Energy-efficient heating control for nearly zero energy residential buildings with deep reinforcement learning

Qin, Haosen; Yu, Zhen; Li, Tailu; Liu, Xueliang; Li, Li

doi:10.1016/j.energy.2022.126209

Cited by 18 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…(4) This study considered seven commonly used ML algorithms for predicting building energy consumption and indoor comfort. With the continuous development of artificial intelligence technologies, boosting techniques such as XGBoost and Catboost have been applied to the prediction of energy consumption [67,68]. In this study, XGBoost, Catboost, and LightGBM were used to establish predictive models for RFCFC systems.…”

Section: Discussionmentioning

confidence: 99%

A Comparative Analysis of Machine Learning Algorithms in Predicting the Performance of a Combined Radiant Floor and Fan Coil Cooling System

Lu,

Cui,

Gao

et al. 2024

Buildings

View full text Add to dashboard Cite

Machine learning algorithms have proven to be practical in a wide range of applications. Many studies have been conducted on the operational energy consumption and thermal comfort of radiant floor systems. This paper conducts a case study in a self-designed experimental setup that combines radiant floor and fan coil cooling (RFCFC) and develops a data monitoring system as a source of historical operational data. Seven machine learning algorithms (extreme learning machine (ELM), convolutional neural network (CNN), genetic algorithm-back propagation (GA-BP), radial basis function (RBF), random forest (RF), support vector machine (SVM), and long short-term memory (LSTM)) were employed to predict the behavior of the RFCFC system. Corresponding prediction models were then developed to evaluate operative temperature (Top) and energy consumption (Eh). The performance of the model was evaluated using five error metrics. The obtained results showed that the RF model had very high performance in predicting Top and Eh, with high correlation coefficients (>0.9915) and low error metrics. Compared with other models, it also demonstrated high accuracy in Eh prediction, yielding maximum reductions of 68.1, 82.4, and 43.2% in the mean absolute percentage error (MAPE), mean squared error (MSE), and mean absolute error (MAE), respectively. A sensitivity ranking algorithm analysis was also conducted. The obtained results demonstrated the importance of adjusting parameters, such as the radiant floor supply water temperature, to enhance the indoor comfort. This study provides a novel and effective method for evaluating the energy efficiency and thermal comfort of radiant cooling systems. It also provides insights for optimizing the efficiency and thermal comfort of RFCFC systems, and lays a theoretical foundation for future studies integrating machine learning algorithms in this field.

show abstract

Section: Discussionmentioning

confidence: 99%

A Comparative Analysis of Machine Learning Algorithms in Predicting the Performance of a Combined Radiant Floor and Fan Coil Cooling System

Lu,

Cui,

Gao

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

“…Fan et al [122] developed a building energy performance model based on interpretable machine learning, which helps to understand the reasoning mechanism of the predictive model and balance model complexity and interpretability through the evaluation of "trust". Haosen Qin et al [174] used reinforcement learning and deep Qlearning to optimize the control of HVAC systems, improving energy efficiency and thermal comfort. Dian Zhuang's team [186] presented a data-driven predictive control approach that uses time-series prediction and reinforcement learning to optimize HVAC operations in IoT smart buildings, resulting in energy savings and improved thermal comfort.…”

Section: Algorithms and Deep Learning For Energy Efficiencymentioning

confidence: 99%

Exploring the Benefits and Limitations of Digital Twin Technology in Building Energy

Tahmasebinia,

Lin,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Buildings consume a significant amount of energy throughout their lifecycle; Thus, sustainable energy management is crucial for all buildings, and controlling energy consumption has become increasingly important for achieving sustainable construction. Digital twin (DT) technology, which lies at the core of Industry 4.0, has gained widespread adoption in various fields, including building energy analysis. With the ability to monitor, optimize, and predict building energy consumption in real time. DT technology has enabled sustainable building energy management and cost reduction. This paper provides a comprehensive review of the development and application of DT technology in building energy. Specifically, it discusses the background of building information modeling (BIM) and DT technology and their application in energy optimization in buildings. Additionally, this article reviews the application of DT technology in building energy management, indoor environmental monitoring, and building energy efficiency evaluation. It also examines the benefits and challenges of implementing DT technology in building energy analysis and highlights recent case studies. Furthermore, this review emphasizes emerging trends and opportunities for future research, including integrating machine learning techniques with DT technology. The use of DT technology in the energy sector is gaining momentum as efforts to optimize energy efficiency and reduce carbon emissions continue. The advancement of building energy analysis and machine learning technologies is expected to enhance prediction accuracy, optimize energy efficiency, and improve management processes. These advancements have become the focal point of current literature and have the potential to facilitate the transition to clean energy, ultimately achieving sustainable development goals.

show abstract

“…As researched in many scientific publications, HVAC systems can be a versatile tool to effectively reduce the energy demand of buildings using renewable energy. Continuous improvement and application of this technology is therefore of significant importance to the global environment [15]. The adopted research method is based on the use of the above technology in the designed layout of residential buildings.…”

Section: Fch Hvac Technologymentioning

confidence: 99%

“…The current situation in the energy market creates opportunities for low-carbon energy to play an important role in building modern and environmentally friendly economies [15,16]. The enormous power of energy stored in groundwater and the independence of this energy from external factors, as well as a very low carbon footprint, make these technologies the undisputed leader in CO 2 reduction in Poland and the world [17].…”

Section: Introductionmentioning

confidence: 99%

FCH HVAC Honeycomb Ring Network—Transition from Traditional Power Supply Systems in Existing and Revitalized Areas

Wrana,

Struzik,

Jaromin-Gleń

et al. 2023

Energies

View full text Add to dashboard Cite

This paper discusses the application of a new honeycomb FCH HVAC (Free Cooling and Heating System, Heating, Ventilation, and Air Conditioning) ring network technology that reduces the primary energy consumption in existing infrastructure. The aim of the research is to evaluate the cost-environmental viability of upgrading the technical infrastructure and moving from traditional to newly designed green systems built on renewable energy sources. The results show that the energy capacity stored in groundwater is equivalent to 65% of building demand, resulting in a 60% reduction in CO2 emissions compared to a traditional HVAC system. The solution reduces the consumption of natural resources by using renewable energy sources with horizontal heat exchangers arranged in independent ring configurations.

show abstract

Energy-efficient heating control for nearly zero energy residential buildings with deep reinforcement learning

Cited by 18 publications

References 34 publications

A Comparative Analysis of Machine Learning Algorithms in Predicting the Performance of a Combined Radiant Floor and Fan Coil Cooling System

A Comparative Analysis of Machine Learning Algorithms in Predicting the Performance of a Combined Radiant Floor and Fan Coil Cooling System

Exploring the Benefits and Limitations of Digital Twin Technology in Building Energy

FCH HVAC Honeycomb Ring Network—Transition from Traditional Power Supply Systems in Existing and Revitalized Areas

Contact Info

Product

Resources

About