Abstract:In order to ensure the security, stability and reliability of power supply and maintain the high quality and economic operation of power, power generation enterprises and power grid enterprises need to have primary frequency regulation, automatic generation control, peak shaving and other services. In view of the performance differences of thermal power units, it may not be able to meet some auxiliary service assessment items at a certain time and be assessed. The dispatch shall assess and reward the relevant contents of its basic auxiliary services and paid auxiliary services according to the regulations. Aiming at the problem of unit fined for assessment, this paper uses Apriori algorithm to mine and analyze the data on the power plant side. As one of the big data algorithms, Apriori algorithm is a recursive algorithm. In the two stages of candidate set generation and downward closed detection of scenarios, the intrinsic relationship of each assessment item is obtained by mining association rules of frequent itemsets. Through the analysis and mining of the relevance of the assessment data of auxiliary services in power plants, the information obtained from data mining provides a reference basis for us to make corresponding optimization adjustments and reduce assessment decisions.