基于相似性度量的风功率数据填补方法

Wind Power Data Filling Method Based on Similarity Measurement

风电机组的运行参数尤其是功率数据具有极其重要的价值,然而在数据采集、传输和记录的过程中存在各种原因会导致数据缺失。为此,提出了一种基于相似性度量的风功率数据填补方法。该方法利用数据特征,使用欧式距离、动态时间弯曲距离和最大公共子序列等相似性度量方法,寻找最相似的等长序列填补缺失值,并与均值插值、多点三次样条插值和自回归滑动平均模型等方法进行对比,结果表明了该方法的有效性和优越性。

The operating parameters of wind turbine,especially the power data,are of great value.However,in the process of data acquisition,transmission and recording,there are various reasons for data loss.Therefore,a wind power data filling method based on similarity measurement is proposed.This method utilizes data features and uses similarity measures such as Euclidean distance,dynamic time-warped distance,and maximum common subsequence to find the most similar equal-length sequences to fill missing values.At the same time,it is compared with methods such as mean interpolation,multi-point cubic spline interpolation and autoregressive moving average model.The results show the effectiveness and superiority of this method.