k-VNN- and LS-SVM-based modelling method for icing of electric transmission line

Abstract

The invention discloses a k-VNN- and LS-SVM-based modelling method for the icing of an electric transmission line. The k-VNN- and LS-SVM-based modelling method comprises the following steps of: taking the historical data provided by the micro-weather station of an overhead line structure as basis, reading in micro-weather parameter values and converting the micro-weather parameter values to a vector form; introducing a k-VNN algorithm so as to select proper samples from a line icing sample database, and calculating the Euclidean distances and included angle information of information vectors; selectively deleting and reserving the similar areas, that is, adjacent points, of the information vectors to form a training sample; optimizing the quantity of the samples selected by the k-VNN adjacent algorithm, by a cross-validation method, so as to acquire proper parameters such as the width delta of a kernel function K(xi, xj) and an error penalty factor gamma in an LS-SVM model, and finding the optimal one; after the parameters are set, training related data by a least squares support vector machine (LS-SVM), and finally acquiring an icing thickness. The algorithm disclosed by the invention is high in prediction accuracy, extremely fast in speed, and suitable for short-term icing prediction for the icing of the electric transmission line.

Description

technical field [0001] This paper invented a data-driven LS-SVM identification theory to predict the development of icing, which belongs to the field of overhead line safety and protection. Background technique [0002] In recent years, due to the proposal of related concepts such as "smart grid" by the State Grid Corporation of China, a large number of researchers have turned their attention to all aspects of the power system. As an energy channel between various transmission networks and users, transmission lines play an important role. It is even more obvious. However, due to the long-term exposure to the wild and the erosion of various factors in nature, the line has become the most vulnerable part of the power system. Whenever winter comes, areas such as Jiangsu, Zhejiang, Yunnan, and Guizhou have too much humidity. Once the cold current invades, it will inevitably cause serious icing of transmission lines in some areas. It will affect the production and life of users...

AI Technical Summary

Problems solved by technology

However, this method often lacks detailed data support in practical applications, which limits the application and extension of this method

[0005] In China, various design, scientific research and operation units have also carried out a lot of research work. Although there are many types of icing prediction models for power lines, the main problems are: 1) The research data is based on various artificially simulated climate conditions 2) Although the online monitoring data of icing on some lines are used for analysis and modeling in some literatures, there are often a lot of redundant and erroneous data in these collected data. Using such a huge amount of data for modeling without screening will not be able to reflect the development law of line icing; 3) Due to the poor real-time performance or low accuracy of the algorithm in the existing research results, there is no suitable method for line icing. A Fast Algorithm for Disaster Early Warning

Images