Using k-means clustering algorithm to predict and calculate the line loss rate in the station area

Abstract

The invention discloses a method for predicting and calculating the line loss rate of the station area by using the K-means clustering algorithm, which includes: step 1, selecting the active power supply amount X 1 , reactive power supply X 2 , total length of power supply line X 3 , power supply radius X 4 and total line resistance X 5 As an electrical characteristic parameter; Step 2, standardize the original data of the electrical characteristic parameter; Step 3, establish the performance index function PI (i) of the station area through the electrical characteristic parameter, select the initial cluster center point and the cluster number K; Step 4, utilize the improved K-means clustering algorithm to predict the line loss rate of the station area; the index function that the present invention utilizes the electrical characteristic parameter of the station area to establish, as the principle of cluster analysis to judge the initial cluster center, improves the clustering The accuracy of the cluster results; and changed the original clustering method algorithm, which not only provides reasonable sample data for the prediction and calculation of the line loss rate in the station area, but also makes the prediction result of the line loss rate more accurate, and improves the calculation speed at the same time.

Description

Technical field: [0001] The invention belongs to the line loss prediction technology of station area, in particular to a method for predicting and calculating the line loss rate of station area by using K-means clustering algorithm. Background technique [0002] Line loss rate is an important economic and technical indicator for comprehensively evaluating the planning and design, production operation, technical management, and operation level of the power system, and it is also an important content for evaluating the management of the power sector. However, due to the characteristics of large scale, many nodes, long lines and wide area in China's distribution network, the power loss of low-voltage distribution network accounts for about 40% of the entire power network loss, and it is urgent to solve the problem of line loss. Therefore, the accurate and simple line loss calculation and analysis method has important guiding significance for the actual management work. It is be...

AI Technical Summary

Problems solved by technology

Zou Yunfeng and others published "Research on the Reasonable Line Loss Prediction Model Based on Data Mining Technology" in the Journal of Power Demand Side Management. In this paper, the initial clustering centers of the K-means clustering algorithm are randomly generated, and the clustering results have randomness, imprecise

Images