基于突变理论的风电爬坡多步预测  

Multi-step Wind Power Ramp Forecasting Based on Catastrophe Theory

作　　者：甘迪[1] 柯德平[1] 孙元章[1] 崔明建[1] 

机构地区：[1]武汉大学电气工程学院,湖北武汉430072

出　　处：《现代电力》2016年第3期14-21,共8页Modern Electric Power

基　　金：国家重点基础研究发展计划项目(973计划)(2012CB215101)

摘　　要：风电爬坡实现的多步预测是保障大规模风电并网后电网安全和电能质量的有效手段。提出了一种基于突变理论的风电爬坡多步预测方法,首先将风电爬坡事件视为一种突变现象,采用相关性分析、主成分分析和线性加权累加方法处理中尺度气象数据,确定突变爬坡的相关变量;然后分别建立上行和下行爬坡的突变预测模型,通过综合考虑增大预测步长和减小预测误差,求解多目标优化问题,以训练模型参数,实现风电爬坡的多步预测。仿真结果表明,该方法可以比较有效地预测风电爬坡事件,与统计方法相比具有更大的预测步长和更高的准确率。The forecasting of multi-step ramp is an effective way to ensure security and power quality of power grid with high penetration of wind energy into power grid. A forecasting model of multi-step wind power ramp based on catastro- phe theory is proposed. Firstly, wind power ramp events are regarded as catastrophe phenomena, and the meso-scale meteorological data is processed by using correlation analysis, principal component analysis and linear weighted accumula- tion, so as to determine relevant variables of catastrophe ramp models. Thus catastrophe forecasting models for up- ramps and down-ramps are built respectively. The multi-ob- jective optimization problem is solved by increasing the fore- casting step and decreasing the forecasting error, by which the parameters are trained and the multi-step wind power ramp is forecasted. The simulation results show that the pro- posed method can effectively forecast wind power ramp events, has larger forecasting step and higher accuracy by comparing with that of the statistical method.

关 键 词：风电爬坡事件 突变理论 中尺度气象信息 数据挖掘 多步预测 

分 类 号：TM614[电气工程—电力系统及自动化]