Control Of HVAC Systems Research Articles

Encrypted fully model-free event-triggered HVAC control

This paper addresses the critical issue of privacy and high computational overhead in cloud-based HVAC control systems for building automation. Cloud computing platforms can infer sensitive information, such as occupancy, from sensor data, making privacy a major concern for users of intelligent buildings. Existing model-based control methods ensure privacy by introducing homomorphic encryption but they rely on approximating building dynamics and are resource-intensive, leading to increasing communication and computation costs. To solve this, we propose an encrypted fully model-free event-triggered control framework that guarantees privacy while minimizing both communication and computational costs without the need for approximating building dynamics. Our approach includes a model-free controller that regulates indoor temperature and CO2 levels, and an event-triggering mechanism that optimizes communication by only transmitting data when necessary. The numerical results from the simulations using the TRNSYS platform show that our method reduces communication between the system and cloud by 64% and decreases computation time by 75% compared to the latest encrypted HVAC control method. The primary contribution of this work is the novel model-free design that simplifies the control process modeling while significantly reducing resource demands, and provides a scalable and cost-effective solution for cloud-based HVAC control, enhancing both privacy and operational efficiency in smart buildings.

Hybrid model-based predictive HVAC control through fast prediction of transient indoor temperature fields

Efforts to reduce energy demand in the building sector have prompted a focus on the operational control of HVAC systems. Despite extensive research on HVAC control based on temperature prediction models, existing approaches often rely on node-based or average temperature predictions, which lack the detailed temperature distribution data necessary for accurate control, especially in transient situations with both spatial and temporal variations. This study introduces a precise HVAC control method based on a fast temperature field prediction model. By combining the single-step prediction response coefficient (SPRC) method with Convolutional Neural Network (CNN) architecture, sub-temperature field prediction models for multiple independent heat sources were constructed and integrated to achieve fast temperature field predictions. Subsequently, utilizing the predicted temperature field, air conditioning operation parameters were optimized and controlled to minimize energy consumption. Application of the proposed method in real building scenarios demonstrated the temperature field predictions closely aligned with computational fluid dynamics (CFD) simulations, achieving a mean absolute error (MAE) of 0.27 °C and a root mean square error (RMSE) of 0.24 °C. Furthermore, this model achieved a notable 57.8 % improvement in prediction accuracy compared to models relying solely on single-step prediction responses. Additionally, the model predictive control based on the hybrid model's temperature field predictions significantly reduced the runtime of the HVAC system by 18.18 % while maintaining temperatures within the comfort range throughout the operation period. The method presents a promising avenue for optimizing HVAC operations and minimizing energy consumption in building environments, thereby contributing to sustainable building management practices.

An Alternative Reinforcement Learning (ARL) control strategy for data center air-cooled HVAC systems

Energy efficiency of data center is of great concern globally due to their large amount of energy consumption and the foreseeable growth in the demand of digital services in the future. Advanced control strategies are needed to reduce energy consumption. However, the optimization of data center HVAC control is a challenge task due to the complexity of the thermal dynamic models of buildings and uncertainties associated with both server loads and outdoor temperature. In this paper, we propose a new control strategy called Alternately-Reinforcement Learning-control(ARL), which realizes the alternating control of RL and proportional, integral and derivative (PID) for optimizing the control of air-cooled HVAC systems in data centers. The control object of the ARL is the speed set of the compressor and the condensing fan, and the control goal is to minimize energy consumption while maintaining temperature stability. The applied RL algorithm is Deep deterministic policy gradient (DDPG) and Proximal policy optimization (PPO). We pre-train the ARL strategy in offline environment firstly and deploy it in real data center environment for online testing. The test results show that the ARL has significant advantages in maintaining temperature stability while reducing energy consumption, and the PPO algorithm performs better than the DDPG algorithm. Compared with the PID algorithm, the PPO algorithm can save energy by 5.27%, and the temperature control effect can be improved by 3.27%,which indicates the feasibility of the ARL for implementation in real data centers.

Multi-source transfer learning method for enhancing the deployment of deep reinforcement learning in multi-zone building HVAC control

Deep reinforcement learning (DRL) control methods have shown great potential for optimal HVAC control, but they require significant time and data to learn effective policies. By employing transfer learning (TL) with pre-trained models, the need to learn the data from scratch is avoided, saving time and resources. However, there are two main critical issues with this approach: the inappropriate selection of the source domain resulting in worse control performance and inefficient utilization of multi-source domain control experience. To address these challenges, a multi-source transfer learning and deep reinforcement learning (MTL-DRL) integrated framework is proposed for efficient HVAC system control. In order to select appropriate source domains, the contribution of various source domains to the target task is quantified first, followed by a comprehensive evaluation of transfer performance based on average energy consumption and average temperature deviation. The well-pretrained DRL parameters from the optimal multi-source transfer set are then sequentially transferred to the target DRL controller. Results from a series of transfer experiments between buildings with different thermal zones and weather conditions indicate that the MTL-DRL framework significantly reduces the training time of HVAC control, with improvements of up to 20% compared to DRL baseline models trained from scratch. Additionally, the MTL-DRL method leads to reductions in average energy consumption ranging from 1.43% to 3.12% and average temperature deviation up to 14.32%. The impact of the source domain transfer sequence on the performance of the DRL-based control method is also discussed. Overall, the proposed framework presents a promising solution for enhancing DRL-based HVAC control methods by reducing training time and energy consumption while maintaining occupants’ comfort.

A novel dynamic predictive control model for variable air volume air conditioning systems using deep learning

Model-based predictive control has proven effective for managing indoor temperature and humidity in variable air volume (VAV) air conditioning systems. However, delays in temperature and humidity adjustments in response to changes in internal and external environmental conditions can impede high-performance operation. This study introduces a dynamic predictive control model for the multi-zone indoor temperature and humidity of VAV systems, designed to predict and control these parameters in real-time. Utilizing the RC network two-node wall structure method and backward finite difference scheme, a multi-zone building model is developed. Coupled with a deep fuzzy cognitive map (DFCM) for temperature and humidity prediction, and controlled by a PID controller, the model dynamically regulates the opening degrees of terminal air dampers and chilled water valves. Implemented on a networked control platform in a large commercial building, the model consistently maintained indoor temperature and humidity within ±0.5 °C and ±0.1 g/(kg dry air) of the target values under varying conditions, demonstrating substantial improvements in stability and operational efficiency. The research enhances the predictability and control of HVAC systems through advanced algorithmic integration, improving real-time indoor climate management in complex building environments. This method offers a practical improvement in HVAC control technologies, which could be beneficial for applications in commercial building management systems, providing a useful tool for supporting energy efficiency and sustainability in modern infrastructures.

Reinforcement learning optimal control method for multi chiller HVAC system in an existing office building

Abstract Given that buildings consume approximately 33% of global energy, and HVAC systems contribute nearly half of a building’s total energy demand, optimizing their efficiency is imperative for sustainable energy use. Many existing buildings operate HVAC systems inefficiently, displaying non-stationary behavior. Current reinforcement learning (RL) training methods rely on historical data, which is often obtained through costly modeling or trial-and-error methods in real buildings. This paper introduces a novel reinforcement learning construction framework designed to improve the robustness and learning speed of RL control while reducing learning costs. The framework is specifically tailored for existing office buildings. Applying this framework to control HVAC systems in real office buildings in Beijing, engineering practice results demonstrate: during the data collection phase, energy efficiency surpasses traditional rule-based control methods from the previous year, achieving significantly improved energy performance (a 17.27% reduction) with minimal comfort sacrifices. The system achieves acceptable robustness, learning speed, and control stability. Reduced ongoing manual supervision leads to savings in optimization labor. Systematic exploration of actions required for RL training lays the foundation for RL algorithm development. Furthermore, by leveraging collected data, a reinforcement learning control algorithm is established, validating the reliability of this approach. This construction framework reduces the prerequisites for historical data and models, providing an acceptable alternative for systems with insufficient data or equipment conditions.

Study on indoor temperature optimal control of air-conditioning based on Twin Delayed Deep Deterministic policy gradient algorithm

The optimization of HVAC system control affects the thermal comfort of building environment and air-conditioning energy consumption. However, most existing studies concentrate on human thermal comfort and neglects to incorporate air-conditioning energy consumption required to establish a controlled indoor thermal environment within the policy, which results in air-conditioning system high energy consumption. This paper suggests an indoor temperature intelligent control method based on thermal comfort and energy consumption of air-conditioning, and the TD3 algorithm is employed as an intelligent control algorithm to obtain the optimal setpoint that maximizes the joint benefit of the occupant’s thermal comfort and the energy saving rate of air-conditioning system. The air-conditioning indoor temperature intelligent control model based on TD3 algorithm is trained by using the experimental data, and the method is simulated in TRNSYS simulation software to corroborate the efficacy and energy saving rate of the method. The results indicate that the indoor temperature intelligent control model based on thermal comfort and energy consumption of air-conditioning has less optimal adjustment of indoor temperature setpoints, which is more stable for the air-conditioning system and can satisfy the thermal comfort demand at the initial control stage to prevent significant fluctuations in human thermal sensation compared to the linear control method based on thermal sensation and the fuzzy control method based on thermal sensation. Besides, the average daily energy consumption can be reduced by 6.54% and 3.37% respectively, when compared to the linear control method based on thermal sensation and the fuzzy control method based on thermal sensation.

Real-time spatial-temporal mapping and visualization of thermal comfort and HVAC control by integrating immersive augmented reality technologies and IoT-enabled wireless sensor networks: Towards immersive human-building interactions

Existing methods to assess and visualize thermal comfort mainly focused on either individual users (e.g., through wearables) or for specific locations where sensors are installed, rather than continuously for the entire indoor space. Also, most of the existing thermal comfort visualization methods and HVAC system control approaches rely on phones and mobile devices and lack a fully immersive/interactive experience and human-building interaction. Thus, this paper develops an immersive human-building interaction framework for real-time spatial-temporal mapping and visualization of indoor thermal comfort by integrating immersive augmented reality (AR) technologies and IoT-enabled smart wireless sensor networks (WSNs) (i.e., temperature and relative humidity data) to provide thermal comfort assessment for the entire space (rather than at localized/individual locations/points) and to enable users to interact with and adjust the HVAC systems from a distance using fully immersive and realistic environments. First, a smart WSN comprised of four IoT-enabled sensing stations was developed to collect real-time thermal comfort-related information (i.e., temperature and relative humidity). Second, an AR environment was created using the Unity engine, where virtual objects were overlayed into, and aligned with, the real-world environment. Third, the real-time data from the IoT-enabled WSN was integrated into the AR environment using various programming scripts that add multiple functionalities to the users, including controlling the HVAC system and visualizing the thermal comfort along the entire indoor space or room of interest through a spatial-temporal map. Fourth, the developed framework was validated and evaluated by 118 participants using a survey questionnaire. The findings showed that the graphical satisfaction achieved an overall average score of 4.75 out of 5, the user's sense of spatial presence was rated at an average score of 4.68 out of 5, the involvement aspects of the developed approach received an overall average score of 4.80 out of 5, and experienced realism was rated at an average score of 4.58 out of 5. Ultimately, this paper contributes to enhanced and intelligent human-building interaction and visualization through the use of emerging technologies by allowing the building users to control and interact with the HVAC systems using AR capabilities to improve the health and well-being of the building occupants.

Stochastic occupancy modeling for spaces with irregular occupancy patterns using adaptive B-Spline-based inhomogeneous Markov Chains

This paper presents a discrete time, discrete state-space in-homogeneous Markov Chains model for stochastic occupancy modeling in spaces with irregular occupancy patterns. The goal of the model is to provide accurate predictions of occupancy numbers, enabling appropriate actions to be taken for HVAC system to maintain optimal indoor environment. The proposed Markov Chain model incorporates time in-homogeneity by coupling the time-varying model parameters using a Periodic B-Spline expansion with adaptive knots, which effectively captures patterns in occupancy activity. This method optimizes the distribution of knots based on specific occupancy characteristics observed in different types of rooms. To evaluate the effectiveness of the proposed method, six months of occupancy data collected from a meeting room are utilized. A comprehensive comparison is conducted between the proposed adaptive B-Spline method and other approaches, including the counting method and uniform B-Spline method. The comparison considers both model accuracy and complexity, using metrics such as the Akaike Information Criterion and Bayesian Information Criterion. Results indicate that the proposed model achieves more accurate predictions with fewer model parameters compared to other methods. These forecasts are particularly useful in optimizing the control of HVAC systems, where accurate predictions of future occupancy numbers are essential.

Indoor Temperature Forecasting in Livestock Buildings: A Data-Driven Approach

The escalating global population and climate change necessitate sustainable livestock production methods to meet rising food demand. Precision Livestock Farming (PLF) integrates information and communication technologies (ICT) to improve farming efficiency and animal health. Unlike traditional methods, PLF uses machine learning (ML) algorithms to analyze data in real time, providing valuable insights to decision makers. Dairy farming in diverse climates is challenging and requires well-designed structures to regulate internal environmental parameters. This study explores the application of the Facebook-developed Prophet algorithm to predict indoor temperatures in a dairy farm over a 72 h horizon. Exogenous variables sourced from the Open-Meteo platform improve the accuracy of the model. The paper details case study construction, data acquisition, preprocessing, and model training, highlighting the importance of seasonality in environmental variables. Model validation using key metrics shows consistent accuracy across different dates, as the mean absolute percentage error on daily base ranges from 1.71% to 2.62%. The results indicate excellent model performance, especially considering the operational context. The study concludes that black box models, such as the Prophet algorithm, are effective for predicting indoor temperatures in livestock buildings and provide valuable insights for environmental control and optimization in livestock production. Future research should explore gray box models that integrate physical building characteristics to improve predictive performance and HVAC system control.

Enhancing HVAC control systems through transfer learning with deep reinforcement learning agents

Traditionally, building control systems for heating, ventilation, and air conditioning (HVAC) relied on rule-based scheduler systems. Deep reinforcement learning techniques have the ability to learn optimal control policies from data without the need for explicit programming or domain-specific knowledge. However, these data-driven methods require considerable time and data to learn effective policies without prior knowledge. Performing transfer learning using pre-trained models avoids the need to learn the underlying data from scratch, thus saving time and resources. In this work, we evaluate reinforcement learning as a method of pretraining and fine-tuning neural networks for HVAC control. First, we train an RL agent in a building simulation environment to obtain a foundation model. We then fine-tune this model on two separate simulation environments such that one environment simulates the same building under different weather conditions while the other environment simulates a different building under the same weather conditions. We perform these experiments with two different reward functions to evaluate their effect on transfer learning. The results indicate that transfer learning agents outperform the rule-based controller and show improvements in the range of 1% to 4% when compared to agents trained from scratch.

Research on Key Technologies for Green Transformation of Existing Residential Buildings in Dense Urban Areas

To achieve green and environmentally friendly urban construction, it is proposed to study a key technology for the green transformation of existing residential buildings in densely populated urban areas. Firstly, using a time series autoregressive model, achieve energy consumption prediction for HVAC heating. Secondly, based on multi-objective particle swarm optimization algorithm, energy-saving control of HVAC systems was achieved. Finally, the effectiveness of the proposed key technology was verified through experiments. The results of this article indicate that the green transformation of existing residential buildings in densely populated urban areas is necessary and feasible, and the application of key technologies can effectively reduce energy consumption and improve the quality of the living environment.

Development of a Building Simulation Model for Indoor Temperature Prediction and HVAC System Anomaly Detection

In order to reduce global energy consumption, energy-efficient, green and smart buildings have to be built. In addition to the application of other energy efficiency measures, an effective management of HVAC systems is required. High quality management and control of these systems ensures optimal occupant comfort levels, proper operation, rational energy consumption, and a positive impact on the environment. This is especially important for large buildings with complex systems such as hotels. As a contribution to the creation of appropriate tools for the management and control of HVAC systems in smart buildings, this paper presents the results of the current development of a detailed dynamic simulation model based on data collected from a smart room system in a hotel in Zagreb, Croatia. The smart room system, which is integrated into the hotel's building management system, provides historical data on set and current room temperatures, room occupancy schedule, window opening, fan coil operation status, fan rotation speed, valve opening, and operating mode with a time step of 5 minutes. The simulation model based on the TRNSYS software uses a part of the available data and calculates the current internal room temperatures. A comparison of the predicted and measured temperatures at each time step showed that the deviations are within the acceptable limits. The final objectives of the model development are the identification of anomalies in the operation of the HVAC system and the optimization of its operation with the aim of reducing energy consumption.

Application of Variable Theory Domain Fuzzy Control Algorithm for Room Temperature Control

With the development of automatic control in the HVAC industry, more and more buildings have adopted automatic control of air conditioning, HVAC systems, but most of the control results can not be satisfactory. The research object of this paper is the elevator machine room equipped HVAC, through accurate control of that room temperature can greatly reduce the elevator shutdown caused by the action of the temperature protection circuit, so as to improve the safety of elevator operation. This paper gives three different temperature control methods, establishes the math representation of the temperature system in the machine room, specifically designs the classical PID controllers, Fuzzy PID controllers and variable domain Fuzzy PID controller, and simulates and analyzes the three algorithms respectively, The results indicate that in comparing the above three algorithms, the variable domain fuzzy PID algorithm has an adjustment time of 63s, and the overshooting amount of 0.4%, which is the best among the three control algorithms.

A comparative investigation between rule- and inverse model-based fault detection and diagnostics for HVAC control systems

Fault detection and diagnostics (FDD) tools provide valuable information regarding system faults and deviation from expected operation. Most existing FDD tools apply rule-based fault detection algorithms that generate an alarm when a rule is met; however, these tools cannot evaluate the overall performance of a system. Inverse-model-based FDD algorithms can be deployed to complement the fault alarms triggered by rule-based building energy management systems (BEMS). This paper examines the faults detected by rule- and inverse model-based algorithms used to detect faults in multiple zone variable air volume air handling unit systems. The capability of the rule- and inverse model-based algorithms in detecting and diagnosing faults is demonstrated through illustrative examples using data from three commercial buildings in New Brunswick, Canada. The results show that inverse model-based algorithms could diagnose faults that were not detected by the rule-based FDD algorithms implemented in a commercially available BEMS tool.

Analysing the indoor temperature ranges for an efficient control of HVAC systems

The selection of a suitable indoor temperature is a challenge to society, since its relationship with thermal comfort and energy consumption. The adaptive thermal comfort theory addresses this problem relating indoor with outdoor temperatures and based on that, defines temperature ranges. This paper defines a fuzzy logic-based methodology to assess the suitability of indoor adaptive temperature ranges proposed by existing regulations of the real thermal sensation of the occupants. For this purpose, the study suggests considering four indicators to evaluate the representativeness of different comfort ranges on the real preferences of the occupants. Based on that, four metrics are proposed for interpreting the needs of the occupants of a building and the changes required to the temperature ranges to satisfy such needs. To validate the proposed methodology, questionnaires on the thermal sensation of the occupants of office buildings considering three case studies (Mediterranean, Europe, ASHRAE) are used, showing the results obtained the representativeness of adaptive comfort ranges for such databases. The feasible introduction of this methodology in a conditioning systems would assist in decision making regarding energy efficiency, thermal comfort and a balance between them.

Non-invasive human thermal comfort assessment based on multiple angle/distance facial key-region temperatures recognition

Accurate monitoring of human thermal comfort is crucial in optimizing HVAC system control scheme and enhancing building energy efficiency. The method based on facial temperature infrared recognition is a non-invasive and real-time thermal comfort predictive strategy, which has been proven great application potential. In response to the limitations of previous fixed-position facial infrared detection in practical applications, this study aims to explore a less restrictive non-intrusive method for assessing human thermal comfort. The temperature features of multiple regions on human face are identified by an infrared camera, and six temperature-sensitive regions are selected through skin thermal sensitivity analysis. Thirty subjects participate in a series of field experiments. To reduce the measurement limitations caused by human postures, the correlation between these six facial regions, indoor air temperature, thermal sensation votes (TSV), and thermal comfort votes (TCV) are analyzed in details to determine two key facial regions for the non-intrusive thermal comfort assessment. By applying the YOLOv5 algorithm, the real-time extraction of facial region temperatures from multiple angles and distances is achieved. On this basis, a data-driven thermal comfort predictive strategy based on facial temperature and optimized SVM model is designed. Results indicate that the method achieves a general accuracy of 85.68% in predicting thermal comfort based on its successful recognition rate of 88.7% for facial key regions.

Performance Evaluation of an Occupancy-Based HVAC Control System in an Office Building

As new algorithms incorporate occupancy count information into more sophisticated HVAC control, these technologies offer great potential for reductions in energy costs while enhancing flexibility. This study presents results from a two-year field evaluation of an occupancy-based HVAC control system installed in an office building. Two wings on each of the building’s 2–11 floors were equipped with occupancy counters to learn occupancy patterns. In combination with proprietary machine learning algorithms and thermal modeling, the occupancy data were leveraged to implement optimized start, early closure, and adjustments to fan operation at the air handling unit (AHU) level. This study conducted a holistic evaluation of technical performance, cost-effectiveness analysis, and user satisfaction. Results show the platform reduced weekday AHU run times by 2 h and 35 min per AHU per day during the pandemic time period. Simulation shows that 6.1% annual whole-building savings can be achieved when the building is fully occupied. The results are compared with prior studies, and potential drivers are discussed for future opportunities. The assessment results shed light on the expected in-the-field performance for researchers and industry stakeholders and enabled practical considerations as the technology strives to move beyond research-grade pilot trials into product-grade deployment.

A data-driven method for the optimal control of centralized cooling station in an office park

An effective way to reduce the energy consumption of a building is to optimize the control strategy for the HVAC system. Load prediction is suggested and used to match the supply and demand for air conditioning and achieve energy savings. However, the gap between load prediction models and real-time optimal control of HVAC systems still exists. Hence, this paper proposed an optimization method for dynamically determining the best setpoints of chillers and chilled water pumps under a specific load. The energy consumption model of each equipment in the centralized cooling station is established and validated using the operational data. Then an optimization problem is defined to find the optimal setpoints for each equipment under certain load, to realize the lowest energy consumption. To verify the validity of the proposed method, a period of real operational data in an office park is used. The proposed method is applied on one centralized cooling station in the office park and results in an 4% lower overall energy consumption than the existing intelligent control strategies in the park. This method provides feasible directions and reference for realizing overall optimal control of the whole HVAC system in the future.

Energy-oriented control retrofit for existing HVAC system adopting data-driven MPC – Methodology, implementation and field test

Energy conservation and carbon reduction of existing buildings have been receiving increasing attention with the proposed carbon neutrality goals. As presented in many studies, adopting model predictive control (MPC) for building HVAC system control is an effective means to realize building energy conservation. However, existing studies rarely addressed the critical challenges for practical applications and integration of MPC in existing Building Automation Systems (BASs). This study proposes a control retrofit approach, which is lightweight and replicable, to realize the improvement of energy efficiency of the existing building HVAC systems through integrating data-driven MPC into existing BASs. The critical challenges in the practical applications of MPC strategies, including MPC strategy development, large-scale data processing, strategy deployment and integration with existing BASs are addressed. The proposed approach was applied to the existing HVAC system of an actual airport terminal and the evaluation results indicate that the control retrofit approach is effective in achieving energy efficiency and thermal comfort improvement. The system daily energy consumption was reduced by 24.5% in average and the percentage of the discomfort time was reduced from 70.2% to 5.7% in average after the control retrofit. The proposed control retrofit approach, with the help of the scalability and distributed computing capabilities of the cloud computing platform, is expected to be able to realize lightweight control retrofit of large number of existing building HVAC systems.