Energy-efficient personalized thermal comfort control in office buildings based on multi-agent deep reinforcement learning

In this work, HVAC (Heating, Ventilation and Air Conditioning) systems applied in university buildings with control based on PMV (Predicted Mean Vote) and aPMV (adaptive Predicted Mean Vote) indexes are discussed. The building’s thermal behavior with complex topology, in transient thermal conditions, for summer and winter conditions is simulated by software. The university building is divided into 124 spaces, on two levels with an area of 5931 m2, and is composed of 201 transparent surfaces and 1740 opaque surfaces. There are 86 compartments equipped with HVAC systems. The simulation considers the actual occupation and ventilation cycles, the external environmental variables, the internal HVAC system and the occupants’ and building’s characteristics. In this work, a new HVAC control system, designed to simultaneously obtain better occupants’ thermal comfort levels according to category C of ISO 7730 with less energy consumption, is presented. This new HVAC system with aPMV index control is numerically implemented, and its performance is compared with the performance of the same HVAC system with the usual PMV index control. Both HVAC control systems turn on only when the PMV index or the aPMV index reaches values below −0.7, in winter conditions, and when the PMV index or the aPMV index reaches values above +0.7, in summer conditions. In accordance with the results obtained, the HVAC system guarantees negative PMV and aPMV indexes in winter conditions and positive PMV and aPMV indexes in summer conditions. The energy consumption level is higher in winter conditions than in summer conditions for compartments with shading, and it is lower in winter conditions than in summer conditions for compartments exposed to direct solar radiation. The consumption level is higher using the PMV control than with the aPMV control. Air temperature, in accordance with Portuguese standards, is higher than 20 °C in winter conditions and lower than 27 °C in summer conditions. In Mediterranean climates, the HVAC systems with aPMV control provide better occupants’ thermal comfort levels and less energy consumption than the HVAC system with PMV control.

In commercial buildings, about 40%-50% of the total electricity consumption is attributed to Heating, Ventilation, and Air Conditioning (HVAC) systems, which places an economic burden on building operators. In this paper, we intend to minimize the energy cost of an HVAC system in a multi-zone commercial building with the consideration of random zone occupancy, thermal comfort, and indoor air quality comfort. Due to the existence of unknown thermal dynamics models, parameter uncertainties (e.g., outdoor temperature, electricity price, and number of occupants), spatially and temporally coupled constraints associated with indoor temperature and CO2 concentration, a large discrete solution space, and a non-convex and non-separable objective function, it is very challenging to achieve the above aim. To this end, the above energy cost minimization problem is reformulated as a Markov game. Then, an HVAC control algorithm is proposed to solve the Markov game based on multi-agent deep reinforcement learning with attention mechanism. The proposed algorithm does not require any prior knowledge of uncertain parameters and can operate without knowing building thermal dynamics models. Simulation results based on real-world traces show the effectiveness, robustness and scalability of the proposed algorithm.

Overall and local environmental collaborative control based on personal comfort model and personal comfort system

The heating, ventilation, and air conditioning (HVAC) system is a major energy consumer in office buildings, and its operation is critical for indoor thermal comfort. While previous studies have indicated that reinforcement learning control can improve HVAC energy efficiency, they did not provide enough information about end-to-end control (i.e., from raw observations to ready-to-implement control signals) for centralized HVAC systems in multizone buildings due to the limitations of reinforcement learning methods or the test buildings being single zones with independent HVAC systems. This study developed a model-free end-to-end dynamic HVAC control method based on a recently proposed deep reinforcement learning framework to control the centralized HVAC system of a multizone office building. By using the deep neural network, the proposed control method could directly take measurable parameters, including weather and indoor environment conditions, as inputs and control indoor temperature setpoints at a supervisory level. In some test cases, the proposed control method could successfully learn a dynamic control policy to reduce HVAC energy consumption by 12.8% compared with the baseline case using conventional control methods, without compromising thermal comfort. However, an over-fitting problem was noted, indicating that future work should first focus on the generalization of deep reinforcement learning.

A review of different strategies for HVAC energy saving

Efficient management of heating, ventilation, and air conditioning (HVAC) systems is paramount for mitigating energy consumption and enhancing climate resilience in modern infrastructure. This review explores the significance of leveraging project management tools to optimize energy efficiency within HVAC operations, thus fostering a pathway towards climate resilience. The integration of project management methodologies offers a systematic approach to address challenges associated with energy consumption in HVAC systems, thereby facilitating informed decision-making processes. Firstly, the review delves into the pressing need for energy conservation in HVAC operations amidst escalating concerns over climate change and its adverse impacts. The imperative to minimize energy consumption in buildings, particularly through HVAC systems, is highlighted as a pivotal step towards achieving climate resilience and sustainability goals. Subsequently, the review outlines the role of project management tools in orchestrating effective strategies to enhance energy efficiency within HVAC operations. By employing techniques such as project scheduling, risk management, and resource allocation, project managers can streamline the implementation of energy-efficient measures, thereby optimizing HVAC system performance and reducing carbon emissions. Moreover, the review underscores the importance of data analytics and technological advancements in augmenting the efficacy of project management tools for energy efficiency in HVAC operations. Leveraging real-time data monitoring, predictive analytics, and IoT-enabled devices enables proactive maintenance and continuous optimization of HVAC systems, thereby maximizing energy savings and bolstering climate resilience. Furthermore, the review elucidates the potential benefits and challenges associated with the adoption of project management tools for energy efficiency in HVAC operations. While improved cost-effectiveness, environmental sustainability, and operational performance emerge as primary benefits, challenges such as initial investment costs, technological complexities, and organizational inertia necessitate careful consideration. This review advocates for the integration of project management tools as a viable approach to foster energy efficiency in HVAC operations, thereby paving the way towards enhanced climate resilience and sustainability in built environments. By embracing innovative methodologies and technological solutions, stakeholders can mitigate energy consumption, reduce greenhouse gas emissions, and fortify infrastructure against the impacts of climate change. Keywords: HVAC, Climate Resilience, Project Management, Energy, Review.

During the operation of HVAC (Heating, Ventilation, and Air-Conditioning) systems, precise energy consumption prediction plays an important role in achieving energy savings and optimizing system performance. However, the HVAC system is a complex and dynamic system characterized by a large number of variables that exhibit significant changes over time. Therefore, it is inadequate to rely on a fixed offline model to adapt to the dynamic changes in the system that consume tremendous computation time. To solve this problem, a deep neural network (DNN) model based on Just-in-Time learning with hyperparameter R (RJITL) is proposed in this paper to predict HVAC energy consumption. Firstly, relevant samples are selected using Euclidean distance weighted by Spearman coefficients. Subsequently, local models are constructed using deep neural networks supplemented with optimization techniques to enable real-time rolling energy consumption prediction. Then, the ensemble JITL model mitigates the influence of local features, and improves prediction accuracy. Finally, the local models can be adaptively updated to reduce the training time of the overall model by defining the update rule (hyperparameter R) for the JITL model. Experimental results on energy consumption prediction for the HVAC system show that the proposed DNN-RJITL method achieves an average improvement of 5.17% in accuracy and 41.72% in speed compared to traditional methods.

Almost every building in the United States has a HVAC (Heating, ventilation, and air conditioning) system that relies on balancing Velocity Pressure and calculated CFM to properly control the atmosphere in a building. This is ensured and tested by Field Engineers whose job it is to maintain the efficiency and proper output of these HVAC systems. These systems are used to improve indoor air quality, control moisture and condensation, and contaminants while satisfying comfort needs of occupants. Just with any mechanical system, HVAC systems function efficiently with multiple formulas derived from calculus and physics. Every building is equipped with a system that needs to meet a certain threshold of air movement, measured in Cubic Feet per Minute (CFM), that creates a stable and comfortable indoor atmosphere by testing and balancing these systems with Velocity Pressure. Velocity Pressure is the base reading it takes to understand and adjust air movement within a HVAC system to guarantee the overall best quality of an indoor air environment. Once a measurement of Velocity Pressure, measured in inches of water column (in-WC) using a tool called a Flow Hood or Straight Pitot Tube, is taken then you can start to calculate flow readings and test if a fan is producing the correct amount of CFM that the system was built to produce and support. This testing is done by using a series of calculus and algebraic equations that takes area and velocity into consideration. When solving these formulas, it can then be determined if a HVAC system and its fans are producing the ideal amount of airflow and air quality to accurately produce the precise environment for any building.

The main objective of this on-site study is to use a full-scale HVAC (Heating, Ventilating and Air-Conditioning) system installed in an office building in Taiwan for comparing the power consumption, energy-saving, and CO2reduction by variable primary flow (VPF) chilled water systems for controlling the HVAC. The on-site experimental results indicate that average power consumptions are 44,935 kWh for the constant volume (CV) chilled water systems, and 39,025 kWh for the VPF system. Approximately 19% of the maximum energy-saving rate can be achieved if the HVAC system is operated as a VPF system. Additionally, the reduced quantity of accumulated CO2emission varies from 0 to 44,186 kg with 0.623 kg-CO2kwh-1emission factor during the office hours of 08:00 (a.m.) to 20:00 (p.m.). The results demonstrate that switching the operation of an office building HVAC system from CV to VPF will significantly enhance energy savings and CO2reduction. This study is will offer useful information for evaluating an indoor environmental policy with respect to energy savings and CO2emission reduction for office HVACs used in subtropical regions.

Optimizing multi-chiller dispatch in HVAC system using equilibrium optimization algorithm

Two main objectives in the control of Heating, Ventilating and Air Conditioning (HVAC) systems are increasing thermal comfort and reducing energy consumption. Achieving these purposes requires a suitable control system design. In this paper, a thorough review of intelligent control techniques used in HVAC systems to date is completed. Such an overview provides an insight into artificial intelligence methods for the control of HVAC systems and can offer scholars and HVAC learners comprehensive information about a variety of soft computing techniques in the field of HVAC. This information can in turn allow for improved designs of a proper controller for their work.

The capacity of intermittent power sources like wind and PV is steadily increasing. The existing balance between production and consumption is seriously affected by these new sources. Flexible demand for example in buildings is one solution to come back to a stable system. Buildings provide a huge potential for flexible electricity demand. This flexibility can be addressed by using model predictive control (MPC) with optimized scheduling for the buildings’ heating, ventilation and air conditioning (HVAC) systems. Therefore, it is necessary to have detailed simulation models of each single building. To avoid the huge effort of setting up lots of different building models, two approaches for self-adapting building models are discussed in this paper. Those approaches can be differentiated by their mathematical structure. The neural network (NN) approach is called “black-box” model. In contrast to that, the physical “white-box” model is a system of differential equations with free parameters. These models are parameterized by measured data and are developed to be used in model predictive control to forecast the building’s thermal behavior. Once the thermal behavior is predictable, the optimal schedule at minimal costs for the HVAC systems can be determined with respect to thermal comfort. The investigations show, that the difference between instance leads to low electricity prices, electrical heating systems are operated at peak load to charge the building with thermal energy. Typically, the heavier the construction of a building is the more energy can be stored. Charging a building means in this case to raise the temperature of floors, walls and ambient air. The optimization process is necessary to find out when the HVAC systems have to operate to charge the building at minimal costs. The solution of this process is the optimal schedule for the HVAC components. Depending on a flexible electricity price, the MPC calculates the optimal schedule for the HVAC systems of the building with an iterative method. To provide thermal comfort inside the building, the thermal behavior of the building is predicted with a model for each optimization step. The optimized schedule is then applied to the HVAC systems of the real building. Figure 1 provides the schematic configuration of the investigated system. self-adapting model € °C the training phase and the prediction phase is decisive for the quality of the forecast. If test and electricity price, weather data electrical HVAC system building training data are similar (e.g. same season), both models deliver satisfying results.

Modeling techniques used in building HVAC control systems: A review

Heating, ventilation, and air conditioning (HVAC) systems are characterized by time-varying, nonlinear, and parametric coupling, making it challenging to design their controllers. As a major source of energy consumption in buildings, the control schemes for HVAC systems need to be optimized to improve energy efficiency. To address the above issues, a fuzzy controller was designed to regulate the HVAC system, and an improved snake optimizer (ISO) was proposed to optimize the membership function of the fuzzy controller in this study. In the ISO algorithm, the parameter Threshold of the snake optimizer (SO) was dynamically adjusted, and the snake egg-hatching formula was improved. Benchmark function tests show that the convergence speed and optimization accuracy of ISO are superior to those of the established comparison algorithms. Furthermore, simulation experiments indicate that the ISO-optimized HVAC system has a temperature error of 0 and a humidity ratio error of less than 1.5% compared to competing methods. In addition, the ISO-optimized HVAC system achieves a 40.8% reduction in annual energy consumption.

A review on available energy saving strategies for heating, ventilation and air conditioning in underground metro stations