摘要
风速预测对风电场和电力系统的运行都具有重要意义。对风速进行比较准确的预测,可以有效地减轻或避免风电场对电力系统的不利影响,同时提高风电场在电力市场中的竞争能力。基于时间序列法和神经网络法,该文对风速预测进行了研究,提出了预测风速的时序神经网络法。该方法用时间序列法建模,得到风速特性的基本参数,并用这些参数选择神经网络的输入变量;为了提高预测精度,提出了滚动式权值调整手段。该方法有效地提高了风速预测的精度。
Wind speed forecasting is very important to the operation of wind power plants and power systems. It can relieve or avoid the disadvantageous impact of wind power plants on power systems and enhance the competitive ability of wind power plants against other power plants in electricity markets. Based on time series method and ANN (artificial neural network), the authors studied the wind speed forecasting and proposed a time series ANN method for wind speed forecasting. In the proposed method the mathematical model was built by time series method to obtain the basic parameters of wind speed characteristics, then these parameters was used to choose input variables of ANN. To improve the forecasting accuracy of ANN a rolling method to adjust weight factors was put forward. With above-mentioned method the wind speed forecasting accuracy was effectively improved.
出处
《中国电机工程学报》
EI
CSCD
北大核心
2005年第11期1-5,共5页
Proceedings of the CSEE
