摘要
风力发电量估算是风机匹配和风电成本分析中的关键步骤。为了准确地估算出风力发电量,利用径向基函数RBF(radial basis function)神经网络对风电场的年度发电量进行估计,并基于中国台湾18个气象台站和韩国26个气象台站的历史数据建模进行各自估计以及相互估计。由于影响风力发电量的主要因素是风速大小以及风机的工作时间,故采取年均风速以及对该年风机工作时间有影响的风速威布尔分布的形状参数k作为输入。将估计的结果与实际结果进行对比,对比结果证明该方法是可行且有效的。
Estimation of wind power generation is the key step in turbine-site matching and wind power cost analysis. In order to estimate the wind power accurately, radial basis function （RBF）neural network is used to estimate the energy output of wind power plant. The modeling is based on the historical data from 18 meteorological stations of Chinese Tai- wan and 26 meteorological stations of Republic of Korea, then their energy outputs are estimated by themselves and among each other. Because the wind speed and generation hours are the main factors affecting wind power, this paper takes average annual wind speed and the k parameter of Weibull distribution which affects the annual generation hours as inputs. The estimated results are compared with actual wind power outputs, and this shows that the presented method is feasible and effective.
出处
《电力系统及其自动化学报》
CSCD
北大核心
2016年第11期32-36,共5页
Proceedings of the CSU-EPSA
基金
国家自然科学基金资助项目(50907005)
湖南高校创新平台开放基金资助项目(10K004)
关键词
径向基函数神经网络
风力发电场
年度发电量估计
风速
radial basis function （RBF） neural network
wind power plant
annual energy output estimation
wind speed
