Prefabricated building construction in materialization phase as catalysts for hotel low-carbon transitions via hybrid computational visualization algorithms

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

Published: March 5, 2025

Language: Английский

---

Enhancing Intelligent HVAC optimization with graph attention networks and stacking ensemble learning, a recommender system approach in Shenzhen Qianhai Smart Community

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

Published: Feb. 11, 2025

This study details the design and implementation of an intelligent HVAC optimization system in Shenzhen Qianhai Smart Community, utilizing advanced machine learning methods like Graph Attention Networks (GATs) stacking ensemble learning. A comprehensive sensor network monitored temperature, humidity, occupancy, air quality, allowing for real-time data collection responsive control. Data preprocessing involved Z-score normalization feature engineering to improve model accuracy. The employed construction based on Pearson Correlation Coefficients, resulting quality embeddings GATs. combined Gradient Boosting Machines, Neural Networks, Random Forests, achieving a high Area Under Curve (AUC) 0.93. deployment led 15% reduction energy consumption increase occupant satisfaction. Comparative analysis shows strength GATs approach over existing systems. case validates methodology presents scalable smart urban settings. Future work will focus expanding more communities, integrating renewable energy, improving capabilities with reinforcement

Language: Английский

---

HVAC Control Based on Reinforcement Learning and Fuzzy Reasoning: Optimizing HVAC Supply Air Temperature, Flow Rate, and Velocity

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: 103, P. 112143 - 112143

Published: Feb. 18, 2025

Language: Английский

---

Reinforcement Learning for Optimizing Renewable Energy Utilization in Buildings: A Review on Applications and Innovations

Energies, Journal Year: 2025, Volume and Issue: 18(7), P. 1724 - 1724

Published: March 30, 2025

The integration of renewable energy systems into modern buildings is essential for enhancing efficiency, reducing carbon footprints, and advancing intelligent management. However, optimizing RES operations within building management introduces significant complexity, requiring advanced control strategies. One branch algorithms concerns reinforcement learning, a data-driven strategy capable dynamically managing sources other subsystems under uncertainty real-time constraints. current review systematically examines RL-based strategies applied in BEMS frameworks integrating technologies between 2015 2025, classifying them by algorithmic approach evaluating the role multi-agent hybrid methods improving adaptability occupant comfort. Following thorough explanation rigorous selection process—which targeted most impactful peer-reviewed publications from last decade, paper presents mathematical concepts RL RL, along with detailed summaries summary tables integrated works to facilitate quick reference key findings. For evaluation, outlines different attributes field considering following: methodologies RL; agent types; value-action networks; reward functions; baseline approaches; typologies. Grounded on findings presented evaluation section, offers structured synthesis emerging research trends future directions, identifying strengths limitations

Language: Английский

---

Dyna-PINN: Physics-informed Deep Dyna-Q Reinforcement Learning for Intelligent Control of Building Heating System in Low-Diversity Training Data Regimes

Energy and Buildings, Journal Year: 2024, Volume and Issue: 324, P. 114879 - 114879

Published: Oct. 9, 2024

Language: Английский

---

Advanced Graph Embedding for Intelligent HVAC Optimization: An Ensemble Learning-Based Recommender System in Shenzhen Qianhai Smart Community

Case Studies in Thermal Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 105888 - 105888

Published: Feb. 1, 2025

Language: Английский

---

Robust Deep Reinforcement Learning Based Optimization for Energy-Comfort Balanced Enhancement in Havc Systems

Published: Jan. 1, 2025

Language: Английский

---

A novel reinforcement learning method based on generative adversarial network for air conditioning and energy system control in residential buildings

Energy and Buildings, Journal Year: 2025, Volume and Issue: unknown, P. 115564 - 115564

Published: March 1, 2025

Language: Английский

---

Towards Sustainable Energy Use: Reinforcement Learning for Demand Response in Commercial Buildings

Energy and Buildings, Journal Year: 2025, Volume and Issue: unknown, P. 115721 - 115721

Published: April 1, 2025

Language: Английский

---

Transforming Hospital HVAC Design with BIM and Digital Twins: Addressing Real-Time Use Changes

Sustainability, Journal Year: 2025, Volume and Issue: 17(8), P. 3312 - 3312

Published: April 8, 2025

Traditional HVAC designs often struggle to respond promptly and accurately dynamic changes in complex environments like hospital usage. This paper introduces a novel framework that integrates Building Information Modeling (BIM), digital twin technology, practical medical processes transform design for construction. The ensured smarter (with reduction of 90% calculation time an improvement 38.20–53.24% respondence speed) cleaner environment after identifying calculating the rational layout functional areas optimizing intersecting flow lines. A key innovation this research was application Support Vector Machine (SVM) deep learning algorithm (Long Short-Term Memory) networks real-time pedestrian traffic prediction. implementation validated through multiple simulations applications including horizontal vertical negative pressure analyses three distinct departments. findings underline potential BIM twins optimize systems design, providing adaptive, data-driven solutions both routine operations emergency scenarios. offers scalable approach modernizing healthcare infrastructure, ensuring resilience efficiency diverse operational contexts.

Language: Английский

---