基于FILTERSIM算法的风力发电功率预测
|
摘要
由于风力发电受天气条件的影响,所以其输出功率难以预测。将风力发电功率与气象数据依据一定的排列规则整理为三维图像,通过FILTERSIM算法对训练数据图像降维并提取其特征,然后在已知的气象数据组成的验证点集上预测风力发电功率。试验结果与验证数据的对比表明,该方法能有效预测风电的发电功率。
Due to the impact of wind power from the weather conditions,the nonlinear characteristics of the output power is difficult to accurately capture. The wind power and meteorological data are arranged into three-dimensional images according to certain arrangement rules. The training data images are reduced in dimension and their characteristics are extracted by FILTERSIMalgorithm. Then the wind power is predicted on the verification point set of known meteorological data. By comparing the experiment results with the validation data,it is shown that the method can effectively predict wind power generation.
Due to the impact of wind power from the weather conditions,the nonlinear characteristics of the output power is difficult to accurately capture. The wind power and meteorological data are arranged into three-dimensional images according to certain arrangement rules. The training data images are reduced in dimension and their characteristics are extracted by FILTERSIMalgorithm. Then the wind power is predicted on the verification point set of known meteorological data. By comparing the experiment results with the validation data,it is shown that the method can effectively predict wind power generation.
引文
[1]王勃,冯双磊,刘纯.考虑预报风速与功率曲线因素的风电功率预测不确定性估计[J].电网技术,2014,38(2):463-468.
[2]黎静华,桑川川,甘一夫,等.风电功率预测技术研究综述[J].现代电力,2017,34(3):1-11.
[3]KHALID M,SAVKIN A V.A method for short-term wind pow er prediction w ith multiple observation points[J].IEEETransactions on Pow er Systems,2012,27(2):579-586.
[4]骆杨,赵彦超.多点地质统计学在河流相储层建模中的应用[J].地质科技情报,2008,27(3):68-72.
[5]ZHANG T.Filter-based training pattern classification for spatial pattern simulation[D].Palo Alto:Stanford University,2006.
[6]LU D T,ZHANG T,YANG J Q,et al.A reconstruction method of porous media integrating soft data w ith hard data[J].Chinese Science Bulletin,2009,54(11):1876-1885.
[7]范高锋,王伟胜,刘纯,等.基于人工神经网络的风电功率预测[J].中国电机工程学报,2008,28(34):118-123.
[8]刘立阳,吴军基,孟绍良.短期风电功率预测误差分布研究[J].电力系统保护与控制,2013(12):65-70.
[9]WU J,BOUCHER A,ZHANG T.A SGeMS code for pattern simulation of continuous and categorical variables:FILTER-SIM[J].Computers&Geosciences,2008,34(12):1863-1876.
[2]黎静华,桑川川,甘一夫,等.风电功率预测技术研究综述[J].现代电力,2017,34(3):1-11.
[3]KHALID M,SAVKIN A V.A method for short-term wind pow er prediction w ith multiple observation points[J].IEEETransactions on Pow er Systems,2012,27(2):579-586.
[4]骆杨,赵彦超.多点地质统计学在河流相储层建模中的应用[J].地质科技情报,2008,27(3):68-72.
[5]ZHANG T.Filter-based training pattern classification for spatial pattern simulation[D].Palo Alto:Stanford University,2006.
[6]LU D T,ZHANG T,YANG J Q,et al.A reconstruction method of porous media integrating soft data w ith hard data[J].Chinese Science Bulletin,2009,54(11):1876-1885.
[7]范高锋,王伟胜,刘纯,等.基于人工神经网络的风电功率预测[J].中国电机工程学报,2008,28(34):118-123.
[8]刘立阳,吴军基,孟绍良.短期风电功率预测误差分布研究[J].电力系统保护与控制,2013(12):65-70.
[9]WU J,BOUCHER A,ZHANG T.A SGeMS code for pattern simulation of continuous and categorical variables:FILTER-SIM[J].Computers&Geosciences,2008,34(12):1863-1876.