Online voltage stability evaluation method based on correlation detection and improved random forest

An online voltage stability evaluation method based on correlation detection and an improved random forest comprises the following steps: based on historical operation data of a power system and acquisition of a synchronous phasor measurement unit, determining a voltage limit, and constructing a database containing a large number of variables and corresponding voltage stability margins; performingfeature selection on the data set by using a correlation detection framework constructed based on partial mutual information and Pearson correlation coefficients, and screening out key variables; constructing a mapping relationship between the key variables and the VSM based on the improved random forest, and establishing a voltage stability evaluation model; receiving selected data online from awide-area measurement system server, and enabling a trained VSA model to immediately provide a real-time evaluation result. The power system online VSA model provided by the invention can provide high-precision and high-effic