神经网络在暂态稳定评估中应用的研究述评

Research overview of neural- network applications to transient stability assessment of power systems

对神经网络在暂态稳定评估问题中应用的研究文献进行调研和综述,对稳定评估的目标、输入特征的选择、所采用的神经模型等进行了述评,对目前存在的问题进行了讨论。建议今后应在特征抽取和选择、训练样本集的压缩、在线训练机制以及类间边界区识别等方面开展深入的研究工作。

This paper serves as a general overview of the literature reported in the area of neural-network-based transient stability assessemnt, describes the state-of-the-art of this research area, distinguishes the problems to be resolved and future research work to be done possibly.