technologies predicting parameters material properties, environmental impact) optimizing criteria minimizing energy consumption), from micro-scope (i.e., microenvironment) macro-scope impact heat). work anticipated yield valuable insights promoting AI-driven solutions tackle both conventional challenges sustainable development.

Language: Английский

---

An integrated artificial intelligence-driven approach to multi-criteria optimization of building energy efficiency and occupants' comfort: A case study

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 111944 - 111944

Published: Feb. 1, 2025

Language: Английский

---

Artificial intelligence models development for profitability factor prediction in concentrated solar power with dual backup systems

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 11, 2025

Hybrid concentrating solar power (CSP) plants with thermal energy storage (TES) and biomass backup enhance reliability efficiency. TES provides during low sunlight or high demand, while continuous heat generation when is depleted. Therefore, the current study developed three tree optimizers (fine, medium, coarse) to predict profitability factor (PF) for hybridized CSP combined technologies. The PF was predicted based on different operating cases such as parabolic trough-base case-no (PT-BC-NB), trough-operation strategy 1-medium (PT-OS1-MB), 2-full (PT-OS2-FB). were evaluated using five capacities (0–20 5 h step). input variables included direct capital costs (power island, field, transfer fluid, TES, boiler) other parameters (biomass cost annual escalation rate, hourly electricity price peaks troughs daily prices) utilized variables. Tree effectively PF, OS2-No configurations achieving highest (mean PF: 0.009 USD/kWh) nearing grid parity (0.000–0.007 a 10.6% probability. These have 95% probability of additional revenues between 0.095 0.114 USD/kWh. Increasing capacity from 0 20 reduced by 52% average but enhanced OS1's firm supply OS2's uncertainty, saving up 55% consumption (109 kt/year).

Language: Английский

---

Informing building retrofits at low computational costs: a multi-objective optimisation using machine learning surrogates of building performance simulation models

Journal of Building Performance Simulation, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 17

Published: July 30, 2024

Machine learning (ML) algorithms are increasingly used as surrogates for building performance simulation (BPS) models to leverage their energy predictive capabilities while reducing computational costs. In parallel, researchers developing optimisation methods inform design and retrofit strategies but rarely employ ML-based BPS this purpose. This study proposes a coupled modelling approach that leverages the of surrogate multi-objective holistic operation retrofits at low The proposed methodology is demonstrated using an archetypal office in Ottawa, Canada. developed achieved competitive accuracies (adjusted R2: 0.90–0.99), identifying total peak saving measures with up 34% improvement occupant thermal comfort speeds 1266 times faster than traditional BPS-based approach. Results offer promising workflow applications requiring extensive computations scenario analyses, such net-zero retrofits.

Language: Английский

---

An Ensemble Model for the Energy Consumption Prediction of Residential Buildings

Energy, Journal Year: 2024, Volume and Issue: unknown, P. 134255 - 134255

Published: Dec. 1, 2024

Language: Английский

---

Artificial intelligence approaches in predicting the mechanical properties of natural fiber-reinforced concrete: A comprehensive review

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 153, P. 110933 - 110933

Published: April 22, 2025

Language: Английский

---

Interpretable building energy performance prediction using xgboost quantile regression

Energy and Buildings, Journal Year: 2025, Volume and Issue: unknown, P. 115815 - 115815

Published: May 1, 2025

Language: Английский

---

Digitization impact on future housing building industry mode

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 96, P. 110202 - 110202

Published: Aug. 8, 2024

Language: Английский

---

Intelligent Design of Ecological Furniture in Risk Areas based on Artificial Simulation

Archives of Surgery and Clinical Research, Journal Year: 2024, Volume and Issue: 8(2), P. 062 - 068

Published: Aug. 5, 2024

The study is based on the characterization of different AI models applied in public furniture design analyzing conditions risk, materiality, and integration variables two generative modeling algorithms. As risky since they contain flood-prone areas, low vegetation coverage, underdevelopment infrastructure; therefore, these characterizations are tested through artificial simulation. experimental method laboratory tests various material components their structuring 3D simulators to check resistance risk scenarios. case one most populated areas informal settlement area Northwest Guayaquil, such as Coop, analyzed. Sergio Toral focal point for on-site testing. It concluded that generation a planned scheme ecological with materials responds more effectively territory simulation an advantage can be obtained terms execution time results, thus demonstrating intelligence ideal tool. To generate proposals diverse, innovative, functional environment, but it generates minimum level error specific designs model_01 0.1% 3% high model_02 increasing from 20% 70%. future line research, proposed simulated system all new settlements Guayaquil establish points implementation furniture.

Language: Английский

---

The Role of AI in Sustainable Business Practices and Reporting in Emerging Economies

Advances in business information systems and analytics book series, Journal Year: 2024, Volume and Issue: unknown, P. 310 - 340

Published: Aug. 19, 2024

This study investigates artificial intelligence and how it can be leveraged upon in order to re-engineer existing business models, towards achieving sustainable development goals. The analysed factors necessary ensure an assisted model innovation provide a framework for businesses emerging economies. A systematic literature review of is undertaken using the Scopus database. Filtering processes are employed arrive at 94 journal articles. adopts PRISMA protocol allow comprehensive disclosure process. process resulted thematic areas which provided that guided study. Case studies were also undertaken, qualitative manner capture perceptions experiences as well problems associated with leveraging innovation. research output includes recommendation policy implication.

Language: Английский

---