摘要
风电机组出力可由风速计算得出,提高风速预测精度对减小风电并网冲击、合理调度风能资源至关重要。基于风电场气象及风速数据的时间连续性,提出了一种加入误差实时校正环节及风速变化趋势分析的改进方法介绍,在提高风速预测精度的同时有效改善了过校正情况。采用某个风电场的实际运行数据进行了仿真,结果表明,所提出的改进BP神经网络风速预测模型方法具有较好的预测精度。
The output of the wind turbine can be calculated by the wind speed, thus it is very important to improve the prediction accuracy of wind speed, so that impact on grid by wind power integration can be reduced, and wind energy resources can be reasonably scheduled. Considering the time continuity of meteorological and wind speed data of wind farms, this paper proposes an ultra-short-term wind speed forecasting model based on the BP neural network with real-time error correction and wind speed change trend analysis. In this way, prediction accuracy can be promoted and over correction can be avoided to some extent. Using the actual operation data of a wind farm, a simulation example is conducted through the MATLAB simulation. The results show that the proposed wind speed prediction model of improved BP neural network is feasible, effective and has better prediction precision.
出处
《电网与清洁能源》
北大核心
2016年第9期118-122,127,共6页
Power System and Clean Energy
基金
国家电网公司科技项目《智能风力发电场监控与预测关键技术研究与应用》(国家电网科[2015]709号文)
关键词
风速预测
BP神经网络
实时校正
wind speed forecasting
BP neural network
real-time correction
