An intelligent system design and analysis for transient stability assessment using four sample input feature vector approach

Abstract

Transient stability assessment (TSA) is essential in power system planning and operation, as it facilitates the system operator to decide and take corrective actions to maintain secure and reliable operation of power system. To this end, this paper develops a fast real time transient stability assessment scheme using four sampled data points of generator bus frequency in pre- and post-fault stages, using phasor measurement units (PMU). As the recurrent neural networks are good at extracting the features of time series data, a stacked Long Short Term Memory (LSTM) based recurrent neural network is designed and trained for transient stability assessment, considering the pre- and post-disturbance time series data of generator bus frequencies. Effectiveness of proposed approach is tested on 10 machine 39bus power system. The results demonstrate that the proposed method performs well under various scenarios, including unscheduled line tripping, random load variations, and failure of PMU or telecommunication channels of measurement units.