Photovoltaic power generation ultra-short-term power prediction method and system

Abstract

The invention provides a photovoltaic power generation ultra-short-term power prediction method and system, and the method comprises the following steps: carrying out the Spearman correlation coefficient analysis between actually measured variable data and meteorological prediction variable data and the power generation power, and selecting a variable with the strong correlation with the power generation power as an input variable of a model; calculating the correlation among the moments in the input variables by using the Spearman correlation coefficient again, and determining the moment variable value with high correlation as the input data of the LSTM prediction model; modeling a nonlinear relationship between the input data sequence and the photovoltaic power generation power sequence at each moment by using an LSTM network, and constructing a time-sharing long-term and short-term memory network prediction model, wherein Spearman correlation coefficient analysis is completed on an SPSS platform, and completing photovoltaic power prediction under a Keras platform and a Tensorflow platform. The ultra-short-term generated power prediction method for the photovoltaic power station is researched, time-sharing prediction is achieved, and the prediction precision of the generated power is improved.

Description

technical field [0001] The invention relates to the technical field of power system engineering, in particular to a photovoltaic power generation ultra-short-term power prediction method and system. Background technique [0002] The ultra-short-term power prediction results of photovoltaic power generation systems are related to the formulation of power system scheduling and production plans. Accurate forecasting of photovoltaic power generation is crucial to power system operation and scheduling. Because the output power of photovoltaic power generation system is affected by natural factors such as day and night, seasons and weather, it has the characteristics of strong intermittency, fluctuation and uncertainty, which brings great challenges to the accurate prediction of power generation. Therefore, there is an urgent need for a prediction method that can better grasp the variation law of power generation. [0003] There are many factors affecting photovoltaic power gener...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a photovoltaic power generation ultra-short-term power prediction method and system, which can effectively solve the problem of low prediction accuracy of power generation due to meteorological conditions

Images