An Improved Prediction Method of Transformer Oil Temperature

Abstract

High temperature of transformer windings will lead to insulation aging and serious harm of the normal operation of power equipment. Transformer oil temperature can be used as an auxiliary basis to judge winding temperature. However, it is greatly affected by seasonal factors and weather changes, so the accuracy of it needs to be further improved. To solve this problem, the Prophet algorithm is used for transformer oil temperature prediction for the first time in this paper, and a transformer oil temperature prediction method combined with adaptive noise-complete total Empirical Mode decomposition is proposed. In order to further improve the accuracy of oil temperature prediction, the influence of seasonal variation on transformer oil temperature is considered in the prediction process. Then the Prophet algorithm is used to predict each component, and the predicted values of the obtained N modal components are summed to get the final result.