Short-term photovoltaic power prediction method, medium and equipment under power market background

Abstract

The invention relates to a short-term photovoltaic power prediction method, medium and equipment under a power market background, and the method comprises the following steps: dividing the weather into four weather models: a sunny day model, a cloudy day model, a gust rain model and a full rain model based on an NWP value; judging the weather type of the day to be measured, and selecting the latest similar solar photovoltaic power historical data and the historical NWP value according to the weather type of the day to be measured; inputting the classified data set into each base learner in a layer of prediction model of the Stacking integration model; obtaining a prediction result of each base learner, constructing a new training set, and inputting the new training set into a two-layer prediction model; and obtaining a prediction result of the two-layer element learner, namely a final photovoltaic power generation power prediction value. According to the method, the dependency of prediction on data can be effectively reduced by adopting a combined mechanism model and a data-driven algorithm, the prediction precision, speed and reliability can be considered under the condition that the data quality and quantity are not ideal, the data acquisition cost in actual production is greatly reduced, and remarkable economic benefits are achieved.

Description

technical field [0001] The invention relates to the technical field of photovoltaic power generation, in particular to a short-term photovoltaic power prediction method, medium and equipment under the background of an electric power market. Background technique [0002] Accurate photovoltaic power forecasting plays a vital role in power system dispatching. To meet this requirement, the present invention conducts research on short-term photovoltaic power forecasting methods under the background of the electricity market. [0003] The data-driven photovoltaic power generation prediction method has simple modeling, mature algorithms, and fast calculation speed, but it is completely based on numerical calculations, highly dependent on data quality and quantity, and does not consider the internal mechanism of photovoltaic power generation, and the reliability of the prediction results is poor. The mechanism-driven method can well reflect the principle and coupling effect of photo...

AI Technical Summary

Problems solved by technology

Patent [5] clusters the daily historical processing data of photovoltaic power plants into K clusters, and constructs an improved generalized weather map corresponding to one or more digital labels for professional meteorological weather, so as to overcome the shortcomings of low prediction accuracy of photovoltaic power generation under non-clear conditions

Images