Power system transient stability assessment based on rough set and deep residual neural network

Abstract

Machine learning algorithms have been widely used in power system transient stability evaluation. The combined application of data analysis and evaluation and neural network provides a new direction for power system transient stability analysis. After the actual power grid is running, there is obviously an imbalance between stable samples and unstable samples. The current deep learning network realizes the power system transient stability assessment method with too many redundant attributes, and the characteristics will inevitably be lost during the data transmission process. This leads to serious problems with the tendency of the training of the data-driven transient stability assessment model. The rough set theory algorithm is introduced to reduce the redundant attributes of power system transient data sets, which simplifies the difficulty of data training. At the same time, as the neural network deepens, the deep residual neural network model has a higher accuracy rate and effectively avoids the “gradient explosion” and “gradient dispersion” problems. Compared with the traditional neural network, it has better Evaluate performance.

Power system transient stability assessment based on improved graph attention broad learning system

“…As a result, they are also used for TSA, such as Zhou et al 8 used Convolutional Neural Network (CNN) for TSA, while active learning and fine-tuning techniques were incorporated to enable the model to perform well, even if the operating conditions change significantly. Chai et al 9 Although all the deep learning models above have achieved relatively good performance, none of them consider the topology of the power system. And it has been shown [10][11][12] that the topological connectivity relationship between power system nodes has a significant effect on transient stability.…”