Trending machine learning models in <scp>cyber‐physical</scp> building environment: A survey

Hasan, Zahid; Roy, Nirmalya

doi:10.1002/widm.1422

Cited by 11 publications

(5 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dong et al [20] discuss the applicability of RL for modelling occupant behavior in buildings; such techniques could be applied in the environment of Figure 1, but the paper does not identify such applications. Reviews that investigated control or machine learning research broadly, with only a very brief treatment of RL articles, were also ignored [21][22][23]. The remainder of the review articles have been discussed in the introduction Section 1.…”

Section: Methodsmentioning

confidence: 99%

A Review of Reinforcement Learning Applications to Control of Heating, Ventilation and Air Conditioning Systems

2022

View full text Add to dashboard Cite

Reinforcement learning has emerged as a potentially disruptive technology for control and optimization of HVAC systems. A reinforcement learning agent takes actions, which can be direct HVAC actuator commands or setpoints for control loops in building automation systems. The actions are taken to optimize one or more targets, such as indoor air quality, energy consumption and energy cost. The agent receives feedback from the HVAC systems to quantify how well these targets have been achieved. The feedback is captured by a reward function designed by the developer of the reinforcement learning agent. A few reviews have focused on the reward aspect of reinforcement learning applications for HVAC. However, there is a lack of reviews that assess how the actions of the reinforcement learning agent have been formulated, and how this impacts the possibilities to achieve various optimization targets in single zone or multi-zone buildings. The aim of this review is to identify the action formulations in the literature and to assess how the choice of formulation impacts the level of abstraction at which the HVAC systems are considered. Our methodology involves a search string in the Web of Science database and a list of selection criteria applied to each article in the search results. For each selected article, a three-tier categorization of the selected articles has been performed. Firstly, the applicability of the approach to buildings with one or more zones is considered. Secondly, the articles are categorized by the type of action taken by the agent, such as a binary, discrete or continuous action. Thirdly, the articles are categorized by the aspects of the indoor environment being controlled, namely temperature, humidity or air quality. The main result of the review is this three-tier categorization that reveals the community’s emphasis on specific HVAC applications, as well as the readiness to interface the reinforcement learning solutions to HVAC systems. The article concludes with a discussion of trends in the field as well as challenges that require further research.

show abstract

Section: Methodsmentioning

confidence: 99%

A Review of Reinforcement Learning Applications to Control of Heating, Ventilation and Air Conditioning Systems

2022

View full text Add to dashboard Cite

show abstract

“…The first component in the equation (8) for angular displacement, which is ∫ 𝑥(𝑢 ′ ). 𝑓 −𝛽(𝑢−𝑢 ′ ) 𝑢 0…”

Section: 𝑄(𝑢mentioning

confidence: 99%

“…It becomes increasingly complex to validate these models against real-world observations, necessitating meticulous evaluation of metrics and criteria to guarantee the model's dependability [7]. As an added complication, incorporating parameters that control the system's reaction to uncertainty is necessary for resilience in the face of interruptions and unforeseen events [8]. As a way to tackle all of these different problems, dynamic modeling that captures the intricacies of nonlinear systems in cyber-physical environments needs to be iterative and interconnected [9], with an emphasis on accuracy, efficiency, and adaptability.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Modeling of Nonlinear Systems in Cyber-Physical Environments

Pandey

2023

cana

View full text Add to dashboard Cite

Complex behavior understanding and prediction relies on dynamic modeling of nonlinear systems in cyber-physical contexts. Critical for improving control systems, anticipating maintenance needs, and bolstering resilience, it permits accurate portrayal of complex interactions between cyber and physical components. Guaranteeing efficient and adaptable performance in networked ecosystems is made possible by this insight. Dynamic modeling of nonlinear systems (DM-NS) in cyber-physical settings has a number of challenges, such as the need to accurately depict complex interdependencies, accommodate changes in real-time, and reduce uncertainty. Advanced modeling techniques are required to capture the subtle behaviours and maintain the accuracy of the models while trying to balance the complicated interactions between physical and cyber components. A novel strategy is suggested to tackle these obstacles: Analysing Nonlinear Systems Cyber-Physical Modeling (ANSC-PM). By integrating complex mathematical models with adaptive learning algorithms, ANSC-PM is able to characterize nonlinear system behaviours, taking into account the dynamic interplay between cyber and physical components. To remain relevant as system dynamics change, the suggested method adjusts in real-time. Numerous disciplines find ANSC-PM useful, such as control system optimization, robotic predictive maintenance, and networked environment resilience enhancement. The effectiveness of ANSC-PM is determined by careful simulation analysis, which provides insight into its possible benefits in improving system performance, flexibility, and resilience in complex cyber-physical settings. Developing a thorough and flexible strategy that is adapted to the intricacies of cyber-physical systems, this research makes a substantial contribution to the progress of dynamic modeling approaches.

show abstract

“…Many types of research on applying ML to thermal comfort are available, among which a popular application is to use ML algorithms to predict personal thermal comfort [22][23][24] . In addition, Shan and Yang [25] combined ML technology and passive electroencephalogram measurement to explore the realtime thermal comfort state of classified occupants.…”

Section: Introductionmentioning

confidence: 99%

Predicted Mean Vote of Subway Car Environment Based on Machine Learning

Huang

et al. 2023

Big Data Min. Anal.

View full text Add to dashboard Cite

The thermal comfort of passengers in the carriage cannot be ignored. Thus, this research aims to establish a prediction model for the thermal comfort of the internal environment of a subway car and find the optimal input combination in establishing the prediction model of the predicted mean vote (PMV) index. Data-driven modeling utilizes data from experiments and questionnaires conducted in Nanjing Metro. Support vector machine (SVM), decision tree (DT), random forest (RF), and logistic regression (LR) were used to build four models. This research aims to select the most appropriate input variables for the predictive model. All possible combinations of 11 input variables were used to determine the most accurate model, with variable selection for each model comprising 102 350 iterations. In the PMV prediction, the RF model was the best when using the correlation coefficients square (R 2 / as the evaluation indicator (R 2 : 0.7680, mean squared error (MSE): 0.2868). The variables include clothing temperature (CT), convective heat transfer coefficient between the surface of the human body and the environment (CHTC), black bulb temperature (BBT), and thermal resistance of clothes (TROC). The RF model with MSE as the evaluation index also had the highest accuracy (R 2 : 0.7676, MSE: 0.2836). The variables include clothing surface area coefficient (CSAC), CT, BBT, and air velocity (AV). The results show that the RF model can efficiently predict the PMV of the subway car environment.

show abstract

Trending machine learning models in cyber‐physical building environment: A survey

Cited by 11 publications

References 64 publications

A Review of Reinforcement Learning Applications to Control of Heating, Ventilation and Air Conditioning Systems

A Review of Reinforcement Learning Applications to Control of Heating, Ventilation and Air Conditioning Systems

Dynamic Modeling of Nonlinear Systems in Cyber-Physical Environments

Predicted Mean Vote of Subway Car Environment Based on Machine Learning

Contact Info

Product

Resources

About