A charging station charging load forecasting method and system

Abstract

The present application discloses a charging load prediction method and system for a charging station. The method includes acquiring historical charging records of a target charging station, screening and preprocessing a charging sample data set, and obtaining the charging duration and charging capacity of each charging record, as well as each charging record. The number of charging vehicles at the charging station in a unit time period; the charging load feature data set is obtained according to the charging time and charging power of each charging record; the number of charging vehicles is obtained according to the number of charging vehicles at the charging station in each unit time period in the charging sample data set. Data set; build and train the charging load prediction model for each unit time period of the charging station according to the time-of-use electricity price, charging load characteristic data set and charging vehicle quantity characteristic data set; Segment charging load forecast. The method based on data law can improve the accuracy and applicability of charging load prediction by forecasting the charging load of a single area charging station.

Description

technical field [0001] The invention belongs to the technical field of load prediction, and relates to a charging load prediction method and system for a charging station. Background technique [0002] At this stage, with the gradual popularization of charging vehicles, charging at charging stations has become one of the main charging methods for residents to drive. As a power load, the charging pile charging load can balance the peak-to-valley difference through effective power dispatching, and increase the power supply utilization rate of grid dispatching. [0003] The traditional charging pile charging load research method is mainly based on the probability model. Typical probability models are: probability average model, Monte Carlo sampling probability model, probability model based on travel statistics, etc. The probability average model uses the idea of ​​probability average to calculate the charging load of discrete points, and considers the probability distributio...

AI Technical Summary

Problems solved by technology

[0004] The above-mentioned traditional charging load forecasting depends on the probability model, and the accuracy of the charging load forecasting depends on the accuracy of the probability statistics, and the charging laws in different regions are not the same, and the traditional model depends on the user habits, battery charging characteristics and other probability models, It has a large randomness, so the traditional probability model is not applicable to the charging load in different regions

Images