Power distribution network flow prediction method based on B-spline substrate developed curve clustering

Abstract

The invention discloses a power distribution network flow prediction method based on B-spline substrate developed curve clustering. The method is characterized in that the clustering technology is used to predict a load, and line loss rate and line loss probability are predicted by flow calculation. By the method based on the B-spline substrate developed curve clustering, curve clustering is discussed under the condition that curve change rate is considered, and comprehensive extraction of function features is benefited. The method has the advantages that nonlinear prediction difficulties during direct line loss rate prediction are solved; curve all-order derivative functions are brought into a curve clustering algorithm, comprehensive extraction of function features is benefited, and clustering accuracy is benefited when load fluctuation is large; the line loss rate is calculated by load prediction, the theoretic basis of line loss prediction is provided, and non-linear prediction difficulties are avoided; a flow occurrence probability concept is introduced, and assistance is provided to power grid economic operation condition measuring, power grid structure and layout reasonability evaluation, reasonable dispatching order giving, and the like.

Description

technical field [0001] The invention belongs to the technical field of electric network theoretical line loss prediction, and in particular relates to a distribution network power flow prediction method based on B-spline base expansion curve clustering. Background technique [0002] Power network loss is the power loss generated during the transmission of electric energy, and the line loss rate is an important technical and economic index of electric power enterprises, and it is also an important symbol to measure the technical level and management level of electric power enterprises. Reducing line loss is an important task for power grids and power supply companies, and it is also an important means to improve corporate profits, save energy and reduce emissions. According to the national policy of "emphasizing both resource evaluation and conservation, and putting conservation first", power companies have invested a lot of manpower, finance and material resources in order t...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a distribution network power flow prediction method based on B-spline base expansion curve clustering, aiming at solving the problem that most of the current theoretical line loss predictions are directly predicted by generator processing, etc. Low, resulting in inaccurate prediction of line loss rate, directly affecting the accuracy of power grid dispatching, affecting the analysis and transformation of power grid line loss management

Images