Electric vehicle charging load prediction method based on ammeter data

Abstract

The invention discloses an electric vehicle charging load prediction method based on ammeter data, and mainly solves the problem that the existing prediction method needs a large amount of information such as traffic flow and position. The method comprises the following steps: (S1) acquiring a charging load of an electric vehicle of a user according to collected electric meter data of the residential user; (S2) input feature selection: according to the identification result of the charging load of the electric vehicle, combining with the total power data of the intelligent electric meter to serve as input data of a prediction network to be constructed; (S3) constructing a prediction network: mining an incidence relation of input data by using CNN-LSTM to obtain an important feature vector, and adding the feature vector into a Dropout layer to prevent overfitting; (S4) outputting a charging load prediction result of the electric vehicle and a total power prediction result of the intelligent electric meter; and (S5) updating the prediction network in a rolling manner. The method can effectively improve the prediction precision, the data type required for prediction is only household electric meter data and is easy to obtain, load density, distribution and the like do not need to be taken, and the operation is simple and convenient.

Description

technical field [0001] The invention belongs to the technical field of electric vehicle charging, and in particular relates to a method for predicting electric vehicle charging load based on electric meter data. Background technique [0002] With the "Double Carbon" goal and the requirements of the new energy vehicle industry development plan, user-side electric vehicles are showing a trend of large-scale growth, and large-scale electric vehicle disorderly charging will lead to an increase in peak load demand, overloading of primary equipment, and Problems such as unbalanced three-phase power seriously affect the safe and stable operation of the power grid. However, the charging behavior of home users is highly subjective, and it is difficult to determine the charging needs of home electric vehicle users. Therefore, it is necessary to explore the charging load forecasting method of household users in order to formulate corresponding demand response strategies and guide thei...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for forecasting electric vehicle charging load based on electric meter data, which mainly solves the problem that existing forecasting methods require a large amount of information such as traffic flow and location and need to simulate user travel and charging process

Images