Search

Green roofs can decrease the energy consumption and improve air quality and durability associated with a roofing material. Previous studies have conducted simulations of the energy performance of green roofs over a limited period, and important parameters such as leaf area index (LAI) was set at a constant value. To develop an energy performance model for a green roof with a variable LAI which is suitable for annual simulation, this paper proposes a method to integrate a seasonally variable LAI equation into a green roof model based on an improved Dickinson's equation. After verification with measured data, this equation has a more accurate temperature setting for calculating seasonally variable LAI, the average error and average relative error are improved from 0.34 to 0.09 and 39.3 to 7.1%, respectively. Thus, it can be applied in different climatic regions. To determine the differences of annual energy performance of green roof, this paper compares simulation results of constant and variable LAI values for a two-story building in Shanghai, China. The simulation is conducted on the EnergyPlus platform. The results show that the simulations of temperature, heat flux, and heat load of the building for green roof modeling differ considerably for a constant and a variable LAI. In summer, the calculated latent heat flux is usually underestimated and the sensible heat flux is usually overestimated. Moreover, if the selected LAI value is higher than that of actual data in winter, the calculated latent heat flux is overestimated and the sensible heat flux is underestimated. The simulation results are more relevant for a seasonally variable LAI. [ABSTRACT FROM AUTHOR]

[Display omitted] • A split-degree days index is proposed for building energy use/climate classification. • Split-degree days index is shown to better estimate solar radiation and humidity data. • The estimation of building energy end-uses is improved using the split-degree days. • Split-degree days also showed improved results for high thermal mass and 24-hr models. • Split-degree days index maintains a high accuracy for varying base temperatures. Degree days have been widely used in different applications in buildings, such as estimating building energy use and climate classification for building energy standards. However, there are limitations with the use of conventional degree days that result in inaccuracies in estimating building energy consumption using degree day-based methods. This paper proposes a new method, the split-degree day method, that shows substantially improved results in the accuracy of the building energy use estimation compared to the conventional degree day methods. The analysis in 801 locations in the U.S. using regression models showed that the new, proposed split-degree day method in this paper, compared to the conventional degree day method, better accounts for the weather parameters and more accurately estimates end-uses. The split-degree days showed an improvement of over 5% in the accuracy of the total annual energy use prediction, 8% for predicting the heating energy use, 0.3% for predicting the cooling energy use, and 33% for predicting the fan energy use. Additionally, the analysis showed improved results for the model with higher thermal mass and the model with a 24-hour operating schedule. These improvements were due to the fact that the split-degree day method includes more information related to the weather characteristics of a location, which is missing in a conventional degree day calculation procedure that relies on aggregated data at daily intervals. Furthermore, as opposed to the conventional degree days, the accuracy of the estimations using the split-degree days are shown to maintain their high accuracy when the base temperature deviates from the optimal base temperature. The proposed method can be used as a more accurate alternative to the conventional degree days in different applications, including but not limited to building climate classification, building energy estimation, and weather normalization for building energy savings calculation. [ABSTRACT FROM AUTHOR]

Energy waste caused by equipment malfunction or inefficient energy utilization is common during the building operation process. Through the anomaly detection of building energy consumption data, the utilization rate of building energy can be improved. A dynamic anomaly detection method for building energy consumption data point anomalies and collective anomalies is proposed in this paper. In the method, the entropy-weighted k-means (EWKM) is coupled with the classification and regression tree (CART) to establish a recognition and matching mechanism for unlabeled energy consumption data. Then, the isolated forest (IF) and local outlier factor (LOF) are combined to enhance the detection ability of point anomaly. Through dynamic time warping, the distance between energy consumption sequences is calculated to realize the collective anomaly detection of energy consumption. The historical dataset could be dynamically updated based on the detection results. Subsequently, the dynamic anomaly detection of EWKM-CART-IF-LOF is achieved. The proposed EWKM-CART-IF-LOF is applied to detect point and collective anomalies in the real energy consumption of an office building in Suzhou. In the test set, the detection performances of EWKM-CART-IF-LOF, EWKM-CART-IF, EWKM-CART-LOF, EWKM-CART-CBLOF and EWKM-CART-KNN are evaluated and compared. Results show that the EWKM-CART-IF-LOF has the best detection performance with an AUC of 0.90, an accuracy of 0.98, a precision of 0.83, and an F-score of 0.82. These outcomes validate the method's efficacy in optimizing building energy consumption, making a significant contribution to the fields of energy management and anomaly detection. [ABSTRACT FROM AUTHOR]

Facing the challage of energy conservation and emission reduction in the building sector, most energy saving strategies of central heating only focus on the performance improvement of building envelope, ignoring the impact of energy use behavior. This paper proposed a building energy conservation strategy based on energy use behavior analysis, which provides a perspective for in-depth exploration of building energy conservation. After investigating a typical university in the northern China, the energy use behaviors were characterized and two different DeST energy consumption models before or after considering energy use behavior were established. By comparing the results calculated by these two models, the impact of energy use behavior analysis on building energy consumption was quantitatively analyzed. The results show that the heating energy consumption and carbon emission can be reduced by 23.28% and 23% respectively through the proposed strategy based on energy use behavior. Therefore, the analysis of energy use behavior can provide a theoretical basis for heating operators to make decisions on energy supply regulation. With central cooling and heating further popularizing in the future, the research methodology of this paper has more extensive reference value for energy conservation and emission reduction strategies in the building sector. [ABSTRACT FROM AUTHOR]

• Obtaining the optimal interpolation method for adjacent sites. • Proposing the method for revising meteorological data at city scale. • Verifying the accuracy of the method by energy consumption simulation. In the development process of building energy conservation design, the correct provision of local Typical Meteorological Year (TMY) data is a prerequisite and basic work to evaluate building energy consumption, which directly affects the fine use of outdoor data for building energy conservation. Based on the recorded and observed data of meteorological stations in China, the acquisition and correction methods of TMY were studied by mathematical statistics and target searching, and the building energy consumption simulation of urban office buildings was conducted to verify the accuracy of the method, including:(1) Reviewed the generation method for TMY and the acquisition of data.(2) Based on the existing TMY data, the best spatial interpolation method of adjacent stations is studied by using the standard deviation method, and the selection method of the best number of stations on a large regional scale is given.(3) An improved method of urban environment TMY is proposed. The dry bulb temperature and relative humidity of the building site are corrected to generate TMY under Urban Heat Island (UHI) effect. The research in this paper improves the coverage and accuracy of urban TMY data and supplies basic research support for building energy-saving designs. [ABSTRACT FROM AUTHOR]

Highlights • A highly interactive web tool for the exploration of NILM results is presented. • Data cube allows insightful integration of NILM components with raw consumption data. • Hospital total demand, 7 cooling machines and temperature each minute for a year. • Fluid feedback by live coordinated views allows to interpret the NILM decomposition. • NMF exploits positivity of energy consumptions for an interpretable decomposition. Abstract Non-intrusive load monitoring (NILM) techniques have recently attracted much interest, since they allow to obtain latent patterns from power demand data in buildings, revealing useful information to the expert user. Unsupervised methods are specially attractive, since they do not require labeled datasets. Particularly, non-negative matrix factorization (NMF) methods decompose a single power demand measurement over a certain time period into a set of components or “parts” that are sparse, non-negative and sum up the original measured quantity. Such components reveal hidden temporal patterns which may be difficult to interpret in complex systems such as large buildings. We suggest to integrate the knowledge of the user into the analysis in order to recognize the real events inside the electric network behind the learnt patterns. In this paper, we integrate the available domain knowledge of the user by means of a visual analytics web application in which an expert user can interact in a fluid way with the NMF outcome through visual approaches such as barcharts, heatmaps or calendars. Our approach is tested with real electric power demand data from a hospital complex, showing how the interpretation of the decomposition is improved by means of interactive data cube visualizations, in which the user can insightfully relate the NMF components to characteristic demand patterns of the hospital such as those derived from human activity, as well as to inefficient behaviors of the largest systems in the hospital. [ABSTRACT FROM AUTHOR]

Building energy consumption forecasting is crucial for energy managers and policymakers. However, acutely predicting the energy consumption of any building is more important in energy efficiency benchmarking of buildings. Energy benchmarking is a precise technique for measuring, tracking, and reducing end-use energy usage of buildings by employing comparative scenarios. Bottom-Up energy consumption assessment has been used in several studies to evaluate a collection of buildings' energy performance to a standard. Traditionally, researchers have used a single approach to predict the energy use of buildings and to conduct benchmarking. However, it has been found that doing so frequently compromises the accuracy of the predicted energy use of buildings. It also has an adverse effect on the buildings' energy benchmarking framework results. This paper will provide an energy benchmarking framework for residential buildings based on the blending techniques of multiple approaches. Over 3000 datasets were gathered from the Indian city of Jaipur. In order to analyse the trends in energy consumption, the data were divided into categories based on economic levels. The data is then subjected to some fundamental statistical analysis, along with several approaches are blended to forecast the energy consumption of the buildings with the highest accuracy. These benchmark levels set guidelines for assessing and recognising strong performance while also identifying underperforming buildings and giving them more priority for energy efficiency improvement. The technique may be used for different metropolitan levels and climatic conditions. [ABSTRACT FROM AUTHOR]

• This paper determines the relationship between urban form and building energy use. • The surface-to-volume ratio and obstruction angle of buildings are important. • Consideration of the heating energy type and building use can yield reliable result. • The urban heat island effect exerts an impact on the electricity use in some months. • Correlation variation is caused by the building permit date. In the climate change era, urban geometry serves to ensure sustainability for urban planners since it notably affects building energy consumption. However, previous studies have mainly conducted experimental investigations under hypothetical conditions. Without empirical evidence, it is difficult to implement these findings under real conditions. This paper examined empirical data to determine the urban geometry effect on building energy consumption in a large, complicated urban area. Urban geometric parameters, including the surface-to-volume ratio, obstruction angle, and building orientation, were measured across Seoul, and their correlations with building energy use were analyzed. The results show that the surface-to-volume ratio and obstruction angle are important, despite the empirical data complexity. Additional data analysis indicates that the heating energy type and building use consideration yields more reliable correlation coefficient trends. The potential impacts of natural ventilation and the urban heat island (UHI) effect on building energy consumption were examined. The UHI effect, rather than shadows on buildings, predominantly impacts the building electricity use in August and September. The correlation variation caused by the building permit date was investigated. The results in this paper could help urban planners and designers develop blueprints to control urban geometry and establish relevant design guidelines. [ABSTRACT FROM AUTHOR]

In order to resolve the contradiction between the lack of building energy data and the need of more detailed information about energy performance, this paper presents a simplified building energy performance diagnosis method which can assess the energy performance from building level to system level with only limited information. Based on multiple-parameter regression between the whole building energy bills and outdoor weather data, the proposed diagnosis method uses the regression coefficients to identify the energy use of main systems (i.e., lighting-plug system and cooling/heating system), as well as other detailed information about physical properties of the building and cooling/heating system (i.e., cooling or heating load, the operation of cooling/heating system and the efficiency of cooling/heating system). One case study was conducted in an office building in China to test the application of this diagnosis method. In addition, the regression result of simulated energy consumption served as benchmark data to further diagnose the performance gap between the operation stage and the design stage and help locate the poor performance and key points of energy-saving. Finally, all diagnosis results have been verified by the performance data from advanced energy consumption monitoring system together with field surveys and measurements. [ABSTRACT FROM AUTHOR]

This paper provides a novel and efficient approach for the simulation-based multi-criteria optimization of the building energy performance. In the current investigation, a multi-objective non-dominated sorting genetic algorithm (NSGA-II) is coupled with EnergyPlus building energy simulation program to obtain optimal solutions leads to increase the building energy performance. The main aim of this work is to explore the effect of some architectural parameters, including the building orientation, the window size and the overhang specifications on the building energy consumption in four major climatic regions of Iran, e.g. cold, mild, warm-dry, and warm-humid. In the optimization section, mono-criterion and bi-criteria optimization analyses of the annual cooling and lighting building energy demands are studied with the purpose of understanding the interactions between these objective functions. The results point out that the bi-criteria optimization of the test case model brings down the annual cooling energy consumption 55.8–76.4% in various climates. However, the annual lighting electricity demand increases 1–4.8%. As a result, the final optimum configuration leads to 23.8–42.2% decrease in the annual total building energy consumption. The results depict that the climate and the appropriate selection of the architectural parameters are very important and critical in reducing the building energy consumption. The proposed optimization methodology is a powerful and useful tool to achieve this goal and to facilitate decision-making in early phases of a building design in order to enhance its energy efficiency. [ABSTRACT FROM AUTHOR]

The large public building energy consumption (BEC) is the focus of Building Energy Saving, therefore, it is necessary to study the characteristics of BEC to find out the important factors affecting BEC. For this purpose, 27 office buildings in the west of Inner Mongolia Autonomous Region were studied, based on statistical analysis of the researched basic information and energy consumption bill of these buildings. This paper focused on the determination of the significant factors affecting the total and subentry energy consumption intensity (ECI) of office building, as well as the establishment of standardized linear regression models between these selected factors and total and subentry ECI. Firstly, eleven continuous variables, three independent categorical variables, and the climate factor were selected and analyzed the impact on total and subentry ECI by statistical software SPSS20.0, in order to find out the significant influencing factors. Then based on the results of curve fitting, standardized models of total and subentry ECI and their respective significant impact factors were established using multiple linear regression analysis. The regression results showed that the electricity use percentage of the total equivalent electricity consumption was an important factor affecting the total ECI of office building in the west of Inner Mongolia Autonomous Region. Finally, univariate analysis of variance (ANOVA) was conducted between the three independent categorical variables and the total and subentry ECI, and the results showed that these factors had no significant effect on the ECI of office building. Process of the regressive model establishment and the results of analysis of variance could both guide us to propose more targeted energy saving measures. [ABSTRACT FROM AUTHOR]

• Meter-level anomaly detection and diagnosis is performed through CMP algorithm. • CMP parameters are automatically set using supervised and unsupervised methods. • A severity score, based on 4 statistical methods, is used to recognize anomalies. • 55 anomalous energy consumption patterns are discovered in a one-year timeseries. • Anomalies at meter-level are diagnosed by exploiting information at sub-load level. Recently, the spread of IoT technologies has led to an unprecedented acquisition of energy-related data providing accessible knowledge on the actual performance of buildings during their operation. A proper analysis of such data supports energy and facility managers in spotting valuable energy saving opportunities. In this context, anomaly detection and diagnosis (ADD) tools allow a prompt and automatic recognition of abnormal and non-optimal energy performance patterns enabling a better decision-making to reduce energy wastes and system inefficiencies. To this aim, this paper introduces a novel meter-level ADD process capable to identify energy consumption anomalies at meter-level and perform diagnosis by exploiting information at sub-load level. The process leverages supervised and unsupervised analytics techniques coupled with the distance-based contextual matrix profile (CMP) algorithm to discover infrequent subsequences in energy consumption timeseries considering specific boundary conditions. The proposed process has self-tuning capabilities and can rank anomalies at both meter and sub-load level by means of robust severity score. The methodology is tested on one-year energy consumption timeseries of a medium/low voltage transformation cabin of the university campus of Politecnico di Torino leading to the detection of 55 anomalous subsequences that are diagnosed by analysing a group of 8 different sub-loads. [ABSTRACT FROM AUTHOR]

• Miscellaneous loads are a major opportunity to save electricity in vacant buildings. • A method for inferring vacancy was developed. • The model generates a continuously updated likelihood of vacancy. • The vacancy inference model requires less ground truth data. • The sensor fusion approach is robust and enables flexibility. Recent events have forced building managers to examine energy use during vacant periods and revealed miscellaneous electrical loads (MELs) as an opportunity for savings. This paper addresses a key step in unlocking these savings, specifically the reliable identification of when a building is vacant. A Vacancy Inference Engine (VIE), using sensor fusion, was developed to identify vacant periods based on outputs from common sensors, historical building vacancy patterns, and expert knowledge. The VIE calculates the confidence that a building is vacant, allowing building managers to balance the capture of energy savings with the possibility of complaints due to powering down MELs. The VIE has the advantage over logistic regression and other models in that it does not require a full set of ground truth for the training process. The VIE successfully predicted vacancy in an office building using input data streams of instantaneous electricity demand, indoor carbon dioxide concentrations, and the number of active Wi-Fi connections. The VIE's ability to predict vacancy was compared to that of logistic regression using a metric based on the Complaint Opportunity Rate and found to be nearly identical (0.94 versus 0.95, respectively). [ABSTRACT FROM AUTHOR]

Currently, there is no clear and unified understanding about the status quo of China's energy consumption in the building sector. In addition, a considerable underestimation of energy associated with buildings has impeded the effective implementation of measures to improve building energy efficiency of China. Thus, in this paper, we seek to identify the building sector's energy consumption of China by establishing an estimation model of building energy consumption from a life cycle perspective. On the basis of macro-level statistical data and relevant literature, we analyze the activities in each phase and calculate associated energy consumptions throughout buildings’ whole life cycle in China from 2001 to 2013. The results show that China's energy consumption associated with buildings has reached 1.66 billion tons coal equivalent in 2013, with a stable growth rate of 7% annually since 2001. Buildings’ life-cycle energy has approximately accounted for 43% of China's total energy consumption for recent three years (2011–2013). What's more, energy consumption in buildings’ operation phase has been salient, accounting for over 20% of China's total energy consumption. More focus should be drawn on energy efficiency in building material production phase and energy consumed in China's rural residential buildings as both have been significantly neglected. [ABSTRACT FROM AUTHOR]

China is currently experiencing rapid urbanization. The building sector plays an important role in China's energy conservation and emission reduction. An increasing amount of energy will be steadily consumed in the building sector as the urbanization process accelerates. China's government attaches great importance to building energy efficiency (BEE). How does the urbanization process affect building energy consumption (BEC)? How much energy can be saved in the building sector through implementation of energy polices? These questions are critical for government development strategies and planning. Thus, in this paper, an econometric model (co-integration technique) is developed to analyze how China's BEC is affected by macroeconomic variables in the context of urbanization, and also forecast the BEC and BEE potential until 2020 under different scenarios. The research result shows that occupants’ lifestyles, residents’ living standards, and energy price have significant influences on BEC. The building sector is likely to contribute approximately 20% to China's energy conservation through electricity pricing reform. [ABSTRACT FROM AUTHOR]

Abstract: Fault detection and diagnosis (FDD) is an important issue in building energy conservation. This paper proposes a new option for solving this problem at the building level by using a recursive deterministic perceptron (RDP) neural network. Results show a higher than 97% level of generalization in all the designed experiments. Based on this high detection ability of RDP model, a new diagnostic architecture is proposed. Our experiments demonstrate that it is able to not only report correct source of faults but also sort sources in the order of degradation likelihood. [Copyright &y& Elsevier]

Abstract: Hainan province is the only tropical and island province in China, with the unique climatic and geographical features. It has a different energy performance in public buildings from those in the inland areas. This paper investigated the current situation of energy consumption of the sampled public buildings, including 26 hotels, 24 office buildings and 7 department stores, through analyzing utility billing data, on-site survey and measurement, and site operational records. The breakdowns of energy consumption found out that the electricity dominated the energy consumption for all the sampled buildings and the air conditioning system played a key role in the energy consumption of major building services. By analyzing the main factors for building energy consumption, the annual average energy use indexes were calculated to be 141.63kWh/m2, 87.70kWh/m2, and 166.95kWh/m2 for hotels, office buildings and department stores, respectively. Besides, the comparison between Hainan province and other areas revealed that the building energy consumption of this tropical province was at a low level. Because indoor environment quality can influence the health and work efficiency of humans in buildings, field tests on the indoor environment quality were also carried out, and the performance of indoor environment quality was rated. [Copyright &y& Elsevier]

Abstract: The current energy distribution infrastructure in many urban areas either cannot support anticipated future energy use or would require significant rehabilitation even if current use were maintained. Understanding the dynamics of local energy use is an important precondition of understanding how to remedy this situation. This paper builds a model to estimate the building sector energy end-use intensity (kwh/m2 floor area) for space heating, domestic hot water, electricity for space cooling and electricity for non-space cooling applications in New York City. The model assumes that such end use is primarily dependent on building function, whether residential, educational or office for example, and not on construction type or the age of the building. The modeled intensities are calibrated using ZIP code level electricity and fuel use data reported by the New York City Mayor''s Office of Long-Term Planning and Sustainability. The end-use ratios were derived from the Residential and Commercial Building Energy Consumption Survey''s Public Use Microdata. The results provide the ability to estimate the end-use energy consumption of each tax lot in New York City. The resulting spatially explicit energy consumption can be a valuable tool for determining cost-effectiveness and policies for implementing energy efficiency and renewable energy programs. [Copyright &y& Elsevier]

Abstract: Due to the current high energy prices it is essential to find ways to take advantage of new energy resources and enable consumers to better understand their load curve. This understanding will help to improve customer flexibility and their ability to respond to price or other signals from the electricity market. In this scenario, one of the most important steps is to carry out an accurate calculation of the expected consumption curve, i.e. the baseline. Subsequently, with a proper baseline, customers can participate in demand response programs and verify performed actions. This paper presents an artificial neural network (ANN) method for short-term prediction of total power consumption in buildings with several independent processes. This problem has been widely discussed in recent literature but a new point of view is proposed. The method is based on two fundamental features: total consumption forecast based on independent processes of the considered load or end-uses; and an adequate selection of the training data set in order to simplify the ANN architecture. Validation of the method has been performed with the prediction of the whole consumption expressed as 96 active energy quarter-hourly values of the Universitat Politècnica de València, a commercial customer consuming 11,500kW. [Copyright &y& Elsevier]

Abstract: Efforts have been devoted to the identification of the impacts of occupant behavior on building energy consumption. Various factors influence building energy consumption at the same time, leading to the lack of precision when identifying the individual effects of occupant behavior. This paper reports the development of a new methodology for examining the influences of occupant behavior on building energy consumption; the method is based on a basic data mining technique (cluster analysis). To deal with data inconsistencies, min–max normalization is performed as a data preprocessing step before clustering. Grey relational grades, a measure of relevancy between two factors, are used as weighted coefficients of different attributes in cluster analysis. To demonstrate the applicability of the proposed method, the method was applied to a set of residential buildings’ measurement data. The results show that the method facilitates the evaluation of building energy-saving potential by improving the behavior of building occupants, and provides multifaceted insights into building energy end-use patterns associated with the occupant behavior. The results obtained could help prioritize efforts at modification of occupant behavior in order to reduce building energy consumption, and help improve modeling of occupant behavior in numerical simulation. [Copyright &y& Elsevier]

Abstract: The evaluation of building energy consumption under typical meteorological conditions requires building energy profiles on an hourly basis. Computer simulations can be used to obtain this information, but generating simulations requires a significant amount of experience, time, and effort to enter detailed building parameters. This paper considers a simple methodology for using existing EnergyPlus benchmark building energy profiles to estimate the energy profiles of buildings with similar characteristics to a given benchmark model. The method utilizes the building monthly energy bills to scale a given benchmark building energy profile to approximate the real building energy profile. In particular, this study examines the robustness of the methodology considered with respect to the parameter discrepancies between a given building and the corresponding EnergyPlus benchmark model used to estimate its profile. Test buildings are defined by perturbing several combinations of the parameters defined in the benchmark building model. The test buildings examined are similar to the EnergyPlus, medium sized office, benchmark building in Baltimore, MD, and a total of 72 distinct test building configurations are examined. The analysis reveals that the methodology can significantly reduce the errors introduced by discrepancies from the EnergyPlus benchmark model. [Copyright &y& Elsevier]

Abstract: The evaluation of building energy consumption usually requires building energy profiles on an hourly basis. Computer simulations can be used to obtain this information but generating simulations requires a significant amount of experience, time, and effort to enter detailed building parameters. This paper presents a simple methodology to estimate hourly electrical and fuel energy consumption of a building by applying a series of predetermined coefficients to the monthly energy consumption data from electrical and fuel utility bills. The advantage of having predetermined coefficients is that it relieves the user from the burden of performing a detailed dynamic simulation of the building. The coefficients provided to the user are obtained by running EnergyPlus Benchmark Models simulations; thus, the simulation process is transparent to the user. The methodology has been applied to a hypothetical building placed both in Atlanta, GA, and in Meridian, MS, and in both cases, errors obtained for the estimated hourly energy consumption are mainly within 10%. [ABSTRACT FROM AUTHOR]

Abstract: This paper reports the development of a building energy demand predictive model based on the decision tree method. This method is able to classify and predict categorical variables: its competitive advantage over other widely used modeling techniques, such as regression method and ANN method, lies in the ability to generate accurate predictive models with interpretable flowchart-like tree structures that enable users to quickly extract useful information. To demonstrate its applicability, the method is applied to estimate residential building energy performance indexes by modeling building energy use intensity (EUI) levels. The results demonstrate that the use of decision tree method can classify and predict building energy demand levels accurately (93% for training data and 92% for test data), identify and rank significant factors of building EUI automatically. The method can provide the combination of significant factors as well as the threshold values that will lead to high building energy performance. Moreover, the average EUI value of data records in each classified data subsets can be used for reference when performing prediction. One crucial benefit is improving building energy performance and reducing energy consumption. Another advantage of this methodology is that it can be utilized by users without requiring much computation knowledge. [ABSTRACT FROM AUTHOR]

Abstract: This paper explores the effects of urban texture on building energy consumption. It is based on the analysis of digital elevation models (DEMs)—raster models of cities which have proven to be very effective in the urban context. Different algorithms are proposed and discussed, including the calculation of the urban surface-to-volume ratio and the identification of all building areas that are within 6m from a façade (passive areas). An established computer model to calculate energy consumption in buildings, the LT model, is coupled with the analysis of DEMs, providing energy simulations over extensive urban areas. Results for the three case study cities of London, Toulouse and Berlin are presented and discussed. [Copyright &y& Elsevier]

• The combination of rough set theory and deep learning algorithms is analyzed. • Rough set theory is used to reduce the influencing factors of building energy consumption. • Deep learning is used to extract features of building energy consumption data. • An accuracy comparison of several prediction models based on rough sets and different neural networks is made. The efficient and accurate prediction of building energy consumption can improve the management of power systems. In this paper, the rough set theory was used to reduce the redundant influencing factors of building energy consumption and find the critical factors of building energy consumption. These key factors were then used as the input of a deep neural network with a "deep" architecture and powerful capabilities in extracting features. Building energy consumption is output of the deep neural network. This study collected data from 100 civil public buildings for rough set reduction, and then collected data from a laboratory building of a university in Dalian for nearly a year to train and test deep neural networks. The test included both the short-term and medium-term predictions of building energy consumption. The prediction results of the deep neural network were compared with that of the back propagation neural network, Elman neural network and fuzzy neural network. The results show that the integrated rough set and deep neural network was the most accurate. The method proposed in this study could provide a practical and accurate solution for building energy consumption prediction. [ABSTRACT FROM AUTHOR]

• Optimizing the integration of renewable energy in existing buildings. • Minimizing required cost to satisfy specified reduction in building energy consumption. • Optimal compliance with EISA2007 energy requirements for federal buildings. • Novel methodology for efficient segmentation of complex buildings. • Complying with building functional requirements and constructability constraints. This paper presents the development of a novel optimization model for optimizing the use of RE measures in existing buildings to satisfy an owner-specified target reduction in energy consumption while minimizing the required building upgrade costs. The model performance was evaluated using a real-life case study of an educational building with a total area of 20,717 m2. The optimization model was used to identify an optimal combination of RE technologies that minimize the upgrade cost for this case study while satisfying its specified 80% energy reduction goal. The model minimized the building upgrade cost by making a number of optimal selections, such as locating the majority of solar RE technologies in building segments facing south due to their higher exposure to the sun radiations. The results of this analysis highlight the original contributions of the model in identifying an optimal set of RE measures that minimize the building upgrade cost while satisfying all owner-specified requirements, providing a detailed description of the optimal building integration plan of RE technologies, and complying with practical functional requirements, and constructability constraints. These capabilities are expected to support building owners and decision-makers in their efforts to integrate cost-effective RE measures in existing buildings. [ABSTRACT FROM AUTHOR]

• A model to simulate interactions between a building and its outdoor conditions. • The model co-simulates EnergyPlus, OpenFOAM, and lumped thermal models. • The model provides proper estimates of outdoor conditions at the urban microscale. • Waste heat releases from the HVAC system can be simulated from the model. • Indirect and direct effects of green roofs can be considered by the model. This paper introduces a physically-based model to simulate interactions between a building and its outdoor conditions at the urban microscale. In the model, the building is simulated with EnergyPlus while its outdoor conditions are assessed from OpenFOAM. Furthermore, the model simulates the street pavement and surrounding buildings based on the lumped thermal theory. All components of the model are quasi-dynamically co-simulated. Through simulations of the model, waste heat releases from a cooling system can be observed with a higher resolution than this achieved by most urban microclimate models in the literature. Unlike several methods in the literature, the model evaluates a countermeasure to urban heat islands by considering direct and indirect effects simultaneously. To validate the model, measurements were collected during a field experiment in an university campus. Comparing measurements to estimates, the model seems to properly approximate the outdoor temperature and the air motion. However, a discrepancy is observed between estimates and measurements of the surface temperature. The discrepancy could be minimised if a better consideration of the net-longwave radiation was possible when co-simulating EnergyPlus. After some improvements, the model could become a support tool to mitigate urban heat islands and climate change in different regions of the world. [ABSTRACT FROM AUTHOR]