Simplified Neural Network Model Design with Sensitivity Analysis and Electricity Consumption Prediction in a Commercial Building
With growing urbanization, it has become necessary to manage this growth smartly. Specifically, increased electrical energy consumption has become a rapid urbanization trend in China. A building model based on a neural network was proposed to overcome the difficulties of analytical modelling. Howeve...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/12/7/1201 |
| _version_ | 1811262682749206528 |
|---|---|
| author | Moon Keun Kim Jaehoon Cha Eunmi Lee Van Huy Pham Sanghyuk Lee Nipon Theera-Umpon |
| author_facet | Moon Keun Kim Jaehoon Cha Eunmi Lee Van Huy Pham Sanghyuk Lee Nipon Theera-Umpon |
| author_sort | Moon Keun Kim |
| collection | DOAJ |
| description | With growing urbanization, it has become necessary to manage this growth smartly. Specifically, increased electrical energy consumption has become a rapid urbanization trend in China. A building model based on a neural network was proposed to overcome the difficulties of analytical modelling. However, increased amounts of data, repetitive computation, and training time become a limitation of this approach. A simplified model can be used instead of the full order model if the performance is acceptable. In order to select effective data, Mean Impact Value (MIV) has been applied to select meaningful data. To verify this neural network method, we used real electricity consumption data of a shopping mall in China as a case study. In this paper, a Bayesian Regularization Neural Network (BRNN) is utilized to avoid overfitting due to the small amount of data. With the simplified data set, the building model showed reasonable performance. The mean of Root Mean Square Error achieved is around 10% with respect to the actual consumption and the standard deviation is low, which reflects the model’s reliability. We also compare the results with our previous approach using the Levenberg–Marquardt back propagation (LM-BP) method. The main difference is the output reliability of the two methods. LM-BP shows higher error than BRNN due to overfitting. BRNN shows reliable prediction results when the simplified neural network model is applied. |
| first_indexed | 2024-04-12T19:30:57Z |
| format | Article |
| id | doaj.art-c0cee6ffaa1c417baa8a10663fb349c4 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-12T19:30:57Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-c0cee6ffaa1c417baa8a10663fb349c42022-12-22T03:19:21ZengMDPI AGEnergies1996-10732019-03-01127120110.3390/en12071201en12071201Simplified Neural Network Model Design with Sensitivity Analysis and Electricity Consumption Prediction in a Commercial BuildingMoon Keun Kim0Jaehoon Cha1Eunmi Lee2Van Huy Pham3Sanghyuk Lee4Nipon Theera-Umpon5Department of Architecture, Xi’an Jiatong-Liverpool University, Suzhou 215123, ChinaDepartment of Electrical and Electronic Engineering, Xi’an Jiatong-Liverpool University, Suzhou 215123, ChinaSocial Science Research Institute, Yonsei University, Seoul 03722, KoreaFaculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City 700000, VietnamDepartment of Electrical and Electronic Engineering, Xi’an Jiatong-Liverpool University, Suzhou 215123, ChinaBiomedical Engineering Institute, Chiang Mai University, Chiang Mai 50200, ThailandWith growing urbanization, it has become necessary to manage this growth smartly. Specifically, increased electrical energy consumption has become a rapid urbanization trend in China. A building model based on a neural network was proposed to overcome the difficulties of analytical modelling. However, increased amounts of data, repetitive computation, and training time become a limitation of this approach. A simplified model can be used instead of the full order model if the performance is acceptable. In order to select effective data, Mean Impact Value (MIV) has been applied to select meaningful data. To verify this neural network method, we used real electricity consumption data of a shopping mall in China as a case study. In this paper, a Bayesian Regularization Neural Network (BRNN) is utilized to avoid overfitting due to the small amount of data. With the simplified data set, the building model showed reasonable performance. The mean of Root Mean Square Error achieved is around 10% with respect to the actual consumption and the standard deviation is low, which reflects the model’s reliability. We also compare the results with our previous approach using the Levenberg–Marquardt back propagation (LM-BP) method. The main difference is the output reliability of the two methods. LM-BP shows higher error than BRNN due to overfitting. BRNN shows reliable prediction results when the simplified neural network model is applied.https://www.mdpi.com/1996-1073/12/7/1201energy managementbuilding modellingBayesian regularization neural networksimplified modelmean impact value |
| spellingShingle | Moon Keun Kim Jaehoon Cha Eunmi Lee Van Huy Pham Sanghyuk Lee Nipon Theera-Umpon Simplified Neural Network Model Design with Sensitivity Analysis and Electricity Consumption Prediction in a Commercial Building Energies energy management building modelling Bayesian regularization neural network simplified model mean impact value |
| title | Simplified Neural Network Model Design with Sensitivity Analysis and Electricity Consumption Prediction in a Commercial Building |
| title_full | Simplified Neural Network Model Design with Sensitivity Analysis and Electricity Consumption Prediction in a Commercial Building |
| title_fullStr | Simplified Neural Network Model Design with Sensitivity Analysis and Electricity Consumption Prediction in a Commercial Building |
| title_full_unstemmed | Simplified Neural Network Model Design with Sensitivity Analysis and Electricity Consumption Prediction in a Commercial Building |
| title_short | Simplified Neural Network Model Design with Sensitivity Analysis and Electricity Consumption Prediction in a Commercial Building |
| title_sort | simplified neural network model design with sensitivity analysis and electricity consumption prediction in a commercial building |
| topic | energy management building modelling Bayesian regularization neural network simplified model mean impact value |
| url | https://www.mdpi.com/1996-1073/12/7/1201 |
| work_keys_str_mv | AT moonkeunkim simplifiedneuralnetworkmodeldesignwithsensitivityanalysisandelectricityconsumptionpredictioninacommercialbuilding AT jaehooncha simplifiedneuralnetworkmodeldesignwithsensitivityanalysisandelectricityconsumptionpredictioninacommercialbuilding AT eunmilee simplifiedneuralnetworkmodeldesignwithsensitivityanalysisandelectricityconsumptionpredictioninacommercialbuilding AT vanhuypham simplifiedneuralnetworkmodeldesignwithsensitivityanalysisandelectricityconsumptionpredictioninacommercialbuilding AT sanghyuklee simplifiedneuralnetworkmodeldesignwithsensitivityanalysisandelectricityconsumptionpredictioninacommercialbuilding AT nipontheeraumpon simplifiedneuralnetworkmodeldesignwithsensitivityanalysisandelectricityconsumptionpredictioninacommercialbuilding |