Offshore wind farm power prediction method considering meteorological similarity and power fluctuation

Abstract

The invention relates to a power prediction method of an offshore wind farm considering meteorological similarity and power fluctuation, comprising the following steps: 1) obtaining wind energy data of an offshore wind farm within a certain period of time, and using it as an original wind energy sample; 2) analyzing the original wind energy The cluster analysis of meteorological similarity is carried out on the sample data, and the classification result of meteorological similarity is obtained; 3) Classify the power fluctuation, and use the extreme learning machine ELM to obtain the category of the power fluctuation range, and obtain the classification result of the power fluctuation; 4) Use The Elman neural network established a preliminary prediction model based on sample similarity, and carried out short-term wind speed rolling prediction of the wind farm for the future time, and obtained the initial prediction results; 5) Using the multi-layer perceptron MLP to establish an NWP correction model to correct the initial prediction results , to get the corrected final result. Compared with the prior art, the present invention has the advantages of considering meteorological similarity and power fluctuation, accurate and comprehensive prediction, and the like.

Description

technical field [0001] The invention relates to the technical field of offshore power forecasting, in particular to a power forecasting method for offshore wind farms considering weather similarity and power fluctuations. Background technique [0002] Offshore wind power has become a key development direction of the wind power industry in the future due to its stable wind power, proximity to the load center, and no occupation of land resources. However, with the increase of installed capacity, the fluctuation and randomness of offshore wind power output have brought many challenges to the stable operation of the system. Therefore, dispatching the power system through accurate short-term power forecasting is of great significance for the stable operation of the power system and the improvement of economic benefits. Traditional wind power prediction methods can be mainly divided into physical methods that describe the outline of the entire area of ​​the wind farm in detail; a...

AI Technical Summary

Problems solved by technology

In terms of physical methods, due to the complexity of the sea environment, the wide range of wake influences, and the lack of climate data, the computational complexity of maritime physical modeling is cumbersome and difficult to model; and due to differences in geographical environments, the flexibility and generalization of physical models is not good.

The extrapolation model method based on the statistical point of view can use the given meteorological conditions for training, avoiding the complicated physical modeling steps in the middle; but on the other hand, the low accuracy of my country's offshore NWP information and large changes in wind power output directly affect Accuracy of Statistical Models

Images