Data driving voltage frequency response characteristic modeling method of renewable power supply

Abstract

The invention discloses a data driving voltage frequency response characteristic modeling method of a renewable power supply. The method comprises the following steps: S1, normalizing input data; S2,initializing the weight and bias parameters of each layer of the neural network; S3, enabling the input data to pass through two convolution layers and two full connection layers to obtain an output value; S4, performing reverse normalization processing on the output value to obtain an original distribution output value; S5, solving an error between the original distribution output value and the target output value; S6, when the error exceeds an allowable range, reversely transmitting the error back to the neural network, sequentially solving the errors of the full connection layer and the convolutional layer, updating the weight and deviation of each layer, and continuing the step S3; when the error is within the allowable range, fixing the weight and the offset, and ending the training.According to the data driving voltage frequency response characteristic modeling method of the renewable power supply, higher accuracy and robustness are achieved.

Description

technical field [0001] The invention relates to the technical field of smart grids, in particular to a data-driven voltage frequency response characteristic modeling method of a renewable power source. Background technique [0002] Since clean energy power generation such as wind energy and solar energy pollutes the environment far less than traditional power generation methods, renewable power generation is in line with my country's sustainable development target strategy. The proportion of renewable power generation will gradually increase, and the impact on grid operation will become more and more significant. The intermittency and uncertainty of renewable power generation make the model about its output power high-dimensional and nonlinear. However, traditional mathematical modeling methods were used in previous studies, and the accuracy of the model was not high. [0003] At the same time, with the development of smart grid and the improvement of automation level, ener...

AI Technical Summary

Problems solved by technology

The intermittence and uncertainty of renewable power generation make the model about its output power high-dimensional and nonlinear, while previous studies used traditional mathematical modeling methods, and the accuracy of the model was not high

Images