A Gaussian hybrid clustering-based method for compensating for the loss of semi-persistent scheduling data in the middle station of large power grid regulation and control

Abstract

In order to ensure the effectiveness of power grid scheduling decisions, ensure the stability, safety, and intelligence level of scheduling operations, and solve the semi persistent problem of station scheduling data loss in power grid scheduling, a Gaussian mixture clustering based method for compensating station scheduling data loss in power grid scheduling is proposed. Based on the role of the intermediate station and its semi persistent scheduling data generation mechanism in the control system of the large power grid, a Gaussian mixture model is constructed to calculate the conditional expected value of missing data as compensation value, and the final compensation result of the semi persistent scheduling data of the intermediate station is obtained. The experimental results show that in various types and degrees of scheduling data missing scenarios, this method performs well, and its Pearson correlation coefficient for compensating data is generally higher than 0.94, fully verifying the effectiveness and accuracy of this method. This achievement not only provides a practical and feasible solution to the problem of data loss in power grid scheduling, but also provides strong technical support for improving the accuracy of power grid regulation and ensuring the safe and stable operation of the power grid.