Very Short-Term Chiller Energy Consumption Prediction Based on Simplified Heterogeneous Graph Convolutional Network

Energy and Buildings, Journal Year: 2025, Volume and Issue: unknown, P. 115249 - 115249

Published: Jan. 1, 2025

Language: Английский

---

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

---

A Literature Review on Sustainable Buildings and Neighborhoods in terms of Daylight, Solar Energy and Human Factors

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 111989 - 111989

Published: Jan. 1, 2025

Language: Английский

---

Analyzing the impact of design factors on external walls in lightweight modular construction based on life-cycle analysis: energy, economic, and environmental trade-offs

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 112090 - 112090

Published: Feb. 1, 2025

Language: Английский

---

Predicting Energy Consumption of Residential Buildings Using Metaheuristic-optimized Artificial Neural Network Technique in Early Design Stage

Building and Environment, Journal Year: 2025, Volume and Issue: unknown, P. 112749 - 112749

Published: Feb. 1, 2025

Language: Английский

---

Integrating Machine Learning and Genetic Algorithms to Optimize Building Energy and Thermal Efficiency Under Historical and Future Climate Scenarios

Sustainability, Journal Year: 2024, Volume and Issue: 16(21), P. 9324 - 9324

Published: Oct. 27, 2024

As the global energy demand rises and climate change creates more challenges, optimizing performance of non-residential buildings becomes essential. Traditional simulation-based optimization methods often fall short due to computational inefficiency their time-consuming nature, limiting practical application. This study introduces a new framework that integrates Bayesian optimization, XGBoost algorithms, multi-objective genetic algorithms (GA) enhance building metrics—total (TE), indoor overheating degree (IOD), predicted percentage dissatisfied (PPD)—for historical (2020), mid-future (2050), future (2080) scenarios. The employs IOD as key indicator (KPI) optimize design operation. While traditional indices such mean vote (PMV) thermal sensation (TSV) are widely used, they fail capture individual comfort variations dynamic nature conditions. addresses these gaps by providing comprehensive objective measure discomfort, quantifying both frequency severity events. Alongside IOD, use intensity (EUI) index is used assess consumption per unit area, critical insights into efficiency. integration with EUI PPD enhances overall assessment performance, creating precise holistic framework. combination ensures efficiency, comfort, occupant well-being optimized in tandem. By addressing significant gap existing methodologies, current approach combines advanced techniques modern simulation tools EnergyPlus, resulting efficient accurate model performance. reduces time Utilizing SHAP (SHapley Additive Explanations) analysis, this research identified factors influence metrics. Specifically, window-to-wall ratio (WWR) impacts TE increasing through higher heat gain cooling demand. Outdoor temperature (Tout) has complex effect on depending seasonal conditions, while (Tin) minor impact TE. For PPD, Tout major negative factor, indicating improved natural ventilation can reduce whereas Tin larger open areas exacerbate it. Regarding WWR significantly affect internal gains, windows temperatures contributing increased reduced comfort. also positive its varying over time. demonstrates conditions evolve, effects become pronounced, highlighting need for effective management envelopes HVAC systems.

Language: Английский

---

Prediction and optimization of wastewater treatment process effluent chemical oxygen demand and energy consumption based on typical ensemble learning models

Bioresource Technology, Journal Year: 2024, Volume and Issue: 411, P. 131362 - 131362

Published: Aug. 27, 2024

Language: Английский

---

Machine learning-based assessment of thermal comfort for the elderly in warm environments: Combining the XGBoost algorithm and human body exergy analysis

International Journal of Thermal Sciences, Journal Year: 2024, Volume and Issue: 209, P. 109519 - 109519

Published: Nov. 9, 2024

Language: Английский

---

Research on typical occupant air-conditioning behavior of Changsha university dormitory buildings based on questionnaire surveys

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 111911 - 111911

Published: Jan. 1, 2025

Language: Английский

---

The impact of urban morphology on sunlight availability at urban and neighborhood scales: a systematic review

Sustainable Cities and Society, Journal Year: 2025, Volume and Issue: unknown, P. 106194 - 106194

Published: Feb. 1, 2025

Language: Английский

---