作者: Ji Yang , Yong Li , Nan Feng Zhang , Jing Feng Yang , Ke Kuang
DOI: 10.1109/CIT/IUCC/DASC/PICOM.2015.192
关键词:
摘要: The traditional water consumption models were mainly focused on the spatial scale of city or district, time year month, and with data precision 0.1 m3. As Internet Thing (IoT) technology develops rapidly, smart meters for water-supply are gradually popularized. In 2013, Guangzhou City China established a demonstration area water-supply, in which residential can be collected every 15 minutes, is 0.001 Such high provide us an opportunity to conduct in-depth research habits patterns, as well relationship between pattern family structure, job type life style. It will also bring big impact management community, plan supply urban water. This paper proposes unsupervised clustering algorithm analyzing by meters. adaptive at daily divide residents addition, this lays foundation further key factors that affect demands forecasting model.