Search

The prediction of the occupancy in buildings is essential to design efficient energy control strategies that optimize consumption and reduce losses while guaranteeing the comfort of the occupants. For this reason, many works address the problem of detecting, estimating, and predicting buildings' occupancy using different techniques, devices, and technologies. The occupancy prediction process can be described in four stages: data acquisition, modeling, evaluation, and testing, which are closely related. This paper reviews the most relevant recent literature on building occupancy estimation and prediction, analyzing the key aspects of its stages. A detailed description of the variables and design considerations is presented, including measurement methods, sensor selection, modeling techniques, evaluation metrics, and different applications. Through its examination, this paper elaborates significant remarks on the interaction between the stages, providing an overview of the suitable design of the occupancy prediction process. Finally, current and future trends are discussed. • A systematic review of the occupancy estimation and prediction process is presented. • Data acquisition, modeling, evaluation, and testing are the four general stages. • The importance of sensor fusion in overcoming individual limitations is presented. • Occupancy detection methods include deterministic, stochastic, and machine learning. • Some potential future research directions are discussed. [ABSTRACT FROM AUTHOR]

• Features are selected from the perspectives of machine learning and field application. • Stepwise FS path combining optimization with machine learning algorithms is proposed. • Best performance using existing features and corresponding feature set are revealed. • Recommendations for feature supplementation to further improve performance are given. • Feature sets are verified to be general and effective by experiments and comparisons. Fault diagnosis (FD) is vital for enhancing chiller efficiency and reliability. Feature selection (FS) is the prerequisite and key to diagnose faults. This paper addresses two intriguing questions from machine learning (ML) and field perspectives. Question-1: Based on commonly installed sensors, what is the best performance that the FD models based on ML algorithms can achieve, and what features are relevant? Question-2: Which features can enhance diagnostic performance? and to what extent? This paper designs a stepwise FS process. First, a field investigation is conducted to gather information on sensors installed in actual chillers. Based on actual field installation, feature calculation cost, and thermodynamic mechanism, three levels of initial feature libraries are created, each containing an increasing number and type of features. An FS method combining an optimization algorithm with an FD model based on ML algorithm is proposed. In the end, the insight into the best diagnostic performance achieved by ML-based models using existing sensors and the corresponding optimal feature subsets is provided, and recommendations for feature supplementation to further improve diagnostic performance are also provided. Compared with other literature-reported feature subsets, the recommended feature subsets show better generality and effectiveness on seven commonly used ML-based models. [ABSTRACT FROM AUTHOR]

• A machine learning classifier trained with multiple RTUs predicts faults well. • Converting insignificant faulty cases to unfaulty cases reduced false alarms. • A reduced set of practical features showed good performance. • The classifier's prediction accuracy improved with increasing fault severity. • Performance was poor when applied in the field to a system not used in training. There have been many recent developments to take advantage of machine learning for the task of automated fault detection and diagnosis in air-conditioning equipment. A common approach is to develop a machine learning model to classify fault status, using simulated or measurement data, and test the model's fault diagnostic capability on the same system that was used for training. However, such models don't generalize well to different systems. Compounding this challenge, machine learning requires a rich dataset to train the models, and many of the measurement features require additional sensors, all making the potential for practical machine learning AFDD questionable. The current paper focuses on these challenges by: (i) training a model using simulation data from three rooftop units (RTU); (ii) rebalancing the training dataset to reduce false alarms; (iii) developing a feature set that minimizes sensor cost without significantly impacting performance; (iv) testing the model's performance on a set of laboratory measurement data from the same RTUs that were simulated for training data; (v) testing the model on a faulted RTU in the field. The results demonstrate good progress toward practical application of machine learning based AFDD for RTU, but generalization to different systems remains a challenge. [ABSTRACT FROM AUTHOR]

• Developed and applied a feature selection algorithm to unitary equipment at part load conditions. • Feature relevancy analysis of the air and refrigerant side is performed. • Feature selection algorithm verified using Artificial Neural Network. • A subset of 33% of features are identified with the same level of accuracy as a complete dataset. • Developed guidelines for the formulation of future models using algorithms. A variable-speed air-conditioning system provides more control than single-or multi-stage units, resulting in increased energy efficiency and more precise temperature control. Current commercial and residential direct expansion (DX) equipment testing standards require the embedded control placed on variable-speed equipment to be deactivated during performance testing and instead the fan and compressor speeds are fixed. For this reason, the test and field performances differ, creating a performance as well as an energy consumption gap. This paper presents a machine learning-based approach to investigate critical features from the air and refrigerant side influencing the cooling capacity of unitary air conditioning equipment. High-fidelity experimental data obtained from 4 different state-of-the-art high-efficiency units, 1 fixed-speed 35.2(10) kW(tons) commercial and 3 variable-speed residential unitary equipment of 12.3(3.5), 14(4), and 17.6(5) kW(tons) of cooling capacity have been analyzed by utilizing a feature selection methodology, Elastic Net (EN). Influential features with higher relevance scores corresponding to the total cooling capacity are fed into a supervised Artificial Neural Network (ANN), formulated as a predictive model to evaluate the validity of features selected. Results show that the proposed method of feature selection when applied, ANN is able to predict the equipment cooling capacity with a mean absolute percent error of less than 2% for all tested units, thus approving the proposed input features. The findings may be used as recommendations for the development of a semi-empirical model for better cooling capacity and COP predictions. [ABSTRACT FROM AUTHOR]

• The importance of 14 parameters for short-term heating load were determined by Relief. • 15 machine-learning models were compared from aspects of accuracy, stability and computation time. • GPR and SVM were recommended for small and large building load datasets, respectively. Short-term building energy consumption prediction is of great significance to the optimal operation of building energy systems and conservation. Machine-learning models are widely used due to their high prediction accuracy and efficiency in dealing with high-dimensional nonlinear problems. To compare the performance of different machine-learning models in building energy consumption prediction, this paper analyzes 15 machine-learning models, including a multi-layer perception, a radials basis function neural network, a generalized regression neural network, an extreme learning machine, a support vector machine, a least-square support vector machine, a Gaussian process regression, a regression tree, a model five tree, a random forest, a gradient boosting decision tree, an extreme gradient boosting tree, a light gradient boosting machine, a categorical gradient boosting tree and a multi-adaptive regression spline, from the aspects of model prediction accuracy, model stability (over-fitting) and calculation speed. The operation parameters determined by ReliefF algorithm were used as input parameters. The results showed that the prediction accuracy of all models is higher in the training phases, with R2 values greater than 0.90, while the prediction accuracy in testing phases was much lower. In terms of prediction accuracy and model stability, the Gaussian process regression model had the best overall performance among the 15 models, while the support vector machine had the faster calculation speed with acceptable prediction accuracy. For small datasets, the Gaussian process regression model is recommended, and the support vector machine should be preferred for large datasets. The results of this paper can provide a basis for model selection and the establishment of combined models for predicting building energy consumption. [ABSTRACT FROM AUTHOR]

• The influences of various common faults on the VRFs under different fault levels and load rates was analyzed. • A faults experienced database for VRFs was provided. • The fault mechanism was clarified through sensitivity analysis between the physical parameters and different faults. • A reference basis for selecting various fault features and key fault decoupling variables was provided when a multiple fault diagnosis model for VRFs is established. Due to improper installation, operation, and maintenance, many common faults inevitably occur in the air conditioning systems. However, the same fault could demonstrate different characteristics under different load rates and fault levels; different faults may present similar fault phenomena. This paper reveals the quantitative impact of faults on system performance of VRF system with common faults imposed in heating mode through fault experiments. The system parameters sensitivity study has been carried out to understand the internal impact mechanism related to system parameters. This provides a reference for selecting characteristic parameters and fault decoupling variables and developing interpretable, professional, and reliable fault detection and diagnosis models. The results show that the outdoor unit fouling fault can cause the heating capacity to drop by 73.2%, and the indoor unit fouling can cause the system power to drop by 65.5%. The coefficient of performance drop is as high as 48.6%. The sensitivity study result shows that the system load rate is an influential parameter; it needs to be considered when characteristic parameters and fault decoupling variables are selected. [ABSTRACT FROM AUTHOR]

• Proposed an interpretable deep learning model using the attention-BiLSTM. • Four typical faults of VRF are well identified with an overall diagnosis accuracy of 97.5%. • Effective fault diagnosis under incomplete information is realized through the integrated model of different feature combinations. • Realize the quantification of diagnosis uncertainty through the ensemble model. • The model performs well on the unknown data set under different working conditions. Developing effective fault detection and diagnosis (FDD) model is of great significance to the energy efficiency and comfort of variable refrigerant flow (VRF) system. In recent FDD studies, the consideration of incomplete information and uncertainty, as well as the generalization of model and the interpretability of fault action mechanism have become a great concern. This paper accordingly proposes a fault diagnosis strategy based on attention-BiLSTM with ensemble feature sets. Three methods including Correlation Analysis, Information Entropy, and Gini Impurity are used for feature selection and ensemble feature sets combination. The proposed model can achieve interpretability of fault diagnosis and quantification of diagnosis uncertainties through attention mechanism and ensemble feature sets. A total of four typical faults under different working conditions are used to verify the accuracy and generalization of the proposed method. The results show that the ensemble attention-BiLSTM model has a fault diagnosis accuracy rate of 98.3% if the first two most likely outputs are considered, and when some sensors fail, the accuracy rate can still remain above 90%. In addition, a generalization verification idea is proposed, that is, the model is trained under specific operating conditions and tested on datasets with different operating conditions or fault levels. The results show that the average generalization of the optimized model reaches 86%. [ABSTRACT FROM AUTHOR]

Data quality assurance of building energy consumption monitoring platform plays an important role in building energy consumption management. However, Data collected and transferred to the cloud platform is affected by many factors and shows some missing values and outliers in the time series. Combining with the correlation of smart meters on branches and regularity of building energy consumption characteristics, this paper proposes a synchronous prediction method for predicting building energy consumption in the secondary branch. In this model, synchronous data feature similarity (SDFS) model is used to find a similar energy consumption feature, Extreme gradient boosting (XGBoost) model is used to train and produce accurate prediction results which are compared with back propagation neural network (BPNN) and adaptive boosting (AdaBoost) and maximum distance outlier correction (MDOC) model can further correct the prediction results. Taking the daily energy consumption of the primary branch with a smart meter in the building energy consumption monitoring platform as the test object, the predition results of VRF energy consumption show that the MAE, MAPE, RMSE, and CVRMSE are 1.150, 0.142, 1.511, and 0.132 respectively, which is much lower than BPNN and AdaBoost. This study explores a novel feature mining method for historical data and an integrated model for outlier recognition and correction which significantly improves the accuracy of prediction results. Moreover, after correlation verification, the prediction model can be widely applied in building distribution system with sub-meter system which improves the data utilization rate of building energy management system. [ABSTRACT FROM AUTHOR]

Accurate energy consumption prediction is the basis of predictive control for heating, ventilation and air conditioning (HVAC) systems. Data-driven models are widely used for energy consumption prediction. The prediction accuracy can be affected by data preprocessing or selection, which are not well studied yet. This paper attempts to study the impacts of different data processing methods and feature selection on the HVAC energy consumption prediction based on data-driven models. Long and short-term memory models are developed based on historical data to predict the day-ahead hourly energy consumption of HVAC systems. Two data smoothing methods, Gaussian kernel density estimation and Savitzky-Golay filter, are selected and compared. The impacts of feature selection, training set volumes and update frequency of models are analyzed and compared. To obtain general results of the above problems, three office buildings are selected. Results show that the smoothing methods can not ensure the improvement in accuracy by removing the exceptional data in the raw data which arise reasonably in practice. The inputs with raw 1-day historical energy consumption, the dry-bulb temperature and dew-point temperature in the next day, holiday type and day type is recommended to predict day-ahead HVAC energy consumption. It is recommended to use a larger training set if computing cost is acceptable. The model should be updated after being used for over 7 weeks. This study would guide the development of prediction models in practice. [ABSTRACT FROM AUTHOR]

[Display omitted] • Multimodal occupancy detection framework for residential buildings. • Two variants of Occ-STPN models with feature level fusion and decision level fusion. • Feature extraction and occupancy detection models for various data modalities. • Transferability of a trained occupancy detection model from one building to another. • Occupancy prediction performance evaluation on three open-sourced datasets. For several years now, smart building energy systems have been a research area of intensive activity. In light of the increasing need for sustainable buildings and energy systems, this trend motivates an increasing need for a solution to reduce carbon dioxide emissions and improve energy efficiency. This paper proposes a high-performing and transferable occupancy detection framework that combines sensor data from different data modalities, including time series environmental data (temperature, humidity, and illuminance), image data, and acoustic energy data using ensemble method. To draw out the best prediction performance in each modality, the proposed framework was developed, including various models that were designed to learn the occupancy patterns reflected in the physical data streams. To tackle the time series environmental data, we designed two variants of an occupancy detection spatiotemporal pattern network (Occ-STPN) that performs both feature level and decision level fusion, respectively. We also propose a new metric; the fading memory mean square error (FMMSE), that provides a fair evaluation and penalization of delayed occupancy predictions. Multiple open-sourced datasets, including the Electricity Consumption and Occupancy and the University of California, Irvine's (UCI) building occupancy detection dataset, along with our own real data collected from six different houses, were used to validate the algorithms' performance. The experimental results presented herein break down the performance for each sensing modality, and a detailed analysis of the performance is also discussed. [ABSTRACT FROM AUTHOR]

[Display omitted] • Most of the reviewed studies (62%) focused on group-based comfort models. • ML models, especially PCMs outperformed conventional models (PMV and adaptive). • ML-based controls can improve IAQ while reducing energy consumption and CO 2 levels. • The most frequently used algorithms were SVM, ANN and Ensemble Learning. This paper provides a systematic review on the application of Machine Learning (ML) in thermal comfort studies to highlight the latest methods and findings and provide an agenda for future studies. Reviewed studies were investigated to highlight ML applications, parameters, methods, performance and challenges. The results show that 62% of reviewed studies focused on developing group-based comfort models, while 35% focused on personal comfort models (PCMs) which account for individual differences and present high prediction accuracy. ML models could outperform PMV and adaptive models with up to 35.9% and 31% higher accuracy and PCMs could outperform PMV models with up to 74% higher accuracy. Applying ML-based control schemas reduced thermal comfort-related energy consumption in buildings up to 58.5%, while improving indoor quality up to 90% and reducing CO 2 levels up to 24%. Using physiological parameters improved the prediction accuracy of PCMs up to 97%. Future studies are recommended to further investigate PCMs, determine the optimum sample size and consider both fitting and error metrics for model evaluation. This study introduces data collection, thermal comfort indices, time scale, sample size, feature selection, model selection, and real world application as the remaining challenges in the application of ML in thermal comfort studies. [ABSTRACT FROM AUTHOR]

• A framework of building energy modeling for data predictive control is developed. • The framework integrates active learning strategy with feature selection technique. • The framework is demonstrated in a virtual testbed (EnergyPlus and BCVTB). • The case study shows improvement in energy modeling accuracy and DPC performance. Three gaps impede the development of cost-effective and accurate data-driven building energy modeling/models (DBEM) for energy forecasting and predictive control strategies. Gap 1: data bias is common in building operation data, but this topic is hardly studied in DBEM; Gap 2: high data dimensionality is common in DBEM, but a systematic and scalable methodology is lacking to solve the problem; Gap 3: the interactions between data bias and high dimensionality have not been systematically studied for DBEM and predictive control in buildings. In this paper, to address the three gaps mentioned above, we develop a framework that integrates active learning and feature selection for DBEM used for whole building data predictive control (or DPC, which is a branch of model predictive control). The framework provides a systematic methodology and automatic workflow that starts with raw data from building automation systems to the establishment of data-driven energy models for DPC controllers. The developed strategies and framework are evaluated in a virtual testbed based on EnergyPlus and BCVTB. Improved performance and reduced computational complexity are observed from the DBEM built with the developed framework, as well as the DPC controller based on that DBEM, indicating the effectiveness of the developed framework. [ABSTRACT FROM AUTHOR]

• Experiments on high-efficiency heat pump with two, three, four simultaneous faults. • Four faults increased refrigerant superheat up to 18 °C. • NC faults tend to increase refrigerant subcooling. • An existing virtual refrigerant charge sensor was tested with simultaneous faults. Faults in air-cooled vapor compression air-conditioning systems are known to reduce performance, including efficiency, capacity, and lifespan. Their effects have been studied, and fault detection and diagnostic (FDD) methods have been developed as tools for field technicians to install or repair systems, or for monitoring to alert operators to the fault's presence. Most of this work has focused on faults that occur singly. It is likely that in some systems, multiple faults occur simultaneously, but it is uncertain what effects this may have on diagnostics. This paper describes a laboratory study of a split system air source heat pump in which combinations of two, three, and four simultaneous faults occur. The study includes all combinations of: improper evaporator airflow; overcharge or undercharge of refrigerant; liquid line restrictions; and non-condensable gas in the refrigerant, each at multiple fault intensities. Fault features – those characteristics that can be determined from measurements, for use in diagnostics – are analyzed, and the key fault features are presented. A robust existing method for determining refrigerant charge, the virtual refrigerant charge sensor (VRC) is tested using the multiple fault data, in order to understand how its performance is impacted by the combined faults. The VRC performs well, typically able to correctly determine whether a system is undercharged or overcharged, but the magnitude estimates are impacted. The results suggest that simple subcooling-based methods of charging a system are likely to provide unsatisfactory results when other faults are present. [ABSTRACT FROM AUTHOR]

The need for accurate balancing in electricity markets and a larger integration of renewable sources of electricity require accurate forecasts of electricity loads in residential buildings. In this paper, we consider the problem of short-term (one-day ahead) forecasting of the electricity-load consumption in residential buildings. In order to generate such forecasts, historical electricity consumption data are used, presented in the form of a time series with a fixed time step. Initially, we review standard forecasting methodologies including naive persistence models, auto-regressive-based models (e.g., AR and SARIMA), and the triple exponential smoothing Holt-Winters (HW) model. We then introduce three forecasting models, namely i) the Persistence-based Auto-regressive (PAR) model, ii) the Seasonal Persistence-based Regressive (SPR) model, and iii) the Seasonal Persistence-based Neural Network (SPNN) model. Given that the accuracy of a forecasting model may vary during the year, and the fact that models may differ with respect to their training times, we also investigate different variations of ensemble models (i.e., mixtures of the previously considered models) and adaptive model switching strategies. Finally, we demonstrate through simulations the forecasting accuracy of all considered forecasting models validated on real-world data generated from four residential buildings. Through an extensive series of evaluation tests, it is shown that the proposed SPR forecasting model can attain approximately a 7% forecast error reduction over standard techniques (e.g., SARIMA and HW). Furthermore, when models have not been sufficiently trained, ensemble models based on a weighted average forecaster can provide approximately a further 4% forecast error reduction. [ABSTRACT FROM AUTHOR]