Urban charging network point planning method for high-elasticity power grid based on LSTM and IQPSO

A high-elasticity, power grid technology, applied in neural learning methods, electrical digital data processing, biological neural network models, etc., can solve problems such as idle charging piles, difficult to determine optimization goals, and complex constraints, so as to reduce interference and promote collaboration The effect of development

Pending Publication Date: 2021-05-11
ZHEJIANG ZHONGXIN POWER ENG CONSTR CO LTD +1
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the continuous expansion of the electric vehicle and charging infrastructure market and the country's policy of vigorously developing new energy vehicles, the number of electric vehicle users continues to increase, and the user's demand for electric vehicle charging services also increases; on the one hand, the current construction of charging outlets Lack of basis, uneven layout, and unscientific site selection have led to extremely serious contradictions between supply and demand, that is, there are "multiple idle piles" with extremely low utilization rates of some charging outlets and "difficult to find one pile" of some charging outlets On the other hand, there are many decision-making factors and complex constraints in the location selection of charging sites, which makes it difficult to determine the optimization goal. Therefore, how to scientifically plan and manage charging sites is an urgent problem to be solved
[0003] First of all, the existing planning method simply predicts the future charging demand and then selects the location and capacity of the outlets, which will lead to the failure of the planned outlets to meet the future charging demand, or the excessive number of charging piles will lead to idle charging piles, or The lack of quantity leads to the inability to meet the charging needs; secondly, the traditional network planning mainly starts from the convenience of electric vehicle users or the benefits of charging service providers, and does not fully consider the comprehensive costs of users, enterprises and power grids, resulting in comprehensive social benefits. Low; finally, the current planning method does not fully consider the construction of the highly elastic power grid. As a new type of load, urban electric vehicles will have a significant impact on the power grid, and the existing methods cannot effectively provide guidance for the construction of the power grid according to the planned network points.

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
  • Urban charging network point planning method for high-elasticity power grid based on LSTM and IQPSO
  • Urban charging network point planning method for high-elasticity power grid based on LSTM and IQPSO
  • Urban charging network point planning method for high-elasticity power grid based on LSTM and IQPSO

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] refer to Figure 1 ~ Figure 3 , for the first embodiment of the present invention, provides a kind of based on LSTM ((Long Short-Term Memory, is a kind of time recurrent neural network) and IQPSO (quantum particle swarm optimization)

[0033] Urban charging network planning methods for highly resilient grids, including:

[0034] S1: Collect the user's driving trajectory in the area to be planned, the location and load rate of the power grid switch station, and the price data of the reserved plots, and perform the second preprocessing. refer to figure 2 , where it should be noted that before the second preprocessing also includes:

[0035] Collect the historical charging load, population density, and electric vehicle ownership data of the area to be planned, and perform the first preprocessing and serialization;

[0036] The long-short-term memory network is constructed based on the attention mechanism, and the first preprocessed data is used as the input data of the...

Embodiment 2

[0068] In order to verify the technical effects adopted in the method of the present invention better, in the present embodiment, the traditional antlion algorithm is selected to carry out comparative tests with the method of the present invention, and the test results are compared with the means of scientific demonstration to verify the method of the present invention the real effect it has.

[0069] The traditional antlion algorithm cannot reduce the interference of local fluctuation data on the overall prediction effect of the algorithm, cannot flexibly capture the relationship between global and local data, and has high comprehensive costs for power grids, enterprises and users. Further, it is highly flexible for the future The urban charging network planning of the power grid cannot be accurately predicted. In order to verify that the method of the present invention has better anti-interference performance, flexibility, prediction accuracy, optimization and lower cost than...

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 discloses an urban charging network point planning method for a high-elasticity power grid based on LSTM and IQPSO, and the method comprises the steps of collecting the user driving track, the power grid switching station position and load rate, and reserve plot price data of a to-be-planned region, and carrying out the second preprocessing; taking the data after the second preprocessing and the predicted charging demand as input values of a multi-objective optimization function, and determining a coefficient weight of the multi-objective optimization function in combination with an AHP strategy; solving a global optimal solution of the multi-objective optimization function by using a quantum particle swarm optimization strategy to obtain an optimal planning position of the charging network point; and performing scoring according to the optimization function of the optimal planning position, and distributing the predicted charging load capacity to each planning branch to obtain the optimal planning position and the corresponding capacity of the charging branch. According to the invention, the interference of local fluctuation data on the overall prediction effect of the algorithm is reduced, and the relationship between global data and local data is captured more quickly and flexibly.

Description

technical field [0001] The present invention relates to the technical field of power grid, deep learning and optimization, in particular to a planning method for urban charging network based on LSTM and IQPSO oriented to highly elastic power grid. Background technique [0002] With the continuous expansion of the electric vehicle and charging infrastructure market and the country's policy of vigorously developing new energy vehicles, the number of electric vehicle users continues to increase, and the user's demand for electric vehicle charging services also increases; on the one hand, the current construction of charging outlets Lack of basis, uneven layout, and unscientific site selection have led to extremely serious contradictions between supply and demand, that is, there are "multiple idle piles" with extremely low utilization rates of some charging outlets and "difficult to find one pile" of some charging outlets On the other hand, there are many decision-making factors...

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 & AuthorityApplications(China)
IPC IPC(8): G06F30/27G06Q10/04G06Q10/06G06Q50/06G06N3/00G06N3/04G06N3/08G06F111/06G06F113/04
CPCG06F30/27G06Q10/04G06Q10/06393G06Q50/06G06N3/006G06N3/049G06N3/08G06F2111/06G06F2113/04Y04S10/50
Inventor余彬刘琳林桢雨范华朱铁铭卜家俊翁利国李建斌楼冯梁朱双双俞蓉张凯张阳辉罗曼沈阳
OwnerZHEJIANG ZHONGXIN POWER ENG CONSTR CO LTD