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%).
Highlights
Energy optimization has become a critical issue in reducing CO2 emissions
We carry out simulation experiments and compare the prediction performance of a neural network (NN) model trained with both original data and generated data: We first produce 2/3 of the training data from the original data [27] and compare the prediction results with those with the generated data based on the proposed processes in Section 3, which is followed by the analysis of simulation results and discussions
We used the mean impact values (MIVs) to screen out insignificant input variables based on the sensitivity analysis and demonstrated its effectiveness [24]
Summary
Energy optimization has become a critical issue in reducing CO2 emissions. By the end of 2017 non-renewable electricity generation still accounted for around 73.5%, despite significant investment in the renewable energy sector; the investment in the renewable energy amounted to $274 billion and. Zeng and Yeung proposed a SA method by combining two approaches and derived an output variance equation based on the perturbation of inputs and weights They emphasized that the result aided in the selection of more weight sets with a low sensitivity level during training [20]. We investigate how different environmental elements—such as temperature, humidity, working day, wind speed, and weather characteristics—influence actual electricity energy consumption in buildings using generated training data. In order to overcome the issue of insufficient training data, we systematically data of a shopping mall in Dalian, China, for 2 months are reordered, i.e., consumption ranged from generate more training data based on the ROC plot. With the help of the ROC plot, input mall in Dalian, China, for 2 months are reordered, i.e., consumption ranged from 17,385 kWh to values of temperature, humidity, working day, weather characteristics and electricity consumption. For each output variation due to input perturbation is expressed by the multiplication of weights from the input to the hidden layer and from the hidden to the output layer [24]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
