CN111179506A - Shared charging pile self-service charging system and shared charging pile recommendation method - Google Patents
Shared charging pile self-service charging system and shared charging pile recommendation method Download PDFInfo
- Publication number
- CN111179506A CN111179506A CN201811332173.8A CN201811332173A CN111179506A CN 111179506 A CN111179506 A CN 111179506A CN 201811332173 A CN201811332173 A CN 201811332173A CN 111179506 A CN111179506 A CN 111179506A
- Authority
- CN
- China
- Prior art keywords
- charging
- shared charging
- shared
- charging pile
- time period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F15/00—Coin-freed apparatus with meter-controlled dispensing of liquid, gas or electricity
- G07F15/003—Coin-freed apparatus with meter-controlled dispensing of liquid, gas or electricity for electricity
- G07F15/005—Coin-freed apparatus with meter-controlled dispensing of liquid, gas or electricity for electricity dispensed for the electrical charging of vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention provides a shared charging pile self-service charging system and a shared charging pile recommendation method.
Description
Technical Field
The invention relates to the technical field of shared services, in particular to a shared charging pile self-service charging system and a shared charging pile recommendation method.
Background
Along with new energy automobile's popularization, it is the indispensable continuation of the journey mode outside new energy automobile to utilize the sharing to fill electric pile to charge, and the car owner can charge through predetermined public charging pile of cell-phone APP usually, and the user pays the charge fee again when the completion charges. Along with new energy automobile to filling electric pile's demand bigger and bigger, to regional electric wire netting, the electric peak of using electricity that a large amount of shares were filled electric pile and are charged simultaneously and cause very big load to the electric wire netting.
Aiming at the problem that a large number of shared charging piles simultaneously charge and cause a large load on a regional power grid in the prior art, technical personnel in the field are always seeking a solution.
Disclosure of Invention
The invention aims to provide a shared charging pile self-service charging system and a shared charging pile recommendation method, and aims to solve the problem that a large load is caused on a regional power grid when a large number of shared charging piles are used for charging simultaneously in the prior art.
In order to solve the technical problem, the invention provides a shared charging pile self-service charging system, and a sharing method of the shared charging pile comprises the following steps:
the shared charging piles are used for providing shared charging service;
the system comprises a user terminal, a server and a server, wherein the user terminal is used for receiving a charging reservation request of a user and a set parking time period and displaying the position of a target shared charging pile fed back by the server, and the parking time period is obtained based on parking starting time and parking ending time; and
the server is connected with the user terminal and used for calculating the charging demand of all parking lots with the shared charging piles in each regional power grid in each time period and taking the parking lot with the shared charging pile with the lowest accumulated value of the charging demand in the parking time period under the current regional power grid as a target parking lot with the shared charging piles; and predicting the charging heat of each shared charging pile in the target parking lot with the shared charging piles in each time period according to a BP neural network, taking the shared charging pile with the lowest charging heat in the parking time period as a target shared charging pile, and feeding back the position of the target shared charging pile to the user terminal.
Optionally, in the shared charging pile self-service charging system, before the server calculates the charging demand of all parking lots with shared charging piles in each regional power grid in each time period, the method includes the following steps:
counting data information of all parking lots with shared charging piles in a city;
abstracting all parking lots with shared charging piles in a city into a connected graph, wherein each node in the connected graph represents a parking lot with the shared charging piles, and the numerical value of each node represents the number of the shared charging piles in the parking lots with the shared charging piles;
and dividing the connected graph into a plurality of sub-graphs according to all regional power grids, wherein each sub-graph corresponds to one regional power grid.
Optionally, in the shared charging pile self-service charging system, the server predicts the charging heat of each shared charging pile in the target shared charging pile parking lot in each time period according to a BP neural network by using the following calculation formula:
in the formula (1), yi(n) is the output value of the nth training neuron i; y isj(n) is the output value of the nth training neuron j, and the neuron i is positioned at the previous layer of the neuron j;
in order to be a function of the excitation,
wij(n) is the correction weight w of the nth trainingij(n) correction amount is Δ wij＝μδj(n)yj(n), μ is a learning rate parameter, δj(n) is the correction weight w of the minimum deviation value epsilon (n)ij(n) a change gradient value, which is selected from the following formula:
in the formula (2), epsilon (n) is the output deviation value of the nth training neuron j; y isj(n) is the output value of the nth training neuron j; djAnd (n) is an ideal output value of the nth training neuron j.
Optionally, in the shared charging pile self-service charging system, the step of predicting, by the server according to the BP neural network, the charging heat of each shared charging pile in the target shared charging pile parking lot in each time period includes:
receiving the charging heat of all the shared charging piles in the target shared charging pile parking lot in each time period;
the charging heat degrees for each period are arranged in an ascending order or a descending order.
Optionally, in the shared charging pile self-service charging system, the server is further configured to periodically correct the charging heat of each shared charging pile.
Optionally, in the shared charging pile self-service charging system, the charging heat of each shared charging pile in a certain time period is the occupied time percentage of the shared charging pile in the time period.
Optionally, in the shared charging pile self-service charging system, the user terminal is further configured to store a plurality of vouchers with different quota, and the lower the accumulated value of the charging demand in the corresponding parking time period under the current regional power grid or the lower the charging heat, the higher the quota of the usable vouchers is.
The invention also provides a recommendation method of the shared charging pile, which adopts the self-service charging system of the shared charging pile, and comprises the following steps:
the method comprises the steps that a user terminal receives a charging reservation request of a user and a set parking time period;
the server calculates the charging demand of all parking lots with the shared charging piles in each regional power grid in each time period, and takes the parking lot with the shared charging piles with the lowest accumulated value of the charging demand in the parking time period under the current regional power grid as a target parking lot with the shared charging piles; predicting the charging heat of each shared charging pile in the target parking lot with the shared charging piles in each time period according to a BP neural network, taking the shared charging pile with the lowest charging heat in the parking time period as a target shared charging pile, and feeding back the position of the target shared charging pile to the user terminal;
and the user terminal displays the position of the target sharing charging pile fed back by the server.
Optionally, in the recommendation method for the shared charging pile, the server predicts the charging heat of each shared charging pile in the target parking lot with the shared charging pile in each time period according to a BP neural network by using the following calculation formula:
in the formula (1), yi(n) is the output value of the nth training neuron i; y isj(n) is the output value of the nth training neuron j, and the neuron i is positioned at the previous layer of the neuron j;
in order to be a function of the excitation,
wij(n) is the correction weight w of the nth trainingij(n) correction amount is Δ wij＝μδj(n)yj(n), μ is a learning rate parameter, δj(n) is the correction weight w of the minimum deviation value epsilon (n)ij(n) a change gradient value, which is selected from the following formula:
in the formula (2), epsilon (n) is the output deviation value of the nth training neuron j; y isj(n) is the output value of the nth training neuron j; djAnd (n) is an ideal output value of the nth training neuron j.
Optionally, in the recommendation method for a shared charging pile, the method further includes:
the user terminal selects available coupons stored in the user terminal according to the numerical value of the charging demand in the corresponding parking time period under the current regional power grid, and the lower the accumulated numerical value of the charging demand or the lower the charging heat degree is, the higher the limit of the available coupons is.
In the shared charging pile self-service charging system and the shared charging pile recommendation method provided by the invention, the shared charging pile recommendation method calculates the charging demand of all parking lots with shared charging piles in each regional power grid in each time period based on the server, and takes the parking lot with the shared charging pile with the lowest accumulated value of the charging demand in the parking time period under the current regional power grid as a target parking lot with the shared charging pile; and predicting the charging heat of each shared charging pile in the target parking lot with the shared charging piles in each time period according to the BP neural network, and taking the shared charging pile with the lowest charging heat in the parking time period as the target shared charging pile. According to the recommendation method of the shared charging piles, the charging heat of each shared charging pile in the current regional power grid is balanced, meanwhile, the power utilization peak is reasonably avoided, the problem that a large number of shared charging piles charge simultaneously to cause a large load on the regional power grid is effectively solved, the user experience is improved, the power utilization cost of a park is reduced, and the problem of power utilization imbalance of power supply enterprises is relieved.
Drawings
Fig. 1 is a schematic diagram of a shared charging pile self-service charging system according to an embodiment of the invention;
fig. 2 is a flowchart of a recommendation method for a shared charging pile according to an embodiment of the present invention.
Detailed Description
The shared charging pile self-service charging system and the shared charging pile recommendation method provided by the invention are further described in detail with reference to the accompanying drawings and specific embodiments. Advantages and features of the present invention will become apparent from the following description and from the claims. It is to be noted that the drawings are in a very simplified form and are not to precise scale, which is merely for the purpose of facilitating and distinctly claiming the embodiments of the present invention.
The present invention will be described in more detail with reference to the accompanying drawings, in order to make the objects and features of the present invention more comprehensible, embodiments thereof will be described in detail below, but the present invention may be implemented in various forms and should not be construed as being limited to the embodiments described.
Please refer to fig. 1, which is a schematic diagram of a shared charging pile self-service charging system according to the present invention. As shown in fig. 1, the shared charging pile self-service charging system includes: the system comprises a plurality of shared charging piles, a user terminal and a server, wherein the plurality of shared charging piles are used for providing shared charging service; the user terminal is used for receiving a charging reservation request of a user and a set parking time period and displaying the position of the target shared charging pile fed back by the server, wherein the parking time period is obtained based on parking starting time and parking ending time; the server is connected with the user terminal and used for calculating the charging demand of all parking lots with the shared charging piles in each regional power grid in each time period and taking the parking lot with the shared charging pile with the lowest accumulated value of the charging demand in the parking time period under the current regional power grid as a target parking lot with the shared charging piles; and predicting the charging heat of each shared charging pile in the target parking lot with the shared charging piles in each time period according to a BP neural network, taking the shared charging pile with the lowest charging heat in the parking time period as a target shared charging pile, and feeding back the position of the target shared charging pile to the user terminal. The charging heat of each shared charging pile in a certain time period is the occupied time percentage of the shared charging pile in the time period.
Preferably, the server can be public clouds such as Ariiyun and Teng-Times cloud, and can also be an I-stack smart city operating system.
Specifically, before the server calculates the charging demand of all parking lots with shared charging piles in each regional power grid in each time period, the method includes the following steps:
counting data information of all parking lots with shared charging piles in a city;
abstracting all parking lots with shared charging piles in a city into a connected graph, wherein each node in the connected graph represents a parking lot with the shared charging piles, and the numerical value of each node represents the number of the shared charging piles in the parking lots with the shared charging piles;
and dividing the connected graph into a plurality of sub-graphs according to all regional power grids, wherein each sub-graph corresponds to one regional power grid.
Further, the step of predicting the charging heat of each shared charging pile in the target shared charging pile parking lot in each time period by the server according to the BP neural network comprises the following steps:
receiving the charging heat of all the shared charging piles in the target shared charging pile parking lot in each time period;
and performing ascending or descending arrangement on the charging heat degree of each time period to determine the shared charging pile with the lowest charging heat degree in the parking time period, so as to determine the target shared charging pile.
Further, the server predicts the charging heat of each shared charging pile in the target parking lot with the shared charging piles in each time period according to a BP neural network by using the following calculation formula:
in the formula (1), yi(n) is the output value of the nth training neuron i; y isj(n) is the output value of the nth training neuron j, and the neuron i is positioned at the previous layer of the neuron j;
in order to be a function of the excitation,
wij(n) is the correction weight w of the nth trainingij(n) correction amount is Δ wij＝μδj(n)yj(n), μ is a learning rate parameter, δj(n) is the correction weight w of the minimum deviation value epsilon (n)ij(n) a change gradient value, which is selected from the following formula:
in the formula (2), epsilon (n) is the output deviation value of the nth training neuron j; y isj(n) is the output value of the nth training neuron j; djAnd (n) is an ideal output value of the nth training neuron j.
In order to avoid that the real-time charging heat degree of each node in the connection graph which is abstractly constructed is greatly different from the expected ideal condition (namely, charging heat degree deviation exists) due to the influence of factors such as weather, faults and the like, aiming at the phenomenon, the charging heat degree of each shared charging pile of the server is periodically corrected, for example, the heat degree is corrected at intervals of time T (such as 4 hours), the charging heat degree deviation is uniformly distributed to the external nodes connected with the nodes in the region, and the accuracy of the charging heat degree of the shared charging piles is improved.
In order to encourage users to charge the shared charging pile according to the target obtained by the server, a plurality of coupons with different limits are stored in the user terminal, and the lower the accumulated value of the charging demand in the corresponding parking time period under the current regional power grid or the lower the charging heat, the higher the limit of the usable coupon is, so that the charging heat of the shared charging pile in the current regional power grid is effectively balanced, and the peak of power utilization is avoided.
Correspondingly, the embodiment also provides a recommendation method for sharing the charging pile. The method for recommending the shared charging pile according to the embodiment is described in detail below with reference to fig. 1 and fig. 2, and specifically includes the following steps:
first, step S1 is executed, and the user terminal receives a charge reservation request from the user and a set parking time period.
Next, step S2 is executed, the server calculates the charging demand of all parking lots with shared charging piles in each regional power grid in each time period, and takes the parking lot with shared charging pile with the lowest accumulated value of the charging demand in the parking time period under the current regional power grid as the target parking lot with shared charging pile; and predicting the charging heat of each shared charging pile in the target parking lot with the shared charging piles in each time period according to a BP neural network, taking the shared charging pile with the lowest charging heat in the parking time period as a target shared charging pile, and feeding back the position of the target shared charging pile to the user terminal.
Next, step S3 is executed, and the user terminal displays the position of the target shared charging pile fed back by the server.
In addition, the recommendation method of the shared charging pile further comprises the following steps:
the user terminal selects available coupons stored in the user terminal according to the numerical value of the charging demand in the corresponding parking time period under the current regional power grid, and the lower the accumulated numerical value of the charging demand or the lower the charging heat degree is, the higher the limit of the available coupons is.
In order to better understand the working principle of the recommendation method for the shared charging pile, the recommendation process is specifically described below.
It is assumed that a user can set two periods, one is a parking period and the other is a charging period (generally, charging takes 3 to 7 hours) by reserving a charging pile through a user terminal. It is understood that the parking period is greater than or equal to the charging period, i.e., | Tce-Tcs | ≦ | Tpe-Tps |, where Tce is the end charging time and Tcs is the start charging time; tps is the start stop time and Tpe is the end stop time. Assuming that charging is completed once (namely, charging time is continuous), the charging time period is a sliding window in the parking time period, so that a user can be guided to set a target shared charging pile in the parking time period, and the purpose of balancing charging heat of multiple charging piles in each time period in the regional power grid is achieved. The realization method is that the charging heat degree of each shared charging pile in the parking period is calculated, the shared charging pile with the lowest charging heat degree is selected as the target shared charging pile, the available coupons are distributed according to the shared charging piles with different charging heat degrees, and the lower the charging heat degree is, the higher the credit of the coupons is. If the user does not select the target shared charging pile to charge the vehicle, the amount of available coupons changes, and the reward is not maximized.
1) Distribution of credit limits
Firstly, counting data information of all parking lots with shared charging piles in a city; secondly, abstracting all parking lots with shared charging piles in the city into a connected graph, wherein each node in the connected graph represents a parking lot with the shared charging piles, and the numerical value of the node represents the number of the shared charging piles in the parking lots with the shared charging piles; then, the connected graph is divided into a plurality of sub-graphs according to all regional power grids, each sub-graph corresponds to one regional power grid, and the charging demand R of all parking lots with the shared charging piles in each period in each regional power grid is calculatedt(ii) a Finally, an accumulated value sigma R of the charging demand in the parking time period is calculatedtThe credit line of the coupon is divided into a plurality of grades, each grade corresponds to a certain demand range, and the smaller the accumulated value of the charging demand is, the larger the credit line of the coupon is.
2) Calculation method of charging demand
The calculation of the charging demand is divided into two steps, and firstly, the 24-hour charging heat degree in one day is independently calculated and predicted for each charging pile in the network. And then, according to the real-time heat data at that time, correcting the predicted value of the heat of the shared charging pile in the regional power grid at intervals of T.
These two parts are described in turn below:
for each charging pile in the network: the BP neural network is used for predicting the charging heat of a plurality of hours in the future in one day, as the parking heat not only has a certain rule every 24 hours, but also has different heat distribution on working days and weekends, a week is divided into four types, namely Monday, Tuesday-Thursday, Friday, Saturday-Sunday, models are respectively built for the four types, and the day type is used as input to realize a universal daily prediction model.
And (3) prediction model:
a three-layer BP neural network model is adopted, the BP neural network comprises an input layer, a hidden layer and an output layer, wherein the hidden layer is provided with 24 nodes, and the output is 24 nodes.
The BP neural network learning comprises two steps:
the method comprises the following steps: in the forward-push (forwortpass) process, the neuron in each layer weights and sums the input signals, then obtains an output value through an excitation function, transmits the output value to the next layer, and directly reaches the output of the final output layer, and is expressed by a formula as follows:
in the formula (1), yi(n) is the output value of the nth training neuron i; y isj(n) is the output value of the nth training neuron j, and the neuron i is positioned at the previous layer of the neuron j;
in order to be a function of the excitation,
wijand (n) is the correction weight of the nth training, and the output layer adopts a linear function.
Step two: in the process of a back-pushing method (backstepass), each training is carried out, an actually obtained output value is compared with an ideal value to obtain a deviation value, wherein an average variance constant deviation value is adopted and is expressed by a formula as follows:
in the formula (2), epsilon (n) is the output deviation value of the nth training neuron j; y isj(n) is the output value of the nth training neuron j; dj(n) is the nth timeThe ideal output value of neuron j is trained.
Correcting weight w layer by layer in reverse direction by calculating deviation value epsilon (n)ij(n), correcting the weight wij(n) correction amount is Δ wij＝μδj(n)yj(n), where μ is a learning rate parameter, δj(n) is the correction weight w of the minimum deviation value epsilon (n)ij(n) the change gradient value, which can be expressed as:
j is neuron of output layer:
j is a neuron in the middle layer (i.e., the hidden layer):
and (4) iterating the BP neural network learning process until the deviation value epsilon (n) is smaller than a certain value, and finishing the BP neural network learning.
Wherein, the input of the prediction model is: 24-hour charging heat data of the previous day and 24-hour charging heat data of the same day of the last week
The inputs to the prediction model are: predicted value of 24-hour parking heat in the same day
Training a prediction model: in order to improve the prediction precision, the prediction model is retrained every day, and forward and backward correction is completed once by adopting each training data learning. Learning in this manner helps to avoid obtaining a locally optimal predictive model.
For the method disclosed by the embodiment, the description is relatively simple because the method corresponds to the system structure disclosed by the embodiment, and the relevant points can be just described by referring to the structural part.
In summary, in the shared charging pile self-service charging system and the shared charging pile recommendation method provided by the invention, the server calculates the charging demand of all parking lots with shared charging piles in each regional power grid in each time period, and the parking lot with the shared charging pile with the lowest accumulated value of the charging demand in the parking time period under the current regional power grid is used as the target parking lot with the shared charging pile; and predicting the charging heat of each shared charging pile in the target parking lot with the shared charging piles in each time period according to the BP neural network, and taking the shared charging pile with the lowest charging heat in the parking time period as the target shared charging pile. According to the recommendation method of the shared charging piles, the charging heat of each shared charging pile in the current regional power grid is balanced, meanwhile, the power utilization peak is reasonably avoided, the problem that a large number of shared charging piles charge simultaneously to cause a large load on the regional power grid is effectively solved, the user experience is improved, the power utilization cost of a park is reduced, and the problem of power utilization imbalance of power supply enterprises is relieved.
The above description is only for the purpose of describing the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention, and any variations and modifications made by those skilled in the art based on the above disclosure are within the scope of the appended claims.
Claims (10)
1. The utility model provides a self-service charging system of shared electric pile that fills which characterized in that includes:
the shared charging piles are used for providing shared charging service;
the system comprises a user terminal, a server and a server, wherein the user terminal is used for receiving a charging reservation request of a user and a set parking time period and displaying the position of a target shared charging pile fed back by the server, and the parking time period is obtained based on parking starting time and parking ending time; and
the server is connected with the user terminal and used for calculating the charging demand of all parking lots with the shared charging piles in each regional power grid in each time period and taking the parking lot with the shared charging pile with the lowest accumulated value of the charging demand in the parking time period under the current regional power grid as a target parking lot with the shared charging piles; and predicting the charging heat of each shared charging pile in the target parking lot with the shared charging piles in each time period according to a BP neural network, taking the shared charging pile with the lowest charging heat in the parking time period as a target shared charging pile, and feeding back the position of the target shared charging pile to the user terminal.
2. The shared charging pile self-service charging system according to claim 1, wherein before the server calculates the charging demand of all parking lots with shared charging piles in each regional power grid in each time period, the method comprises the following steps:
counting data information of all parking lots with shared charging piles in a city;
abstracting all parking lots with shared charging piles in a city into a connected graph, wherein each node in the connected graph represents a parking lot with the shared charging piles, and the numerical value of each node represents the number of the shared charging piles in the parking lots with the shared charging piles;
and dividing the connected graph into a plurality of sub-graphs according to all regional power grids, wherein each sub-graph corresponds to one regional power grid.
3. The self-service charging system of claim 1, wherein the server predicts the charging heat of each shared charging pile in the target shared charging pile parking lot in each time period according to a BP neural network by using the following calculation formula:
in the formula (1), yi(n) is the output value of the nth training neuron i; y isj(n) is the output value of the nth training neuron j, and the neuron i is positioned at the previous layer of the neuron j;
in order to be a function of the excitation,
wij(n) is the correction weight of the nth training, and the correction is carried outPositive weight wij(n) correction amount is awij＝μδj(n)yj(n), μ is a learning rate parameter, δj(n) is the correction weight w of the minimum deviation value epsilon (n)ij(n) a change gradient value, which is selected from the following formula:
in the formula (2), epsilon (n) is the output deviation value of the nth training neuron j; y isj(n) is the output value of the nth training neuron j; djAnd (n) is an ideal output value of the nth training neuron j.
4. The self-service charging system of claim 1, wherein the step of predicting, by the server, the charging heat of each shared charging pile in the target shared charging pile parking lot at each time slot according to the BP neural network comprises the steps of:
receiving the charging heat of all the shared charging piles in the target shared charging pile parking lot in each time period;
the charging heat degrees for each period are arranged in an ascending order or a descending order.
5. The shared charging pile self-service charging system according to claim 4, wherein the server is further configured to periodically correct the charging heat of each shared charging pile.
6. The shared charging post self-service charging system of claim 4, wherein the heat of charge of each shared charging post for a time period is a percentage of time the shared charging post is occupied during the time period.
7. The self-service charging system of claim 1, wherein the user terminal is further configured to store a plurality of coupons with different credit limits, and the lower the accumulated value of the charging demand or the lower the charging heat degree in the corresponding parking time period under the current regional power grid, the higher the credit limit of the available coupons is.
8. A recommendation method for a shared charging pile is characterized in that the self-service charging system for the shared charging pile as claimed in claims 1-7 is adopted, and comprises the following steps:
the method comprises the steps that a user terminal receives a charging reservation request of a user and a set parking time period;
the server calculates the charging demand of all parking lots with the shared charging piles in each regional power grid in each time period, and takes the parking lot with the shared charging piles with the lowest accumulated value of the charging demand in the parking time period under the current regional power grid as a target parking lot with the shared charging piles; predicting the charging heat of each shared charging pile in the target parking lot with the shared charging piles in each time period according to a BP neural network, taking the shared charging pile with the lowest charging heat in the parking time period as a target shared charging pile, and feeding back the position of the target shared charging pile to the user terminal;
and the user terminal displays the position of the target sharing charging pile fed back by the server.
9. The method for recommending a shared charging pile according to claim 8, wherein the server predicts the charging heat of each shared charging pile in the target parking lot with the shared charging pile in each time slot according to a BP neural network by using the following calculation formula:
in the formula (1), yi(n) is the output value of the nth training neuron i; y isj(n) is the output value of the nth training neuron j, and the neuron i is positioned at the previous layer of the neuron j;
in order to be a function of the excitation,
wij(n) is the correction weight w of the nth trainingij(n) correction amount is Δ wij＝μδj(n)yj(n), μ is a learning rate parameter, δj(n) is the correction weight w of the minimum deviation value epsilon (n)ij(n) a change gradient value, which is selected from the following formula:
in the formula (2), epsilon (n) is the output deviation value of the nth training neuron j; y isj(n) is the output value of the nth training neuron j; djAnd (n) is an ideal output value of the nth training neuron j.
10. The method for recommending a shared charging pile according to claim 9, further comprising:
the user terminal selects available coupons stored in the user terminal according to the numerical value of the charging demand in the corresponding parking time period under the current regional power grid, and the lower the accumulated numerical value of the charging demand or the lower the charging heat degree is, the higher the limit of the available coupons is.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811332173.8A CN111179506A (en) | 2018-11-09 | 2018-11-09 | Shared charging pile self-service charging system and shared charging pile recommendation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811332173.8A CN111179506A (en) | 2018-11-09 | 2018-11-09 | Shared charging pile self-service charging system and shared charging pile recommendation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111179506A true CN111179506A (en) | 2020-05-19 |
Family
ID=70649840
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811332173.8A Pending CN111179506A (en) | 2018-11-09 | 2018-11-09 | Shared charging pile self-service charging system and shared charging pile recommendation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111179506A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111967696A (en) * | 2020-10-23 | 2020-11-20 | 北京国新智电新能源科技有限责任公司 | Neural network-based electric vehicle charging demand prediction method, system and device |
| CN111967698A (en) * | 2020-10-23 | 2020-11-20 | 北京国新智电新能源科技有限责任公司 | Electric automobile charging system and device based on mobile charging pile scheduling |
| CN113159907A (en) * | 2021-05-22 | 2021-07-23 | 重庆紫微星新能源科技有限公司 | Method and device for sharing private pile, computer equipment and storage medium |
| CN113505149A (en) * | 2021-07-21 | 2021-10-15 | 车主邦（北京）科技有限公司 | Charging station recommendation method, server, medium and computer equipment |
| WO2022036675A1 (en) * | 2020-08-21 | 2022-02-24 | 深圳市华思旭科技有限公司 | Shared charger cabinet and ejection control method therefor |
| CN114913611A (en) * | 2022-04-07 | 2022-08-16 | 杭州炬华科技股份有限公司 | Electric automobile charging and parking management linkage system and method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103241130A (en) * | 2013-04-10 | 2013-08-14 | 华中科技大学 | Energy management method and system for electric bus charging and swap station |
| US20140129139A1 (en) * | 2012-11-07 | 2014-05-08 | Intertrust Technologies Corporation | Vehicle charging path optimization systems and methods |
| CN105205561A (en) * | 2015-09-25 | 2015-12-30 | 东南大学 | Expressway charging station real-time interaction electricity price setting method based on mobile energy carrying |
| CN107194487A (en) * | 2017-07-20 | 2017-09-22 | 万帮充电设备有限公司 | Charging pile sharing method, device and shared platform |
| CN108182483A (en) * | 2017-11-23 | 2018-06-19 | 南京邮电大学 | Extensive electric vehicle charging schedule system and its optimization method based on secondary cluster |
| CN108458716A (en) * | 2018-02-02 | 2018-08-28 | 北京交通大学 | A kind of electric vehicle charging air navigation aid based on the prediction of charging pile dynamic occupancy |
-
2018
- 2018-11-09 CN CN201811332173.8A patent/CN111179506A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140129139A1 (en) * | 2012-11-07 | 2014-05-08 | Intertrust Technologies Corporation | Vehicle charging path optimization systems and methods |
| CN103241130A (en) * | 2013-04-10 | 2013-08-14 | 华中科技大学 | Energy management method and system for electric bus charging and swap station |
| CN105205561A (en) * | 2015-09-25 | 2015-12-30 | 东南大学 | Expressway charging station real-time interaction electricity price setting method based on mobile energy carrying |
| CN107194487A (en) * | 2017-07-20 | 2017-09-22 | 万帮充电设备有限公司 | Charging pile sharing method, device and shared platform |
| CN108182483A (en) * | 2017-11-23 | 2018-06-19 | 南京邮电大学 | Extensive electric vehicle charging schedule system and its optimization method based on secondary cluster |
| CN108458716A (en) * | 2018-02-02 | 2018-08-28 | 北京交通大学 | A kind of electric vehicle charging air navigation aid based on the prediction of charging pile dynamic occupancy |
Non-Patent Citations (1)
| Title |
|---|
| 刘超: "《集中式电动汽车充电站站内通信***研究与实现》", 《集中式电动汽车充电站站内通信***研究与实现》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022036675A1 (en) * | 2020-08-21 | 2022-02-24 | 深圳市华思旭科技有限公司 | Shared charger cabinet and ejection control method therefor |
| CN111967696A (en) * | 2020-10-23 | 2020-11-20 | 北京国新智电新能源科技有限责任公司 | Neural network-based electric vehicle charging demand prediction method, system and device |
| CN111967698A (en) * | 2020-10-23 | 2020-11-20 | 北京国新智电新能源科技有限责任公司 | Electric automobile charging system and device based on mobile charging pile scheduling |
| CN111967696B (en) * | 2020-10-23 | 2021-01-29 | 北京国新智电新能源科技有限责任公司 | Neural network-based electric vehicle charging demand prediction method, system and device |
| CN113159907A (en) * | 2021-05-22 | 2021-07-23 | 重庆紫微星新能源科技有限公司 | Method and device for sharing private pile, computer equipment and storage medium |
| CN113159907B (en) * | 2021-05-22 | 2024-02-13 | 重庆紫微星新能源科技有限公司 | Private pile sharing method and device, computer equipment and storage medium |
| CN113505149A (en) * | 2021-07-21 | 2021-10-15 | 车主邦（北京）科技有限公司 | Charging station recommendation method, server, medium and computer equipment |
| CN113505149B (en) * | 2021-07-21 | 2024-05-31 | 浙江安吉智电控股有限公司 | Charging station recommending method, server, medium and computer equipment |
| CN114913611A (en) * | 2022-04-07 | 2022-08-16 | 杭州炬华科技股份有限公司 | Electric automobile charging and parking management linkage system and method |
| CN114913611B (en) * | 2022-04-07 | 2024-04-16 | 杭州炬华科技股份有限公司 | Electric automobile charging and parking management linkage system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111179506A (en) | Shared charging pile self-service charging system and shared charging pile recommendation method | |
| Wang et al. | A scenario-based stochastic optimization model for charging scheduling of electric vehicles under uncertainties of vehicle availability and charging demand | |
| CN109177802B (en) | Electric automobile ordered charging system and method based on wireless communication | |
| CN106469926B (en) | Consider to be that electric vehicle automatically selects charge routine by balance utility program and user | |
| US20190041886A1 (en) | Method and system for scheduling the discharge of distributed power storage devices and for levelizing dispatch participation | |
| CN108688503B (en) | Electric vehicle user charging selection auxiliary decision-making method considering output resistor plug | |
| He et al. | Optimal scheduling for charging and discharging of electric vehicles | |
| Goebel et al. | Using ICT-controlled plug-in electric vehicles to supply grid regulation in California at different renewable integration levels | |
| CN110774929A (en) | Real-time control strategy and optimization method for orderly charging of electric automobile | |
| JP5511924B2 (en) | Charge control device | |
| Erden et al. | Adaptive V2G peak shaving and smart charging control for grid integration of PEVs | |
| CN108458716A (en) | A kind of electric vehicle charging air navigation aid based on the prediction of charging pile dynamic occupancy | |
| DE112014002012T5 (en) | Electric Vehicle Management System | |
| CN106204937A (en) | The car rental cost of a kind of ladder valuation calculates system and method | |
| CN112101637B (en) | Dynamic charging optimization method based on time-of-use electricity price and energy consumption control and application thereof | |
| CN115345451A (en) | Electric vehicle charging guiding method based on charging station recommendation strategy | |
| CN112507506A (en) | Multi-objective optimization method for sharing automobile pricing planning model based on genetic algorithm | |
| Wang et al. | Towards accessible shared autonomous electric mobility with dynamic deadlines | |
| CN112602247A (en) | A method for controlling energy exchange between energy subsystems under equilibrium conditions; a control center; an energy system; computer program and storage medium | |
| Karbasioun et al. | Optimal charging strategies for electrical vehicles under real time pricing | |
| McClone et al. | Hybrid Machine Learning Forecasting for Online MPC of Work Place Electric Vehicle Charging | |
| CN110048421B (en) | Energy storage device capacity selection method and device | |
| Helmus et al. | SEVA: A data driven model of electric vehicle charging behavior | |
| Guo et al. | Analyzing the impacts of Plug-in EVs on the California power grid using quadratic programming and fixed-point iteration | |
| Soares et al. | Assessment of real-time tariffs for electric vehicles in denmark |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200519 |