Successful application of predictive information in deep reinforcement learning control: A case study based on an office building HVAC system

Energy, Journal Year: 2024, Volume and Issue: 291, P. 130344 - 130344

Published: Jan. 15, 2024

Language: Английский

---

Reinforcement learning for HVAC control in intelligent buildings: A technical and conceptual review

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 95, P. 110085 - 110085

Published: July 3, 2024

niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français étrangers, laboratoires publics privés.

---

Utilizing the Kolmogorov-Arnold Networks for Chiller Energy Consumption Prediction in Commercial Building

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 96, P. 110475 - 110475

Published: Aug. 15, 2024

Language: Английский

---

Chiller energy prediction in commercial building: A metaheuristic-Enhanced deep learning approach

Energy, Journal Year: 2024, Volume and Issue: 297, P. 131159 - 131159

Published: April 4, 2024

Language: Английский

---

Efficient management of HVAC systems through coordinated operation of parallel chiller units: An economic predictive control approach

Energy and Buildings, Journal Year: 2024, Volume and Issue: 304, P. 113879 - 113879

Published: Jan. 3, 2024

In developed countries, air conditioning systems have become major contributors to energy consumption in buildings. Cooling installations made up of independent chiller units connected parallel pose a challenge finding the most energy-efficient management strategy. This article proposes novel economic model predictive control strategy optimize operation multiple-chiller HVAC according an cost comprising as well thermal comfort index. Provided that gradient function can be calculated or estimated, proposed controller only entails solution single quadratic programming (QP) problem at each sampling period, reducing computational requirements and thus facilitating deployment on commercial embedded platforms. The improves performance. As our numerical analysis shows, optimal sequencing is achieved for case dual-chiller plants. Moreover, adapts possible variations criteria, enabling system respond changes electricity price user preferences. A realistic study, using high fidelity building simulated TRNSYS, demonstrates effectiveness methodology. particular, more efficient than state-of-the-art QP-based controllers achieving reduction 5.19%, which line with targeted 7.9% by 2030 EU Green Deal's 'Fit 55' package.

Language: Английский

---

A global optimization method for data center air conditioning water systems based on predictive optimization control

Energy, Journal Year: 2024, Volume and Issue: 295, P. 130925 - 130925

Published: March 21, 2024

Language: Английский

---

Enhancing Air Conditioning System Efficiency Through Load Prediction and Deep Reinforcement Learning: A Case Study of Ground Source Heat Pumps

Energies, Journal Year: 2025, Volume and Issue: 18(1), P. 199 - 199

Published: Jan. 5, 2025

This study proposes a control method that integrates deep reinforcement learning with load forecasting, to enhance the energy efficiency of ground source heat pump systems. Eight machine models are first developed predict future cooling loads, and optimal one is then incorporated into learning. Through interaction environment, strategy identified using Q-network optimize supply water temperature from source, allowing for savings. The obtained results show XGBoost model significantly outperforms other in terms prediction accuracy, reaching coefficient determination 0.982, mean absolute percentage error 6.621%, variation root square 10.612%. Moreover, savings achieved through forecasting-based greater than those traditional constant methods by 10%. Additionally, without shortening interval, improved 0.38% compared do not use predictive information. approach requires only continuous between agent which makes it an effective alternative scenarios where sensor equipment data present. It provides smart adaptive optimization solution heating, ventilation, air conditioning systems buildings.

Language: Английский

---

A novel energy saving framework based on optimal chiller loading and parameter optimization for HVAC: a case study for subway station

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 111887 - 111887

Published: Jan. 1, 2025

Language: Английский

---

Optimization Control Strategies and Evaluation Metrics of Cooling Systems in Data Centers: A Review

Sustainability, Journal Year: 2024, Volume and Issue: 16(16), P. 7222 - 7222

Published: Aug. 22, 2024

In the age of digitalization and big data, cooling systems in data centers are vital for maintaining equipment efficiency environmental sustainability. Although many studies have focused on classification optimization center systems, systematic reviews using bibliometric methods relatively scarce. This review uses analysis to explore classifications, control optimizations, energy metrics aiming address research gaps. Using CiteSpace databases like Scopus, Web Science, IEEE, this study maps field’s historical development current trends. The findings indicate that, firstly, strategies, focal points. Secondly, assesses applicability air-cooled liquid-cooled different operational environments, providing practical guidance selection. Then, air demonstrates that optimizing design static pressure chamber baffles has significantly improved airflow uniformity. Finally, article advocates expanding use artificial intelligence machine learning automate collection analysis, it also calls global standardization metrics. offers new perspectives design, optimization, performance evaluation systems.

Language: Английский

---

Prospects and Challenges of Reinforcement Learning- Based HVAC Control

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 111080 - 111080

Published: Oct. 1, 2024

Language: Английский

---