Power distribution network three-phase power flow linearization method based on support vector regression

Abstract

The invention relates to a power distribution network three-phase power flow linearization method based on support vector regression, and belongs to the technical field of power distribution networks.The method comprises four steps of data-driven three-phase linearization power flow modeling, support vector regression, three-phase power flow linearization based on support vector regression and online three-phase power flow linearization calculation. According to the method, a data driving method is adopted, and linear approximation is performed on the power distribution network power flow onthe basis of the support vector regression, so that an accurate and efficient power system power flow linear model is obtained. On-line load flow calculation only needs to use the three-phase load flow linearization model obtained through training to perform load flow calculation; matrix inversion calculation is not needed during load flow calculation; and therefore, the method has high load flowcalculation efficiency and can be widely applied to power system analysis to obtain an efficient and accurate load flow analysis result.

Description

technical field [0001] The invention belongs to the technical field of distribution network, and in particular relates to a three-phase power flow linearization method of distribution network based on support vector regression. Background technique [0002] In recent years, with the development of active distribution network technology and the integration of a large number of distributed power sources and loads with demand-side response capabilities into the power grid, problems such as voltage over-limit, branch overload and three-phase imbalance have occurred in the active distribution network. Efficient power system analysis is particularly important to solve the above problems. The power flow equation is the basis of power system analysis, but the traditional power system power flow equation has nonlinear characteristics, which leads to problems such as non-convergence of optimization problems and slow calculation speed. Power flow linearization is a relatively common m...

AI Technical Summary

Problems solved by technology

However, in the current situation, the model parameters of the distribution network are mainly theoretical parameters, not measured parameters, and there are large errors

Secondly, the system model parameters will change due to environmental factors (such as temperature), so the distribution network model parameters cannot reflect the real situation of the system, and there is a large error, which leads to inaccurate model-based power flow linearization methods, thus affecting Accuracy of Power System Analysis

[0004]At the same time, the current power flow linearization method based on the power system model mainl

Images