A Rapid Evaluation Method for Transient Power Angle Stability by Combining Causal Analysis and Machine Learning

Abstract

The invention discloses a transient power angle stability rapid evaluation method of comprehensive causal analysis and machine learning. Based on the historical data stored by the online security analysis application transient stability evaluation function, the historical operation mode samples are divided into several operation mode clusters, temporarily The state power angle stability margin is described by a linearization formula according to the difference between the modes, and the key characteristic quantities of the power grid are extracted; the key characteristic quantities are used as the input quantity, and the formed historical operation mode cluster classification is used as the output quantity to build a deep learning model And use the historical data sample training to establish the connection between the current real-time operation mode and the historical operation mode, and estimate the transient power angle stability of the current real-time operation mode; the present invention can ensure the accuracy of the transient power angle stability analysis while , effectively reduce the time-consuming calculation, and quickly obtain the quantitative analysis results of the transient power angle stability of the power grid, which is helpful to timely discover the transient operation risks in the power grid and improve the safe operation level of the power grid.

Description

technical field [0001] The invention relates to the technical field of power system security and stability analysis, in particular to a method for rapidly evaluating transient power angle stability through comprehensive causal analysis and machine learning. Background technique [0002] In order to ensure the safe and stable operation of the power grid, especially the UHV AC-DC hybrid power grid, dispatching agencies at all levels need to be able to quickly grasp the safe and stable operation of the power grid, and quickly locate the risk points and risk levels of the power grid operation, so as to provide risk prevention and control for the power grid. Provide a basis for control decisions. At present, most of the power grid dispatching control institutions at the provincial level and above in China have established the online security analysis application function of the power grid. Comprehensively evaluate the safety and stability of the power grid from multiple aspects ...

AI Technical Summary

Problems solved by technology

The above method has achieved certain results, but the application of historical analysis results is not sufficient. There is a certain degree of blindness in the use of pure machine learning methods. At the same time, the method of manually screening state quantities relies heavily on personnel experience

Images