期刊名称：International Journal on Smart Sensing and Intelligent Systems
印刷版ISSN：1178-5608
出版年度：2015
卷号：8
期号：2
页码：869-895
出版社：Massey University
摘要：In this paper, we proposed to use the Efficient Indoor Thermal Time Constant (EITTC) to characterize the indoor thermal response in old buildings. Accordingly, a low cost, energy-efficient, wide-applicable indoor thermal modeling solution is developed by combining Wireless Sensor Network (WSN) and Artificial Neural Network (ANN). Experiments on both prototype and building room showed consistent results that the combination of WSN and ANN can provide accurate indoor thermal models. A linear approximation of these models makes it possible to estimate the EITTC of building room. Statistical computations confirmed these estimations by showing a strong correlation between the model's predicted EITTC and measured data. Thus the indoor thermal response under different indoor/outdoor conditions can be characterized. Finally, a model based adaptive heating Start/Shut control method is proposed and tested, with which, direct energy saving is achieved.
关键词：Wireless Senso rs Network; Back-propagation Neural Network; Thermal Modeling; Linear ; Approximations; E ; ff ; ective Indoor Thermal Time Constant
