LAPSE:2019.1322
Published Article
LAPSE:2019.1322
Neural-Network-Based Building Energy Consumption Prediction with Training Data Generation
Sanghyuk Lee, Jaehoon Cha, Moon Keun Kim, Kyeong Soo Kim, Van Huy Pham, Mark Leach
December 10, 2019
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%).
Keywords
building modelling, energy management, mean impact value (MIV), neural network (NN), receiver operating characteristic (ROC)
Suggested Citation
Lee S, Cha J, Kim MK, Kim KS, Pham VH, Leach M. Neural-Network-Based Building Energy Consumption Prediction with Training Data Generation. (2019). LAPSE:2019.1322
Author Affiliations
Lee S: Department of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, Suzhou 215123, China; Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City 700000, Vietnam [ORCID]
Cha J: Department of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, Suzhou 215123, China
Kim MK: Department of Architecture, Xi’an Jiaotong‐Liverpool University, Suzhou 215123, China [ORCID]
Kim KS: Department of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, Suzhou 215123, China [ORCID]
Pham VH: Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City 700000, Vietnam
Leach M: Department of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, Suzhou 215123, China
Journal Name
Processes
Volume
7
Issue
10
Article Number
E731
Year
2019
Publication Date
2019-10-12
Published Version
ISSN
2227-9717
Version Comments
Original Submission
Other Meta
PII: pr7100731, Publication Type: Journal Article
Record Map
Published Article

LAPSE:2019.1322
This Record
External Link

doi:10.3390/pr7100731
Publisher Version
Download
Files
[Download 1v1.pdf] (3.6 MB)
Dec 10, 2019
Main Article
License
CC BY 4.0
Meta
Record Statistics
Record Views
483
Version History
[v1] (Original Submission)
Dec 10, 2019
 
Verified by curator on
Dec 10, 2019
This Version Number
v1
Citations
Most Recent
This Version
URL Here
https://psecommunity.org/LAPSE:2019.1322
 
Original Submitter
Calvin Tsay
Links to Related Works
Directly Related to This Work
Publisher Version