State classification of transformer in the renewable power grid based on principal component analysis and support vector machine evaluation system

With the development of big data mining and analysis in the field of renewable power system, the renewable power grid is moving towards the direction of intelligence, informatization and networking. In this trend, considering the complexity of state evaluation, this paper adopts principal component analysis (PCA) to conduct dimensionality reduction processing for the numerous state data, eliminate the correlation between data and select the most valuable key parameters, thus reducing the complexity of subsequent calculation. Then, LS-SVM is used as the classifier, the key parameters mentioned above are taken as input, and particle swarm optimization is used for parameter optimization to evaluate the state level of the transformer. At the same time, a multistage SVM system is proposed to solve the problem of SVM one-to-many classification, and a transformer state evaluation model is established. The research results will lay the foundation for the application of big data technology and artificial intelligence technology in the field of state assessment of substation equipment in the renewable power grid.