AWNN-Assisted Wind Power Forecasting Using Feed-Forward Neural Network
AWNN-Assisted Wind Power Forecasting Using Feed-Forward Neural Network
复制标题
DOI：
10.1109/tste.2011.2182215
复制
发表时间：
2012-04-01
影响因子：
8.8
通讯作者：
Singh, S. N.
中科院分区：
文献类型：
--
作者：
Bhaskar, Kanna;Singh, S. N.
随着风力发电在新兴电力系统中的渗透，准确的风电功率预测方法是非常必要的，以帮助系统运营商，包括风力发电的经济调度，机组组合和备用分配问题。它还帮助风力发电商在电力市场中通过投标实现利益最大化。本文提出了一种不使用数值天气预报（NWP）输入的基于统计的风电预测方法。所提出的方法包括两个阶段。在第一阶段，风序列进行小波分解，并使用自适应小波神经网络（AWNN）对每个分解后的信号进行回归，预测风速提前30 h。在第二阶段，前馈神经网络（FFNN）用于风速和风力输出之间的非线性映射，将预测的风速转换为风力预测。与持久性（PER）和新参考（NR）基准模型的有效性进行了比较，结果表明，所提出的模型优于基准模型。
With the growing wind power penetration in the emerging power system, an accurate wind power forecasting method is very much essential, to help the system operators, to include wind generation into economic scheduling, unit commitment, and reserve allocation problems. It also assists the wind power producers to maximize their benefits by bidding in the electricity markets. A statistical-based wind power forecasting without using numerical weather prediction (NWP) inputs is carried out in this work. The proposed approach consists of two stages. In stage-I, wavelet decomposition of wind series is carried out and adaptive wavelet neural network (AWNN) is used to regress upon each decomposed signal, to predict wind speed up to 30 h ahead. In stage-II, a feed-forward neural network (FFNN) is used for nonlinear mapping between wind speed and wind power output, which transforms the forecasted wind speed into wind power prediction. The effectiveness of the proposed method is compared with persistence (PER) and new-reference (NR) benchmark models and the results show that the proposed model outperforms the benchmark models.