Short-term Wind Power Forecasting Based on BP Neural Network with Improved Ant Lion Optimizer

Abstract

In order to improve the prediction accuracy of short-term wind power, this paper proposes a short-term wind power prediction model based on an improved ant lion optimizer algorithm to optimize BP neural network (IALO-BP). The model uses the improved ant lion optimizer algorithm (IALO) to optimize the weights and thresholds of BP neural network, so as to improve the convergence rate and generalization ability of BP neural network. The algorithm is tested by the data of an Irish wind farm in November 2017. The experimental results show that the IALO algorithm can overcome the defect that the original algorithm is easy to fall into the local optimum and the convergence speed is slow. Moreover, the IALO-BP algorithm is superior to BP neural network, GRNN and SVR in the prediction accuracy and stability.