Dynamic State Estimation for Power System Based on the Measurement Data Reconstructed by RGAN

Abstract

Aiming at the problem of incomplete measurement data in the power system state estimation process, the missing data reconstructed by the residual generative adversarial network (RGAN) was introduced for the power system dynamic estimation. RGAN is a deep learning model based on the idea of a “two-player zero-sum” game, in which two deep neural networks compete with each other to mine the relevant features of the data. Distinguish from existing structure, skip connection and residual network (ResNet) were incorporated into two deep neural networks. And the incomplete measurement data were reconstructed accurately from the remaining measurement data. To lessen the impact of reconstruction errors, the unscented Kalman filter (UKF) method was used to estimate power system state. A case studied in the IEEE 30-bus shows that the UKF based RGAN dynamic estimation can maintain a high accuracy under different proportions of missing data.

Keywords

• Incomplete measurement data
• power system dynamic estimation
• residual generative adversarial network
• unscented Kalman filter