A review of intelligent control techniques in HVAC systems

Mirinejad, Hossein; Welch, Karla Conn; Spicer, Lucas

doi:10.1109/energytech.2012.6304679

Cited by 49 publications

(35 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to lots of disturbances, time delays, contingencies and vagueness about thermal comfort, make finding a proper mathematical model for the system much more difficult [69]. According to the structure of the intelligent control methods, a model of the system is not required for designing the controller and it only depends on the human's thermal comfort feeling.…”

Section: Soft Control Category or Intelligent Control Categorymentioning

confidence: 99%

Review of Control Techniques for HVAC Systems—Nonlinearity Approaches Based on Fuzzy Cognitive Maps

et al. 2018

View full text Add to dashboard Cite

Heating, Ventilating, and Air Conditioning (HVAC) systems are the major energy-consuming devices in buildings. Nowadays, due to the high demand for HVAC system installation in buildings, designing an effective controller in order to decrease the energy consumption of the devices while meeting the thermal comfort demands in buildings are the most important goals of control designers. The purpose of this article is to investigate the different control methods for Heating, Ventilating, and Air Conditioning and Refrigeration (HVAC & R) systems. The advantages and disadvantages of each control method are discussed and finally the Fuzzy Cognitive Map (FCM) method is introduced as a new strategy for HVAC systems. The FCM method is an intelligent and advanced control technique to address the nonlinearity, Multiple-Input and Multiple-Output (MIMO), complexity and coupling effect features of the systems. The significance of this method and improvements by this method are compared with other methods.

show abstract

Section: Soft Control Category or Intelligent Control Categorymentioning

confidence: 99%

Review of Control Techniques for HVAC Systems—Nonlinearity Approaches Based on Fuzzy Cognitive Maps

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Therefore, modeling BEMS performance using traditional methods is difficult [18]- [20]. However, it has been shown that fuzzy modeling is suited to model the non-linearity and interrelationships between different data sources existing in BEMSs [15], [17]. Similarly, human occupant comfort is also highly subjective, and also relies on a large number of factors [14], [20].…”

Section: Linguistic Rule Based Behavior Extractionmentioning

confidence: 99%

“…Therefore, building HVAC control is a multi criteria optimization problem that tries to maintain human occupant comfort while increasing the energy efficiency [16], [17]. In order to achieve these goals, modern buildings use advanced control systems known as Building Energy Management Systems (BEMSs).…”

Section: Introduction (Heading 1)mentioning

confidence: 99%

Fuzzy linguistic knowledge based behavior extraction for building energy management systems

Wijayasekara

Manic

Rieger

2013

2013 6th International Symposium on Resilient Control Systems (ISRCS)

View full text Add to dashboard Cite

Abstract-Significant portion of world energy production is consumed by building Heating, Ventilation and Air Conditioning (HVAC) units. Thus along with occupant comfort, energy efficiency is also an important factor in HVAC control. Modern buildings use advanced Multiple Input Multiple Output (MIMO) control schemes to realize these goals. However, since the performance of HVAC units is dependent on many criteria including uncertainties in weather, number of occupants, and thermal state, the performance of current state of the art systems are sub-optimal. Furthermore, because of the large number of sensors in buildings, and the high frequency of data collection, large amount of information is available. Therefore, important behavior of buildings that compromise energy efficiency or occupant comfort is difficult to identify. This paper presents an easy to use and understandable framework for identifying such behavior. The presented framework uses human understandable knowledge-base to extract important behavior of buildings and present it to users via a graphical user interface. The presented framework was tested on a building in the Pacific Northwest and was shown to be able to identify important behavior that relates to energy efficiency and occupant comfort.

show abstract

“…These classical methods have been investigated extensively in HVAC lower-loop controls [4][5][6], such as room temperature control [7][8][9] and supply air temperature control [10][11][12]. Despite their popularity, these classical methods do not perform optimally.…”

Section: Motivation and Backgroundmentioning

confidence: 99%

“…The REINFORCE [38] policy gradient provides an unbiased estimate of the gradient of the policy with respect to the objective function J(θ) given in Equation (6).…”

Section: Policy Gradientmentioning

confidence: 99%

A Long-Short Term Memory Recurrent Neural Network Based Reinforcement Learning Controller for Office Heating Ventilation and Air Conditioning Systems

2017

View full text Add to dashboard Cite

Energy optimization in buildings by controlling the Heating Ventilation and Air Conditioning (HVAC) system is being researched extensively. In this paper, a model-free actor-critic Reinforcement Learning (RL) controller is designed using a variant of artificial recurrent neural networks called Long-Short-Term Memory (LSTM) networks. Optimization of thermal comfort alongside energy consumption is the goal in tuning this RL controller. The test platform, our office space, is designed using SketchUp. Using OpenStudio, the HVAC system is installed in the office. The control schemes (ideal thermal comfort, a traditional control and the RL control) are implemented in MATLAB. Using the Building Control Virtual Test Bed (BCVTB), the control of the thermostat schedule during each sample time is implemented for the office in EnergyPlus alongside local weather data. Results from training and validation indicate that the RL controller improves thermal comfort by an average of 15% and energy efficiency by an average of 2.5% as compared to other strategies mentioned.

show abstract

A review of intelligent control techniques in HVAC systems

Cited by 49 publications

References 35 publications

Review of Control Techniques for HVAC Systems—Nonlinearity Approaches Based on Fuzzy Cognitive Maps

Review of Control Techniques for HVAC Systems—Nonlinearity Approaches Based on Fuzzy Cognitive Maps

Fuzzy linguistic knowledge based behavior extraction for building energy management systems

A Long-Short Term Memory Recurrent Neural Network Based Reinforcement Learning Controller for Office Heating Ventilation and Air Conditioning Systems

Contact Info

Product

Resources

About