Optimal control of HVAC and window systems for natural ventilation through reinforcement learning

Chen, Yujiao; Norford, Leslie K.; Samuelson, Holly; Malkawi, Ali

doi:10.1016/j.enbuild.2018.03.051

Cited by 226 publications

(81 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors report a 15% energy saving improvement upon the base case. Chen et al applied Q learning to control both the HVAC and window systems [72]. The authors report energy savings of 13 and 23% and lowered discomfort ratings by 62 and 80% in the two buildings tested.…”

Section: Hvacmentioning

confidence: 99%

A review of reinforcement learning for autonomous building energy management

Mason

Grijalva

2019

Computers & Electrical Engineering

214

View full text Add to dashboard Cite

The area of building energy management has received a significant amount of interest in recent years. This area is concerned with combining advancements in sensor technologies, communications and advanced control algorithms to optimize energy utilization. Reinforcement learning is one of the most prominent machine learning algorithms used for control problems and has had many successful applications in the area of building energy management. This research gives a comprehensive review of the literature relating to the application of reinforcement learning to developing autonomous building energy management systems. The main direction for future research and challenges in reinforcement learning are also outlined.

show abstract

Section: Hvacmentioning

confidence: 99%

A review of reinforcement learning for autonomous building energy management

Mason

Grijalva

2019

Computers & Electrical Engineering

214

View full text Add to dashboard Cite

show abstract

“…This control method includes an air temperature prediction model and a PI controller. In [8], a reinforcement learning control strategy is presented using Q-learning in natural ventilation, which combines HVAC and window operations. The learning control function has been strengthened by comparing numerical simulations on the thermal construction model and comparing that with traditional horizontal controls.…”

Section: Related Workmentioning

confidence: 99%

“…In [9], a method for constructing a state-space model of a building is presented, which can be used to predict indoor temperature, humidity, and thermal comfort to control the indoor environment with MPC. With the rapid development of machine learning [10,11] and data mining technology [12,13], especially deep learning [14][15][16] and reinforcement learning [8,17], the HVAC of a building structure will become smarter based on historical data such as temperature, humidity, and energy consumption.…”

Section: Related Workmentioning

confidence: 99%

Modeling and Controlling of Temperature and Humidity in Building Heating, Ventilating, and Air Conditioning System Using Model Predictive Control

et al. 2019

View full text Add to dashboard Cite

Nowadays, by huge improvements in industrial control and the necessity of efficient energy consumption for buildings, unified managing systems are established to monitor and control mechanical equipment and energy usage. One of the main portions of the building management system (BMS) is the cooling and heating equipment called heating and ventilation and air-conditioning (HVAC). Based on temperature slow dynamic and presented uncertainty in modeling, a model predictive control (MPC) strategy to track both temperature and humidity is proposed in this study. The main goal of this study is to provide a framework to describe temperature and humidity elements required for dynamic modeling. Following that, by utilizing a predictive approach, a control strategy is obtained, which optimizes the tracking error of two interactional channel and performs the effort control by minimizing the optimization index. Other articles have mostly only had control over the temperature variable, but in our article, we tried to study the equations of temperature and humidity as well as their interference and according to the ASHRAE standard, both temperature and humidity controls must be accurate. The humidity was the novelty in our article. Simulation results proved the effectiveness of the proposed approach compared to the conventional proportional-integral controller. Evidently, the key idea behind the control objective is providing the comfort condition while consuming the least possible energy.

show abstract

“…New ANNs were created with neurons in the hidden layer in the proportions of 0.35, 0.50, 0.80, 0.95, 1.10, 1.25, 1.40, 1.55, 1.70, 1.85, and 2.00 times the value of the sum of the number input and outputs neurons. Since the model has 18 predictors and 1 response, the new ANNs were created with 7,10,15,18,21,24,27,29,32,35, and 38 neurons in the hidden layer. Each ANN was used to predict the annual HVAC cooling energy consumption of each case of the data and the performance indicators (R 2 , RMSE, NRMSE) were calculated.…”

Section: Refining Architecture Of Neural Networkmentioning

confidence: 99%

“…The statistical methods (also known as black box methods) are based on the deduction of a function that describes the behavior of a specific system from a relevant database. Additionally, these methods have been regarded as an alternative to the engineering methods, especially for the modeling of existing buildings [8], or during the early stage of architectural design [9], or in the control and operation of the buildings systems [10]. The main techniques used to create statistical models for estimate building energy consumption are multiple linear regression, artificial neural networks (ANN) and support vector machines (SVM).…”

Section: Introductionmentioning

confidence: 99%

Development of a Metamodel to Predict Cooling Energy Consumption of HVAC Systems in Office Buildings in Different Climates

Lopes

Lamberts

2018

Sustainability

View full text Add to dashboard Cite

The use of energy for space cooling is growing faster than any other end use in buildings, justifying the search for improvements in the energy efficiency of these systems. A simplified model to predict cooling energy consumption in Brazilian office buildings was developed. Artificial neural networks (ANNs) were trained from consumption data obtained by building simulation. As it is intended to be applicable to different climates, a new climate indicator also appropriate for hot and humid climates was proposed and validated. The Sobol sensibility analysis was performed to reduce the number of input factors and thus the number of cases to be simulated. The data was built with the simulation of 250,000 cases in Energyplus. Studies were conducted to define the sample size to be used for the ANN training, as well as to define the best ANN architecture. The developed metamodel was used to predict the consumption of Heating, Ventilating and Air Conditioning (HVAC) system of 66,300 new unseen cases. The results showed that the new proposed climate indicator was more accurate than the usual climate correlations, such as cooling degree hours. The developed metamodel presented good performance when predicting annual HVAC consumption of the cases used to obtain the model (R2 = 0.9858 and NRMSE = 0.068) and also of the unseen cases (R2 = 0.9789 and NRMSE = 0.064).

show abstract

Optimal control of HVAC and window systems for natural ventilation through reinforcement learning

Cited by 226 publications

References 41 publications

A review of reinforcement learning for autonomous building energy management

A review of reinforcement learning for autonomous building energy management

Modeling and Controlling of Temperature and Humidity in Building Heating, Ventilating, and Air Conditioning System Using Model Predictive Control

Development of a Metamodel to Predict Cooling Energy Consumption of HVAC Systems in Office Buildings in Different Climates

Contact Info

Product

Resources

About