Power distribution network dynamic reconstruction method based on improved fuzzy C-means clustering algorithm

Abstract

The invention discloses a power distribution network dynamic reconstruction method based on an improved fuzzy C-means clustering algorithm, and the method comprises the steps: carrying out the day-ahead power prediction of DG output power and load power through an EEMD-SVR combined prediction model and historical power data; inputting a power distribution network initial parameter, a load power prediction amount, a DG prediction output value and other related initial parameters; constructing a segment-loss function according to the power prediction data to determine an optimal segment number; realizing intra-day dynamic reconstruction period division by improving a fuzzy C optimal clustering analysis algorithm; according to a clustering algorithm, determining a time period division scheme and an equivalent load center of each time period; performing static reconstruction optimization on each time period of the power distribution network by improving a bacterial foraging algorithm; and calculating and determining intra-day operation network loss and voltage fluctuation conditions of the power distribution network according to an optimization adjustment scheme of each intra-day reconstruction time period, and outputting solved related parameters. The method is simple and efficient, can be applied to the medium and low voltage distribution network with new energy access, and has certain popularization and practical values.

Description

technical field [0001] The invention relates to the technical field of distribution network dynamic reconfiguration, in particular to a distribution network dynamic reconfiguration method based on an improved fuzzy C-means clustering algorithm. Background technique [0002] In the actual operation of the distribution network, distribution network reconfiguration is an important optimization method for operation. By controlling the switching status of tie switches and section switches in the network, the goals of reducing network loss and balancing loads are achieved. Under the background that new energy is gradually connected to the distribution network on a large scale, the load of the grid and the output of distributed generation (DG) are always in a time-varying state, and the operation status of the distribution network is relatively complicated. It is difficult to achieve a multi-period distribution network through static reconstruction. Run state optimization. In orde...

AI Technical Summary

Problems solved by technology

However, when the FCM algorithm clusters power data, it only considers the size similarity and does not consider the timing of the data; at the same time, considering the impact of the number of segments on the reconstruction effect, it is necessary to determine the optimal number of time divisions

Images