HVAC Energy Consumption Research Articles

Prediction of building HVAC energy consumption based on least squares support vector machines

Air conditioning, as an essential appliance in daily life, has the function of ensuring comfortable room temperature, but it is also accompanied by a large amount of power consumption. Consequently, the study suggests an energy consumption prediction model based on improved genetic algorithm—least squares support vector machine—to accurately predict the energy consumption of building heating, ventilation, and air conditioning. This model uses the improved genetic algorithm for regularization parameter and kernel parameter optimization to prevent overfitting and underfitting issues. According to the testing results, the least squares support vector machine, an upgraded genetic algorithm, may accomplish convergence faster than other algorithms, taking only 0.2 milliseconds to finish. In addition, the average relative error of the improved genetic algorithm- least squares support vector machine did not exceed 0.6%. In the energy consumption prediction for the whole year of 2022, the average error of the improved genetic algorithm-least squares support vector machine was only 2.0 × 106 kWh, and the prediction accuracy could reach up to 97.2%. The above outcomes revealed that the energy consumption prediction model can accurately predict the air conditioning energy consumption, which provides a strong support for the control and optimization of the air conditioning system.

Energy performance evaluation of the ASHRAE Guideline 36 control and reinforcement learning–based control using field measurements

This study evaluates the energy performance of ASHRAE Guideline 36–compliant control (ASHRAE 36 control) and reinforcement learning (RL)–based control through experimental field tests and a simulation study. Three field tests were conducted at Oak Ridge National Laboratory’s commercial building test facility in Oak Ridge, Tennessee: a baseline with a baseline conventional control, a test with ASHRAE 36 control, and a test with RL-based control. The selected ASHRAE 36 controls were trim and respond control, as well as variable air volume (VAV) box control. We compared the measured supply air temperature of the rooftop unit, VAV box supply air temperature, and VAV box supply airflow rate across the three test cases. The field data indicated that ASHRAE 36 controls operated as specified by ASHRAE Guideline 36. Based on these data, ASHRAE 36 control achieved a 45 % reduction in hourly averaged HVAC energy consumption compared with the baseline, and RL-based control achieved a 66 % reduction. These potential annual energy savings were confirmed using a calibrated whole-building energy model. Compared with the baseline, ASHRAE 36 control reduced HVAC energy consumption by 42 %, and RL-based control achieved a 54 % reduction. Furthermore, RL-based control reduced total HVAC energy consumption by 21 % more than ASHRAE 36 control.

Protocols for planning micro-zones to facilitate occupant-centric control (OCC) to reduce HVAC energy consumption in Indian open-plan offices

Protocols for planning micro-zones to facilitate occupant-centric control (OCC) to reduce HVAC energy consumption in Indian open-plan offices

BEForeGAN: An image-based deep generative approach for day-ahead forecasting of building HVAC energy consumption

This study presents a pioneering approach in building energy forecasting by introducing a novel reformulation framework that transforms the forecasting task into an image inpainting problem. Based upon the fundamental notion that “forecasting is about generating data of the future”, we propose BEForeGAN, an innovative deep generative approach for day-ahead Building HVAC Energy consumption Forecasting based on multi-channel conditional Generative Adversarial Networks (GANs) with U-Net generators. Our method is evaluated using 96,360 hourly HVAC energy consumption records from 11 buildings, demonstrating significant accuracy improvements of 17%∼76% and a substantial variability reduction of 3%∼96% compared to a suite of conventional and deep learning benchmark models across individual-building and zero-shot cross-building forecasting tasks. Notably, BEForeGAN exhibits robustness to noisy inputs, with an increase below 3% in Coefficient of Variation of Root Mean Square Error (CV-RMSE) for each 10% noise increment. This study addresses critical gaps in existing literature by showcasing the untapped potential of GANs as standalone forecasters, advocating for further exploration of two-dimensional (2D) GAN-based methods in building energy forecasting, and emphasising the need for more studies focusing on cross-building forecasting tasks. In conclusion, our findings underscore the transformative impact of GANs in revolutionising building energy forecasting practices, paving the way for enhanced energy-efficient building management and beyond.

Load prediction and energy efficiency improvement of steelmaking waste heat centralized heating systems under mild climate in China

HVAC energy consumption accounts for more than 50 % of the total building energy consumption globally and using industrial waste heat has huge potential for energy savings in central heating systems. Under the background of the use of renewable energy and the gradual rise of central heating in mild climate areas in China, it is worth paying attention to the problem of excessive energy consumption caused by the inaccurate load prediction of central heating systems when the ambient temperature changes. L City, Guizhou Province, is the first city with central heating in southern China. The temperature variation during winter in L City can manifest the climatic characteristics of a mild region. Therefore, based on the operational data of the steel waste heat central heating system in L City, Guizhou Province, China, during the heating season of 2022–2023, this study discusses the load prediction and energy-saving optimization strategy of the central heating system in a mild climate. SketchUp was used to conduct 3D modeling of the actual buildings in the heating area and TRNSYS was imported to simulate the system load. The difference between the heating load forecast and the actual operating data was analyzed in detail by using the calculation results. Based on the simulation results, the waste heat utilization strategy was adjusted and the influence of different heating schemes on the pump energy consumption under different load demands was discussed. The results reveal that based on the temperature change rule, the accurate load prediction can lead to a 28.64 % saving of the system energy. Concerning system energy consumption, by adjusting the water flow and choosing the large and small pump system, the energy saving amounts to 39.48 % compared with the traditional single-pump system. Meanwhile, in the transition season when the heating demand is less than 20 MW, the adjusted heating scheme can achieve a 38.5 % saving based on the constant flow scheme and a 5.4 % saving based on the constant temperature difference scheme. This article provides a scientific energy-saving solution for heating in mild climates using industrial waste heat, not only reducing energy consumption but also providing an important reference for the energy-saving renovation of heating systems in similar areas.

Investigating enhanced thermal comfort and energy efficiency through strategized airflow in Micro-Zonal Occupant-Centric Control (MZOCC)

The potential of Micro-Zonal Occupant Centric Control (MZOCC) to save HVAC energy consumption in medium sized open-plan offices has been established in literature. This is done by virtually dividing a thermal zone into micro-zones and allowing independent diffuser-level control in each micro-zone when the micro-zone is occupied. In continuation, there is a need to ensure that thermal comfort is achieved within micro-zones under such localised control. This is important because several forms of discomfort such as draft, horizontal thermal asymmetry and vertical thermal gradients may arise in MZOCC. Further, the effect of MZOCC airflow control strategies, such as setback flow and setback temperature, which were proposed in previous studies on thermal comfort of occupants needs to be evaluated. In an attempt to address these research gaps, this study explores thermal comfort for different scenarios of diffuser arrangements, airflow control strategies and occupancy conditions and also explores the effect of varying supply velocities used in setback flow and setpoint temperatures used as setback temperatures on air distribution and thermal comfort.Results show that low PMV values, increased draft discomfort and heavy thermal gradients are observed for certain scenarios of MZOCC. Tuning airflow control by choosing appropriate setback flow or setback temperature helps in restoring thermal comfort. As different forms of discomfort are observed in different cases, it is important to plan micro-zones and control airflow, such that, MZOCC does not violate thermal comfort criteria while optimising energy efficiency. This study gives a framework for selecting appropriate airflow control strategies for a selected diffuser arrangement for a given occupancy condition. Comfort-based MZOCC that uses appropriate airflow control strategy saves about 60% energy when the zone is half occupied and about 85% energy when the zone is quarter occupied. Results also show that, improving the diffuser arrangement improves energy savings and increases the options of airflow control strategies that can be used. Also, different airflow control strategies behave differently for each diffuser arrangement and has to be chosen separately for given diffuser setting and occupancy condition.

Comparasion of HVAC Energy Consumption Prediction in an Academic Building using LSTM and DNN

Energy consumption information is a collection of information obtained from datasets that is useful for making decisions for energy conservation. In this paper, we proposed a modern approach based on LSTM and DNN. While many researchers have employed these methods for predicting energy consumption, this paper seeks to compare their efficacy to determine which is superior. The comparative analysis in question employs accuracy metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R2) values. Furthermore, the accuracy metric outcomes indicate that the LSTM method surpasses the DNN approach in terms of the R-squared (R2) value, with respective scores of 0.931 and 0.782. Meanwhile, for other accuracy metrics, the DNN method outperforms LSTM. Nevertheless, the performance of the two proposed methods is excellent, as evidenced by the R-squared (R2) value exceeding 0.75, which aligns with modeling standards observed in numerous research studies.

Investigation of the indoor CO2 removal efficiency and fresh air energy savings of living walls in office spaces

Elevated indoor CO2 levels might have adverse effects on human health. However, conventional physical and chemical methods for indoor CO2 removal face the challenges of high energy consumption, low efficiency at low CO2 concentrations, and high costs. Furthermore, the introduction of outdoor air to lower indoor CO2 concentrations results in significant HVAC energy consumption. Aligning with office hours and the natural light cycle, the utilization of photosynthesis in living walls (LWs) offers an energy-efficient and sustainable solution for the mitigation of high CO2 levels in office spaces. This study experimentally investigates the impacts of the carbon fixation pathways, light flux density, and substrate moisture content on the CO2 removal rate of LWs in two identical rooms. The findings provide practical suggestions for plant species selection, lighting design, and irrigation management in office spaces to enhance the CO2 removal efficiency of LWs. Additionally, the fresh air energy-saving effects of LWs under different scenarios are accurately simulated in EnergyPlus. The results demonstrate that choosing C3 plants over CAM plants in LWs yields higher CO2 removal efficiency. The activation of artificial lighting is recommended when the surface light flux density of LWs drops below the light compensation point (LCP), ensuring favorable conditions for growth. In a 30-m2 office room accommodating two and three occupants, LWs can respectively reduce the demand for fresh air by 13.9 %–38.5 % and decrease fresh air energy consumption by 11.2 %–28.2 %.

Thermochromic Smart Windows with Ultra-High Solar Modulation and Ultra-Fast Responsive Speed Based on Solid–Liquid Switchable Hydrogels

Thermo-responsive hydrogels can dynamically modulate incident light, providing a broad prospect for development of smart windows, which are of pivotal importance for energy conservation in buildings. However, these hydrogels normally exhibit slow response speed and tend to contract over extended phase transition, compromising structural integrity of smart windows. In this study, a solid–liquid switchable thermochromic hydrogel, denoted as SL-PNIPAm, was synthesized by cross-linking PNIPAm with AMEO through dynamic imine bonds. Due to its distinctive solid–liquid transformation characteristics, SL-PNIPAm demonstrates rapid response time (within 5 s) and retains structural integrity without undergoing shrinkage during heating/cooling and freezing/thawing cycles. SL-PNIPAm can also be encapsulated within 2 glass panels to prepare smart windows, which showed extraordinary luminous transmittance ( T lum = 96.8%) and solar modulation ability (Δ T solar = 89.7%) and effectively reduced the indoor temperature (22 °C) in a simulated indoor experiment. Energy consumption simulation investigations are performed in diverse cities. The results reveal that SLW is capable of achieving a remarkable 54% reduction of HVAC energy consumption, leading to substantial decrease in CO 2 emissions by up to 40 kg m −2 annually. This work develops a new hydrogel system with outstanding durability for smart windows and will promote the development and renovation of thermochromic smart windows.

Correlation of AC energy consumption and passive thermal comfort with floor levels in tropical high-rise residential dwellings

The relationship between thermal comfort, building floor levels, and HVAC energy consumption in tropical high-rise residential buildings remains unclear. These buildings face heavy cooling demands due to their immense height and volume, as well as hot-humid weather found in the tropics. Architects and building developers understand that an increase in a building's floor count increases its energy requirements, but the impact on occupant thermal requirements and AC energy consumption needs further investigation. This study aimed to evaluate the relationship between passive thermal comfort, AC energy consumption, and floor levels in tropical high-rise residential buildings through survey and experimental methods. The results showed a significant relationship between thermal sensation votes and building floor levels, as well as AC energy consumption and floor levels. The study also found a strong correlation between thermal sensation votes and predicted mean votes, AC energy use, and predicted people dissatisfied. The optimal cut-off floors for thermal dissatisfaction according to (TSV) are 22nd floor and 8th floor in summer and monsoon seasons respectively. With a 90% sensitivity and 92% specificity. This research highlights the importance of addressing thermal comfort in high-rise buildings to improve energy efficiency and thermal comfort in tropical climates.

Prediction of window opening behavior and its impact on HVAC energy consumption at a residential dormitory using Deep Neural Network

Prediction of window opening behavior and its impact on HVAC energy consumption at a residential dormitory using Deep Neural Network

Heating and ventilation performance investigation of a novel linear slot diffuser with adaptive outlet area for near window applications

The linear slot diffuser has ideal cooling performance for near-window applications, and is used for ventilation by utilizing the coandă effect in some cases. However, it has insufficient throw distance due to buoyancy impact during heating periods. And airflow near window surfaces increases convection heat transfer, resulting in extra HVAC energy consumption. Our research focuses on a prototype linear slot diffuser with an adaptive outlet area. Two deflection panels are installed for adjusting the outlet area depending on temperature or usage scenarios. Supply air has a low velocity and wide diffusion range when the panels are open. It can utilize the coandă effect as well as keep convection heat transfer within an appropriate range. Closing the panels will halve the supply area and completely change airflow diffusion and turbulence characteristics. This is considered suitable for heating, but the mounting location needs to be re-evaluated. Therefore, this prototype's heating and ventilation performance is numerically investigated using a low-Reynolds number turbulence model with fine meshes. Temperature, airflow, tracer gas distribution in a typical office space, and the ADPI, DR, and age-of-air indexes are compared before and after outlet area adjustment. Diffuser mounting locations and exhaust methods are also altered to balance heating and ventilation efficiency. As a result, a proper installation location for this prototype is suggested. The adaptive supply area significantly improved this terminal's heating and ventilation performance. Temperature stratification was reduced to a maximum of one-tenth, and impinging jets or displacement ventilation were observed in some cases.

An energy consumption prediction method for HVAC systems using energy storage based on time series shifting and deep learning

The prediction of building energy consumption plays a crucial role in responding to energy demands and achieving low-carbon control through energy saving. In this study, we focused on peak shaving and valley filling in the energy consumption of office building energy-storage HVAC systems. A time series shifting method based on the Pearson correlation coefficient was combined with a gate recurrent unit (GRU) deep learning model to predict HVAC energy consumption. Additionally, we explored the adaptability of this method to non-deep learning support vector regression (SVR) and random forest (RF) models. The results demonstrated that the Kaiser-Meyer-Olkin test values of HVAC energy consumption, meteorological parameters, and indoor environmental parameters improved by 10.8%. The GRU model exhibited a 12% reduction in the root mean square error (RMSE), and the coefficient of determination (R2) was 0.850. The RMSE of the RF model decreased to 12.24 kW·h, with a 12% increase in R2 to 0.760. The SVR model achieved an RMSE of 12.59 kW·h and an R2 of 0.793. Therefore, this method can effectively improve the prediction accuracy of models by enhancing the correlation between their input and output variables.

Demystifying energy savings from dynamic temperature setpoints under weather and occupancy variability

Building temperature setpoints affect both HVAC energy consumption and occupant comfort. To reduce HVAC energy usage, researchers often investigate how system operations can be optimized under weather and occupancy variability subject to a fixed setpoint that minimizes any possible discomfort. While previous research has explored the selection of dynamic setpoints to minimize HVAC energy consumption based on outdoor temperature, they have often neglected the impact of varying occupancy rates on the setpoints. This paper aims to demystify energy savings derived from fixed and dynamic temperature setpoints under weather and occupancy variability and explores the additional energy savings that can be achieved through dynamic temperature setpoints. An exhaustive HVAC zone temperature setpoint optimizer was developed to determine dynamic setpoints with respect to weather and occupancy (i.e., setpoints that minimize HVAC energy consumption at different occupancy rates based on outdoor weather). U.S. DOE reference building energy models for small, medium, and large office buildings were simulated at 17 climate zones, 4 occupancy rates (25%, 50%, 75%, 100%) and 7 setpoints (19.5°C to 25.5°C at 1°C interval). It was found that, both fixed and dynamic setpoints benefit from the energy reduction of approximately 2-4% from the lower heat generated by the occupants at lower occupancy rates. However, at outdoor temperatures between 5°C and 32°C where occupant heat loads can swing the building between heating, free-running, and cooling modes, dynamic setpoints yield additional 2-10% energy savings, compared to fixed setpoints.

A novel and lean data-based method to calculate the actual HVAC zone energy consumption and cooling load in sustainable smart cities using a single temperature sensor

Sustainability and energy savings are two intertwined research aims for humanity’s long-term survival, aligned with the Paris Agreement and the Egyptian vision of 2030. The purpose of this research is to minimize the cost needed to measure the HVAC energy consumption in educational and commercial buildings to save energy for energy efficiency strategies to serve the future smart and sustainable cities. These facilities are among the most energy-consuming loads, and this research proposes a technique to determine real HVAC energy consumption and cooling load using a single-sensor method. Calculating the as-built HVAC energy usage and real cooling load, especially in complex HVAC systems like VRV, which are some of the most challenging gaps, is achieved through a revolutionary and cost-effective approach. The proposed approach computes the actual HVAC energy consumption of each specific zone in the building using data from a single temperature sensor. Furthermore, the real and instantaneous cooling load of each zone was calculated, and the results show a promising agreement between the proposed techniques and the real measured consumption of the HVAC system. This approach can be integrated into the BMS building management system to determine the actual HVAC energy usage and cooling load for each zone individually in real time, enabling significant energy reduction decisions with optimal cost efficiency. Furthermore, it can be used by the BMS system as a real-time On-Board Diagnostic of the HVAC system.

Thermal heat transfer and energy modeling through incorporation of phase change materials (PCMs) into polyurethane foam

Decreasing HVAC energy consumption through insulation effectiveness enables low energy use, low carbon emissions, and high thermal comfort in sustainable buildings. PCMs for energy storage are an innovative option, but in buildings, their high thermal conductivity is a concern.The PCM latent heat of fusion and thereby it’s transition temperature has been a key parameter in PCM selection but little is known of the effect of PCM on building energy contributions arising from increasing thermal conductivity (k), density (ρ), and specific heat capacity (Cp). To resolve this, in this paper, two PCMs with transition temperature above and below the outdoor temperature incorporated in highly porous flexible polyurethane foam were evaluated using a one-dimensional (1D) foam core panel built in COMSOL Multiphysics®. The simulations were run using the summer season in a humid subtropical climate zone with an outdoor temperature of 35 °C. It was found that apart from the latent heat of fusion, the combined effects of high ρ and Cp could mitigate the increased k of PU-PCM composites to improve the insulation performance. Building energy modeling using EnergyPlus with the foam core incorporated into a structural insulated panel (SIP), revealed that the use of PCMs regardless of the transition temperature could reduce annual electricity consumption by 15–20%, with a significant amount of energy savings arising from the cooling load in summer.

Using building cooling for load shifting on a 5-minute wholesale energy market

To achieve carbon neutrality there must be a significant increase in the proportion of renewable generation. Energy storage and demand flexibility will accommodate more solar and wind generation. Some energy markets in Australia, northern Europe and the USA have moved or are moving to a 5-min settlement period to increase energy flexibility. Commercial building’s HVAC systems could capitalise on new market conditions through 5-min load shifting strategies that have negligible impact on occupant comfort. Here the effectiveness HVAC load shifting strategies for cost arbitrage in 5-min wholesale electrical energy markets are examined. Five strategies are compared using global zone setpoint adjustment and chilled water leaving setpoint adjustment. Results show significant energy flexibility can be achieved without violating occupant comfort. High priced 5-min settlement periods can be successfully coasted over with no HVAC energy consumption for temperatures under 36 °C. Over a 10 week period the case study achieved 14.2% energy cost savings.

SIREN – smart ventilation for infection risk mitigation and HVAC energy efficiency: a case study amid the COVID-19 pandemic

The COVID-19 pandemic has underscored the need for effective ventilation control in public buildings. This study develops and evaluates a smart ventilation control algorithm (SIREN) that dynamically adjusts zone and system-level HVAC operation to maintain an acceptable COVID-19 infection risk and HVAC energy efficiency. SIREN uses real-time building operation data and Trim & Respond control logic to determine zone primary and system outdoor airflow rates. An EnergyPlus and CONTAM co-simulation framework was developed to assess its performance across various control scenarios and US climate zones. Results show that SIREN can flexibly control infection risk within a customized threshold (e.g. 3%) for every zone, while traditional controls cannot. At the building level, SIREN’s HVAC energy consumption is comparable to a fixed 70% outdoor airflow fraction scenario, while its infection risk is lower than the 100% outdoor airflow scenario, illustrating its potential for safe and energy-efficient HVAC operation during pandemics.

Energy-saving potential in Indian open-plan offices using Micro-Zonal Occupant Centric Control (MZOCC)

HVAC energy consumption can be reduced by air-conditioning only the regions which are occupied. Though occupancy-based smart controllers are common in this regard, they are mostly used for physically separated HVAC zones. Only limited studies have explored localized conditioning within HVAC zones. Micro-zonal occupant-centric control (MZOCC) aims at maintaining a target air temperature only in the virtual micro-zones where occupants are present, leaving other regions unconditioned. There is a need to understand the potential of MZOCC in terms of investment and energy savings and develop strategies for improving it. This study addresses these research gaps by exploring MZOCC in a typical Indian open-plan office using an experimentally validated CFD model. Cooling pattern, energy consumption and thermal contours for varying (1) diffuser arrangement, (2) airflow control, and (3) occupancy conditions are explored.The study’s key findings are (1) MZOCC induces substantial energy savings at minimal additional investment; (2) Strategizing diffuser location and airflow control are required to avoid merging of air jets and heavy thermal gradients; (3) Using a low-velocity flow (setback-flow) or maintaining a higher setpoint temperature (setback-temperature) in unoccupied micro-zones improves the efficiency of MZOCC. This study extends the literature on MZOCC by addressing operational challenges in MZOCC.

HVAC Optimal Control Based on the Sensitivity Analysis: An Improved SA Combination Method Based on a Neural Network

Aiming at optimizing the energy consumption of HVAC, an energy conservation optimization method was proposed for HVAC systems based on the sensitivity analysis (SA), named the sensitivity analysis combination method (SAC). Based on the SA, neural network and the related settings about energy conservation of HVAC systems, such as cooling water temperature, chilled water temperature and supply air temperature, were optimized. Moreover, based on the data of the existing HVAC system, various optimal control methods of HVAC systems were tested and evaluated by a simulated HVAC system in TRNSYS. The results show that the proposed SA combination method can reduce significant computational load while maintaining an equivalent energy performance compared with traditional optimal control methods.