风电功率区间预测是应对大规模风电机组并网运行的有效手段之一。针对山东风电并网运行建立了一种考虑山东半岛不同风能特征的风电功率区间预测模型。对比了不同风能条件下半岛内风电场出力特征和风电功率历史预测误差分布特点,发现风...风电功率区间预测是应对大规模风电机组并网运行的有效手段之一。针对山东风电并网运行建立了一种考虑山东半岛不同风能特征的风电功率区间预测模型。对比了不同风能条件下半岛内风电场出力特征和风电功率历史预测误差分布特点,发现风电场出力分布范围随风速增加呈"先增后减"趋势,在出力分布范围较大的风速区间内,预测误差也相对较大。以风速、风向和预测功率为特征变量,在利用层次聚类法对样本数据进行聚类分析基础上,采用非参量核密度估计方法,建立了各类样本在不同风向条件下风速-风电功率预测误差的联合概率密度分布模型。将该模型与NARX(nonlinear auto regressive models with exogenous inputs)网络确定性风电功率预测结果相结合,得到一定置信水平的风电功率区间预测结果,最后通过实际算例验证了模型的有效性。展开更多
针对风速点预测无法对预测结果进行风险评估、区间预测难以满足电网精细化要求,以及现有静态预测方法难以描述风速序列长期相关性的现象,提出一种基于模糊信息粒化(Fuzzy Information Granulation,FIG)和长短期记忆(Long Short-Term Mem...针对风速点预测无法对预测结果进行风险评估、区间预测难以满足电网精细化要求,以及现有静态预测方法难以描述风速序列长期相关性的现象,提出一种基于模糊信息粒化(Fuzzy Information Granulation,FIG)和长短期记忆(Long Short-Term Memory,LSTM)网络的动态预测模型。该方法先对风速序列进行模糊信息粒化,提取出粒化后数据的最大值 (区间上界)、最小值(区间下界)和平均值。其次采用ADAM算法优化的LSTM网络对各粒化数据进行动态建模,得到能描述风速波动性的区间预测结果和点预测结果。算列表明,所提动态模型的预测效果比其它基本模型的预测效果更好。展开更多
With the increased promotion of integrated energy power systems(IEPS),renewable energy and energy storage systems(ESS)play a more important role.However,the fluctuation and intermittent nature of wind not only results...With the increased promotion of integrated energy power systems(IEPS),renewable energy and energy storage systems(ESS)play a more important role.However,the fluctuation and intermittent nature of wind not only results in substantial reliability and stability defects,but it also weakens the competitiveness of wind generation in the electric power market.Meanwhile,the way to further enhance the system reliability effectively improving market profits of wind farms is one of the most important aspects of Wind-ESS joint operational design.In this paper,a market-oriented optimized dispatching strategy for a wind farm with a multiple stage hybrid ESS is proposed.The first stage ESS is designed to improve the profits of wind generation through day-ahead market operations,the real-time marketbased second stage ESS is focused on day-ahead forecasting error elimination and wind power fluctuation smoothing,while the backup stage ESS is associated with them to provide the ancillary service.An interval forecasting method is adopted to help to ensure reliable forecast results of day-ahead wind power,electricity prices and loads.With this hybrid ESS design,supply reliability and market profits are simultaneously achieved for wind farms.展开更多
文摘风电功率区间预测是应对大规模风电机组并网运行的有效手段之一。针对山东风电并网运行建立了一种考虑山东半岛不同风能特征的风电功率区间预测模型。对比了不同风能条件下半岛内风电场出力特征和风电功率历史预测误差分布特点,发现风电场出力分布范围随风速增加呈"先增后减"趋势,在出力分布范围较大的风速区间内,预测误差也相对较大。以风速、风向和预测功率为特征变量,在利用层次聚类法对样本数据进行聚类分析基础上,采用非参量核密度估计方法,建立了各类样本在不同风向条件下风速-风电功率预测误差的联合概率密度分布模型。将该模型与NARX(nonlinear auto regressive models with exogenous inputs)网络确定性风电功率预测结果相结合,得到一定置信水平的风电功率区间预测结果,最后通过实际算例验证了模型的有效性。
基金This work was supported in part by the National Natural Science Foundation of China(No.51607025).
文摘With the increased promotion of integrated energy power systems(IEPS),renewable energy and energy storage systems(ESS)play a more important role.However,the fluctuation and intermittent nature of wind not only results in substantial reliability and stability defects,but it also weakens the competitiveness of wind generation in the electric power market.Meanwhile,the way to further enhance the system reliability effectively improving market profits of wind farms is one of the most important aspects of Wind-ESS joint operational design.In this paper,a market-oriented optimized dispatching strategy for a wind farm with a multiple stage hybrid ESS is proposed.The first stage ESS is designed to improve the profits of wind generation through day-ahead market operations,the real-time marketbased second stage ESS is focused on day-ahead forecasting error elimination and wind power fluctuation smoothing,while the backup stage ESS is associated with them to provide the ancillary service.An interval forecasting method is adopted to help to ensure reliable forecast results of day-ahead wind power,electricity prices and loads.With this hybrid ESS design,supply reliability and market profits are simultaneously achieved for wind farms.
