Big Data Mining Method of Thermal Power Based on Spark and Optimization Guidance

Abstract

With the increasing degree of information technology in the electric-power industry, the amount of big data in thermal power has increased geometrically. To address the problem of the computational bottlenecks in traditional data mining deal with big data of thermal power, big data mining of thermal power method based on Spark is presented in this paper. According to the characteristics of the actual operation of the unit, the proposed method determines the steady-state conditions of big data of thermal power and divides the working conditions based on external constraints. In addition, data mining method based on distributed computing is used to mine big data of thermal power to get the strong association rules, thus the best value of the parameters under each working condition can be got. Lastly, the historical knowledge base is established, which can guide the operation of the unit by the proposed method. This method is applied to a 300 MW unit in a power plant in Anhui Province, and mines the operation data of the unit for 10 days in a month. The results of simulation show that the proposed method can effectively mine big data of thermal power and has the advantage of computational efficiency compared with traditional data mining for big data.