Micro-grid dynamic equivalent modeling method based on GRU recurrent neural network

Abstract

To solve the problem that dynamic modeling is difficult under the condition that a micro-grid has an unknown part, the invention belongs to a modeling method, and particularly relates to a micro-grid dynamic equivalent modeling method based on a GRU recurrent neural network, which comprises the following steps of: firstly, acquiring disturbance data of a micro-grid common coupling point during disturbance; secondly, determining the structure and parameters of the GRU recurrent neural network, and finally training the GRU recurrent neural network by using the collected disturbance data, and collecting a proper amount of simulation results as training and test data of a neural network model to be established to obtain a dynamic equivalent model capable of representing a micro-grid containing an unknown part. According to the method, a dynamic equivalent model of the microgrid based on the GRU recurrent neural network is established by utilizing the good capacity of the GRU recurrent neural network for processing complex nonlinear problems and the capacity of the GRU for overcoming gradient disappearance and explosion, so that the dynamic performance of the microgrid with an unknown part is accurately expressed, the requirement of system analysis is met. The gap of short-term scale dynamic modeling research of the micro-grid is filled.

Description

technical field [0001] The invention belongs to the technical field of power system modeling and control, and in particular relates to a dynamic equivalent modeling method of a microgrid based on a GRU cyclic neural network. Background technique [0002] Distributed power generation systems have been developed and utilized to a great extent due to their renewable and clean advantages. With the widespread application of grid-connected power converters, more and more micro-grids have been incorporated into the distribution network. The development and extension of the microgrid has fully promoted the large-scale access of distributed power generation systems and renewable energy, and realized the highly reliable supply of various forms of energy for the load. It is an effective way to realize the active distribution network, making the traditional Grid transition to smart grid. With the increasing popularity of distributed generation and energy storage, the dynamic behavior o...

AI Technical Summary

Problems solved by technology

[0005] The present invention aims at the defects existing in the prior art, and proposes a dynamic equivalent modeling method of a microgrid based on the GRU cyclic neural network, utilizing the good ability of the GRU cyclic neural network to handle complex nonlinear problems, and GRU to overcome gradient disappearance and the ability to explode, establish a dynamic equivalent model of the microgrid based on the GRU cyclic neural network, so as to express the dynamic performance of the microgrid with unknown parts well, meet the needs of system analysis, and fill in the short-term scale dynamic modeling of the microgrid research vacancies

Images