Long-term wind speed and power forecasting using local recurrent neural network models
Long-term wind speed and power forecasting using local recurrent neural network models
复制标题
DOI：
10.1109/tec.2005.847954
复制
发表时间：
2006-03-01
影响因子：
4.9
通讯作者：
Dokopoulos, PS
中科院分区：
文献类型：
--
作者：
Barbounis, TG;Theocharis, JB;Dokopoulos, PS
本文讨论了基于气象信息的长期风速和力量预测的问题。在希腊克里特岛上的风公园生产了最高72-H的小时预测。当输入时，我们的模型使用了大气建模系统Skiron提供的风速和方向的数值预测，可用于距离风力涡轮机群集最多30公里的四个位置。三种类型的局部复发性神经网络被用作预测模型，即无限脉冲响应多层感知器（HR-MLP），局部激活反馈多层网络（LAF-MLN）和对角色复发性神经网络（RNN）。这些网络包含内部反馈路径，通过HR突触过滤器实现了神经元连接。根据递归预测误差算法，建议了两种新颖和最佳的在线学习方案以更新复发网络的权重。这些方法可以确保与传统的动态反向传播相比，在学习阶段，网络的连续稳定性和表现提高了性能。进行了广泛的实验，将三个复发网络与两个静态模型进行比较，一个有限型响应NN（FIR-NN）和常规的静态MLP网络进行比较。仿真结果表明，经过建议的方法训练的复发模型在静态方法上表现出显着改善的静态方法。
This paper deals with the problem of long-term wind speed and power forecasting based on meteorological information. Hourly forecasts up to 72-h ahead are produced for a wind park on the Greek island of Crete. As inputs our models use the numerical forecasts of wind speed and direction provided by atmospheric modeling system SKIRON for four nearby positions up to 30 km away from the wind turbine cluster. Three types of local recurrent neural networks are employed as forecasting models, namely, the infinite impulse response multilayer perceptron (HR-MLP), the local activation feedback multilayer network (LAF-MLN), and the diagonal recurrent neural network (RNN). These networks contain internal feedback paths, with the neuron connections implemented by means of HR synaptic filters. Two novel and optimal on-line learning schemes are suggested for the update of the recurrent network's weights based on the recursive prediction error algorithm. The methods assure continuous stability of the network during the learning phase and exhibit improved performance compared to the conventional dynamic back propagation. Extensive experimentation is carried out where the three recurrent networks are additionally compared to two static models, a finite-impulse response NN (FIR-NN) and a conventional static-MLP network. Simulation results demonstrate that the recurrent models, trained by the suggested methods, outperform the static ones while they exhibit significant improvement over the persistent method.