Mining Dynamic Association Rules from Multiple Time-Series Data Based on Data of Power Plant

Plenty of data are generated from sectors such as industrial manufacture, financial service, e-commerce, satellite remote sensing, sensor network and so on. Normally these data are often with time tags, which are called as time series steams. In this paper sliding window is used to limit the time series data; pretreatment process proceeds linear approximation to the sequences; the sequences after linearization are cut. In the sliding window, we maintaining a global SWIU-tree (Incremental Updating tree based on Sliding Window) to store the synopsis structures of scanned datasets, to get rid of the unfrequent patterns and outdated patterns by pruning strategy. With the comparation between the existing algorithm and SWIU-tree algorithm on the data of actual thermal power plant, illustrating that SWIU-tree algorithm is effective and which is able to quickly and precisely dig the association rules among multiple time series streams.