Unbalanced load data type identification method based on VAE preprocessing and RP-2DCNN

Abstract

The invention provides an unbalanced load data type identification method based on VAE preprocessing and RP-2DCNN. The method comprises the following steps: step 1, acquiring load data; step 2, preprocessing the load data; step 3, carrying out balance processing on the minority class of load data by using a variational auto-encoder; 4, converting the load data into a two-dimensional recurrence plot without a threshold value by using a recurrence plot algorithm; and 5, establishing a two-dimensional convolutional neural network, training and optimizing the two-dimensional convolutional neural network to obtain a load data type identification model, and inputting the recurrence plot into the load data type identification model to obtain a classification result of the load data.

Description

technical field [0001] The invention belongs to the field of classification and identification of electric loads, and in particular relates to a method for identifying unbalanced load data types based on VAE preprocessing and RP-2DCNN. Background technique [0002] In recent years, with the rapid development of the intelligentization of the power Internet of Things, more and more advanced measurement systems have been put into operation, resulting in the accumulation of a large amount of user electricity consumption data. Mining and extracting valuable potential information from massive load data, researching reasonable and effective load classification algorithms, is conducive to formulating personalized power consumption strategies, and is of great significance for rational regulation of power resources, improving energy utilization, and improving economic benefits of enterprises . [0003] Currently, load classification methods can be divided into unsupervised clustering...

AI Technical Summary

Problems solved by technology

Unsupervised clustering is to divide the data according to the specified rules under the labels of unknown samples. However, this method has problems such as complex parameter adjustment and data sensitivity.

With the rapid growth of load data, unsupervised clustering often requires a lot of running time and wastes some of the labeled data, which is difficult to meet the needs of rapid classification under the background of massive load data

[0004] The supervised classification method can effectively balance the classification speed and classification accuracy, but it will be affected by the imbalance of data categories during the training process, which will lead to poor classification results.

In addition, most of the existing classifiers start from the perspective of sequences, and it is difficult to extract their deep features, which affects the final load identification results.

Images