Improved active power distribution network large-scale scene analysis method

Abstract

The invention relates to an improved active power distribution network large-scale scene analysis method, and the method comprises the following steps: obtaining historical data which comprises wind power data, photovoltaic data and load data; generating a large number of scenes on the basis of the probability density distribution function of the wind power data, the photovoltaic data and the load data; and taking the maximum ratio LS of the inter-class distance L1 to the intra-class distance L2 as a selection basis of a k value, and performing scene reduction on the generated scene by using a k-means clustering algorithm to obtain a typical planning scene. Compared with the prior art, the method has the advantages that the scene reduction part is improved, and the optimal value of the k value is found according to the ratio LS of the inter-class distance L1 to the intra-class distance L2, so that the optimal clustering number can be obtained, the classification effect can be guaranteed, and the integrating degree with original data can also be guaranteed.

Description

technical field [0001] The invention relates to the field of distribution networks, in particular to an improved method for analyzing large-scale scenarios of active distribution networks. Background technique [0002] Energy is an indispensable part of human survival and social development. With the continuous growth of power demand, the deepening of traditional energy shortages and the increasingly prominent environmental problems, distributed generation (DG, Distributed Generation) In particular, the development of renewable energy generation technologies has received broad support. Active distribution network (Active Distribution Network, ADN) is an effective solution for future intelligent distribution network to realize active management of a large number of distributed power sources because of its flexibility, compatibility and optimization. However, the access of a large number of distributed power sources will increase the complexity and uncertainty of distribution...

AI Technical Summary

Problems solved by technology

Each iteration of the hierarchical clustering algorithm needs to calculate the minimum distance between layers, which requires a large amount of calculation. When the number of scenes is large, the calculation time is too long and the efficiency is reduced.

When the fuzzy clustering algorithm performs scene reduction, it needs to establish a storage membership matrix, which requires iterative calculations. When the number of scenes is large, the computational complexity increases, and the exact set after clustering cannot be obtained

Although the commonly used partition clustering algorithm K-Means clustering algorithm has high performance advantages, its disadvantage is that the selection of the initial centroid is too random, which often leads to unstable clustering results and low clustering accuracy.

Images