Plateau mountain multi-model multi-scale new energy power station output joint prediction method

Abstract

The invention discloses a multi-scale new energy power station output joint prediction method based on a plateau mountain multi-model area. The method comprises the following steps: S1, establishing a wind energy joint prediction basic model; s2, selecting a feature day which is the same as or similar to the weather state of the prediction day based on the four-dimensional features; s3, establishing a characteristic day turbulence prediction model based on the characteristic day and the wind energy prediction basic model; and S4, performing new energy power station output joint prediction based on the characteristic daily turbulence prediction model. The invention further discloses a corresponding prediction system, electronic equipment and a computer readable storage medium, wind energy prediction is subjected to joint or coordinated prediction according to geographical and meteorological influence factors, coupling is analyzed, respective input quantities and coupling characteristics are determined, model complexity and generalization ability are taken into consideration, and the prediction efficiency is improved. And automatically selecting the date with the highest similarity with the weather condition of the prediction day as a feature day, and training the prediction model by taking the meteorological data and the output power data of the feature day as training samples so as to obtain relatively high prediction precision.

Description

technical field [0001] The present invention relates to the technical field of new energy power generation, in particular to a method, system and electronic equipment for joint forecasting of output of new energy power stations based on plateau and mountainous multi-model regions and multi-scales. Background technique [0002] The development and utilization of new energy is the requirement of realizing the sustainable development of society, and wind power generation has become an important form of new energy power generation because of its own unique advantages. Because wind energy can change some factors that affect wind power generation in local areas, wind power generation will also change the impact, so it is necessary to jointly predict the output of the two. The external factors that affect the output of wind turbines are wind speed and direction, and the temperature of the engine room. The internal factors include the type of generator, impact capacity, hub height, ...

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problems existing in the prior art, the present invention provides the following technical solution, a joint prediction method for the output of new energy power stations based on plateau mountainous multi-model regions and multi-scales, which combines or coordinates wind energy prediction and analyzes the relationship between the two The coupling of the two, determine the respective input and coupling characteristics of the two, and determine a new forecast model according to the characteristic day and optimize it. There is no need to build a forecast model for each weather type. Although high forecast accuracy can be obtained, there is a large workload. Due to the complexity of the model and the problem of over-matching, it is very important to select training data that is consistent with the weather conditions of the forecast day to improve the forecast accuracy and efficiency. Taking into account the complexity and generalization ability of the model, the date with the highest similarity to the weather conditions of the forecast day is automatically selected as the feature Day, the meteorological data and output power data of the characteristic day are used as training samples to train the prediction model to obtain higher prediction accuracy, and to realize the combined output of multiple new energy hybrid power stations under multi-scale weather conditions in plateau mountainous multi-model regions predict

Images