Transmission line icing prediction based on DWT feature extraction

2016 International Conference on New Energy and Future Energy System

Ma, T.N.^1 ; Niu, D.X.^1 ; Huang, Y.L.^1

Research Institute of Technology Economics Forecasting and Assessment, North China Electric Power University, Beijing

102206, China^1

关键词: Low-frequency signals;    Partial least squares regression models;    Prediction accuracy;    Prediction model;    Prediction-based;    Safe operation;    Support vector;    Transmission line icings;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/40/1/012038/pdf
DOI  :  10.1088/1755-1315/40/1/012038

来源: IOP

【 摘 要 】

Transmission line icing prediction is the premise of ensuring the safe operation of the network as well as the very important basis for the prevention of freezing disasters. In order to improve the prediction accuracy of icing, a transmission line icing prediction model based on discrete wavelet transform (DWT) feature extraction was built. In this method, a group of high and low frequency signals were obtained by DWT decomposition, and were fitted and predicted by using partial least squares regression model (PLS) and wavelet least square support vector model (w-LSSVM). Finally, the final result of the icing prediction was obtained by adding the predicted values of the high and low frequency signals. The results showed that the method is effective and feasible in the prediction of transmission line icing.