Search

Currently, building energy consumption prediction models are usually based on a large amount of historical operational data in high demands of building operating hours and monitoring systems. However, many buildings may lack operational data due to relatively limited monitoring systems, causing the failure to use data-driven methods to characterize the energy profile. In this context, transfer learning is a promising method to establish the knowledge transfer between many high-quality building operation datasets and a small amount of target building data, and to help predict energy consumption in the target building. This paper studies the possibility of employing transfer learning to achieve both short and long-term building energy consumption prediction. Firstly, a similarity analysis method, based on variable modal decomposition and dynamic time warping, is proposed for identifying the source buildings with the most similar energy features to the target building. Then, transfer learning for long-term prediction air-conditioning energy consumption is developed with weather parameters generated by the Morphing method as inputs. For the short-term single-step prediction, the proposed model CV-RMSE improves 81.3% (AEC) and 77.4% (EEC), respectively, compared to the prediction model that does not implement the transfer learning strategy and directly uses the target BEC data. As for the short-term multi-step prediction, the proposed model CV-RMSE improves 62.0% (AEC) and 65.5% (EEC), respectively. For the long-term prediction, the average CV-RMSE for the whole year is 6.62% and 11.15% for the proposed and directly target domain-based model, respectively. The proposed method explores the practicality of transfer learning in building energy forecasting, contributing to the use of existing building operation data for energy management at different timespan. • A similarity analysis method for building energy consumption data based on VMD-DTW is proposed. • The Seq2Seq-Transformer model is applied to short-term multi-step prediction of building energy consumption. • Transfer learning idea is first introduced to the long-term building energy consumption prediction. [ABSTRACT FROM AUTHOR]

In the 21st century, urbanization has caused rapid growth in the global construction area, resulting in high building resource consumption and long-term environmental impacts. Analyzing the resource consumption of public buildings and identifying the key factors that affect the consumption of building resources is important for developing of targeted policies. In this paper, we analyzed each branch of the People's Bank of China based on energy, water, and land resource consumption as well as the structure of energy consumption. Based on resource-consumption indicators, we divided 31 provincial-level administrative regions into four resource consumption levels; 65% were in the low-to-medium resource consumption levels. Medium-sized buildings had the highest energy consumption level and a more balanced energy consumption structure. The energy consumption per capita, water consumption, and utilization rate of small-sized buildings were low. To reduce resource consumption by public buildings, the construction of large-sized buildings should be limited. • The comprehensive evaluation method is used to calculate the resource consumption of the People's Bank of China. • Regression equations were established for energy consumption and resource consumption. • Medium-sized institutions had the highest energy consumption level and a more balanced energy consumption structure. [ABSTRACT FROM AUTHOR]

Accurate building energy consumption forecasting is crucial for developing efficient building energy management systems, improving energy efficiency, and local building energy supervision and management. However, short-term building energy consumption forecasting is challenging due to highly non-smooth and volatile trends. In this paper, we present a novel methodology that combines interpretable decomposition methods with an interpretable forecasting model. We first illustrate a daily energy consumption pattern recognition (DECPR) method, which decomposes daily energy consumption patterns into interpretable energy consumption subsequences. To achieve satisfactory forecasting performance, we design the vector representation of each subsequence as a static input to the temporal fusion transformers (TFT) model. This vector representation integrates the DECPR method into the TFT model. The TFT model produces interpretable outputs, such as the attention analysis of different step lengths and the visualization of the importance ranking of exogenous variables, including meteorological data, calendar information, and the vector representation. Empirical studies demonstrate that our proposed DECPR-TFT system outperforms comparable models with a mean absolute percentage error (MAPE) of 6.11%, which is significantly lower than other models. These interpretable outputs provide valuable insights for researchers seeking to develop energy-saving operation strategies in buildings. Overall, our methodology offers a promising solution for short-term building energy consumption forecasting that can contribute to more efficient building energy management and energy-saving operation strategies. • This study proposes DECPR, an interpretable decomposition method, explaining decomposed subsequences. • TFT, a deep learning-based approach with interpretability, predicts hourly energy consumption for the next day. • The interpretability of TFT model are used to analyze the effects of exogenous variables on energy consumption • The proposed DECPR-TFT model outperforms others, with 6.11% MAPE, significantly lower than competitors. [ABSTRACT FROM AUTHOR]

The impact of village morphology on habitats' daily spatiotemporal behavior and building energy consumption is still vague. This research aims to propose a method to reveal how and to what extent village morphology and residents' demographic structure influence farmhouses' occupancy rate and energy consumption. For this purpose, a combined time geography and building energy consumption method was proposed to disclose the relationship among residents' family roles, village morphology and household energy consumption. To explore the occupancy rate of farm-houses with different family members in different village morphology, resident types based on field research (retrospective interviews and aggregation behavior observation) were formulated. Residents with similar time-space behavior seemed as an "agent" and then a specified number of agents are combined into different families for ideal experiments. By placing different households in different villages for multi-factor cross-experiment, the occupancy rates of different households are obtained based on individual time-space behavior patterns, and then the energy consumption of each household under different scenarios is obtained by combining building energy consumption simulation. In addition, the relationship between resident's disposable personal time, local public space' quality, and the house occupancy rate was analyzed. Combined with a case study in Shanghai with 417 valid questionnaires, it can be seen that the method proposed in this paper is effective and villages with high quality public space have the potential to reduce household energy consumption from 2.17% to 38.82% for diverse families. The quantitative result indicated that the occupancy rate is mainly influenced by residents having more disposable personal time, and such space-time behavior is sensitive to village morphology. This study proposed a combined method and case evidence to systematically analyze the complex relationship between resident behavior, the village morphology, and household energy consumption, thus contributing to the sustainable plan and design of the community spatial system. [Display omitted] • Proposed systematic approach to reveal the relationship between morphology and energy. • Energy-saving effect of public space is revealed from villagers' behavior chain. • The influence of the village morphology on energy consumption is between 2.17% and 38.82%. • Alternative mode of villager's space usage in disposable personal time was proved. [ABSTRACT FROM AUTHOR]

Building Archetypes (BAs) are often used in modeling urban-scale building energy consumption profiles to represent the energy consumption behavior of typical buildings within the modeled urban environment. One current approach to the development of BAs involves the creation of Building Energy Models (BEMs) using surveyed data coupled with codes, standards, or engineering experience. Another approach is the modification of existing standardized BEMs using available data to produce a suitable BA for the representation of the building stock. The adoption of either of these methods has been treated as an axiom or a step that did not need much consideration. However, the results produced by BEMs created according to different methodologies present several differences. The discrepancy in the produced results is shown not only in the results of the BEMs developed according to different methodologies but also in the degree to which these results vary when changing input values. Limited studies analyzed the sensitivity of these models to uncertain inputs, even though it is essential for the development of BA libraries. This paper comparatively investigates the Region-Specific (RS) and Department of Energy (DOE)-based BEM creation methods for BA library development. The models are developed by following the two methodologies, and their predictions are compared to the metered data from a high-rise residential building in the Marina district of Lusail City, Qatar. A Global Sensitivity Analysis (GSA) method is used to identify the most influential parameters contributing to the energy consumption variation of these models. Further, a parametric simulation campaign is conducted by varying the inputs determined earlier to quantify the BEMs' output variability. According to the results, the baseline RS BEM and DOE BEM yield an Energy Use Intensity (EUI) of 211.03 kWh/m2 and 137.9 kWh/m2, respectively. The deviation of these values from the metered EUI of 185,37 kWh/m2 indicates that the RS BEM development methodology is preferable to the DOE BEM for the BA development. Based on the GSA results, regardless of the BEM development methodology used, the most important parameters contributing to output variation are the Cooling Setpoint, the Outdoor Air Requirements, the Equipment Power Density, and the Lighting Power Density. Further, the RS BEM's parametric simulations produce a mean cooling EUI of 324.83 kWh/m2, closer to the literature benchmarks than the mean cooling EUI of DOE BEM, 341.62 kWh/m2. The results obtained from the baseline model and the uncertainty analysis support the conclusion that a Region-Specific Model developed from the ground up serves to better represent high-rise residential buildings in regions with extreme climate conditions. The impact this work achieves is providing decision-making support for urban scale building energy modelers for future building stock representation efforts in such areas while also providing an expected uncertainty range for the developed high-rise residential archetypes. [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]

[Display omitted] • The proposed method can be applied to all window types and does not require the manual adjustment of threshold values according to different weather conditions. • The prediction accuracy of the proposed method in the case study reaches 97.79%. • The features of window opening behavior for a teaching building in severe cold regions are explored. • Occupants of teaching buildings in severe cold regions in the transition season prefer a large opening angle (45°∼180°). The building industry plays an important role in the effort to achieve carbon neutrality, and window opening behavior is a major contributor to building energy consumption. In severe cold regions, opening windows during the heating period causes energy waste. If the window opening behavior can be monitored in real time, then the occupants' energy use behavior can be guided to reduce energy waste. This paper proposes a window opening behavior monitoring method using a deep learning-based image recognition model that can identify the window state based on real-time video and was validated in a case study based on outdoor thermal and wind data. A teaching building with casement windows was used as a case study. The results showed that the occupants preferred a large window opening angle (45°∼180°), which is a choice that significantly affects the building energy consumption. The prediction accuracy of the proposed method can reach 97.79%, which also serves to avoid the difficulty of manually calibrating the pixel threshold and realize real-time feedback. This method has a wide range of application scenarios that enable us to obtain window opening behavior to improve the building performance simulation accuracy and guide occupants' energy consumption behavior. [ABSTRACT FROM AUTHOR]

In recent years, a large number of building energy consumption prediction models, with various intended uses, have been proposed. The majority of these models have either taken a data-driven or a physical modeling approach, with each approach having its own strengths and limitations. Towards leveraging the strengths and reducing the limitations of each approach for improved prediction performance, this paper presents a hybrid machine-learning approach for occupant-behavior-sensitive energy consumption prediction. The proposed approach is composed of three constituent models: (1) a machine-learning model that learns the impact of outdoor weather conditions from simulation-generated data, (2) a machine-learning model that learns the impact of occupant behavior from real data, and (3) an ensemble model that predicts cooling energy consumption based on the outputs of the first two models. The simulation-generated data were created through simulating a set of reference buildings in EnergyPlus. The real data were collected from an office building in Pennsylvania. The proposed hybrid model was validated on an unseen real dataset. It achieved 0.73 kWh RMSE and 9.07% CV in hourly cooling energy consumption prediction, which indicates that the proposed approach is promising. [ABSTRACT FROM AUTHOR]

The objective of this work was to evaluate the interactions of users with air conditioning systems, lighting, natural ventilation, internal shading devices, and costs related to automation of a teaching building. Three behavior patterns (proactive, intermediate and careless) were created. The proactive user seeks to use natural light, uses passive solar shading and integration of natural and artificial ventilation. The intermediate user does not seek integration of natural and artificial lighting, they use hybrid ventilation as a ventilation strategy. The careless user does not use any passive strategy, predominantly uses artificial conditioning and adjusts cooling and heating setpoint to values out of the norms. In addition to the users' behaviors, the automated building was modeled. Computer simulations were performed in the EnergyPlus program, in order to measure the influence of behavior patterns on the building's energy consumption. Based on the analysis of the building's energy consumption profile, results indicate users are between the intermediate and the careless user classification, with a tendency to the intermediate user profile. The paper also presents an analysis of the payback time with the building automation in face of the user profiles. [ABSTRACT FROM AUTHOR]

• End-use of electricity consumption in residential buildings in Gulf Cooperation Council countries was presented. • Discrepancies in certain indicators have been observed by the end-use of electricity consumption. • Improving the efficiency of air conditioners and thermal insulation of the walls are the best measures to conserve electricity in residential buildings. • The results can be used in areas with a similar climate, living standard, buildings types, and the inhabitants' behavior. Energy conservation and improvement in energy efficiency yield multiple technical, economic, environmental, and social benefits and realize comfort and sustainability of residential buildings (RBs). This review paper presents the end-use of electricity consumption in RBs and the results of economic analysis. In addition, a description and discussion of studies on energy conservation measures, Net Zero Energy Building, and renewable energy in RBs are discussed. The percentage of end-used energy consumption for different purposes obtained in many studies are often not consistent. Moreover, discrepancies in certain indicators have been observed, necessitating the need to clarify the factors in the consumption of electricity in RBs. Further, a few studies used the term energy consumption in buildings (total or electrical); however, specifying the type of buildings to identify and use the necessary indicators of energy consumption in each type of building are desirable. Furthermore, most studies emphasized improving the efficiency of air conditioners and thermal insulation of the walls as these are the best measures to conserve electricity. [ABSTRACT FROM AUTHOR]

• The degree of influence of residential cluster layout factors on building heating energy consumption levels in cold regions of China. • Provides an idea of residential layout optimization and design based on the energy saving objectives of residential clusters, translating quantitative indicators such as wind environment into residential layout form design problems. • Energy simulation-based residential planning and layout design method is used to quantify the relationship between residential cluster design factors and energy efficiency in Jinan, resulting in optimal design parameters for residential planning factors in Jinan. • The study of building heating energy consumption in a city in a cold region of China, with a methodology that can be used in countries or cities with similar climate characteristics. Residential heating energy consumption in China accounts for about 34% of the total building operation energy consumption in the country. The layout pattern of residential clusters is one of the most critical factors affecting building heating energy consumption, yet few scholars have studied the layout of residential clusters in a quantitative way. This paper takes Jinan, a typical city in cold region IIB of China, as an example, to quantify and analyse the residential layout parameters related to heating energy consumption: group layout, building orientation and building spacing; ECOTECT and HTB2 are used to model and simulate the energy consumption of the three types of layout residential groups selected for the study, and the relationship between residential group layout parameters and residential heating energy consumption is analysed based on multiple linear regression analysis. The relationship between residential group layout parameters and residential heating energy consumption was analysed based on multiple linear regression analysis. The study shows that, on the premise of ensuring the same building density, the group layout has the greatest influence on the building energy consumption, and the courtyard layout has lower heating energy consumption compared to the row and staggered layout; on this basis, the influence of building orientation and building spacing on heating energy consumption is discussed. The study shows that increasing the spacing between buildings to meet the daylight spacing will reduce energy consumption by 4% and that a 15° shift to the west will reduce energy consumption by 5%. This result confirms the importance of cluster layout in terms of heating energy consumption and urban energy efficiency in cities in cold regions. [ABSTRACT FROM AUTHOR]

Industrial robots have been widely utilized in factories to replace or help employees performing tasks such as handling, welding, and assembly. With the increasing breadth of installation and deployment of industrial robots, it is critical to predict and optimize their energy consumption in order to assure their environmentally friendly characteristics. While the data-driven modeling method based on multi-layer perception has been demonstrated to be a viable way for revealing quantitative relationships between operating parameters and energy consumption for industrial robots regardless of physical process or case-specific information, there are still some limitations in terms of prediction range, modeling efficiency, and sample size requirement. To accelerate model rebuilding and improve model accuracy without collecting a large number of samples simultaneously, this paper proposes a transfer-learning-based model creation method for energy consumption of industrial robots, where the associated operating parameters are analyzed, and structure adjustment strategies for multi-layer perception are planned for various industrial robot systems, then, schemes for the reuse of parameters in well-trained networks on source domain and the fine-tunning of multi-layer perception model are formulated to efficiently build the accurate energy consumption model on target domains. Experiments are conducted on two distinct robot systems, the Epson C4 and the Siasun SR10C, with nonidentical operating parameter structures and sample sizes. The results demonstrate that transfer learning models with fine-tuning strategy outperform previous data-driven modeling methods in terms of model accuracy and modeling efficiency in both of these situations. [Display omitted] • The transfer-learning based model creation method for predicting the energy consumption of industrial robots. • Analyze related operating parameters and design MLP's structure adjustment strategies to help knowledge transfer among domains. • Create EC models for target domains by reusing and fine-tunning parameters on case-related transferred layers. • Boost the energy consumption modeling accuracy on small scale dataset and enhance the efficiency of modeling process. [ABSTRACT FROM AUTHOR]

[Display omitted] • The communal areas can have different levels of energy performance in the 15 types of public residential buildings under study. • Spatial design features can evidently affect the energy consumption in the communal areas. • The ability to harvest daylight serves as a key determinant of energy efficiency. • Both econometric and machine learning techniques are proved to be effective to generate reliable findings. In this paper, we construct a unique database for 1228 residential buildings in Hong Kong to investigate how the spatial features of these residential buildings affect the electricity consumption in the communal area. We choose Hong Kong for this analysis as the city owns a large number of standard-type residential buildings managed by the public institution, which could be affected strongly by environmental policies. Both the machine learning method, based on the Least Absolute Shrinkage and Selection Operator (LASSO), and econometric regressions are adopted to analyse the data. We first utilize the machine learning LASSO technique to identify the most relevant factors for the subsequent econometric analysis. Our results show that the electricity demand for relatively low consumption building types, such as Twin Tower, is 6% lower than that of the high consumption building types. Newly constructed buildings usually belong to the medium consumption types, with the estimated monthly electricity consumption per apartment in communal areas to be around 50.2 kWh on average in 2020. These findings shed light on the nexus between spatial features and energy use for complex buildings, potentially contributing to the better crafting of energy-saving policy and the improvement of residential building programmes. [ABSTRACT FROM AUTHOR]