Power grid dynamic track trend prediction method based on long-term and short-term memory network

Abstract

The invention discloses a power grid dynamic track trend prediction method based on a long-term and short-term memory network. The method is characterized by firstly, aiming at a geometrical characteristic of a voltage time sequence vector track, extracting a time sequence evolution rule of a node state, and quickly identifying a same tropism of a system generator; secondly, rapidly predicting a disturbed track of an equivalent machine system based on the long-term and short-term memory network; and finally, calculating a generator tripping amount according to an extended equal-area criterion,and realizing emergency control of transient power angle stability. The method has advantages of scientific and reasonable performance, high applicability and the like.

Description

technical field

[0001] The invention belongs to the application field of transient stability control of a large power grid, and in particular relates to a method for predicting a dynamic track trend of a power grid based on a long-term and short-term memory network. Background technique

[0002] With the continuous expansion of the scope of grid interconnection and the scale of new energy power generation, the characteristics of high penetration rate and high proportion of power electronics of renewable energy have become increasingly prominent, making the grid develop into a high-dimensional time-varying nonlinear power information physics system with multi-source information interaction. system. The existing grid online security defense concept and stability control technology with the core of modeling simulation and expected faults are difficult to adapt to the development requirements of the grid. The complexity of the physical system and multi-source informatization aff...

Images