Variable Refrigerant Flow Air-conditioning System Research Articles

Analysis and prediction of energy consumption in office buildings with variable refrigerant flow systems: A case study

Accurately predicting building air-conditioning energy consumption is particularly important for energy management. However, for small datasets, there is a lack of simple and effective prediction methods applicable to multiple buildings. In order to fully explore the energy consumption mode of Variable Refrigerant Flow (VRF) air conditioning system and improve the accuracy of the model. This study uses the weather data of an outdoor meteorological data collection system and the air conditioning system and energy consumption data of an office building in Jinan. Initial analysis revealed that occupant behavior and daily variations in outdoor air temperatures significantly impact the energy consumption of air conditioning systems. Then, by applying the random forest algorithm and Pearson correlation analysis, the study identified daily average outdoor air temperature and VRF indoor unit running time as critical features for prediction. Subsequently, three machine learning models—Multiple Linear Regression (MLR), Back Propagation Neural Network (BPNN), and Long Short-Term Memory (LSTM) neural network—were developed and assessed using a 4:1 training-to-testing set ratio. Comparative analysis revealed that all models performed robustly, with the MLR model exhibited superior predictive accuracy (R2 (Coefficient of Determination) = 0.98, MAE (Mean Absolute Error) = 0.005 kWh/(m2·day), and RMSE (Root Mean Square Error) = 0.007 kWh/(m2·day) for the testing set) and simplicity. Furthermore, the effectiveness of the MLR model in handling small sample sizes was confirmed through cross-validation of data from two additional office buildings, highlighting its suitability for predicting energy consumption of VRF air conditioning systems in office buildings.

Development and validation of intelligent load control for VRF air-conditioning system with deep learning based load forecasting

Variable refrigerant flow (VRF) air-conditioning systems have seen significant growth in Asia and its application is expanding globally. Despite the expanded application, most previous studies have focused on developing fault detection and diagnostics to achieve energy-efficient operations than on predicting power consumption. It's very difficult to predict the electrical consumption owing to its complex system configuration and various control strategies. A new control strategy is described for optimal adjustment of the desired target level based on time series forecasting using the optimized sequence to sequence model for VRF systems. Sequence to sequence (seq2seq) model with attention mechanism and Bayesian optimization is developed to predict accurate hourly and daily forecasts and rapid feedback control for fluctuating power consumption for VRF systems. The optimized seq2seq model is integrated into the intelligent load control (ILC). ILC can be used to manage VRF systems by dynamically prioritizing indoor units for curtailment using both quantitative inputs and qualitative rules. Overall, the results demonstrate that the deep learning based control allows coordination of the controllable loads of VRF systems in three commercial buildings. ILC with deep learning manages the power consumption within a desired target level, as well as indoor temperature reflecting the status of controlled indoor units, as objective functions of the control algorithm.

Development of TRNSYS model for energy performance simulation of variable refrigerant flow air-conditioning system combined with energy recovery ventilation

ABSTRACT The variable refrigerant flow air-conditioning system is an HVAC system that can perform at a high capacity with low consumption thanks to its variable-speed compressor. The paper introduces a TRNSYS model to build a simulation model to calculate the energy performance of an existing variable refrigerant flow system and to build a model that can be used as a reference when a VRF system is proposed to a certain situation. The TRNSYS model was compared with the actual energy consumption to see the data agreement between the two models. Temperature, Relative Humidity, and energy consumption were metered using proper instruments, and it was compared with the obtained simulation results. The validation of the simulation model showed close values to the actual system, as the obtained Normalized Mean Bias Error (NMBE) between the simulation and measured values for temperature and relative humidity was 4.3 and 7.6%, respectively. While it was around 7.8% for the total energy consumption. Besides, the paper proposed an Energy Recovery Ventilation to be simulated with the existing TRNSYS model to compare it with the same system without ventilation to see if it is feasible to add an Energy Recovery Ventilation unit to the existing system. It shows a worthy reason to be used, as it saves 18.8% annually of the energy consumption of the system.

Fault diagnosis of VRF air-conditioning system based on improved Gaussian mixture model with PCA approach

Abstract The timely fault diagnosis of HVAC systems is important for building energy saving, equipment maintenance and indoor comfort. The Gaussian mixture model method has rarely been studied in the fault diagnosis application of HVAC systems. Therefore, a novel fault diagnosis strategy is proposed based on the Gaussian mixture model (GMM) method for the variable refrigerant flow air-conditioning system. To reduce excessive input variables resulting in large model complexity and long running time, the principal component analysis approach (PCA) is used to perform data dimensionality reduction. Therefore, the fault diagnosis model combining the Gaussian mixture model and principal component analysis is established, which is evaluated using the four types of faults of the variable refrigerant flow system. These faults include refrigerant undercharge, refrigerant overcharge, outdoor unit fouling and four-way reversing valve faults. Experiments are carried out under three heating conditions. Results show that the PCA-GMM approach can effectively reduce the running time. Especially for the VVV type model, the running time is reduced from 176.78 s to 15.18 s. Meanwhile, established PCA-GMMs still have good fault diagnosis correct rates when the input data dimension is reduced. Especially, some PCA-GMMs have fault diagnosis correct rates of over 99% when the number of principal components exceeds 7.

Assessing the energy performance of VAV and VRF air conditioning systems in an office building located in the city of Florianópolis

Abstract The objective of this study is to analyze the energy performance of two types of water-cooled air conditioning systems, variable air volume (VAV) and variable refrigerant flow (VRF), in terms of their cooling energy use through building simulation. These systems were designed to operate in an office building located in the city of Florianópolis, Brazil. The analysis involved the application of two building use schedules: a) constant and b) variable. Moreover, an analysis of the coefficient of performance (COP) and partial load ratio (PLR), and the percentage of operating hours for each range of cooling COP and PLR for each air conditioning system, allowed the system cooling efficiency to be assessed and the results to be related to the annual energy consumption. The coefficient of performance of VAV and VRF is 6.7 and 5.0, respectively, but the VRF system presented the lowest energy consumption for both schedules. The difference in the cooling energy consumption values for the VRF and VAV systems, for the variable schedule compared with the constant schedule, is mainly influenced by the partial load performance during the hottest period of the year.

Experimental analysis of a solar thermal hybrid VRF system for maximum energy economy based on Delhi (India) climate

ABSTRACT The main objective of the present study is to develop a solar thermal hybrid variable refrigerant flow (VRF) air-conditioning system and predict energy saving in this system compared to normal VRF air-conditioning system. In R410a based VRF system compressor works partially to increase pressure and temperature up to 27 bar, 55°C from compressor suction pressure and temperature 27 bar, 55°C. Further increase in temperature and pressure from approximate 55°C, 27 bar (Solar heat exchanger inlet) to 80°C, 34.39 bar (Solar heat exchanger outlet) is achieved with the help of evacuated tube type solar collector-based heat exchanger. The calculation of energy saving in solar thermal hybrid VRF system has been compared with fully electric-fired VRF system. The energy saving of approximate 45–50% can be achieved in solar thermal hybrid VRF system as compared to normal VRF system.

Abnormal energy identification of variable refrigerant flow air-conditioning systems based on data mining techniques

Identifying abnormal energy consumption in the variable refrigerant flow (VRF) system is important for its energy efficiency enhancement and energy saving. The energy performances of the VRF system are extremely distinct under various operation conditions. In order to evaluate the VRF’s energy performance, this study proposes a data-mining-based method to identify the abnormal energy consumption under different operation conditions. The local outlier factor (LOF) algorithm is used to distinguish transient data and three operation conditions are partitioned through clustering analysis. Besides, the correlation analysis is employed for key variables extraction. Then, the energy consumption is forecasted by support vector regression (SVR). The residuals of the measured energy values and the predicted values are applied in support vector data description (SVDD) algorithm to develop the responding D statistic as abnormal energy identification threshold. Finally, experiment data of various refrigerant charge level (RCL) are used to validate the proposed method. The methodology is sensitive to identifying abnormal energy consumption in VRFs at various RCLs. Nearly 100% of the abnormal energy consumption data can be accurately identified at some refrigerant charge levels. Operation condition partitioning can definitely enhance the identification efficiency.

Deep learning-based fault diagnosis of variable refrigerant flow air-conditioning system for building energy saving

The fault diagnosis of air-conditioning systems is of great significance to the energy saving of buildings. This study proposes a novel fault diagnosis approach for building energy saving based on the deep learning method which is deep belief network, and its application potential in the air conditioning fault diagnosis field is investigated. Then, a parameter optimization selection strategy is developed for model optimization. Four kinds of faults of the variable flow refrigerant system under heating mode are used to evaluate the performance of the models. The fault diagnosis results show that the deep belief network model with initial parameters can be used to diagnose the faults of the variable flow refrigerant system. Through the parameter optimization selection strategy, the fault diagnosis correct rate of the optimized model is 97.7%, which is improved by 5.05% compared with the model with initial parameters. The number of hidden layers of the deep belief network model is selected to be 2 layers. This result indicates that the fault diagnosis for variable flow refrigerant systems may not require a very deep model. Additionally, the performance of the optimized deep belief network model is compared with that of the traditional back propagation neural network, and the former is better. This finding also shows that the unsupervised restricted Boltzmann machine layer for data feature reconstruction can improve the fault diagnosis performance.

Outdoor air thermal plume simulation of layer-based VRF air conditioners in high-rise buildings

Variable refrigerant flow (VRF) air conditioning system is widely used in commercial buildings for space cooling and heating. However, some VRF systems used in high-rise buildings cannot work efficiently or even stop working because of the relatively high ambient air temperature, caused by the thermal plume effect of exhaust heat from outdoor units. In this paper, the thermal plume air flow of the layer-based VRF systems is investigated through computational fluids dynamics (CFD) simulation. Moreover, an illustrative example of practical VRF system in a 30-storey office building in Shenzhen is analyzed to optimize the layout of the outdoor units. Preliminary results show that the exhaust heat of outdoor units can cause ascending thermal plume flow, leading to higher inlet temperatures for VRF air conditioners on upper floors, even exceeding the warning upper threshold value. It also indicates that enlarging the distance between outdoor units on different floors is an effective way to impair the thermal plume effect for VRF outdoor units and improve the thermal performance of the whole system. For the studied case, the average inlet temperatures can be decreased by 22% for VRF outdoor units with floor interval. This work can provide guidance for the optimization layout design of practical VRF air conditioning systems used in high-rise buildings.

EXERGY ANALYSIS OF THE PERFORMANCE OF A VARIABLE REFRIGERANT FLOW (VRF) AIR CONDITIONING SYSTEM

Commercial multiple evaporators variable refrigerant flow (VRF) HVAC systems present many advantages such as being energy saving and the capability of adjusting refrigerant mass flow rate according to the change of high rises occurrence. This paper deals with an experimental control volume exergy analysis in a VRF air conditioning system. The experimental results show that the brunt of the total exergy destroyed in the whole system occurs in the outdoor unit, where the exergy destroyed in the condenser is more important. The values of coefficient of performance (COP) obtained for the tests increase as the system reaches operational conditions imposed in every indoor unit zone. The VRF system analyzed is highly sensitive to the action of the constant speed compressor. The use of an inverter compressor improves the system performance by adjusting the power consumption according to the cooling load in the evaporators.

Simulation comparison of VAV and VRF air conditioning systems in an existing building for the cooling season

Performance of two widely used air conditioning (AC) systems, variable air volume (VAV) and variable refrigerant flow (VRF), in an existing office building environment under the same indoor and outdoor conditions for an entire cooling season is simulated by using two validated respective models and compared. It was observed that the indoor temperatures could not be maintained properly at the set temperature by the VAV no-reheat boxes. However, it could be maintained by the VAV boxes with reheat with a significant energy consumption penalty. It was found that the secondary components (indoor and ventilation units) of the VRF AC system promised 38.0–83.4% energy-saving potential depending on the system configuration, indoor and outdoor conditions, when compared to the secondary components (heaters and the supply fan) of the VAV AC system. Overall, it was found that the VRF AC system promised 27.1–57.9% energy-saving potentials depending on the system configuration, indoor and outdoor conditions, when compared to the VAV AC system.

Energy simulation in the variable refrigerant flow air-conditioning system under cooling conditions

As a high-efficiency air-conditioning scheme, the variable refrigerant flow (VRF) air-conditioning system is finding its way in office buildings. However, there is no well-known energy simulation software available so far which can be used for the energy analysis of VRF. Based on the generic dynamic building energy simulation environment, EnergyPlus, a new VRF module is developed and the energy usage of the VRF system is investigated. This paper compares the energy consumption of the VRF system with that of two conventional air-conditioning systems, namely, variable air volume (VAV) system as well as fan-coil plus fresh air (FPFA) system. A generic office building is used to accommodate the different types of heating, ventilating, and air-conditioning (HVAC) systems. The work focuses on the energy consumption of the VRF system in the office buildings and helps the designer's evaluation and decision-making on the HVAC systems in the early stages of building design. Simulation results show that the energy-saving potentials of the VRF system are expected to achieve 22.2% and 11.7%, compared with the VAV system and the FPFA system, respectively. Energy-usage breakdown for the end-users in various systems is also presented.