Training sample grouping construction method used for support vector regression (SVR) short-term load forecasting

Abstract

The invention discloses a training sample grouping construction method used for support vector regression (SVR) short-term load forecasting, and belongs to the field of intelligent computing and machine study. The training sample grouping construction method comprises a step of analyzing correlation, wherein the correlation degree of the load of each time interval and the loads of other time intervals is analyzed through the Tangs correlation degree of the grey correlation degree to form a correlation degree matrix; a step of grouping prediction problems, wherein the time intervals with high load correlation degree are divided into one group according to the correlation degree matrix; a step of constructing a reference load matrix; a step of selecting a reference load to construct a training sample, wherein linear function fitting is carried out on each row of the loads in a load variation rate matrix in a least square fit mode, and fitting variance is calculated; and a step of selecting the load of the time interval with small fitting variance to serve as the forecasting reference load of the group. The training sample grouping construction method used for the SVR short-term load forecasting is capable of improving the load forecasting accuracy, and avoids the problem of high time complexity. The experiment result shows that a short-term load forecasting model trained by the training sample constructed through the method has good performance in forecasting accuracy and time complexity.

Description

technical field [0001] The invention relates to the grouping structure of short-term load forecasting training samples for SVR (Support Vector Regression), which is a key link in load forecasting by using the SVR model, and belongs to the field of intelligent computing and machine learning. Background technique [0002] SVR (Support Vector Regression) is a generalization of SVM (Support Vector Machine) to solve function fitting problems in machine learning. SVM was first proposed by Cortes and Vapnik in 1995. It shows many unique advantages in solving small samples, nonlinear and high-dimensional pattern recognition. The SVM method maps the sample space to a high-dimensional or even infinite-dimensional feature space (Hilbert space) through a nonlinear mapping p, so that the non-linearly separable problem in the original sample space is transformed into a feature space in the feature space. linearly separable problems. Linear partitioning is achieved through a linear hyper...

AI Technical Summary

Problems solved by technology

The second direction is the research on the construction of training samples, and the current research is relatively small

Using this method can remove factors with weak correlation and reduce the dimensionality of training samples, but the genetic algorithm tends to converge to a local optimum, resulting in poor reliability of the results, which may lead to unsatisfactory training samples.

Images