Multi-time scale electric vehicle clustering schedulable capacity prediction method

Abstract

The invention discloses a multi-time scale electric vehicle clustering schedulable capacity prediction method. The method is characterized in that the method includes the following steps: establishing a real-time electric vehicle clustering schedulable capacity prediction model on a distributive parallel big data processing platform, using real-time state data, acquiring the result of real-time electric vehicle clustering schedulable capacity prediction based on the prediction model; based on the result of real-time electric vehicle clustering schedulable capacity prediction and feature data of symptom feature attributes, performing correlation analysis, extracting the feature data and establishing a data set, establishing the parallel big data algorithm on the distributive parallel big data processing platform, using the big data algorithm and the data set to establish the current electric vehicle clustering schedulable capacity prediction model. According to the invention, the method brings the advantages of big data parallel processing into full play, can provide strong data support for grid multi-time scale scheduling, electric vehicle charging and discharging control and gird reliability.

Description

technical field [0001] The invention relates to a method for predicting the schedulable capacity of an electric vehicle cluster, more specifically, a method for predicting the schedulable capacity of an electric vehicle cluster based on big data. Background technique [0002] Electric vehicles have advantages that traditional vehicles cannot match in terms of environmental protection, cleanliness and energy saving. Due to the great randomness of electric vehicle charging, the access of large-scale electric vehicles will have adverse effects on the power grid, including affecting the power quality of the distribution network and increasing the difficulty of control optimization. The development of Vehicle-to-grid (v2g) technology brings new opportunities for large-scale access of electric vehicles. The electric vehicle cluster connected to a certain grid area can be used as a large distributed energy storage system, which can provide various auxiliary support services for th...

AI Technical Summary

Problems solved by technology

[0006] One is the use of probability model prediction method to face the problems of human factor interference and low accuracy of probability model

[0007] The second is that it does not consider multi-time scale power dispatching, and cannot meet the requirements of multi-time scale dispatching of power systems.

[0008] The third is that it does not consider that the data for the calculation and prediction of dispatchable capacity is a big data problem. In order to obtain higher prediction accuracy, the method of using the probability model also needs to conduct research on a large amount of electric vehicle charging data.

Images