Load prediction method and device for parking charging of electric vehicle

Abstract

The invention relates to a load prediction method for parking charging of an electric vehicle. The method is characterized by comprising the following steps: step 1, based on relevant parameters of a charging pile and an electric vehicle, calculating a difference value between a parking demand and a parking quantity in each time period of a prediction day, and modifying a driving or parking state of each vehicle according to the difference value; 2, based on the driving or parking state of each vehicle, obtaining the parking duration of each vehicle; 3, updating state parameters of the charging pile and each vehicle in each time period of the prediction day based on the electric quantity drop rate of the electric vehicle, and selecting the corresponding vehicle to be charged based on the state parameters; and 4, obtaining a load curve of the prediction day based on the operation of charging the corresponding vehicle. According to the method, the charging load curve of the electric vehicle within 24 hours can be predicted based on different application scenes so that an effective reference is provided for a power grid.

Description

technical field [0001] The present invention relates to the field of electric power technology, and more specifically, to a load forecasting method and device for electric vehicle parking and charging. Background technique [0002] At present, electric vehicles (EV, Electric Vehicles), as the mainstream development direction of the automobile field in recent years, have the advantages of energy saving and environmental protection, and can effectively alleviate the problems of traditional energy supply shortage and environmental pollution. When large-scale electric vehicles are connected to the grid, the charging behavior of electric vehicles will have an important impact on the grid load. Therefore, it is very necessary to make a reliable prediction of the electric vehicle charging load. [0003] In the prior art, the prediction of electric vehicle charging load is usually affected by factors such as user travel habits, road congestion, and travel purpose. Focusing on the ...

AI Technical Summary

Problems solved by technology

However, in the prior art, for charging stations in parking lots that have been built, the difference between the predicted load and the actual load is large, the accuracy of the predicted load is low, and there is a lack of effective correction feedback in the forecasting algorithm

These problems make the reference value of the forecasting algorithm not high, and cannot meet the needs of the grid for electric vehicle charging load forecasting

Images