Space load prediction method based on principal component analysis of comprehensive mutual information degree

Abstract

The invention relates to a spatial load prediction method based on principal component analysis of a comprehensive mutual information degree. The method comprises the following steps: S1, performing screening and dimension reduction on spatial information data collected from a geographic information system by using an MIS-PCA algorithm; s2, on the basis of the information processed by the MIS-PCA algorithm, establishing a land use type prediction model based on the spatial data mining technology; and S3, predicting the spatial load by using the land use classification result. The invention provides an improved comprehensive mutual information degree principal component analysis method (MIS-PCA), which can effectively improve the accuracy of data classification after dimension reduction and the effectiveness of a selected feature subset, can obtain fewer principal component dimensions, and reduces the feature dimension so as to reduce the calculation amount of back-end classification or recognition; according to the method, the MIS-PCA algorithm is introduced into a land use rule mining process, and numerous related attributes possibly influencing cellular land use type decision making are reduced, so that the land use decision making process is simplified, and the space load prediction efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of electric power system planning, in particular to a space load forecasting method based on principal component analysis of comprehensive mutual information degree. Background technique [0002] Spatial Load Forecasting (SLF) refers to the prediction of the size and location of future power loads in the power supply area. As one of the basic tasks for power system degradation, the capacity that power supply equipment should be configured and its optimal capacity can be determined based on the results of SLF. The location can improve the economy, efficiency and reliability of power system construction. [0003] In the spatial load forecasting method, the land use simulation method predicts the land use type, geographical distribution and area composition by analyzing the characteristics and development laws of land use, and combines the intelligent algorithm to obtain the conversion rules of the land load ty...

AI Technical Summary

Problems solved by technology

[0005] 2. The amount of spatial data is large, and there may be some repeated information among the data. How to reduce the amount of data while retaining key information

However, the core of the traditional principal component analysis method - correlation calculation, can only reflect the linear relationship between features, and cannot measure the nonlinear relationship

Although the mutual information matrix can be introduced in the feature selection algorithm instead of the covariance matrix to evaluate the linear and nonlinear relationship between features, the effectiveness of the selected feature subset is still not good enough

[0008] Based on the above situation, the traditional principal component analysis method and the traditional land use simulation method are difficult to meet the requirements of space load prediction in terms of accuracy and simplicity, so it is necessary to improve the traditional method

Images