Power transmission line icing prediction method based on relevance vector machine

Abstract

The invention belongs to the technical field of power system disaster warning, and particularly relates to a power transmission line icing prediction method based on a relevance vector machine. According to the prediction method, according to features of an icing phenomenon, the input quantity and weight index of an icing prediction model are selected and processed in a targeted mode; a power transmission line icing prediction model is built through a relevance vector machine method; training is conducted on the model through sample data, and the model is optimized by the adoption of a quantum particle swarm optimization and a K-fold cross-validation method; the icing thickness and probability distribution of a power transmission line are predicted according to the test data, and correction is further conducted on the model through repeated training to improve prediction accuracy. The prediction method considers the influences, on power transmission line icing, of various factors comprehensively, can predict the icing thickness of the power transmission line precisely and has very high prediction accuracy and generalization ability.

Description

technical field [0001] The invention belongs to the technical field of electric power system disaster early warning, and in particular relates to a method for predicting icing of transmission lines based on a correlation vector machine. Background technique [0002] If the ice thickness of the transmission line exceeds its design standard, it will cause serious accidents such as flashover, tripping or even disconnection and tower collapse. In recent years, there have been more and more power grid accidents due to icing, which have brought huge losses to society and people's property. Therefore, it is urgent to study the icing prediction method of transmission lines to provide early warning and other decision-making support for the anti-icing disaster mitigation work of the power sector. [0003] At present, there are mainly two kinds of physical models and empirical models for conductor icing prediction at home and abroad. Due to the limitation of measurement technology an...

AI Technical Summary

Problems solved by technology

Due to the limitation of measurement technology and other reasons, some information required in the physical model is difficult to obtain or the accuracy is not high in the actual line, and it is difficult to directly apply to the icing prediction of the actual line; the empirical model is based on fuzzy logic theory, support vector machine, etc. method to achieve icing prediction, but there are disadvantages such as poor generalization ability and low prediction accuracy.

Images