Load prediction method for electric vehicle charging station based on copula algorithm

Abstract

A load prediction method for an electric vehicle charging station based on a copula algorithm comprises the following steps of (1) classifying users; (2) classifying and fitting data; (3) extending the data; and (4) outputting a load curve of the electric vehicle charging station. According to the load prediction method for the electric vehicle charging station based on the copula algorithm, the users are firstly classified; a kernel function and a copula function are selected by use of an AIC (Akaike Information Criterion) and a BIC (Bayesian Information Criterion), data are fitted by use ofa kernel density function, extended data including a coupling relation between the data are obtained in combination with the copula algorithm, the extended data can really reflect actual charging behaviors of the users, and an obtained prediction curve better accords with the actual situation.

Description

technical field [0001] The invention belongs to the field of load forecasting of electric vehicle charging stations, and provides a load forecasting method for electric vehicle charging stations according to the scale of a planned and constructed charging station. Background technique [0002] Traditional cars consume a lot of fossil energy, emit a lot of smoke and dust, pollute the environment, and bring great troubles to people's lives. With the rapid development of electric vehicles, electric vehicles have gradually entered people's lives, reducing carbon dioxide emissions and eliminating human dependence on fossil energy. Electric vehicles are a clean and green means of transportation, and have received strong support from the government. The Ministry of Industry and Information Technology predicts that the number of electric vehicles in the country will reach 60 million by 2030. With the popularization of electric vehicles, charging facilities need to be improved urgen...

AI Technical Summary

Problems solved by technology

Based on random number generation to model the overall electric vehicle load, the main algorithm used in this method is the model Carlo model, which makes statistics on the charging laws of different types of electric vehicles, fits the statistical data, and then adopts a curve similar to the fitted curve Random numbers are generated to calculate the charging load. The prediction is a macroscopic prediction, and the prediction accuracy for a single power station is low. Based on the EV spatio-temporal distribution model, this method uses the electric vehicle driving and parking characteristics to establish a prediction model, but the initial charging time of the electric vehicle The SOC at the initial charging time is still based on the model Carlo model. Based on the energy equivalent load model, this model uses the equal load distance distribution method to equate the refueling amount of the car to the charging amount, and use this as data to predict the load of electric vehicles. The method does not take into account the difference in duration and location of refueling and charging, and the short range of electric vehicles

Images