测风数据间隔对风速预测精度影响的研究  

Anemometric interval influence on wind speed forecasting accuracy

作　　者：田蔷蔷[1] 许昌[1] 李承奇[1] 郑源[1] 刘德有[1] 于洋[1] 张凯[1] 

机构地区：[1]河海大学能源与电气工程学院,江苏南京210098

出　　处：《可再生能源》2012年第5期18-23,共6页Renewable Energy Resources

基　　金：中央高校基本科研业务费专项资金项目(2009B19414);河海大学优秀创新人才项目

摘　　要：风速预测对风电场控制和电网调度具有十分重要的意义。文章以不同时间间隔的测风数据为基础,采用时间序列法和人工神经网络法对风速进行预测,通过比较风速预测绝对平均误差,说明时间间隔较短时,采用BP神经网络预测精度较高;当时间间隔增大时,采用时间序列法预测精度较高;时间间隔过大,即风速数据太少时,两种预测方法误差都较大,须谨慎使用。该研究结果对风电机组控制系统的设计以及电网调度计划的制定具有参考价值。Wind speed forecasting is very important to wind turbine control system and power grid scheduling.Based on time series method and artificial neural network（ANN）respectively,the forecasting accuracy of wind speed via the various anemometry time intervals was studied.The result shows the method of BP neural network prediction gets higher accuracy if the time interval is short enough,but the time series prediction method is better when the time interval gets longer via the comparison between the average absolute errors of the wind speed forecasting.In addition,when the time interval is too big as well the historical data scale is too small,accuracies of the two kinds of methods are very low,so it should be not recommended usually.The present research in the paper provides an important reference for the design of wind turbine control system and the plan of power grid scheduling.

关 键 词：风速数据 风速预测 时间序列 人工神经网络 

分 类 号：TK89[动力工程及工程热物理—流体机械及工程] TM614[电气工程—电力系统及自动化]