Accurate classification method of zone area load based on fuzzy C-means clustering analysis

Abstract

The invention discloses an accurate classification method of the zone area load based on fuzzy C-means clustering analysis. The method comprises steps of S1: selecting a 48-point load curve of one day which is usual to carry out preprocessing; S2: using the FCM clustering algorithm to realize the division of the zone area and adopting the cluster validity function P '(U; c) to determine the best result of load classification; and S3, determining the typical daily load curve of each type of the load and the zone area included in its classification. In the accurate classification method of the zone area load based on fuzzy C-means clustering analysis, based on the comparative analysis of a variety of clustering effectiveness functions, the most suitable one is selected to judge the load classification result, furthermore, the key load eigenvectors are extracted from the user daily load curve of the actual measurement, and the cluster analysis is carried out by using the fuzzy C-means clustering algorithm to ensure a high consistency among the loads classified into the same category.

Description

technical field [0001] The invention relates to the technical field of load classification, in particular to a method for accurately classifying station area loads based on fuzzy C-means cluster analysis. Background technique [0002] Load classification is of great significance to the economic analysis, operation and planning of the power system, especially with the continuous development of the power market and the wide application of power demand side management technology, load classification has become an important part of power price formulation, load forecasting, system planning, An important basis for work such as load modeling. The traditional load classification method in the power supply department is often based on the characteristics of users' economic activities, which has a certain degree of subjectivity. Due to the influence of factors such as equipment composition and living habits, the load characteristics of users with the same economic activity character...

AI Technical Summary

Problems solved by technology

[0003] At present, many studies use the gray relational clustering method. This method can accurately extract the common essential characteristics of similar loads. It is not only effective for the classification and synthesis of basic characteristic quantities based on the proportion of substation loads, but also can be extended to typical users in the industry. Screening can also be applied to the classification and synthesis of load dynamic characteristics based on measurement, but this algorithm has a large amount of calculation; some people use the Ward method, and the determination of the final cluster number of this method needs to be selected according to the results and experience; the density gradient algorithm It can identify classes of arbitrary shapes, but it cannot guarantee the impact of different disturbance intensities on clustering results; many people classify user loads and use fuzzy clustering algorithms, which are sensitive to isolated points and can identify For samples with particularity, the maximum and minimum distance can be used as a similarity measure for cluster analysis; or the neural network can be used for cluster analysis to obtain various typical load curves, and then the total load curve can be obtained by superimposing the typical load curves

Images