Short-term Load Forecasting of PowerSystem Based on Improved Feedforward Neural Network

Abstract

Short-term load forecasting of power system is the foundation of safe and stable operation of power grid, at present, short-term load forecasting of power system is easily affected by external features, so it is difficult to extract load data features accurately. Aiming at the problem of nonlinear, high-dimensional and poor generalization ability of load data, the short-term load forecasting method based on flower pollination algorithm and feedforward neural network is proposed. Flower pollination algorithm is used to optimize the combination of feedforward neural network weight threshold to reduce the error and improve the robustness of the algorithm. Finally, the prediction results of similar algorithms and those of the proposed method are compared through prediction evaluation indexes. After comparison, it is found that the method in this paper can effectively improve the accuracy of load prediction, which is conducive to increasing the safety and economy of power grid.