Control Of HVAC Systems Research Articles

Modeling and multiobjective optimization of indoor airborne disease transmission risk and associated energy consumption for building HVAC systems

The COVID-19 pandemic has renewed interest in assessing how the operation of HVAC systems influences the risk of airborne disease transmission in buildings. Various processes, such as ventilation and filtration, have been shown to reduce the probability of disease spread by removing or deactivating exhaled aerosols that potentially contain infectious material. However, such qualitative recommendations fail to specify how much of these or other disinfection techniques are needed to achieve acceptable risk levels in a particular space. An additional complication is that application of these techniques inevitably increases energy costs, the magnitude of which can vary significantly based on local weather. Moreover, the operational flexibility available to the HVAC system may be inherently limited by equipment capacities and occupant comfort requirements. Given this knowledge gap, we propose a set of dynamical models that can be used to estimate airborne transmission risk and energy consumption for building HVAC systems based on controller setpoints and a forecast of weather conditions. By combining physics-based material balances with phenomenological models of the HVAC control system, it is possible to predict time-varying airflows and other HVAC variables, which are then used to calculate key metrics. Through a variety of examples involving real and simulated commercial buildings, we show that our models can be used for monitoring purposes by applying them directly to transient building data as operated, or they may be embedded within a multi-objective optimization framework to evaluate the tradeoff between infection risk and energy consumption. By combining these applications, building managers can determine which spaces are in need of infection risk reduction and how to provide that reduction at the lowest energy cost. The key finding is that both the baseline infection risk and the most energy-efficient disinfection strategy can vary significantly from space to space and depend sensitively on the weather, thus underscoring the importance of the quantitative predictions provided by the models.

Controlling distributed energy resources via deep reinforcement learning for load flexibility and energy efficiency

Behind-the-meter distributed energy resources (DERs), including building solar photovoltaic (PV) technology and electric battery storage, are increasingly being considered as solutions to support carbon reduction goals and increase grid reliability and resiliency. However, dynamic control of these resources in concert with traditional building loads, to effect efficiency and demand flexibility, is not yet commonplace in commercial control products. Traditional rule-based control algorithms do not offer integrated closed-loop control to optimize across systems, and most often, PV and battery systems are operated for energy arbitrage and demand charge management, and not for the provision of grid services. More advanced control approaches, such as MPC control have not been widely adopted in industry because they require significant expertise to develop and deploy. Recent advances in deep reinforcement learning (DRL) offer a promising option to optimize the operation of DER systems and building loads with reduced setup effort. However, there are limited studies that evaluate the efficacy of these methods to control multiple building subsystems simultaneously. Additionally, most of the research has been conducted in simulated environments as opposed to real buildings. This paper proposes a DRL approach that uses a deep deterministic policy gradient algorithm for integrated control of HVAC and electric battery storage systems in the presence of on-site PV generation. The DRL algorithm, trained on synthetic data, was deployed in a physical test building and evaluated against a baseline that uses the current best-in-class rule-based control strategies. Performance in delivering energy efficiency, load shift, and load shed was tested using price-based signals. The results showed that the DRL-based controller can produce cost savings of up to 39.6% as compared to the baseline controller, while maintaining similar thermal comfort in the building. The project team has also integrated the simulation components developed during this work as an OpenAIGym environment and made it publicly available so that prospective DRL researchers can leverage this environment to evaluate alternate DRL algorithms.

Development of a personalized thermal comfort driven controller for HVAC systems

Increasing thermal comfort and reducing energy consumption are two main objectives of advanced HVAC control systems. In this study, a thermal comfort driven control (PTC-DC) algorithm was developed to improve HVAC control systems with no need of retrofitting HVAC system components. A case building located in Izmir Institute of Technology Campus-Izmir-Turkey was selected to test the developed system. First, wireless sensors were installed to the building and a mobile application was developed to monitor/collect temperature, relative humidity and thermal comfort data of an occupant. Then, the PTC-DC algorithm was developed to meet the highest occupant thermal comfort as well as saving energy. The prototypes of the controller were tested on the case building from July 3rd, 2017 to November 1st, 2018 and compared with a conventional PID controller. The results showed that the developed control algorithm and conventional controller satisfy neutral thermal comfort for 92 % and 6 % of total measurement days, respectively. From energy consumption point of view, the PTC-DC decreased energy consumption by 13.2 % compared to the conventional controller. Consequently, the PTC-DC differs from other works in the literature that the prototype of PTC-DC can be easily deployed in real environments. Moreover, the PTC-DC is low-cost and user-friendly.

Model Predictive Control-Based Hierarchical Control of a Multi-Zone Commercial HVAC System

Abstract This paper presents a novel architecture for model predictive control (MPC)-based indoor climate control of multi-zone buildings to provide energy efficiency. Unlike prior works, we do not assume the availability of a high-resolution multi-zone building model, which is challenging to obtain. Instead, the architecture uses a low-resolution model of the building that is divided into a small number of “meta-zones” that can be easily identified using existing data-driven modeling techniques. The proposed architecture is hierarchical. At the higher level, an MPC controller uses the low-resolution model to make decisions for the air handling unit (AHU) and the meta-zones. Since the meta-zones are fictitious, a lower level controller converts the high-level MPC decisions into commands for the individual zones by solving a projection problem that strikes a trade-off between two potentially conflicting goals: the AHU-level decisions made by the MPC are respected while the climate of the individual zones is maintained within the comfort bounds. The performance of the proposed controller is assessed via simulations in a high-fidelity simulation testbed and compared to that of a rule-based controller that is used in practice. Simulations in multiple weather conditions show the effectiveness of the proposed controller in terms of energy savings, climate control, and computational tractability.

Reinforcement learning of occupant behavior model for cross-building transfer learning to various HVAC control systems

Occupant behavior plays an important role in the evaluation of building performance. However, many contextual factors, such as occupancy, mechanical system and interior design, have a significant impact on occupant behavior. Most previous studies have built data-driven behavior models, which have limited scalability and generalization capability. Our investigation built a policy-based reinforcement learning (RL) model for the behavior of adjusting the thermostat and clothing level. Occupant behavior was modelled as a Markov decision process (MDP). The action and state space in the MDP contained occupant behavior and various impact parameters. The goal of the occupant behavior was a more comfortable environment, and we modelled the reward for the adjustment action as the absolute difference in the thermal sensation vote (TSV) before and after the action. We used Q-learning to train the RL model in MATLAB and validated the model with collected data. After training, the model predicted the behavior of adjusting the thermostat set point with R2 from 0.75 to 0.8, and the mean absolute error (MAE) was less than 1.1 °C (2 °F) in an office building. This study also transferred the behavior knowledge of the RL model to other office buildings with different HVAC control systems. The transfer learning model predicted the occupant behavior with R2 from 0.73 to 0.8, and the MAE was less than 1.1 °C (2 °F) most of the time. Going from office buildings to residential buildings, the transfer learning model also had an R2 over 0.6. Therefore, the RL model combined with transfer learning was able to predict the building occupant behavior accurately with good scalability, and without the need for data collection.

Application Research of Intelligent Control Algorithm in Air Conditioning System

In order to reduce the energy consumption of HVAC system, we analyzed and compared modern intelligent control algorithm applied to HVAC control system, introduced the basic principles of fuzzy control, neural network and genetic algorithm, and analyzed the applicability of intelligent algorithm in HVAC system with engineering examples.

Feasibility study to detect occupant thermal sensation using a low-cost thermal camera for indoor environments in Indonesia

This paper concerns the feasibility study of 7 classes of thermal sensation detection in Indonesia's indoor environment using a low-cost thermal camera through face skin temperature. This study is required as an initial step to build a thermal comfort sensor system of HVAC control systems to produce a comfortable indoor environment with minimum and efficient energy use. The feasibility study was started by studying the thermoregulation system of respondents in Indonesia through measuring their body and facial skin temperatures under heating and cooling conditions, including their relationship with thermal sensations. The facial skin temperature variable, which is covered by four measurement points, namely forehead, nose, cheeks, and chin, represents the MST variable by the coefficient of determination of 0.54. The thermal sensation detection algorithm based on Artificial Neural Network (ANN) is 35.7% of accuracy. The thermal sensation questionnaire with 7 class categories is unsuitable for Indonesian respondents, and the number of the category classes predicted too much compared to the number of inputs. The detection algorithm has better accuracy with a smaller number of classes, namely 52.2% and 68.70% for the 5 and 3 classes of thermal sensation. Practical application: The air conditioning buildings system is possible to influence a thermal environmental control system to meet the occupants' thermal comfort level requirement in an indoor environment if the system is equipped with a sensor that can detect the occupants' thermal sensations. The thermal camera can be used as a non-contact sensor, detecting the occupant’s thermal sensation by reading the occupant's face skin temperature in an indoor environment.

Online Implementation of a Soft Actor-Critic Agent to Enhance Indoor Temperature Control and Energy Efficiency in Buildings

Recently, a growing interest has been observed in HVAC control systems based on Artificial Intelligence, to improve comfort conditions while avoiding unnecessary energy consumption. In this work, a model-free algorithm belonging to the Deep Reinforcement Learning (DRL) class, Soft Actor-Critic, was implemented to control the supply water temperature to radiant terminal units of a heating system serving an office building. The controller was trained online, and a preliminary sensitivity analysis on hyperparameters was performed to assess their influence on the agent performance. The DRL agent with the best performance was compared to a rule-based controller assumed as a baseline during a three-month heating season. The DRL controller outperformed the baseline after two weeks of deployment, with an overall performance improvement related to control of indoor temperature conditions. Moreover, the adaptability of the DRL agent was tested for various control scenarios, simulating changes of external weather conditions, indoor temperature setpoint, building envelope features and occupancy patterns. The agent dynamically deployed, despite a slight increase in energy consumption, led to an improvement of indoor temperature control, reducing the cumulative sum of temperature violations on average for all scenarios by 75% and 48% compared to the baseline and statically deployed agent respectively.

Economic Model Predictive Control of HVAC System in Electric Vehicles

Economic Model Predictive Control of HVAC System in Electric Vehicles

Integrating Renewable Energy Sources with HVAC Control Systems

Integrating Renewable Energy Sources with HVAC Control Systems

Automation systems in smart buildings: a review

In the present scenario everyone turned into smart applications by including the intelligence into the applications and this reduces the burden of frequent interruption or control by the humans. Smartness makes the ability to interconnect more real time parameters by M2M (Machine to Machine) interaction and make wise decisions in harmful situations. Many low-cost devices are available in the market to collect the real time data and transmit them using Internet of Things (IoT). So, the control can be done remotely. In this work, few basic applications in smart buildings are going to be studied to analyze with the technical advances which can bring better solutions automatically. The details collected from different sensors will be useful for analytics and the need for smart design models for better buildings. The services needed in smart building such as security control, energy management, control and monitoring of HVAC system, water management, lighting systems, health system of elders and fire detection are going to be surveyed. The major objective of this study is to identify the issues faced by current methodologies with these applications and give a guideline for future research. From analyzing the relevant methods and needs it is observed that, the buildings construction and usage can depend on the applications, the smart system can respond intelligently for further events. In future all the traditional buildings will be automotive based on HVAC.

Improving cooling load prediction reliability for HVAC system using Monte-Carlo simulation to deal with uncertainties in input variables

Accurate and reliable cooling load prediction is the basis for model predictive control (MPC) of HVAC systems. Cooling load prediction process is constrained by many input variables. These input variables contain different kinds of uncertainties that should not be ignored in pursuing a reliable prediction result. However, previous load prediction methods usually improve the prediction accuracy by optimizing model structure but fail to consider the influence of input variables uncertainties. To reduce the influence of uncertainty of input variables forecast data scientifically, this paper proposes an improved cooling load prediction reliability method in which the input variables are calibrated offline with Monte-Carlo simulations and stochastic treatment before inputting them into the prediction model. A machine learning algorithm (support vector machine, SVM) is used as the prediction model. Uncertainties in weather parameters, indoor heat gains, and historical cooling load were taken into consideration. Uncertainty analysis results showed that prediction accuracy with calibrated input variables was much better (R2 = 0.9627) than those predicted with forecast input data directly (R2 = 0.9488), which was closer to load prediction obtained by using measured input data (R2 = 0.9632). The coefficient of variation (CV) value using the calibrated input data was less than 15%. The reliable cooling load prediction results are beneficial for more informed, reliable decisions on MPC application, thereby promoting energy conservation potential of HVAC systems.

An agent-based distributed real-time optimal control strategy for building HVAC systems for applications in the context of future IoT-based smart sensor networks

Existing studies on distributed optimal control of HVAC systems rarely consider the needs and constraints for practical applications and the deployment of control strategies on the physical building automation platforms. This paper proposes an agent-based distributed real-time control strategy for building HVAC systems with the objective to be deployed in the local control devices with limited programming and computation capacities, i.e. smart sensors integrated in future IoT-based field networks and local controllers in field networks of current LAN-based building automation systems. A complex optimization task with high computational complexity (i.e., computation code and computation load) is decomposed into a number of simple tasks, which can be handled by coordinating agents among the integrated local control devices. The computation task of an optimization decision is further distributed into a number of steps, each performed at a sampling interval of controllers. The test results show that the computation loads of all individual agents at each step were below 2000 FLOPs, which can be handled by the typical smart sensors using simple optimization codes and the number of iterations for each optimization decision was within 50, well below the convergence rate needed for optimal control with typical time interval of minutes. The proposed agent-based optimal control strategy is also convenient and effective to deal with multiple components of different performances and the optimization considering such performance deviations could reduce the overall energy consumption significantly.

Evaluation of energy-saving potential for optimal time response of HVAC control system in smart buildings

In some fields, such as the semiconductor manufacturing process, museum, pharmaceutical, and medicine manufacturing industry, the HVAC system needs a very fast response time to protect products and more energy-efficient buildings than traditional controllers. So, the proposed controller is designed to overcome such problems by using integrated fuzzy PI-PD Mamdani-type (FPIPDM) and cluster adaptive training based on Takagi-Sugeno-Kang (CABTSK) type. The spans of the fuzzy membership functions of the FPIPDM are tuned online by the Nelder-Mead simplex search (NMSS) algorithm to minimize time response, while the CABTSK model is tuned offline and online using a gradient descent (GD) algorithm to enhance the stability of the overall system and reject disturbances. Then, the integration framework is used to enable the concept of time-optimal based on the bang-bang code delegation. In this sense, a selected switch delegates the execution of proper control code to the action processor that provides computational resources to control indoor conditions. The predicted mean vote (PMV) index provides a higher comfort level than the temperature, as it considers six variables related to thermal comfort. The results of the proposed structure show that it improves the overall output accuracy and significantly reduces the response time. Furthermore, it increases the robustness of the indoor conditions and it is quite applicable to the MIMO HVAC systems processes with strong coupling actions between temperature and humidity, large time delay, noise, disturbances, nonlinearities, and imprecise identification model.

Fault Diagnosis of HVAC System Considering LMBP Neural Network Method

Given the complexity of the mathematical model for the HVAC system and the constant changes of multiple external disturbances and working conditions, the application of intelligent control in the HVAC control system to improve the control performance of the HVAC control system has become a research hotspot. The Levenberg-Marquart algorithm (LM algorithm) is studied to address the defects of slow convergence speed and prone to falling into local minimum in the learning process of the BP neural network. To solve the two issues (the choice of the learning rate, and the solution of the inverse matrix) that significantly affect the training time and convergence accuracy, we improved and optimized the LM algorithm using the LU decomposition method and implemented the algorithm through the MATLAB programming language. The LMBP neural network method obtained is applied to the control loop of the HVAC chilled water cycle. The simulation comparison study is performed on its control effect and that of the PID control algorithm and BP neural network PID control algorithm. The research results show that the LMBP neural network method has significantly improved the performance in aspects such as reducing overshoot, accelerating convergence speed and reducing steady-state error, etc.

Indoor haze particulate control using knowledge graphs within self-optimizing HVAC control systems

Transboundary haze pollution in South East Asia is posing a threat to conventional design of buildings yet indoor air pollution from haze particulate infiltration has still received less attention in Malaysia compared to haze pollution outdoors. Because of this minimal research effort, indoor building environments have increasingly become very complex environments for facility managers to monitor and control due to the corresponding growth in heterogeneity within building behavioural information and monitoring (sensory) systems. As a solution to this and part of an ongoing study, this paper presents the preliminary process of modelling heterogeneous building information related to indoor air quality (IAQ) (building envelope, sensors, contaminant properties, geometry, occupancy schedules and weather data) within modular and extensible semantic web knowledge graphs (KG). This work argues that this data model can preserve the existential and latent parametric relationships within such information therafter availing an accurate representation of the heterogeneous state-space in machine learning workflows of self-learning building monitors and controllers. Compared to the conventional homogenous feature vectors, KGs hold sufficient context-aware semantics for an algorithmic building control system to smartly monitor the IAQ and autonomously learn to adapt air handling units towards occupant comfort in an energy efficient manner. Specifically, this paper highlights the high-level implementation process of KGs within the deep Q-learning process of the aforementioned control systems. Finally, a brief discussion is provided on how this process reduces the complexity that facility managers face while operating their IAQ control systems followed by the conclusions and future work to be carried out in this study.

Development and validation of a smart HVAC control system for multi-occupant offices by using occupants’ physiological signals from wristband

Since people spend most of their time indoors, it is important to create comfortable indoor environments for building occupants. However, unsuitable thermostat settings lead to energy waste and an undesirable indoor environment, especially in multi-occupant rooms. This study aimed to develop and validate a control strategy for the HVAC systems in multi-occupant offices using physiological parameters measured by wristbands. We used an ANN model to predict thermal sensation from indoor environmental and physiological parameters such as air temperature, relative humidity, clothing level, wrist skin temperature, skin relative humidity and heart rate. The model was trained by data collected in seven multi-occupant offices in the course of a year, and it was able to predict the thermal sensation with high accuracy. Next, we developed a control strategy for the HVAC system to improve the thermal comfort of all the occupants in the room. The control system was smart and could adjust the thermostat set point automatically in real time. We validated the system by means of both experiments and numerical simulations. In most cases, we improved the occupants’ thermal comfort level. After using the wristband control, over half of the occupants experienced a neutral sensation, and fewer than 5% still felt uncomfortable. The energy consumption by the HVAC system with the wristband control was almost the same as when the constant set point was used. After coupling with occupancy-based control by means of lighting sensors or wristband Bluetooth, the heating and cooling loads were reduced by 90% and 30%, respectively, in interior offices. Therefore, the smart HVAC control system can effectively control the indoor environment for thermal comfort and energy saving.

Mathematical Modelling and Characterization of a Poultry Egg Incubator

Hatching chicken eggs is an extremely rewarding experience, which requires good organization, dedication flexibility, and good observation capacity. Chicken eggs have a 21-day incubation period and can be hatched with a specialized incubator under carefully controlled conditions. The incubator is the apparatus that gives the eggs it contains the same conditions of temperature, humidity, aeration, and movement that the eggs receive under the broody hen. The proper functioning of the incubator is based on the correct regulation of temperature and humidity. The losses in productions explain the errors of settings of these two parameters. This work proposes a mathematical model for a commercial chicken egg incubator. The approach that uses the thermal energy of egg incubation is used in conjunction with the construction details of the incubator in order to model the heat transfer between an egg and its microenvironment. The thermal model of the microenvironment is similar to the ones used for the analysis and control of other HVAC systems (heating, ventilation, and air conditioning). Studies have been conducted to verify and validate the mathematical model for both types of the incubator: ventilated that are fan-equipped and static that does not have a fan. The values of the system tested under real conditions have given good results. T = 37.5 °C is the ideal temperature for a better development of the embryo and an optimal hatching and, H = 60% is the relative humidity value which facilitates hatching and digging; in addition, it influences the weight of the chick.

HVAC and Audio Control System using Gesture Recognition in Cars

Gesture recognition technology entails a wide variety of touch-free interaction capabilities which controls notably contribute to easing our interaction with devices, reducing the need for a keys, or button. To recognize the different hand gestures for different control system in cars is done through image processing. A new method for the hand gestures is that, the hand part gets extracted from the background using background subtraction algorithm using raspberry pi, there is no need of buttons for using of some equipments in different vehicles by using an advanced technology. In gesture recognition technology we can control the audio and HVAC system automatically instead of searching for a particular button, which causes distraction while driving.

Assessment of the impact of HVAC system configuration and control zoning on thermal comfort and energy efficiency in flexible office spaces

In office buildings, the space layout usually needs to be repeatedly redesigned in order to meet tenants’ requirements during the building's life cycle. In this study, the effect of a flexible space layout design on thermal comfort and energy demand is investigated in a modern open-plan office space. Using dynamic thermal simulation, the applicability of three different HVAC systems (mechanical ventilation, radiant ceiling and a thermally-active building system) combined with four control zoning strategies are assessed. Finding a robust solution for each configuration and control strategy can support design decisions during the design planning or interior renovation phase. The main objective is to enable a flexible space layout design during the complete building life cycle without compromising on thermal comfort or energy efficiency.The results show that radiant ceilings and thermally-active building systems are promising solutions for flexible office spaces in the location of Stuttgart, whereas mechanical ventilation systems require a more complex control strategy to ensure thermal comfort. Connecting the field of building controls with parametric building modeling enables flexible space layout designs to be assessed with different HVAC systems.