FIM Algorithm for Multi-Source Heterogeneous Information in Power Grid Intelligent Dispatching

摘要

Power grid dispatching has involved large amount of multi-source heterogeneous data with high complexity, therefore transforming power data into knowledge by data mining is the inevitable trend of intelligent dispatching development. Applying big data technology to power grid dispatching, the analysis model of multi-source heterogeneous data based on big data is built and a frequent itemset mining (FIM) algorithm for processing big data is proposed in this paper. Combining MapReduce programming and combinatorics, the algorithm will scan transaction database once to complete the target frequent itemset mining, and support is changing with no need to mining. The algorithm can overcome the problem of multiple scanning transaction database and low mining efficiency. In this paper, compared with other frequent itemset mining, the algorithm take advantage of Hadoop to deal with fault information transaction database. Experimental results show the proposed algorithm performs well in expansibility and has a little time cost with large transaction database. The method in this paper will provide useful knowledge for realizing intelligent analysis and decision making with comprehensive optimal objectives of accuracy, security, economic, which single data source can't achieve.