PEDI-GAN: power equipment data imputation based on generative adversarial networks with auxiliary encoder

Smart grids commonly rely on analyzing sensor data to monitor power equipment. However, these sensor data can suffer varying levels of loss or corruption due to complex interferences, leading to a pressing need for precise missing value imputation in power equipment data. We propose a data imputation model for power equipment based on generative adversarial networks with an auxiliary encoder, named PEDI-GAN. In particular, the auxiliary encoder is designed and integrated into the GAN structure to optimize random vectors for the generator. Through data masking, we pinpoint missing data locations, enabling the generator to focus on generating accurate values for those points. Additionally, we address gradient disappearance and model collapse in GAN training by using the gradient penalty to redesign the loss function for PEDI-GAN. Experimental results demonstrate PEDI-GAN’s superiority in accuracy and generalization compared to baseline methods, with notable reductions in mean absolute error and root mean square error by an average of 16.75% and 11.09%, respectively.