Wind speed data cleaning method for wind speed correlation analysis of wind generation sets

Abstract

The invention relates to a wind speed data cleaning method for wind speed correlation analysis of wind generation sets. The wind speed data cleaning method for the wind speed correlation analysis of the wind generation sets is applied to cleaning wind speed data of every wind generation set during wind speed correlation analysis of a plurality of wind generation sets. The method comprises the following steps of (1) performing processes to acquire the original wind speed time sequence data of every wind generation set and corresponding generation output power time sequence data; (2) performing retrieval marking on the generation output power time sequence data to acquire the retrieval matrix of every wind generation set; (3) performing comprehensive correction on the retrieval matrix of every wind generation set to acquire a corrected retrieval matrix; (4) according to the corrected retrieval matrix, performing data rejection on the original wind speed data of every wind generation set to acquire cleaned wind speed time sequence data of every wind generation set. Compared with the prior art, the wind speed data cleaning method for the wind speed correlation analysis of the wind generation sets is simple and reliable, improves the usability of wind generation set wind speed data and ensures correctness of correlation analysis results.

Description

technical field [0001] The invention relates to a wind speed data cleaning method, in particular to a wind speed data cleaning method used for wind speed correlation analysis of a wind turbine. Background technique [0002] With the rapid development of wind power generation, the research on wind power generation is of great significance to the construction of clean energy and the improvement of power grid structure. Among them, the information mining of wind farm operation data has gradually become a research hotspot in the industry. The amount of wind power data generated during the operation of wind farms has grown exponentially, and the huge database contains the internal links between wind turbines. The on-site operation data of the wind turbine includes time, wind speed, wind direction angle, wind power, pitch angle, frequency, generator voltage and other main parameters of the unit. [0003] In the actual operation of wind farms, due to the random fluctuations of win...

AI Technical Summary

Problems solved by technology

[0003] In the actual operation of wind farms, due to the random fluctuations of wind energy, sensor failures, wind turbine downtime, abnormal wind farms, and human factors, the operating data of wind turbines must have a series of dirty data or missing data, which cannot be true. Effectively reflect the operating status of wind turbines and the input and output characteristics of each unit

Images