Classification Method for Power Load Data of New Energy Grid based on Improved OTSU Algorithm

The classification method for power load data of new energy grid based on improved OTSU algorithm is studied to improve the accuracy data. According idea two-dimensional visualization time series, GAF (Geographical Adaptive Fidelity) used transform current in into image grid. intra class dispersion introduced, and segment foreground background according pixel gray value one-dimensional inter variance corresponding neighborhood value. taken as input sample convolution neural network. network extracts features through layer. extracted features, results are output three steps: nonlinear processing, pooling processing full connection layer classification. experimental show that this can accurately classify grid, higher than 97%.