Study on stability feature extraction of power system using deep learning

Abstract

Dynamic security assessment (DSA) of power grids is widely used in dispatching operation systems, and calculation speed is one of its most important performance indicators. In this paper, a stability feature extraction method is proposed, which is useful for quick judgment of stability and assisted decision-making. Firstly, a simulation sample database is constructed based on historical online data and a deep learning model with least absolute shrinkage and selection operator (LASSO) is trained to pick both the high level and low level stability features. While a new operation mode needs to be evaluated, a fast search is implemented to obtain the most similar samples in the database using the chosen high level features; the final result will be determined comprehensively by the familiar samples. If the power grid is in critical condition, a decision-making will be done by using the low level features. The validity of proposed method is verified by the simulation using online data of Northeast Power Grid of China. It is proved that the method meets the requirements for speed and accuracy of online analysis system.