Neural-Network-Based Building Energy Consumption Prediction with Training Data Generation

Abstract

The importance of neural network (NN) modelling is evident from its performance benefits in a myriad of applications, where, unlike conventional techniques, NN modeling provides superior performance without relying on complex filtering and/or time-consuming parameter tuning specific to applications and their wider ranges of conditions. In this paper, we employ NN modelling with training data generation based on sensitivity analysis for the prediction of building energy consumption to improve performance and reliability. Unlike our previous work, where insignificant input variables are successively screened out based on their mean impact values (MIVs) during the training process, we use the receiver operating characteristic (ROC) plot to generate reliable data with a conservative or progressive point of view, which overcomes the issue of data insufficiency of the MIV method: By properly setting boundaries for input variables based on the ROC plot and their statistics, instead of completely screening them out as in the MIV-based method, we can generate new training data that maximize true positive and false negative numbers from the partial data set. Then a NN model is constructed and trained with the generated training data using Levenberg–Marquardt back propagation (LM-BP) to perform electricity prediction for commercial buildings. The performance of the proposed data generation methods is compared with that of the MIV method through experiments, whose results show that data generation using successive and cross pattern provides satisfactory performance, following energy consumption trends with good phase. Among the two options in data generation, i.e., successive and two data combination, the successive option shows lower root mean square error (RMSE) than the combination one by around 400~900 kWh (i.e., 30%~75%).

Special Issue on “Dynamic Modeling and Control in Chemical and Energy Processes”

“…Another research study focused on smart city organization through efficient energy control in buildings. As described in [2], building electricity consumption needs to be controlled by considering local environmental factors such as the working day, temperature and humidity (or a combination of these). Moreover, the implementation of an optimal electricity consumption strategy is challenging from a microgrid electricity management viewpoint.…”

“…Moreover, the implementation of an optimal electricity consumption strategy is challenging from a microgrid electricity management viewpoint. For this purpose, S. Lee et al [2] employed neural network modeling with training data generation in order to predict a building's energy consumption (actual electricity consumption data from a shopping mall in Dalian, China were used). Based on the testing of their training data, the authors developed a robust building energy management strategy and were able to improve the energy efficiency, performance and reliability.…”

English Grammar Discrimination Training Network Model and Search Filtering

“…is is mainly due to the rapid development of the Internet and the increasing demand for Chinese information on the Internet at an unprecedented rate and the rapid increase in the number of Chinese Internet users. All of these put forward higher and newer requirements for English grammar search filtering [19,20]. As far as the Chinese-oriented search filter system is concerned, its development is still in the preliminary stage.…”

An Expert System Based on Data Mining for a Trend Diagnosis of Process Parameters

“…Researchers have recently proposed various methods for diagnosing abnormal process parameters, including clustering-based methods, density-based methods, data-driven methods, and expert system methods [6][7][8][9]. The clustering-based approach involves clustering the data of parameters into multiple clusters, where the cluster with the least data points is considered to be the abnormal cluster.…”