风电场输出功率的多时段联合概率密度预测[EB/OL]
北京：中国科技论文在线
形成预测效果好、计算效率高的风电场输出功率多时段联合概率密度预测方法
将未来多个时段风电场输出功率的联合概率密度预测问题分解为风电场在各个时段独立的输出功率概率密度预测子问题与时段间关联的输出功率相关系数矩阵估计子问题
给出了一种基于数值天气预报信息的风电场输出功率的短期多时段联合概率密度预测方法
利用稀疏贝叶斯学习方法在概率密度预测问题上的优势
） Abstract： Wind farm generation with strong volatility is difficult to precisely forecast
Grasping the distribution feature of wind farm generation is vital for the operation of power system with significant wind power injection
For this reason, based on the wind farm generation feature analysis, wind farm generation joint probability density forecast is proposed here to estimate the fluctuation range and rate of wind farm generation which has close correlation between time intervals
And this may provide more comprehensive information for power system operation decision
The paper proposes a short-term wind farm generation multi-time-interval joint probability density forecast approach using numerical weather prediction information based on CCC-MGARCH (Constant Conditional Correlation - Multivariate Generalized Auto Regressive Conditional Heteroskedasticity) model and Sparse Bayesian Learning method
According to CCC-MGARCH, the wind farm generation multi-time-interval joint probability density forecast problem is divided into two parts which are wind farm generation probability density forecast sub-problem for each single time interval and correlation coefficient matrix estimation sub-problem among the time intervals
Then, an effective and efficient multi-time-interval joint probability density forecast approach with the advantages of Sparse Bayesian Learning at probabilistic density forecast is formed
At last, one application instance is given in the paper to illustrate the application value of the proposed approach
Keywords： power system
提出应对风电场输出功率实施多时段联合分布预测
掌握其输出功率的分布规律对含有风电场电力系统的运行决策具有重要意义
【详情见下载】
