A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Prediction of Electricity Consumption of a HVAC System in a Multi-Complex Building Using Back Propagation and Radial Basis Function Neural Networks
This study examined approaches to predict electricity consumption of a Heating, Ventilation and Air- Conditioning (HVAC) system in a multi-complex building using two neural network models: Back Propagation (BP) and Radial Basis Function (RBF) with input nodes, e.g., temperature, humidity ratio, and wind speed. Predicting HVAC energy consumption of buildings is a crucial part of energy management systems. We used two main neural network models, BP and RBF, to evaluate the prediction performance of electricity consumption of HVAC systems. The BP neural network method exhibited good performance, but it exhibited relatively large fluctuations and slow convergence in the training process. In contrast, RBF exhibited relatively fast learning and reduced computing costs. The HVAC energy consumption rate of working days was higher than that of non-working days. The results indicate that the prediction of HVAC energy consumption using neural networks can effectively control the relationship between the HVAC system and environment conditions. ; publishedVersion
Prediction of Electricity Consumption of a HVAC System in a Multi-Complex Building Using Back Propagation and Radial Basis Function Neural Networks
This study examined approaches to predict electricity consumption of a Heating, Ventilation and Air- Conditioning (HVAC) system in a multi-complex building using two neural network models: Back Propagation (BP) and Radial Basis Function (RBF) with input nodes, e.g., temperature, humidity ratio, and wind speed. Predicting HVAC energy consumption of buildings is a crucial part of energy management systems. We used two main neural network models, BP and RBF, to evaluate the prediction performance of electricity consumption of HVAC systems. The BP neural network method exhibited good performance, but it exhibited relatively large fluctuations and slow convergence in the training process. In contrast, RBF exhibited relatively fast learning and reduced computing costs. The HVAC energy consumption rate of working days was higher than that of non-working days. The results indicate that the prediction of HVAC energy consumption using neural networks can effectively control the relationship between the HVAC system and environment conditions. ; publishedVersion
Prediction of Electricity Consumption of a HVAC System in a Multi-Complex Building Using Back Propagation and Radial Basis Function Neural Networks
Liu, Benhao (author) / Kim, Moon Keun (author) / Zhang, Nan (author) / Lee, Sanghyuk (author) / Liu, Jiying (author)
2021-01-01
Article/Chapter (Book)
Electronic Resource
English
DDC:
690
ELECTRICITY CONSUMPTION PREDICTION SYSTEM USING A RADIAL BASIS FUNCTION NEURAL NETWORK
| BASE | 2017
| British Library Conference Proceedings | 2002
Uncertainty propagation through radial basis function networks. Part II: Classification networks
| British Library Conference Proceedings | 2005