Electric power system load prediction method and system

Abstract

The present invention discloses an electric power system load prediction method and system. The method comprises the steps of: obtaining historical load data of an electric power system; performing preprocessing of the obtained historical load data; employing a grey theory to perform de-trending processing of the data after preprocessing, and obtaining a trend item; performing spectrum analysis todetermine the number of decomposition layers, and employing variation modal decomposition to perform decomposition of data after the de-trending processing; and employing a support vector machine optimized by an improved NSGA-II to perform classification summation reconstruction of the decomposed data; obtaining a final prediction result according to a reconstructed result and the trend item; andperforming superposition of the prediction value of each load component to determine an actual prediction result. The electric power system load prediction method and system can effective respond todefects that the load prediction fluctuation is large, the accuracy is not high and it is easy to be caught in local optimum based on the grey theory-variation modal decomposition and the support vector machine method optimized by the NSGA-II.

Description

technical field [0001] The invention relates to the technical field of electric power systems, in particular to a method and system for load forecasting of electric power systems. Background technique [0002] Power load forecasting is an important content, premise and foundation of power system planning and grid operation. Under the situation that the country is vigorously advocating energy conservation and environmental protection to save existing energy consumption, the accuracy of power load forecasting is related to the economic and efficient operation of the entire power grid enterprise and the safe operation of the entire power grid. Accuracy sets higher standards. [0003] At present, the commonly used traditional methods of short-term load forecasting include classical forecasting methods represented by time series method and regression analysis method, and artificial intelligence methods represented by expert system method, neural network and fuzzy logic method. ...

AI Technical Summary

Problems solved by technology

[0006] The object of the present invention is exactly in order to solve above-mentioned problem, has proposed a kind of power system load forecasting method and system, and this method and system are based on the support vector machine method of gray theory-variational mode decomposition and NSGA-II optimization, can deal with load effectively The accuracy of forecasting large fluctuations is not high, and it is easy to fall into the disadvantage of local optimum

Images