Stochastic optimization of energy systems configuration for nearly-zero energy buildings considering load uncertainties

Renewable Energy, Год журнала: 2025, Номер unknown, С. 122610 - 122610

Опубликована: Фев. 1, 2025

Язык: Английский

---

Residential Building Renovation Considering Energy, Carbon Emissions, and Cost: An Approach Integrating Machine Learning and Evolutionary Generation

Applied Sciences, Год журнала: 2025, Номер 15(4), С. 1830 - 1830

Опубликована: Фев. 11, 2025

As the dual carbon goals are being approached, there has been an increase in number of energy-saving renovation projects for existing buildings. However, building also brings about environmental impacts and incremental costs, which need to be addressed urgently. This study proposes integrated artificial intelligence framework facilitate multi-criteria energy decision making by combining a surrogate-based machine learning (ML) model evolutionary generative algorithm efficiently accurately identify optimal strategies. To enhance robustness methodology, comparative analysis four different ML models—light gradient boosting (LightGBM), fast random forest (FRF), multivariate linear regression (MVLR), neural network (ANN)—was conducted, with LightGBM demonstrating best performance terms accuracy, adaptability, efficiency. Using heuristic optimization entropy-weighted method, achieved average savings 56.62%, reduction emissions 51.60%, 24.27% decrease life-cycle costs. Compared local ultra-low-energy standards, solutions resulted 2.60% 15.85% demonstrates potential surrogate models, generation, methods retrofitting optimizations, offering novel, efficient, adaptable approach researchers practitioners seeking balance consumption, emissions, costs projects.

Язык: Английский

---

Determination of Optimum Passive Design Parameters for Industrial Buildings in Different Climate Zones Using an Energy Performance Optimization Model Based on an Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO)

Sustainability, Год журнала: 2025, Номер 17(6), С. 2357 - 2357

Опубликована: Март 7, 2025

With a focus on reducing building energy consumption, approaches that simultaneously optimize multiple passive design parameters in industrial buildings have received limited attention. Most existing studies tend to examine geometry or individual under scenarios, underscoring the potential benefits of adopting comprehensive, multiparameter approach integrates climate-responsive and sustainable strategies. This study bridges gap by systematically optimizing key parameters—building geometry, orientation, window-to-wall ratio (WWR), glazing type—to minimize loads enhance sustainability across five distinct climate zones. Fifteen different geometries with equal floor areas volumes were analyzed, considering fifteen types orientations varying 30° increments. DesignBuilder simulations yielded 16,900 results, due inherent challenges directly within simulation environments, data restructured reveal underlying relationships. An Energy Performance Optimization Model, based Particle Swarm (PSO) algorithm integrated an Artificial Neural Network (ANN), was developed identify optimal solutions tailored specific climatic conditions. The optimization results successfully determined combinations WWR, type reduce heating cooling loads, thereby promoting efficiency carbon emissions buildings. offers practical solution set provides architects actionable recommendations during early phase, establishing machine learning-based framework for achieving sustainable, energy-efficient, designs.

Язык: Английский

---

A TOPSIS-XGBoost evaluation method for train-track-bridge system travelling safety based on probability density evolution theory and machine learning

Structures, Год журнала: 2025, Номер 74, С. 108614 - 108614

Опубликована: Март 7, 2025

Язык: Английский

---

Optimizing office building performance in the HSWW region of China using simulation with Hyperopt CatBoost and SPEA2

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 10, 2025

At present, the evaluation of comprehensive performance urban office buildings remains an area significant discussion. This research aims to optimize building in hot summer and warm winter (HSWW) region, focusing on three key aspects: energy use intensity (EUI), useful daylight illuminance (UDI), percentage thermal comfort (PTC). The study employs Hyperparameter Optimization (Hyperopt)-Categorical Boosting (CatBoost)-Strength Pareto Evolutionary Algorithm 2 (SPEA2) multi-objective optimization method, generating 3,000 datasets via Latin Hypercube Sampling (LHS). Building parameters are simulated using Ladybug Honeybee models, consumption levels predicted CatBoost model. Subsequently, Hyperopt is used hyperparameters, SPEA2 algorithm applied identify optimal solutions. results indicate that Hyperopt-CatBoost demonstrates excellent predictive performance, with R² values 0.996, 0.954, 0.985 for consumption, lighting, comfort, respectively. By (MOO) design parameters, reduced by 29.61%, lighting efficiency improves 59.61%, increases 37.69% compared original design. provides a systematic plan data support energy-saving design, improving enhancing renovation villages.

Язык: Английский

---

Обоснование комбинации стандартных значений характеристик материалов слоев в составе ограждающей конструкции на основе квадратичной оптимизации

Vestnik MGSU, Год журнала: 2025, Номер 20(2), С. 193 - 214

Опубликована: Фев. 28, 2025

Язык: Русский

---

Enhancing Performance and Generalization in Dormitory Optimization Using Deep Reinforcement Learning with Embedded Surrogate Model

Building and Environment, Год журнала: 2025, Номер unknown, С. 112864 - 112864

Опубликована: Март 1, 2025

Язык: Английский

---

Design optimization of climate-responsive rural residences in solar rich areas considering sustainability and occupant comfort

Energy and Buildings, Год журнала: 2025, Номер 336, С. 115546 - 115546

Опубликована: Март 5, 2025

Язык: Английский

---

Application of machine learning and genetic algorithms in environmental performance assessment and optimization of traditional Huizhou houses in China

Frontiers of Architectural Research, Год журнала: 2025, Номер unknown

Опубликована: Март 1, 2025

Язык: Английский

---

Optimizing Urban Block Morphology for Energy Efficiency and Photovoltaic Utilization: Case Study of Wuhan

Buildings, Год журнала: 2025, Номер 15(7), С. 1118 - 1118

Опубликована: Март 29, 2025

With global carbon emissions continuing to rise and urban energy demands growing steadily, understanding how block morphology impacts building photovoltaic (PV) efficiency consumption has become crucial for sustainable development climate change mitigation. Current research primarily focuses on individual optimization, while block-scale coupling relationships between PV utilization remain underexplored. This study developed an integrated prediction optimization tool using deep learning physical simulation assess design parameters (building morphology, orientation, layout) affect performance. Through a methodology combining modeling, potential assessment, simulation, the quantified parameters, utilization, consumption. Results demonstrate that appropriate forms layouts reduce shadow obstruction, enhance system capability, simultaneously improve reducing The provides improved accuracy, enabling planners scientifically maximize generation minimize use. Extensive experimental validation demonstrates model analytical methods proposed in this will help break through limitations of research, making PV-energy analysis at scale possible, providing scientific basis achieving low-carbon transformation sector.

Язык: Английский

---