A step-by-step method for forecasting power generation of photovoltaic power plants

Abstract

The invention discloses a method for predicting electricity generation power of a photovoltaic power station in a step-by-step way. The method is used for reducing the influence of correlative coupling between input variables of a prediction model on prediction performance and improving the prediction effect. According to the technical scheme provided by the invention, the method comprises the following steps: selecting meteorological parameters having influence on photovoltaic electricity generation power as electricity generation power meteorological factors based on a statistical rule of historical data of the photovoltaic power station; predicting the meteorological factors by using an intelligent method; and finally, mapping by using a prediction result of the meteorological factors and an electricity generation power characteristic model of the photovoltaic power station to obtain a prediction value of the electricity generation power of the photovoltaic power station. The method has clear physical significance and contributes to implementation of a prediction algorithm and the model in engineering practice, and the accuracy for electricity generation power prediction of the photovoltaic power station is improved.

Description

technical field [0001] The invention relates to a method for predicting the generating power of a photovoltaic power station in a step-by-step manner, and belongs to the technical field of power generation. Background technique [0002] As an important part of renewable energy, photovoltaic power generation has developed rapidly in recent years, and grid-connected photovoltaic power plants are currently the main form of utilization of photovoltaic power generation. The power of photovoltaic power generation is affected by various factors, showing obvious intermittency and volatility. Large-scale photovoltaic power generation grid connection will bring severe challenges to the dispatching control of the power system. In order to maximize the consumption of these green power sources by the grid, grid-connected photovoltaic power plants must have the ability to predict power generation. For a photovoltaic power station that has been built, the specifications, models, physical ...

AI Technical Summary

Problems solved by technology

Although the direct prediction method is simple and easy, it covers the prediction of input factors and the complex mapping relationship between input factors and output power in the same prediction model, which is not conducive to the optimal selection of input factors, optimization of model parameters and model prediction performance. At the same time, it is not conducive to the design and implementation of prediction algorithms and models in engineering practice

Images