Hybrid Modeling of Central Air-Conditioning Cold Source System Energy Consumption with K-means Cluster Algorithm

2019 5th International Conference on Energy Materials and Environment Engineering

能源学;生态环境科学

Zhou, Zhihao^1

School of Energy and Environment, Southeast University, Nanjing

210096, China^1

关键词: Artificial neural network models;    Central air-conditioning;    Energy consumption prediction;    Gray-box models;    Prediction accuracy;    Simulation data;    Source systems;    System operation;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/295/5/052035/pdf
DOI  :  10.1088/1755-1315/295/5/052035

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

Gray box model and artificial neural network (ANN) model of central air-conditioning cold source system have been established with simulation data to predict system operation energy consumption and compare the prediction accuracy difference of models under variable training data. A hybrid model is proposed to combine gray box model and ANN model based on K-means cluster algorithm. The results show that ANN model has higher prediction accuracy than gray box model when the membership of model input variables to trained input data is greater than 0.4. Otherwise, the gray box model has higher energy consumption prediction accuracy. Compared with gray box model and ANN model, prediction accuracy of hybrid model increases 27.7% and 33.85% on average under different training data.