Transient overvoltage assessment method for multi-type clean energy through direct current island delivery system

Through adaptive genetic algorithms, the backpropagation neural network is optimized, and the mathematical model of the clean energy DC island transmission system is established, which solves the problem of evaluating the transient overvoltage of the transmission end power grid after the failure of the high-voltage DC transmission system, and achieves the improvement of the safety and economics of the power grid.

CN120278381APending Publication Date: 2025-07-08GUO JIA DIAN WANG YOU XIAN GONG SI XI NAN FEN BU
0 Cites 0 Cited by

Patent Information

Application Number
CN202510331663.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-20
Publication Date
2025-07-08

AI Technical Summary

Technical Problem

The existing technology is difficult to evaluate the transient overvoltage of the transmission terminal power grid after a high-voltage DC transmission system failure in real time and accurately, resulting in new energy disconnection, affecting the stability and economics of the power grid.

Method used

Adaptive genetic algorithm is used to optimize the backpropagation neural network, establish a mathematical model of multiple types of clean energy transmission systems through DC islands, train the neural network through grid simulation data, evaluate transient overvoltage, and provide a theoretical basis for subsequent suppression.

Benefits of technology

It improves the economy and efficiency of the power system under the premise of ensuring safety and stability, optimizes the neural network model through adaptive genetic algorithms, avoids local optimal solutions, and improves evaluation accuracy and real-time performance.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a transient overvoltage evaluation method for a multi-type clean energy delivery system through a direct current island, and the method comprises the following steps: S1, building models of various types of power generation systems, and analyzing the voltage and power characteristics of the multi-type clean energy delivery system through the direct current island; s2, establishing a back propagation neural network model according to the voltage and power characteristics of the direct current island delivery system; s3, performing global optimization on the weight and the threshold of the back propagation neural network model by using an adaptive genetic algorithm; and S4, training the back-propagation neural network model by using the power grid simulation data, inputting the output of the active power of each power generation system in the to-be-tested power grid into the trained back-propagation neural network model, and outputting a transient overvoltage value. According to the method, the transient overvoltage after commutation failure is evaluated, a theoretical basis is provided for subsequent transient overvoltage suppression, and the economical efficiency and efficiency of a power system on the premise of ensuring safety and stability are improved.
Need to check novelty before this filing date? Find Prior Art