摘要
风电功率短期预测对于电网的调度运行有着极为重要的意义,BP神经网络算法作为一种常见的风电功率预测方法,针对其易于陷入局部最优、精度不稳定的缺点,引入改进的二阶震荡粒子群算法优化BP神经网络的初始权值和阈值,构建复合型神经网络预测模型。同BP神经网络、粒子群BP神经网络、二阶震荡粒子群BP神经网络进行实验对比,验证了改进二阶震荡粒子群BP神经网络有较高的预测精度。
Short term wind power forecasting is of great significance for power grid dispatching,BP neural network algorithm as a common wind power prediction method.Aiming at the shortcomings of easy to fall into local optimum and unstable precision,the initial weight and threshold of BP neural network are optimized by using the improved second order oscillatory particle swarm optimization algorithm.In order to improve the prediction accuracy of BP neural network,a compound neural network prediction model is constructed in this paper.Compared with BP neural network,particle swarm optimization neural network and second order oscillation particle swarm optimization neural network,it is proved that the BP neural network based on improved second order oscillatory particle swarm optimization has higher prediction accuracy.
出处
《工业控制计算机》
2021年第11期119-121,共3页
Industrial Control Computer
基金
宁夏自然科学基金项目(2021AAC03073),含高比例新能源的电力系统优化调度研究。
关键词
风电功率预测
BP神经网络
粒子群算法
wind power prediction
BP neural network
particle swarm optimization