Research on Quality Control Algorithm of Power Grid Big Data Based on Artificial Intelligence

To reduce the linear loss of electricity grid big data within a specified control time and achieve stable load coordination among power information, an artificial intelligence-based (decision tree self-identification) algorithm for quality control of electricity grid big data is proposed. Based on the actual mining requirements of electricity grid data, the basic measurement conditions for the structural attributes of big data are determined. In conjunction with self-identified decision association rules, a decision tree for the electricity grid is established based on self-identification processing of the data. A direct-drive permanent magnet motor is set up to obtain the transmission parameters of big data in the output control loop. By solving the electronic control equation, the application of the quality control algorithm for electricity grid big data based on decision tree self-identification is completed. Experimental results show that compared to the PSCAD electricity grid information coordination model, the minimum linear loss of electricity grid big data using the proposed algorithm is reduced to 3.2×107 T, and the maximum linear loss reaches only 7.8×107 T. This achieves effective control of the linear loss of electricity grid big data within a specified detection time, solving the problem of poor coordination ability among power information for stable load coordination.