Cluster division method based on wind turbine generator operation performance evaluation index system

Abstract

The invention discloses a cluster division method based on a wind turbine generator operation performance evaluation index system. The method mainly comprises the steps that the wind turbine generator operation performance evaluation system is established, wind turbine generator operation performance evaluation indexes are classified, the weight of each index of a wind turbine generator is determined, and cluster division is conducted on the wind turbine generator according to the index weights. According to the method, index calculation is carried out by utilizing existing actual data, a large amount of index data influencing operation of the wind turbine generator is obtained, classification is carried out on the basis, indexes with similar characteristics are classified into one class, and use is convenient. By considering that the classification number is mainly obtained by experience and is possibly not rigorous, the classification number is judged by calculating an inconsistent coefficient after each time of classification merging, and the analysis and decision-making capability of scheduling operation is improved. And in consideration of the applicability of the index system for different generator groups and the speed and precision of processing the wind power plant model, all the wind turbine generators are classified by using the classified indexes, so that the system complexity is reduced, the precision is improved, and a manager can observe and control conveniently.

Description

technical field [0001] The invention belongs to the field of wind turbine cluster division, and in particular relates to a cluster division method based on a wind turbine operating performance evaluation index system. Background technique [0002] As the most widely developed and utilized renewable clean energy, wind power has mature development conditions and broad application prospects. Since the randomness and fluctuation of wind turbines pose a certain threat to the stable and safe operation of the power system, and there may be many types of units in a large wind farm, it is necessary to build an accurate and simple model. When constructing the model, the units with similar conditions are generally divided into the same unit, and their equivalents are treated as a unit, so as to simplify the analysis. When the terrain of the wind farm is relatively flat and the unit arrangement is relatively regular, the fleet division is generally carried out according to the unit typ...

AI Technical Summary

Problems solved by technology

[0006] The existing wind farm equivalent methods mainly have the following problems: too few cluster division indicators, resulting in cluster division results only for one or some physical quantities, which are not suitable for most scenarios; too many cluster division indicators, resulting in cluster division results that cannot Clearly point out the indicators with great influence and make targeted processing; when processing, the number of equivalent fans is not scientifically processed, and no in-depth research has been carried out. An appropriate clustering number can not only improve the accuracy and The speed is more conducive to the comparison between models, and the method of reasonably and efficiently solving the above problems is of great significance to guide the operation of wind power and provide decision-making support for the power grid dispatching management department

Images