基于提升人工神经网络的短期负荷预测模型

本文提出了一种基于提升人工神经网络的短期负荷预测方法。该方法由一组经过训练的人工神经网络迭代组合而成。在每次迭代中,对新的人工神经网络模型进行了调整,使前期迭代的模型得到的估计值与真实值之间的误差最小化。通过仿真可知,当计算输出的模型个数大于20时,可以获得较低的预测误差,与现有方法相比具有更高的预测精度。

A Short-Term Load Forecasting Model Based on Boosted Artificial Neural Network

A short-term load forecasting method based on lifting artificial neural network is proposed.This method is composed of a group of trained artificial neural networks iteratively.The new artificial neural network model is adjusted to minimize the error between the estimated value and the real value of the previous iteration model.The simulation results show that when the number of output models is more than 20,a lower prediction error can be obtained,and the prediction accuracy is higher than that of the existing methods.