Electrical load classification algorithm based on small samples

Abstract

The invention provides an electrical load classification algorithm based on small samples, which comprises the following steps: firstly, extracting features of different non-stable change load samples and preprocessing the features, then, expanding and evaluating the features through network training, then, carrying out mixed training on simplified data by adopting mixed training of a K proximity algorithm, a support vector machine and a decision tree, and finally, adjusting the weight of each algorithm on the classification result precision through a weighted optimization mode, carrying out evaluation, and when the classification precision of the hybrid model meets the condition, carrying out actual sample testing. The electrical load classification algorithm has the following advantages that 1, an original sample has good representativeness and general applicability; 2, the consistency of samples is expanded before and after expansion; and 3, by adopting a hybrid classifier and a weighting mode, the limitation of a single algorithm can be overcome.

Description

technical field [0001] The invention relates to an electric load classification algorithm, in particular to an electric load classification algorithm based on small samples. Background technique [0002] With the large-scale integration of clean energy such as wind power and photovoltaics in the power system and the large-scale use of electric vehicles, the power load components of the power system are becoming more and more complex. Analyzing them will help grid personnel formulate a reasonable plan based on the law of power load. Once the classification of electricity load is not clear, it will cause errors in load forecasting of the power sector and chaotic power system scheduling, and will destroy the laws of the power marketing market, resulting in huge economic losses. Therefore, it is of great significance to carry out the research on the classification of power consumption load in the power system. [0003] At present, the classification of electricity load is analy...

AI Technical Summary

Problems solved by technology

[0004] The present invention mainly solves the technical problems existing in the prior art: a sample expansion algorithm is provided, which expands a small number of power load samples showing non-stationary changes, and solves the problem of unbalanced sample distribution

Images