基于MEA-小波Elman神经网络的光伏超短期预测方法

Photovoltaic Ultra-Short-Term Prediction Method Based on MEA-Wavelet Elman Neural Network

将小波理论和Elman神经网络相结合,采用思维进化算法对网络初始权值和阈值进行优化,建立了MEA-小波Elman神经网络预测模型,应用于光伏出力超短期预测。使用小波函数作为传递函数,提高了函数逼近能力,有效解决了预测模型在对光伏出力预测跟踪中的容易陷入局部最小值,迭代速度慢,预测精度不高等问题。最后,本文采用敦煌地区实测数据分析验证,通过与传统Elman神经网络模型进行比较,表明该模型对光伏超短期预测具有较好的效果,进而为调度人员提供决策辅助。

The MEA-wavelet Elman neural network prediction model is established by combining the wavelet theory with the Elman neural network, and the initial weight and threshold of the network are improved by the mind evolutionary algorithm. It is applied to the prediction of the ultra-short term photovoltaic output. Using the wavelet function as a transfer function, which improves the function approximation ability and effectively solves the problem that the prediction model is easy to fall into the local minimum value, the iteration speed is slow and the prediction accuracy is not high in the prediction of light output. Finally, this paper is verified by the measured data of Dunhuang area. Compared with the traditional Elman neural network model, it shows that the model has a good effect on the ultra-short-term prediction of PV, and then provides decision-making assistance for dispatchers.