基于数值模拟和统计分析及智能优化的风速预报系统

风速预报是风力发电研究中的关键问题,也是一个十分困难的问题,其预测、评估技术还有待进一步提高.在预测短期风力(提前48～72 h对每小时的风速进行预测)时,通常采用数值天气预报模型进行预测.然而,初始扰动和模式物理过程的不确定性会影响气象数值预报的精度.将为数值天气预报模式提出一种新的后处理优化方法作为主要的思路,利用数据挖掘得到的关联规则来优化气象数值预报的结果,在中尺度模式WRF对风电场风速进行预报的基础上,将模式预测与统计分析及智能优化算法相结合,针对中国风电场的气候特征,利用一种新的修正模式误差的方法,极大地提高了风电场风速预报精度,提出了适合中国风力发电场的有效风速预报系统方案.

Program of Wind Speed Prediction Based on Numerical Simulation with Intelligent Optimization Algorithm

Wind speed prediction is a key factor for wind farm planning and the operational planning of power grids; accurate forecasting of wind speed can minimize the scheduling errors and in turn increase the reliability of the electric power grid and reduce the power market ancillary service costs. Based on the mesoscale model WRF(Weather Research and Forcasting) for wind speed forecasting, combined with model prediction and statistical analysis using an intelligent optimization algorithm we have greatly improved the forecasting precision of wind speed, employing a new method to correct the model errors. In view of the climatic feature of Chinese wind farms, the wind speed prediction program in China has been enhanced.