Unlock instant, AI-driven research and patent intelligence for your innovation.

Electric vehicle user charging behavior prediction method based on BP neural network

A BP neural network and electric vehicle technology, applied in the field of electric power system, can solve the problems of low reliability and not being able to accurately reflect the charging characteristics of electric vehicles

Pending Publication Date: 2020-06-23
SOUTHEAST UNIV
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Research shows that simulation and classification are not reliable enough to accurately reflect real-world charging characteristics of EVs

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Electric vehicle user charging behavior prediction method based on BP neural network
  • Electric vehicle user charging behavior prediction method based on BP neural network
  • Electric vehicle user charging behavior prediction method based on BP neural network

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0033] Example 1: According to the four dependent variables of the car battery: battery capacity, cruising range, unit power consumption and battery SOC, the charging behavior (charging / not charging) of the user is obtained by using Monte Carlo random sampling to obtain 37607 sets of data.

[0034] A prediction method of charging behavior of electric vehicle users based on BP neural network, its application in Example 1 is as follows:

[0035] Step 1: Data preprocessing.

[0036] Step 2: Determine the training data for the neural network. 30,000 data are randomly selected as training data, and the remaining data are divided into two categories, of which 5,000 data are used as verification data and 2,607 data are used as test data;

[0037] Step 3: Build the neural network architecture.

[0038] Step 4: Select activation function δ(z) and loss function Cost function J(w,b).

[0039] Step 5: Calculate the loss function by forward propagation from the input layer to the hidd...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to an electric vehicle user charging behavior prediction method based on a BP neural network. The method comprises the following steps: step 1, data preprocessing; 2, determiningtraining data, verification data and test data of the neural network; 3, establishing a neural network architecture; 4, selecting an activation function delta (z) and a loss function cost function J(w, b); step 5, calculating a loss function and a cost function J (w, b) through forward propagation from the input layer to the hidden layer; 6, judging whether the calculated loss function meets therequirement for errors or not, if yes, skipping to the step 7, and if not, correcting the offset matrix b of the weight matrix omega by adopting a gradient descent method, and skipping to the step 5,and recalculating by using the newly calculated weight matrix omega; and step 7, using the weight matrix omega offset matrix b obtained by training for testing data, and comparing and evaluating an obtained neural network prediction result with a real result. According to the invention, a considerable and reliable basis is provided for charging behavior prediction.

Description

technical field [0001] The invention belongs to the technical field of power systems, and in particular relates to a method for predicting charging behavior of electric vehicle users based on BP neural network. Background technique [0002] Power system load forecasting is an important basis for distribution network control strategy research. With the development of new energy and electric vehicles, there are more and more variable factors in power load forecasting. Especially the development of electric vehicles today has increased the number of electric vehicle users in my country. Electric vehicles as a A load with strong flexibility and dispatchability, which can absorb energy from the grid and charge it to the grid, which makes the control strategy of the distribution network more complicated. If the charging behavior of electric vehicle users is effectively controlled Forecasting will help to realize peak-shaving and valley-filling of power loads, and ease the power tra...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q50/06G06N3/08
CPCG06Q10/04G06Q50/06G06N3/084
Inventor 谭林林卞正达
Owner SOUTHEAST UNIV