Research on Frequency Characteristics and Analysis Methods of New Power System

For the last few years, as the country puts forward and promotes the “double carbon” strategy, the proportion of new energy power generation in the power grid has been increasing, a large number of traditional thermal power units have been replaced, the system inertia has been reduced, and the frequency regulation ability has been weakened. On the other hand, with the rapid development of UHV DC transmission projects, the scale of asynchronous interconnection of power grids is increasing, and the frequency characteristics of power grids after faults or disturbances are becoming more and more complex. In this paper, aiming at the problems of large amount of calculation and difficult modeling in the frequency analysis of new energy high-proportion power grids by traditional frequency analysis methods, the frequency characteristics of new energy high-proportion power grids are studied, and the method of using deep learning network to predict the frequency characteristics of new energy high-proportion power grids is explored. Finally, a case study is carried out in the East China Power Grid model, which verifies that the proposed method has high accuracy and adaptability.