Regional new energy ultra-short-term power prediction method and system

Abstract

The invention discloses a regional new energy ultra-short-term power prediction method. The method comprises the following steps: determining a new energy station with the highest correlation between the actual generated power and the actual generated power of a to-be-predicted region; acquiring historical power generation power prediction data preliminarily predicted by the new energy station with the highest correlation; extracting power generation power prediction data of the last prediction period in each prediction period from the preliminarily predicted historical power generation power prediction data, and constructing a new energy power prediction sequence according to the data; training the prediction model according to the new energy power prediction sequence and historical measured data of the to-be-predicted region in the same time period; and predicting the future generation power data of the to-be-predicted region by using the trained prediction model. The ultra-short-term new energy power prediction method can accurately predict the ultra-short-term new energy power.

Description

technical field [0001] The invention belongs to the technical field of new energy power prediction, and in particular relates to a method and system for regional new energy ultra-short-term power prediction. Background technique [0002] As one of the basic systems for grid-connected new energy power plants, the new energy power prediction system is the main reference means for the grid dispatch management department to formulate grid-connected power generation plans. The operation of the power generation power prediction system will affect the grid-connected power generation of new energy power plants. At the same time, it directly affects the dispatching strategy of the grid company. With my country's "dual carbon" goal and the tight power market, the assessment accuracy of new energy power generation consumption has gradually improved. The new national standard GB / T40607-2021 "Dispatching Side Wind Power or Photovoltaic Power Prediction System Technology" requires regiona...

AI Technical Summary

Problems solved by technology

The input data for ultra-short-term regional new energy power prediction is the previous measured power, meteorological information or weather forecast, and station predicted power. No matter which method or input data is used, the power prediction accuracy usually decreases with the extension of the forecast length, because The longer the forecast time, the smaller the impact of the current measured information on it, and the difficulty of forecasting will increase

Images