Transient voltage stability assessment of renewable energy grid based on residual SDE-Net

Abstract

For the purpose of assessing the transient voltage stability of renewable energy grid more effectively and to measure the epistemic uncertainty of the evaluation results, a power system transient voltage stability assessment method based on residual stochastic differential equation network (SDE-Net) is proposed in this paper. Considering the transient stability characteristics is chronological, the proposed network takes the time series of the basic physical quantity measurement data of the power system as the input. The internal features of time series data are extracted by residual convolution block based stochastic differential equation network in this paper. Meanwhile, the proposed method introduces the focal loss function to eliminate the imbalance of the samples and improve the accuracy of transient stability assessment. In particular, the drift network for learning prediction of stability and the diffusion network for learning uncertainty measurement in residual SDE-Net are trained respectively. As a result, case study on modified IEEE 30- bus system demonstrate the residual SDE-Net’s superior performances on both transient voltage stability assessment and stability evaluation result confidence estimation.

Keywords

• Transient voltage stability assessment
• Deep learning
• Renewable energy grid
• Focal loss
• Uncertainty