Search

Highlights • Interdisciplinary approaches are proposed to predict multi-building energy use. • Social network analysis is applied to identify reference buildings in a building group. • Artificial neural network (ANN) algorithm is integrated in energy use prediction with reference buildings. • Office, education, laboratory, and residence building groups on campus are tested. • Proposed SNA-ANN can accurately predict multi-building energy use with reference buildings. Abstract Predicting multi-building energy use at campus or city district scale has recently gained more attention; and more researchers have started to define reference buildings and study inter-impact between building groups. However, how to integrate the relationship to define reference buildings and predict multi-building energy use, using significantly less amount of building data and reducing complexity of prediction models, remains an open research question. To resolve this, this study proposed a novel method to predict multi-building energy use by integrating a social network analysis (SNA) with an Artificial Neural Network (ANN) technique. The SNA method was used to establish a building network (BN) by identifying reference buildings and determine correlations between reference buildings and non-reference buildings. The ANN technique was applied to learn correlations and historical building energy use, and then used to predict multi-building energy use. To validate the SNA-ANN method, 17 buildings in the Southeast University campus, located in Nanjing, China, were studied. These buildings have three years of actual monthly electricity use data and were grouped into four types: office, educational, laboratory, and residential. The results showed the integrated SNA-ANN method achieved average prediction accuracies of 90.67% for the office group, 90.79% for the educational group, 92.34% for the laboratory group, and 83.32% for the residential group. The results demonstrated the proposed SNA-ANN method achieved an accuracy of 90.28% for the predicted energy use for all building groups. Finally, this study provides insights into advancing the interdisciplinary research on multi-building energy use prediction. [ABSTRACT FROM AUTHOR]

Remote sensing technology is becoming mainstream for mapping the growing stem volume (GSV) and overcoming the shortage of traditional labor-consumed approaches. Naturally, the GSV estimation accuracy utilizing remote sensing imagery is highly related to the variable selection methods and algorithms. Thus, to reduce the uncertainty caused by variables and models, this paper proposes a combined strategy involving improved variable selection with the collinearity test and the secondary ensemble algorithm to obtain the optimally combined variables and extract a reliable GSV from several base models. Our study extracted four types of alternative variables from the Sentinel-1A and Sentinel-2A image datasets, including vegetation indices, spectral reflectance variables, backscattering coefficients, and texture features. Then, an improved variable selection criterion with the collinearity test was developed and evaluated based on machine learning algorithms (classification and regression trees (CART), k-nearest neighbors (KNN), support vector regression (SVR), and artificial neural network (ANN)) considering the correlation between variables and GSV (with random forest (RF), distance correlation coefficient (DC), maximal information coefficient (MIC), and Pearson correlation coefficient (PCC) as evaluation metrics), and the collinearity among the variables. Additionally, we proposed a secondary ensemble with an improved weighted average approach (IWA) to estimate the reliable forest GSV using the first ensemble models constructed by Bagging and AdaBoost. The experimental results demonstrated that the proposed variable selection criterion efficiently obtained the optimal combined variable set without affecting the forest GSV mapping accuracy. Specifically, considering the first ensemble, the relative root mean square error (rRMSE) values ranged from 21.91% to 30.28% for Bagging and 23.33% to 31.49% for AdaBoost, respectively. After the secondary ensemble involving the IWA, the rRMSE values ranged from 18.89% to 21.34%. Furthermore, the variance of the GSV mapped by the secondary ensemble with various ranking methods was significantly reduced. The results prove that the proposed combined strategy has great potential to reduce the GSV mapping uncertainty imposed by current variable selection approaches and algorithms. [ABSTRACT FROM AUTHOR]

The sintering process is the main process that affects the performance of ternary cathode materials. Due to the closed, continuous, and long-term characteristics of the sintering process carried out in a roller kiln, the reaction state including reaction degree, particle size, and etc., of the raw materials cannot be directly obtained through sampling detection, resulting in ineffective temperature control. This article mainly focuses on modeling the dehydration reaction stage of the sintering process to obtain the reaction state of the raw materials. Firstly, a two-sphere model is established based on Newton's second law and the particle volume conservation equation to describe the relationship between the particle radius and sintering temperature of lithium hydroxide and ternary precursor; Secondly, the chemical kinetic parameters of the dehydration reaction in the two-sphere model are obtained by combining the single heating rate scanning method with the multiple heating rate scanning method; Then, in order to improve the accuracy of the two-sphere model and reduce the impact of external environmental temperature changes, a physics-informed neural network model is constructed by combining the two-sphere model with the neural ordinary differential equation model. Finally, the effectiveness of the modeling method is verified through numerical simulation and empirical data. [ABSTRACT FROM AUTHOR]

• Incorporated inter-building effects and energy consumption correlations. • Integrated building network and long short-term memory algorithm. • Five building groups on two campuses was used for validation. • The proposed model can forecast accurate energy dynamics at district-scale. With the development of data-driven techniques, district-scale building energy prediction has attracted increasing attention in recent years for revealing energy use patterns and reduction potentials. However, data acquisition in large building groups is difficult and adjacent buildings also interact with each other. To reduce data cost and incorporate the inter-building impact with the data-driven building energy model, this study proposes a deep learning predictive approach that fuses the building network model with a long short-term memory learning model for district-scale building energy modeling. The building network was constructed based on correlations between the energy use intensity of buildings, which can significantly reduce the computational complexity of the deep learning models for energy dynamic prediction. Five typical building groups with energy use data from 2015 to 2018 on two institutional campuses were selected to perform the validation experiment with TensorFlow. Based on the prediction error assessments, the results suggest that for total building energy use intensity prediction, the proposed model can achieve a mean absolute percentage error of 6.66% and a root mean square error of 0.36 kWh/m2, compared to 12.05% and 0.63 kWh/m2 of the conventional artificial neural network model and to 11.06% and 0.89 kWh/m2 for the support vector regression model. [ABSTRACT FROM AUTHOR]

Buildings are one of the most important energy use sectors in cities, and forecasting the abnormal increase in building energy demand in certain climatic conditions is necessary to adjust building energy operations and implement energy policy. Accordingly, this research proposes a data-driven abnormally high energy demand detection framework in urban buildings based on their design parameters and local weather data, with the support of machine learning techniques. In this study, 71 public buildings with energy records in Jianhu city, Jiangsu province, China, were selected to abstract urban morphologies at community scale. The weather profile for the city was obtained from year 2015–2018 to create weather characteristics. Three machine learning algorithms—random forest, support vector machine, and artificial neural network—were applied to identify the months of abnormally high electricity consumption in different building types. This framework also explores key variables in the data and provides the basis for a system that prioritizes the acquisition of variables when complete data is unavailable. The results show that, with complete data, the accuracy score of the system in this study can reach 0.854 with the SVM algorithm, and the model returned an accuracy of 0.865 with the RF model after the key variable selection. Based on those results, the framework in this study can generate preemptive warnings for months with an expected abnormally high energy consumption in target buildings as a prerequisite of energy policy. • A data-driven abnormally high electricity use detection system is proposed. • Different morphologies under different weather conditions were tested. • Key factors of urban morphologies and weather conditions were identified. • Three machine learning techniques were applied for the prediction in the system. • This study can be applied for energy management in building and urban scales. [ABSTRACT FROM AUTHOR]