考虑测风数据缺失的短期风电功率预测算法  

Short-term wind power prediction algorithm considering missing wind measurement data

作　　者：曾杰 陈晓科 

机构地区：[1]广东电网有限责任公司电力科学研究院,广东省智能电网新技术企业重点实验室,广东广州510080

出　　处：《可再生能源》2017年第2期298-303,共6页Renewable Energy Resources

基　　金：中国南方电网有限责任公司科技项目(GDKJ00000065)

摘　　要：准确的风电功率预测是提高电网稳定性、增加风电场竞争力的重要途径。文章提出了一种以虚拟测风塔技术对测风塔数据进行预处理的方法,对缺失数据进行补全,利用RBF神经网络建立风速预测模型,拟合风速功率曲线得到风电功率预测结果。实验分析显示,基于虚拟测风塔技术的数据预处理方法可有效增加测风数据完整度,提高预测精度,降低风电场的运行维护成本,进一步提高风电场竞争力,具有实际应用价值。Accurate forecast of wind power is an important way to both improve the stability of power grid and increase the competitiveness of wind farm. In this paper,a technology of virtual wind measurement mast method is put forward for pretreatment in order to filling the missing values. Then, RBF model is applied to establish wind speed forecasting model and wind speed - power curve is finally used to obtain the wind power forecasting result. The simulation shows that the pretreatment method based on technology of virtual wind measurement mast can not only effectively increase the integrity of wind measurement data and improve the accuracy of forecasting but also reduce the cost of maintenance and improve the competitiveness of wind farm ,which is of practical application value.

关 键 词：风力发电 功率预测 虚拟测风塔 RBF神经网络 

分 类 号：TK89[动力工程及工程热物理—流体机械及工程]