A Pseudo-Measurement Generation Method for Distribution Network Based on Kernel Density Estimation

Abstract

The invention relates to an interpolation method applied to pseudo-measurement generation, and belongs to the technical field of power system scheduling automation and power grid simulation. First, the load data collected by the electricity billing system is used as the load measurement; and an unknown prediction value is obtained by using a certain algorithm; then, the prediction value is used, based on historical data, combined with a high-efficiency equidistant node interpolation method ; To supplement the shortage of distribution network measuring devices. The pseudo measurement generation method of the present invention makes full use of the load data in the metering system of the distribution network, and its algorithm is simple, and the convergence performance is guaranteed. As long as the node spacing is sufficiently small, the equidistant node method can always obtain the required accuracy, and the calculation The speed is fast, and the accuracy of the pseudo-measurement load of the non-measurement point can be reached or close to the actual measurement value, and the smoothness of the load data can be maintained, thereby improving the accuracy of the state estimation of the distribution network.

Description

Technical field [0001] The invention relates to a method for generating pseudo measurement of distribution network based on nuclear density estimation. The pseudo measurement is obtained by using historical data of the power grid and the predicted value of a regression load forecasting method of nuclear density estimation and equidistant interpolation method. System dispatch automation and power grid simulation technology field. Background technique [0002] Distribution network state estimation is one of the most basic and most important functions of the distribution network management system. However, the current collection of distribution network data is huge and complex, and the hardware installation of measuring points requires a lot of money and energy. It is uneconomical and unrealistic to install measurement at each node, resulting in a serious shortage of measurement data in the distribution network, so it is necessary to introduce pseudo measurement to supplement the la...

AI Technical Summary

Problems solved by technology

However, the common feature of these data is that the real-time performance is poor, and the load pseudo-measurement accuracy obtained by using these data is not high.

At the same time, due to the requirements of computational efficiency, the pseudo-measurement data cannot achieve the same frequency of real-time measurement, so the unpredicted pseudo-measurement data needs to be obtained by interpolation

Images