Heating, Ventilation, And Air Conditioning Load Research Articles

Photovoltaic capacity dynamic tracking model predictive control strategy of air-conditioning systems with consideration of flexible loads

Building photovoltaic (PV) power generation is intermittent, volatile, random, and uncontrollable; thus, the use of solar grid-connected power generation can lead to a series of problems, such as grid voltage fluctuations and power imbalance. As a typical flexible load, the scheduling and regulation of the heating, ventilation, and air conditioning (HVAC) system load can help a grid-connected solar grid achieve balanced and flexible operation. This study proposes a PV capacity dynamic tracking model predictive control strategy for air-conditioning systems with flexible loads. This strategy aims to effectively address the issue of unstable grid-connected output of solar PV systems. In particular, a solar radiation prediction model based on a long short-term memory neural network optimized by the grey wolf optimization algorithm was established, which effectively improved the model prediction accuracy. The cost function of HVAC flexible load control considers the law of solar PV output and the human thermal comfort model. A genetic algorithm (GA) is used to obtain the optimal control parameters for dynamic regulation. The GA was employed to efficiently and effectively optimize the control of flexible HVAC loads, considering the variability of the solar PV output and ensuring human thermal comfort. A dynamic regulation model was developed for a typical office building with a grid-connected solar PV power generation system. TRNSYS was utilized for verification based on the actual measured data and relevant meteorological parameters of the case building. A new evaluation metric, volatility, was proposed to evaluate net load fluctuation. The simulation platform based on the physical building yield results indicated a strong resemblance between the energy consumption curve under the predicted control conditions using the flexible model and the PV generation curve. Additionally, the net load volatility was measured to be 2.63. Compared with the predicted control condition without the flexible model, the net load volatility of the grid was reduced by 47.08%, and the energy-saving rate reached 10.89% in the summer.

HVAC Load Forecasting Based on the CEEMDAN-Conv1D-BiLSTM-AM Model

Heating, ventilation, and air-conditioning (HVAC) systems consume approximately 60% of the total energy consumption in public buildings, and an effective way to reduce HVAC energy consumption is to provide accurate load forecasting. This paper proposes a load forecasting model CEEMDAN-Conv1D-BiLSTM-AM which combines empirical mode decomposition and neural networks. The load data are decomposed into fifteen sub-sequences using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). The neural network inputs consist of the decomposition results and five exogenous variables. The neural networks contain a one-dimensional convolutional layer, a BiLSTM layer, and an attention mechanism layer. The Conv1D is employed to extract deep features from each input variable, while BiLSTM and the attention mechanism layer are used to learn the characteristics of the load time series. The five exogenous variables are selected based on the correlation analysis between external factors and load series, and the number of input steps for the model is determined through autocorrelation analysis of the load series. The performance of CEEMDAN-Conv1D-BiLSTM-AM is compared with that of five other models and the results show that the proposed model has a higher prediction accuracy than other models.

A Transactive Energy Framework for Inverter-Based HVAC Loads in a Real-Time Local Electricity Market Considering Distributed Energy Resources

Rapidly increasing distributed energy resources (DERs) bring more fluctuating output power to the distribution network and put forward a higher requirement on local regulation resources for maintaining the network's balance. Heating, ventilation, and air conditioning (HVAC) loads account for more than 40% of power consumption in modern cities and have huge regulation potential as flexible loads. However, HVACs equipped with inverter devices have rarely been studied for providing regulation services in the local electricity market (LEM), even though they have exceeded regular fixed-speed HVACs. To address this issue, this article proposes a real-time LEM and a distribution network's optimization framework to exploit the regulation potential of inverter-based HVACs considering multiple DERs. This LEM can avoid iterations in real time and significantly decrease the difficulty related to the participation of small end-users in urban distribution networks. Moreover, in this article, we propose a transactive capacity evaluation method to assist end-users in deciding their inverter-based HVACs regulation capacities in the real-time LEM, which considers buildings’ thermal features, users’ multiple comfort requirements, and dynamic ambient temperature. On this basis, a multilevel bidding strategy is developed for inverter-based HVACs to decrease energy cost, increase fluctuating DERs local utilization rate, and alleviate the distribution network's congestion. Finally, a realistic distribution network is utilized to verify the effectiveness of the proposed methods.

Demand response strategy for HVAC based on reinforcement learning and imitation learning

Heating, ventilation and air conditioning (HVAC) loads have great potential for demand response due to the buildings' thermal inertia. Modelling the complex thermal dynamics of realistic buildings is essential for the building energy optimization. In this paper, Deep Q-Network (DQN), a reinforcement learning (RL) algorithm, is used to decide the indoor temperature setpoint in response to the real-time price. The agent can adjust the HVAC load to reduce the electricity cost while considering the occupants' comfort requirement. To significantly accelerate the training process, imitation learning is adopted to pre-train the RL agent using historical data. The results of the case study show that the agent's performance improves steadily and exceeds the benchmark after a short period of training.

Multi-Objective Control of Residential HVAC Loads for Balancing the User’s Comfort With the Frequency Regulation Performance

In this paper, a comprehensive solution is proposed for the optimal scheduling of Heating, Ventilation, and Air-Conditioning (HVAC) loads to balance the user’s comfort with the frequency regulation performance. The asynchronous model, which engages several HVAC loads, uses grid frequency measurement devices for primary frequency regulation (PFR). The time when each load detects the frequency disturbance, and its triggering time for frequency response, are asynchronous which could mitigate impulses caused by simultaneous sudden applications or removals of considerably similar loads. The implementation of the proposed strategy provides decision-makers with optimal combinations of frequency deviation thresholds and monitoring periods, in which the monitoring period is denoted as a working period for HVAC load controller. The proposed optimal solution considers the maximum frequency deviation, duration of abnormal frequency, and temperature deviation from the user’s set temperature. The Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) algorithm and a fuzzy-decision selection method are developed to obtain the optimal compromise as a Pareto solution of the multi-objective optimization problem for implementing the proposed PFR strategy. The simulation results are presented and discussed for a given system in which 0.2Hz and 5.5s represent the respective typical settings for the optimal frequency deviation threshold and the monitoring period.

Implementation of a Hybrid Technique for the Predictive Control of the Residential Heating Ventilation and Air Conditioning Systems

Since daily energy needs are increasing, it is imperative to find ways to save energy, such as improving the energy consumption of buildings. Heating Ventilating and Air-Conditioning (HVAC) loads account for the majority of a building's energy use. The accurate estimation of energy consumption and the examination of various ways to improve the energy efficiency of buildings are very important. This paper presents an analysis of HVAC loads in a residential building by examining three Neural Networks (NNs): Feed-Forward (FF), Cascaded Forward Backpropagation (CFBP), and Elman Backpropagation (EBP) networks, based on Mean Absolute Error (MAE), Mean Square Error (MSE), and Mean Relative Error (MRE). Furthermore, these networks were combined in hybrid NNs to obtain more optimized results. These results were also compared with other approaches and showed better prediction performance.

Generation of sub-item load profiles for public buildings based on the conditional generative adversarial network and moving average method

Increasing research on data-driven methods to optimize energy systems and power grid operation requires a large amount of data with regard to building energy consumption profiles; owing to the difficulty in availing load data, time-consuming collection and the privacy issues in the collection process have become limitations and previous research on total load generation cannot meet research requirements of refined energy control and optimization. In this study, we propose a novel approach based on the conditional generative adversarial network (CGAN) and moving average method to generate sub-item load profiles of building energy consumption to solve the aforementioned problems. Sub-item load profiles include light and socket load, HVAC (Heating Ventilation and Air Conditioning) load, impetus load and special load. The CGAN algorithm is employed to generate sub-item load profiles considering specific conditions (multiple labels) e.g. time, weather, and load shape labels. In addition, the moving average method was used to reduce noise in the generated profiles. The case study was conducted based on real-world sub-item load data collected from office buildings, commercial buildings, and hospitals in Shenzhen, China. We validated the generation performance of the sub-item load profile of CGAN-MA by comparing it with the traditional load profile generation method GAN and variational autoencoder based on three aspects: similarity, variability and diversity. Compared with the traditional model, the proposed model improves the similarity and variability by about 5.7% to 64.8%, 76.7% to 135.5% respectively, and can satisfy the requirements of diversity with the diversity indicator of four sub item generated load is 1.36, 1.93, 1.81 and 2.08 respectively. Furthermore, we compared the generated load and real load possibility distributions under the selected conditions. The results show that the load generated by CGAN-MA is higher on working days, rainy days and hot days than on non-working days, sunny days and cool days, which correspond to the real circumstances, and sub-item B (HVAC) is the most sensitive one to different conditions. The proposed model can be applied to effectively generate sub-load profiles under the required conditions and further help in studies related to the development of data-driven methods for energy consumption prediction, demand-side management and the optimization of power grid operation.

Coordinated control of Incentive-Based Demand Response Program and BESS for frequency regulation in low inertia isolated grid

With the increase in penetration of inverter-based renewable energy resources (RES) to meet the increasing demand, frequency regulation is a major concern in low inertia isolated microgrids. Conventionally, a battery energy storage system (BESS) regulates the frequency in coordination with RES. Using only BESS for frequency regulation may not be sufficient during high penetration of RES. Therefore, maintaining the BESS state of charge (SOC) at a nominal value for up/down frequency regulation services becomes daunting. Customers’ participation through the Demand Response (DR) programs is investigated to provide frequency regulation services when the existing BESS and other resources are insufficient for regulation services. The coordination between the Incentive-Based Demand Response (IBDR) program and BESS is used to provide frequency regulation services and maintain the nominal SOC of the battery. For the IBDR program, the power consumption of commercial buildings’ heating ventilating and air-conditioning (HVAC) systems are controlled by changing air handling units’ fan speed (AHUs). The speed of the fan in AHUs is tracked to regulate the frequency. A decentralized control scheme with a simple PI and PD controller is proposed. The simulated results show that smooth frequency regulation is achieved through coordinated control of HVAC loads and BESS.

Demonstration of Intelligent HVAC Load Management With Deep Reinforcement Learning: Real-World Experience of Machine Learning in Demand Control

Buildings account for 40% of total primary energy consumption and 30% of all CO₂ emissions worldwide. A large portion of building energy consumption is due to heating, ventilation, and air-conditioning (HVAC) systems. In the summer, for example, more than 50% of a building’s electricity consumption is used for cooling. With proper energy management, buildings can provide load shifting, peak shaving, frequency regulation, and many other demand response services.

Smart Thermostats for a Campus Microgrid: Demand Control and Improving Air Quality

Achieving nearly zero-energy buildings (nZEB) is one of the main objectives defined by the European Union for achieving carbon neutrality in buildings. nZEBs are heavily reliant on distributed renewable generation energy sources, which create new challenges associated with their inherent intermittency. To achieve nZEB levels, demand management plays an essential role to balance supply and demand. Since up to two-thirds of the total consumed energy in buildings is dispended for Heating, Ventilation and Air Conditioning (HVAC) operations, intelligent control of HVAC loads is of utmost importance. The present work aims to offer a solution to improve a building microgrids’ flexibility by shifting thermal loads and taking advantage of room thermal inertia. Innovation is present in using the internet of things to link several decentralized local microcontrollers with the microgrid and in the applicability of different control algorithms, such as the pre-emptive heating/cooling of a room. The developed solution relies on smart thermostats, which can be integrated into a building management system, or in a microgrid, and are capable of fulfilling the occupants’ need for comfort while complementing the building with needed power flexibility. The equipment is capable of controlling several HVAC systems to guarantee thermal and air quality comfort, as well as coordinate with a building/microgrid operator to reduce energy costs by shifting thermal loads and enacting demand control strategies. The smart thermostat uses an algorithm to calculate room inertia and to pre-emptively heat/cool a room to the desired temperature, avoiding peak hours, taking advantage of variable tariffs for electricity, or periods of solar generation surplus. The smart thermostat was integrated into a university campus microgrid and tested in live classrooms. Since the work was developed during the COVID-19 pandemic, special attention was given to the air quality features. Results show that smart HVAC control is a viable way to provide occupant comfort, as well as contribute to the integration of renewable generation and increase energy efficiency in buildings and microgrids.

Real-time building heat gains prediction and optimization of HVAC setpoint: An integrated framework

Heating, ventilation and air-conditioning (HVAC) systems are responsible for a large part of building energy consumption. Lowering HVAC's energy consumption without compromising occupants' thermal satisfaction has been the focus of recent research. Existing studies showed that this requirement could be met by optimizing HVAC setpoints or using demand-based control strategies. However, such strategies require coupling with dynamic information such as occupancy to be effective. This study proposes an integrated framework to achieve real-time optimization of HVAC setpoints. This framework has three core components: a vision-based camera for detection, predictive HVAC energy and thermal comfort models, and HVAC temperature setpoint optimizer. Vision-based cameras were used to identify activities of occupants and equipment usage and predict a real-time value of internal heat gains. By feeding the information into the predictive HVAC energy and thermal comfort models, the HVAC load (heating or cooling) and the level of occupants' thermal dissatisfaction, predicted percentage dissatisfied were obtained using developed models, based on shallow neural networks. Afterwards, the HVAC temperature setpoint optimizer determined an optimal temperature setpoint following two optimization rules. When occupants were absent, HVAC system would be turned off to save energy. When they were present, an optimal temperature setpoint was determined by using Pareto-front. Based on the initial findings, the utilization of this framework can potentially lead to a reduction of HVAC heating energy by up to 36.8% and occupants' thermal dissatisfaction by up to 5.26%. In the summer, the savings of HVAC cooling energy would range from 3.5% to 33.9%, whilst occupants' thermal dissatisfaction could be decreased by 0.17–2.89%. Overall, this paper paved a path to achieve a win-win on HVAC energy savings and comfort by combining artificial intelligence techniques and building services.

Virtual Power Plant Control for Large Residential Communities Using HVAC Systems for Energy Storage

Heating, ventilation, and air-conditioning (HVAC) systems use the most electricity of any household appliance in residential communities. HVAC system modeling facilitates the study of demand response (DR) at both the residential and power system levels. In this article, the equivalent thermal model of a reference house is proposed. Parameters for the reference house were determined based on the systematic study of experimental data obtained from fully instrumented field demonstrators. Energy storage capacity of HVAC systems is calculated and an equivalent state-of-charge is defined. The uniformity between HVAC systems and battery energy storage system is demonstrated by DR control. The aggregated HVAC load model is based on the reference house and considers a realistic distribution of HVAC parameters derived from one of the largest smart grid field demonstrators in rural America. A sequential DR scheme as part of a virtual power plant control is proposed to reduce both ramping rate and peak power at the aggregated level, while maintaining human comfort according to ASHRAE standards.

상업용 건물 내 HVAC 시스템의 온라인 지도학습 기반 최적 수요반응

This paper proposes an online supervised-learning-based strategy for the optimal operation of a heating, ventilation, and air conditioning (HVAC) system in a commercial building. Conventionally, it requires time-consuming techniques to estimate physics-based parameters, preventing practical applications to building energy management systems (BEMSs). In this paper, an artificial neural network (ANN) is trained online with building energy data and equivalently represented using a set of linear and nonlinear equations. An optimization problem is formulated using the equation set and repeatedly solved for every day, producing data on optimal HVAC load schedules under various conditions of building thermal environments. Given the data, a BEMS updates the ANN-based model of an HVAC system and the optimization problem for optimal HVAC load scheduling. The case study results verify that the proposed strategy is effective in exploiting an HVAC system as a price-based demand response resource.

Load shifting and energy conservation using smart thermostats in contemporary high-rise residential buildings: Estimation of runtime changes using field data

As the proportion of the population who resides in urban centers grows, the number of dwellings in high-rise residential buildings is also increasing. In Canada, heating, ventilation, and air conditioning (HVAC) typically accounts for over half of all energy use in this building type and, as such, consideration of these loads is key to effective energy demand-side management. Smart thermostats present a new opportunity conserve energy and shift electricity load to off-peak periods in these buildings through modifications to HVAC control strategies. In this study, three thermostat control strategies were tested in 49 suites across two contemporary high-rise residential buildings: 1) baseline operation (thermostat operating as a standard programmable thermostat); 2) occupancy-based control (thermostat operating using an occupancy-reactive control strategy); 3) load shifting control (thermostat operating using a pre-conditioning strategy). HVAC runtime data was collected from smart thermostats installed in the suites and was used to develop data-driven regression models to estimate baseline suite HVAC runtime based on weather conditions and suite characteristics. Thermostat-measured HVAC runtime data for periods in which occupancy-based or load shifting control strategies were in use in the suite was then compared with estimated baseline runtime for similar outdoor conditions. Occupancy-based control was found to reduce HVAC system runtime during the cooling seasonby 5.9% ± 46% on average. On aggregate, the load shifting control strategy was not effective at reducing peak period HVAC load during the cooling season. The strategy was able to reduce peak period loads in a subset of suites substantially, which may be leveraged to reduce electricity demand during capacity-constrained periods of grid operation, however, based on marginal emissions factors for Ontario’s electricity grid, even in these suites, the strategy was not effective in reducing GHG emissions overall.

Influence of climates and materials on the moisture buffering in office buildings: a comprehensive numerical study in China.

In recent years, moisture buffering materials for interior finishing have received much attention for their ability to regulate indoor humidity passively. It is necessary to investigate the potential of such materials' moisture buffering performance before application because the effect is highly climate and material dependent. However, existing studies in China lack a comprehensive overview of the moisture buffering potential of different interior finishing materials throughout the large country with a wide spectrum of climates. This paper aims to outline the moisture buffering potential for office buildings in various climates in China through numerical methods. Specifically, simulations in 15 representative Chinese cities are conducted with five interior finishing materials under two heating, ventilation, and air conditioning (HVAC) scenarios. The results show that the moisture buffering materials hold a general potential to regulate indoor humidity conditions and reduce buildings' HVAC load. Such benefits are evident in the mild climate but weak in humid areas. The moisture buffering effect also displays significant seasonal variations and could worsen indoor humidity conditions in some cases, indicating the importance of utilizing moisture buffering materials properly. In addition, although moisture buffering materials can reduce the HVAC load, the reduction is limited, within 3 kWh/m2, in most simulated cases. The energy-saving benefits of moisture buffering materials should thus not be over-emphasized. Finally, suggestions are put forward to instruct the choice of interior finishing material according to climate and buildings' HVAC scenarios.

Parametric study of solid-solid translucent phase change materials in building windows

Thermal energy storage and solar radiation management are crucial to improve the sustainability and energy efficiency of buildings. Compared with the implementation of phase change materials (PCMs) in opaque components, the energy saving potential of incorporating PCMs in transparent glazing windows is much less studied and not well understood. Here we present a comprehensive parametric study of novel PCM windows for building energy saving with a focus on optimizing and quantitatively distinguishing the contributions from the optical and thermal properties of the PCM, which is particularly useful for the design of solid-solid PCM windows. We investigate a reference commercial office building using EnergyPlus by developing an equivalent model of our PCM window that is compatible with EnergyPlus’s modeling capabilities. Compared with a clear-clear double-pane window, the integration of 3 mm solid-solid PCMs with optimal properties in warm, mixed, and cold climates can respectively save up to 17.2%, 14.0%, and 5.8% energy for the HVAC (heating, ventilation, and air conditioning) system, and 9.4%, 6.7%, and 3.2% energy for the whole building. We also demonstrate that these energy savings are most sensitive to the solar absorptance of PCMs for all three climates. The optimal transition temperature varies with climate and is related to the climate and solar radiation heat gain. Other issues are also briefly discussed, such as hysteresis, window orientations, and the effect of interior lighting. Although the optimal PCM windows show energy saving performance comparable with low-emissivity windows, the PCM windows provide a unique advantage in terms of shifting HVAC loads which can provide benefits to the electrical grid.

Decoupled building-to-transmission-network for frequency support in PV systems dominated grid

Tendency towards installation of distributed photo-voltaic (PV) systems has led to an increased emphasis on grid frequency control. Grid-interactive buildings equipped with heating ventilation and air conditioning (HVAC) system has a great potential to regulate the frequency in renewable energy resources rich grids. This paper integrates distributed PV systems in a decoupled building-to-transmission-network (B2TN) and explicitly formulates the interaction between a grid and the buildings through real time pricing (RTP). As grid frequency conveys the information about operating conditions of a power system, therefore, frequency based RTP generators namely; linear, hyperbolic tangent and inverse hyperbolic tangent are used. A price responsive model predictive controller (MPC) for optimal scheduling of HVAC load is developed where reference temperature set point is dynamically adjusted subject to RTP. Moreover, the clear and cloud covered sky impacts of PV power generation on frequency and RTP deviations are investigated. Comparatively, inverse hyperbolic tangent model maps the frequency deviations on a wider RTP range which increases the scale of reference temperature set point resulting peak frequency deviation suppression up to 40% and load regulation beyond 12 MW without inherently affecting the building electricity cost when compared to ordinary MPC (without demand response service).

Optimisation of a smart energy hub with integration of combined heat and power, demand side response and energy storage

An operational cost minimisation model is established for a smart energy hub (S.E. Hub) consisting of a combined heat and power (CHP) unit, a heating, ventilation and air-conditioning (HVAC) system, and thermal and electricity storage units. The optimal operation of CHP is combined with the load management of HVAC under a time-of-use (TOU) tariff. The heat and power split ratio of CHP is dynamically determined during the operation. The scheduling of HVAC load and the charging/discharging of energy storage systems are also determined through the optimisation model. The energy management system can therefore shift the load demand and manage energy supply simultaneously. System operation requirements and environment factors including the outdoor air-temperature variation, seasonal variation, and battery degradation are considered. Comprehensive case studies are carried out to examine the effectiveness of the proposed strategy, from which insights are obtained for different energy management strategies and possible upgrade of S.E. Hub. Simulation results reveal that dynamic control of the CHP heat and power split ratio is an effective way to save the total operational cost, and a clear cost saving is shown through the proposed optimal operation strategy.

Demand-side flexibility and demand-side bidding for flexible loads in air-conditioned buildings

Demand-side flexibility (DSF) has been touted as a possible solution to the challenges in power system operation arising from increasing intermittent renewables penetration and the emergence of electric vehicles. In Singapore, where around 24 to 60% of electricity demand in buildings could be attributed to heating, ventilation, and air conditioning (HVAC) purposes, air-conditioned buildings represent a significant flexibility resource which could be used to provide DSF and help tackle these challenges. This study aims to investigate the DSF potential of Singapore’s building stock and to explore how this potential could be realized through demand-side bidding. To this end, a building energy modeling tool with explicit modeling of the relationship between occupant comfort and HVAC load with model predictive control, CoBMo, is used. CoBMo allows optimal load scheduling to be expressed as a linear programming problem: minimizing overall electricity cost while maintaining occupant comfort. A price-based market clearing model is developed to evaluate demand-side bidding implementation, for which a case study on Singapore’s Downtown Core district is developed. Three scenarios with possible future utility-scale photovoltaic (PV) penetration in Singapore’s electricity system are explored, alongside a sensitivity analysis and a comparison between centralized dispatch and demand-side bidding with price-quantity pairs and linear curves. Results of the analysis show that DSF potential varies between building types, depending on cooling load and occupancy schedule. When extreme price fluctuations happen in future Singapore electricity market with 10 GWp PV penetration, demand-side bidding could aid consumers to utilize their DSF potential by encouraging more effective energy use and in turn, reducing their total electricity cost.

Optimal HVAC System Operation Using Online Learning of Interconnected Neural Networks

Optimizing the operation of heating, ventilation, and air-conditioning (HVAC) systems is a challenging task that requires the modeling of complex nonlinear relationships among the HVAC load, indoor temperature, and outdoor environment. This article proposes a new strategy for optimal operation of an HVAC system in a commercial building. The system for indoor temperature control is divided into three sub-systems, each of which is modeled using an artificial neural network (ANN). The ANNs are then interconnected and integrated into an optimization problem for temperature set-point scheduling. The problem is reformulated to determine the optimal set-points using a deterministic search algorithm. After the optimal scheduling has been initiated, the ANNs undergo online learning repeatedly, mitigating overfitting. Case studies are conducted to analyze the performance of the proposed strategy, compared to strategies with a pre-determined temperature set-point, an ideal physics-based building model, and other types of machine learning-based modeling and scheduling methods. The case study results confirm that the proposed strategy is effective in terms of the HVAC energy cost, practical applicability, and training data requirements.