Short-term load prediction method based on variant selection and Gaussian process regression

Abstract

The present invention discloses a short-term load prediction method based on variable selection and Gaussian process regression. The method includes the following steps that: 1) bad data elimination, supplementation and normalization pre-processing are performed on sample data; 2) candidate input variables are selected from the perspectives of historical load, temperature and humidity, and the date type of a prediction date, and the scores of the importance of the variables are calculated through a random forest algorithm, and the scores of the importance of the variables are sequenced; 3) an optimal variable set is determined through adopting a sequence forward search strategy and based on a Gaussian process regression model; 4) the Gaussian process regression model is trained based on the determined optimal variable set, and the parameters of the model are optimized based on improved particle swarm optimization; and 5) the predictive performance of the model is verified in a test set. With the method provided by the invention adopted, prediction accuracy can be effectively improved, and the load prediction problem of a power system can be solved.

Description

technical field [0001] The invention relates to a short-term load prediction method of a power system, which is used to predict the load of the power system and belongs to the technical field of power systems. Background technique [0002] Improving the accuracy of power system load forecasting is one of the technical measures to effectively ensure the safe, stable, and economical operation of the power system. Load forecasting at different time scales is of great significance for the arrangement of power production scheduling, equipment maintenance planning, and medium- and long-term power grid planning. The actual system operation has accumulated a large amount of historical load and meteorological data, and fully mining the information contained in these data provides a new way to improve the accuracy of power load forecasting. [0003] Gaussian process regression (GPR) is based on Bayesian theory and statistical learning theory. When dealing with high-dimensional, nonlin...

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: The present invention is aimed at the problems existing in the existing power system load forecasting technology, such as when using Gaussian process regression to establish a load forecasting model, the traditional conjugate gradient method is easy to fall into a local optimal solution for solving model hyperparameters, and the optimization performance is affected. The initial value selection has a large impact and the number of iterations is difficult to determine, which leads to the defects of low accuracy of the prediction results. A short-term load forecasting method based on improved particle swarm optimization Gaussian process regression is provided, that is, the PSO-GPR load forecasting method

Images