1. A charging area charging margin evaluation method is characterized by comprising the following steps:

acquiring historical power information of a charging area where a charging pile to be evaluated is located;

training a power prediction model according to the historical power information, and acquiring the total conventional power consumption of the charging area predicted and output by the power prediction model;

and calculating the estimated power supply allowance of the charging area according to the maximum power of the charging area and the total conventional power consumption.

2. The method for evaluating the charging area charge allowance according to claim 1, wherein before obtaining the historical power information of the charging area where the charging pile to be evaluated is located, the method further comprises:

receiving a charging allowance evaluation request, wherein the charging allowance evaluation request is generated based on selection trigger of a user on a to-be-evaluated charging pile in candidate charging piles, and the charging allowance evaluation comprises position information of the to-be-evaluated charging pile.

3. The method according to claim 1, wherein the power prediction model is trained according to loop specific power data in the historical power information, and the power prediction model is tested according to power data in the historical power information.

4. The method for estimating charging area remaining charge according to claim 3, wherein the training of a power prediction model according to the historical power information and the obtaining of the total regular power consumption of the charging area predicted and output by the power prediction model comprise:

performing the current round of training of the power prediction model according to the ring ratio power data in the historical power information;

acquiring a power prediction model of the current round, and predicting the output quasi-total conventional power consumption of the charging area based on the ring ratio power data;

randomly acquiring power data with the same ratio in the historical power information, and taking the power data as the total conventional power consumption for testing the charging area;

calculating the fitting degree of a power prediction model of the current round according to the quasi-total conventional power consumption and the test total conventional power consumption;

judging whether the fitting degree of the power prediction model of the current round is within a set fitting range;

if yes, determining the total conventional power consumption based on the quasi-total conventional power consumption;

and if not, executing the next round of training of the power prediction model according to the ring ratio power data in the historical power information.

5. The charging region charge headroom evaluation method of claim 4, wherein the power prediction model comprises a plurality of regression models, each having different time properties,

training each regression model according to ring ratio power data with corresponding time attributes in the historical power information to obtain quasi-total conventional power consumption of the charging area predicted and output by each regression model;

randomly acquiring the power data with the same proportion and corresponding to the time attribute in the historical power information to be used as the total conventional power consumption for testing each regression model;

the step of judging whether the fitting degree of the power prediction model of the current round is within a set fitting range comprises the following steps: judging whether the fitting degrees of all the regression models of the current round are all within a set fitting range;

if so, the determining the total regular electricity consumption power based on the quasi-total regular electricity consumption power comprises: and carrying out weighted average on the quasi-total normal power consumption of each regression model to obtain the total normal power consumption.

6. The method of estimating the charging area remaining charge according to claim 5, further comprising, if the degree of fit of the regression model for the current round is not within the set fitting range:

and adjusting the weight of the regression model, wherein the weight of the regression model is inversely related to the fitting degree of the regression model.

7. The charging region charging margin evaluation method according to claim 1, further comprising:

acquiring the total number of idle charging piles and the power of a single charging pile in a charging area where the charging pile to be evaluated is located;

calculating total power data of the idle charging piles in the charging area according to the total number of the idle charging piles in the charging area and the power of each charging pile;

taking the total power data of the idle charging piles in the charging area and the data with smaller value in the estimated power supply allowance of the charging area as reference allowances;

and calculating the charging residual amount information of the charging area according to the reference residual amount.

8. The charging area charge remaining amount evaluation method according to claim 7, wherein the charge remaining amount information is a ratio of the reference remaining amount to the individual charging post power.

9. The method for evaluating the charging surplus of a charging area according to any one of claims 1 to 8, wherein the historical power information of the charging area where the charging pile to be evaluated is located is obtained from a network element device on a door side of a circuit part.

10. The method according to any one of claims 1 to 8, wherein the power prediction model predicts and outputs a total regular power consumption at a time when a user is expected to reach the charging post to be evaluated.

11. A charging area charge remaining amount evaluation system, comprising:

the acquisition module is configured to acquire historical power information of a charging area where the charging pile to be evaluated is located;

the power prediction module is configured to train a power prediction model according to the historical power information and acquire the total conventional electricity utilization power of the charging area predicted and output by the power prediction model;

a margin estimation module configured to calculate an estimated power supply margin for the charging area based on the maximum power of the charging area and the total regular power usage.

12. A charging area charging remaining amount evaluation device characterized by comprising:

a processor;

a memory having stored therein executable instructions of the processor;

wherein the processor is configured to perform the steps of the charging area charge balance assessment method of any one of claims 1 to 10 via execution of the executable instructions.

13. A computer-readable storage medium storing a program which, when executed, implements the steps of the charging area charge remaining amount evaluation method of any one of claims 1 to 10.

Background

At present, a charging pile management system is a system which takes a charging manufacturer or a manager in a charging area as a service object and aims at managing and controlling charging behaviors of users. However, how to predict the estimated power supply margin by combining the historical power information of the charging area is an urgent technical problem to be solved by those skilled in the art.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the invention and therefore may include information that does not constitute prior art that is already known to a person of ordinary skill in the art.

Disclosure of Invention

In view of the problems in the prior art, an object of the present invention is to provide a method, a system, a device and a storage medium for estimating a charging margin of a charging area, which overcome the difficulties in the prior art and perform a prediction for estimating a power supply margin by combining historical power information of the charging area.

The embodiment of the invention provides a charging area charging allowance evaluation method, which comprises the following steps:

acquiring historical power information of a charging area where a charging pile to be evaluated is located;

training a power prediction model according to the historical power information, and acquiring the total conventional power consumption of the charging area predicted and output by the power prediction model;

and calculating the estimated power supply allowance of the charging area according to the maximum power of the charging area and the total conventional power consumption.

In some embodiments of the present invention, before obtaining the historical power information of the charging area where the charging pile to be evaluated is located, the method further includes:

receiving a charging allowance evaluation request, wherein the charging allowance evaluation request is generated based on selection trigger of a user on a to-be-evaluated charging pile in candidate charging piles, and the charging allowance evaluation comprises position information of the to-be-evaluated charging pile.

In some embodiments of the present invention, the power prediction model is trained according to the loop specific power data in the historical power information, and the power prediction model is tested according to the power data in the historical power information.

In some embodiments of the present invention, the training a power prediction model according to the historical power information, and obtaining the total regular power consumption of the charging area predicted and output by the power prediction model includes:

performing the current round of training of the power prediction model according to the ring ratio power data in the historical power information;

acquiring a power prediction model of the current round, and predicting the output quasi-total conventional power consumption of the charging area based on the ring ratio power data;

randomly acquiring the power data with the same ratio in the historical power information as the total conventional power consumption for testing the charging area;

calculating the fitting degree of a power prediction model of the current round according to the quasi-total conventional power consumption and the test total conventional power consumption;

judging whether the fitting degree of the power prediction model of the current round is within a set fitting range;

if yes, determining the total conventional power consumption based on the quasi-total conventional power consumption;

and if not, executing the next round of training of the power prediction model according to the ring ratio power data in the historical power information.

In some embodiments of the invention, the power prediction model comprises a plurality of regression models, each regression model having different time attributes,

training each regression model according to ring ratio power data with corresponding time attributes in the historical power information to obtain quasi-total conventional power consumption of the charging area predicted and output by each regression model;

randomly acquiring the power data with the same proportion and corresponding to the time attribute in the historical power information to be used as the total conventional power consumption for testing each regression model;

the step of judging whether the fitting degree of the power prediction model of the current round is within a set fitting range comprises the following steps: judging whether the fitting degrees of all the regression models of the current round are all within a set fitting range;

if so, the determining the total regular electricity consumption power based on the quasi-total regular electricity consumption power comprises: and carrying out weighted average on the quasi-total normal power consumption of each regression model to obtain the total normal power consumption.

In some embodiments of the present invention, if the fitting degree of the regression model in the current round is not within the set fitting range, the method further includes:

and adjusting the weight of the regression model, wherein the weight of the regression model is inversely related to the fitting degree of the regression model.

In some embodiments of the invention, further comprising:

acquiring the total number of idle charging piles and the power of a single charging pile in a charging area where the charging pile to be evaluated is located;

calculating total power data of the idle charging piles in the charging area according to the total number of the idle charging piles in the charging area and the power of each charging pile;

taking the total power data of the idle charging piles in the charging area and the data with smaller value in the estimated power supply allowance of the charging area as reference allowances;

and calculating the charging residual amount information of the charging area according to the reference residual amount.

In some embodiments of the invention, the charging headroom information is a ratio of the reference headroom to the individual charging post power.

In some embodiments of the present invention, the historical power information of the charging area where the charging pile to be evaluated is located is obtained from a network element device on a door side of a circuit part.

In some embodiments of the invention, the power prediction model predicts and outputs the total regular power consumption at the time when the user is expected to reach the charging pile to be evaluated.

According to still another aspect of the present invention, there is also provided a charging area charging remaining amount evaluation system including:

the acquisition module is configured to acquire historical power information of a charging area where the charging pile to be evaluated is located;

the power prediction module is configured to train a power prediction model according to the historical power information and acquire the total conventional electricity utilization power of the charging area predicted and output by the power prediction model;

a margin estimation module configured to calculate an estimated power supply margin for the charging area based on the maximum power of the charging area and the total regular power usage.

An embodiment of the present invention further provides a charging area charging remaining amount evaluation device, including:

a processor;

a memory having stored therein executable instructions of the processor;

wherein the processor is configured to perform the steps of the above charging area charge remaining amount evaluation method via execution of the executable instructions.

An embodiment of the present invention also provides a computer-readable storage medium for storing a program, which when executed, implements the steps of the above charging area charge remaining amount evaluation method.

Compared with the prior art, the invention aims to:

according to the historical power information of a charging area where a charging pile to be evaluated is located, a power prediction model is trained, the total conventional power consumption of the charging area output by the power prediction model in a prediction mode is obtained, and the estimated power supply allowance of the charging area is calculated according to the total conventional power consumption. Therefore, on one hand, the problem that the charging pile in the charging area is not opened after the user arrives at the charging area according to the recommendation information is solved by considering the power load of the charging area where the charging pile is located; on the other hand, the comprehensive analysis of the charging service of the charging area can be realized through the historical power information of the charging area where the charging pile to be evaluated is located; on the other hand, the estimation of the charging allowance information which is allowed to be charged in the current or future period of the charging area can be carried out, so that the charging allowance information can be conveniently pushed to the user, and the charging experience of the user is improved.

Drawings

Other features, objects and advantages of the present invention will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, with reference to the accompanying drawings.

Fig. 1 is a flowchart of a charging area charging margin evaluation method according to an embodiment of the present invention.

Fig. 2 is a flowchart of another embodiment of a charging area charging margin evaluation method according to the present invention.

Fig. 3 is a schematic diagram of the operation of the charging area charge remaining amount evaluation system of the present invention.

Fig. 4 is a schematic diagram of the total conventional power usage of an implementation charging area of the present invention.

Fig. 5 is a block diagram of a charging area charging allowance evaluation system according to an embodiment of the invention.

Fig. 6 is a block diagram of another embodiment of the charging area charging margin evaluation system of the present invention.

Fig. 7 is a schematic structural diagram of a charging area charge remaining amount evaluation device of the present invention.

Fig. 8 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and thus their repetitive description will be omitted.

Fig. 1 is a flowchart of a charging area charging margin evaluation method according to an embodiment of the present invention. The embodiment of the invention provides a charging area charging allowance evaluation method, which comprises the following steps:

and S110, obtaining historical power information of a charging area where the charging pile to be evaluated is located.

Specifically, the historical power information of the charging area where the charging pile to be evaluated is located may be obtained from the network element device on the door side of the circuit part. The network element device may communicate with other devices using, for example, a telecommunications network. Due to the high coverage of the telecommunication network or the network of another network provider, historical power information of the charging area on the door side of the circuit section can be obtained in step S110.

And S120, training a power prediction model according to the historical power information, and acquiring the total conventional power consumption of the charging area predicted and output by the power prediction model.

Specifically, the power prediction model may be trained according to loop specific power data in the historical power information, and the power prediction model may be tested according to power data in the historical power information. Therefore, the prediction accuracy of the power prediction model is improved.

Specifically, step S120 may be implemented by the following steps: performing the current round of training of the power prediction model according to the ring ratio power data in the historical power information; acquiring a power prediction model of the current round, and predicting the output quasi-total conventional power consumption of the charging area based on the ring ratio power data; randomly acquiring the power data with the same ratio in the historical power information as the total conventional power consumption for testing the charging area; calculating the fitting degree of a power prediction model of the current round according to the quasi-total conventional power consumption and the test total conventional power consumption; judging whether the fitting degree of the power prediction model of the current round is within a set fitting range; if yes, determining the total conventional power consumption based on the quasi-total conventional power consumption; and if not, executing the next round of training of the power prediction model according to the ring ratio power data in the historical power information.

Therefore, the calculation and determination of the fitting degree can be used as the basis for the iteration ending of the power prediction model, and the invention is not limited by this. Further, the above steps will be described and explained with reference to fig. 4, and will not be described herein.

Further, the power prediction model may, for example, comprise a plurality of regression models, each of which may, for example, have a time attribute. For example, the regression model may be one or more of an electric regression model, a holiday-daily power regression model, a non-holiday-daily power regression model, a summer-daily power regression model, a winter-daily power regression model, a spring festival-daily power regression model, for example, for different times of day. The total conventional power consumption of different time attributes can be predicted through a plurality of regression models with different time attributes, and the prediction accuracy of the total power prediction model can be provided further based on the predicted total conventional power consumption of different time attributes.

And S130, calculating the estimated power supply allowance of the charging area according to the maximum power of the charging area and the total conventional power consumption.

Specifically, the maximum power of the charging area may be calculated and obtained according to the transformer rated capacity information and the actual power factor information of the charging area, which are acquired from the network element device of the power supply department. The estimated power supply margin is a difference between the maximum power of the charging region and the total regular power consumption.

Further, the estimated supply headroom is power information. In order to more intuitively provide the user with the power supply margin information, the ratio of the estimated power supply margin to the individual charging post power may be calculated after step S130, so that information on how many vehicles the power supply margin can supply power may be obtained.

The existing mode has the following defects: 1) the application of the recommended charging area for the user does not consider the power load of the charging area where the charging pile is located, so that the problem that the charging pile in the charging area is not opened after the user arrives at the charging area according to the recommended information is solved; 2) because each party is limited by network and information isolation, the current charging manufacturer or the management server of the charging area can only perform one-sided analysis on the state of the charging service according to the electricity utilization information of the limited area; 3) limited by a network, the established user charging behavior model is only suitable for a specific power distribution area, and power data related to a charging area in an electric power department is not considered; 4) only a Monte Carlo method, a random forest and other classification and clustering algorithms are used for establishing and optimizing a possible future charging behavior model of the user, the load and the possible power consumption of the regional power grid when the vehicle of the user is charged are predicted, and the power data of the electric power department side and the charging region in recent years can not be acquired for more accurate judgment; 5) the charging allowance information which is allowed to be charged at the current or a certain future period of the charging area is not predicted, so that the charging allowance information is conveniently pushed to a user, and the charging experience of the user is improved.

According to the method, a power prediction model is trained according to historical power information of a charging area where a charging pile to be evaluated is located, the total conventional power consumption of the charging area output by the power prediction model in a prediction mode is obtained, and the estimated power supply allowance of the charging area is calculated according to the total conventional power consumption. Therefore, on one hand, the problem that the charging pile in the charging area is not opened after the user arrives at the charging area according to the recommendation information is solved by considering the power load of the charging area where the charging pile is located; on the other hand, the comprehensive analysis of the charging service of the charging area can be realized through the historical power information of the charging area where the charging pile to be evaluated is located; on the other hand, the estimation of the charging allowance information which is allowed to be charged in the current or future period of the charging area can be carried out, so that the charging allowance information can be conveniently pushed to the user, and the charging experience of the user is improved.

Fig. 2 is a flowchart of another embodiment of a charging area charging margin evaluation method according to the present invention. As shown in fig. 2, the method for estimating the charging area remaining charge further includes steps S100, S140 to S170 on the basis of steps S110, S120 and S130 in the embodiment of fig. 1, and the following steps are described one by one in order of steps.

And S100, receiving a charging allowance evaluation request.

Specifically, the charging allowance evaluation request is generated based on a selection trigger of a user on a to-be-evaluated charging pile in candidate charging piles, and the charging allowance evaluation includes position information of the to-be-evaluated charging pile.

Specifically, the charge remaining amount evaluation request may be generated in an application installed in the user equipment. User devices may include, but are not limited to, smart phones, tablets, laptops, desktops, in-vehicle devices, and the like. Further, the aforementioned application program may acquire the remaining capacity of the user vehicle, the current location of the user vehicle, and destination information of the user vehicle. The information can be used for calculating path information, so that available or idle charging pile information can be acquired according to the state information in the charging piles along the path information to serve as candidate charging piles to be provided for users. And selecting the charging piles to be evaluated by the user through the operation of the candidate charging piles in the application program so as to generate a charging allowance evaluation request.

And S110, obtaining historical power information of a charging area where the charging pile to be evaluated is located.

Specifically, the historical power information of the charging area where the charging pile to be evaluated is located may be obtained from the network element device on the door side of the circuit part. The network element device may communicate with other devices using, for example, a telecommunications network. Due to the high coverage of the telecommunication network or the network of another network provider, historical power information of the charging area on the door side of the circuit section can be obtained in step S110.

And S120, training a power prediction model according to the historical power information, and acquiring the total conventional power consumption of the charging area predicted and output by the power prediction model.

Specifically, the power prediction model may be trained according to loop specific power data in the historical power information, and the power prediction model may be tested according to power data in the historical power information. Therefore, the prediction accuracy of the power prediction model is improved.

Specifically, step S120 may be implemented by the following steps: performing the current round of training of the power prediction model according to the ring ratio power data in the historical power information; acquiring a power prediction model of the current round, and predicting the output quasi-total conventional power consumption of the charging area based on the ring ratio power data; randomly acquiring the power data with the same ratio in the historical power information as the total conventional power consumption for testing the charging area; calculating the fitting degree of a power prediction model of the current round according to the quasi-total conventional power consumption and the test total conventional power consumption; judging whether the fitting degree of the power prediction model of the current round is within a set fitting range; if yes, determining the total conventional power consumption based on the quasi-total conventional power consumption; and if not, executing the next round of training of the power prediction model according to the ring ratio power data in the historical power information.

Therefore, the calculation and determination of the fitting degree can be used as the basis for the iteration ending of the power prediction model, and the invention is not limited by this. Further, the above steps will be described and explained with reference to fig. 4, and will not be described herein.

Further, the power prediction model may, for example, comprise a plurality of regression models, each of which may, for example, have a time attribute. The regression model may be, for example, a function of power versus time. For example, the regression model may be one or more of an electric regression model, a holiday-daily power regression model, a non-holiday-daily power regression model, a summer-daily power regression model, a winter-daily power regression model, a spring festival-daily power regression model, for example, for different times of day. The total conventional power consumption of different time attributes can be predicted through a plurality of regression models with different time attributes, and the prediction accuracy of the total power prediction model can be provided further based on the predicted total conventional power consumption of different time attributes.

Specifically, the power prediction model may predict and output total regular power usage in real time or at a time when a user is expected to arrive at the charging pile to be evaluated. In the embodiment that the power prediction model predicts and outputs the total conventional power consumption of the time when the user is predicted to reach the charging pile to be evaluated, the time when the user is predicted to reach the charging pile to be evaluated can be obtained by prediction according to the current position of the vehicle of the user and the position of the charging pile to be evaluated. Further, the time when the user expects to reach the charging pile to be evaluated can also be the arrival time selected by the user in the application program. In some embodiments, the time when the user expects to arrive at the charging post to be evaluated may be included in the power headroom evaluation request. In other embodiments, the time when the user expects to arrive at the charging pile to be evaluated may also be calculated in real time based on the information in the power headroom evaluation request. The present invention can be implemented in many different ways, which are not described herein.

And S130, calculating the estimated power supply allowance of the charging area according to the maximum power of the charging area and the total conventional power consumption.

Specifically, the maximum power of the charging area may be calculated and obtained according to the transformer rated capacity information and the actual power factor information of the charging area, which are acquired from the network element device of the power supply department. The estimated power supply margin is a difference between the maximum power of the charging region and the total regular power consumption.

S140, acquiring the total number of the idle charging piles in the charging area where the charging pile to be evaluated is located and the power of a single charging pile.

Specifically, the total number of idle charging piles and the power of a single charging pile in a charging area where the charging pile to be evaluated is located may be obtained from network element equipment on the charging pile side near the charging area. The network element device on the charging post side may be, for example, a mall parking lot or other network element device on the parking lot side.

S150, calculating total power data of the idle charging piles in the charging area according to the total number of the idle charging piles in the charging area and the power of each charging pile.

Specifically, the total power data of the idle charging piles in the charging area is the product of the total number of the idle charging piles in the charging area and the power of a single charging pile.

And S160, taking the total power data of the idle charging piles in the charging area and the data with smaller value in the estimated power supply allowance of the charging area as reference allowances.

And S170, calculating the charging residual amount information of the charging area according to the reference residual amount.

Specifically, the charging remaining amount information may be pushed to an application of the user. In order to more intuitively enable a user to obtain the charging remaining amount information, the charging remaining amount information may be a ratio of the reference remaining amount to the power of the single charging pile, or may be the number of vehicles with which the remaining amount is chargeable.

Further, when the user selects a plurality of different charging piles to be evaluated, the above steps S110 to S170 may be repeated to push the charging remaining amount information of the plurality of different charging piles to be evaluated to the user, respectively, so that the user may charge the charging area having a sufficient charging remaining amount (number of vehicles) according to the obtained charging remaining amount information.

Further, fig. 2 shows a specific implementation manner of the present invention, and the combination, the division, and the execution order of the steps are all within the scope of the present invention.

The invention relies on the high coverage rate of the operator network, combines the power data of the power department and the charging area, can provide charging allowance (vehicle) evaluation of different charging areas for users one by one according to the recommendation information of the application program, and verifies the actual availability of the charging pile for the users to make decisions. The invention trains, tests and optimizes each regression model according to the ring ratio and the same ratio power data related to the charging area of the power department. The power prediction model of the invention can adjust the weight of each regression model according to the range of the fitting degree of each regression model when calculating the power prediction value.

In addition, the method can guide a new energy vehicle owner to avoid the peak of electricity consumption in the charging area where the recommended charging pile is located, and the charging service of the charging area is used in a staggered mode. The method and the system can also assist the user to verify the reliability of the charging pile recommendation information of the charging service company, and increase the viscosity of the operator user. In the process, the invention can also realize the communication and interaction between the operator server and the power department, the charging building property and the charging service provider server, and provide high-added-value and differentiated data analysis service for the user after acquiring more comprehensive data.

Referring now to fig. 3, fig. 3 is a schematic diagram of the operation of the charge zone charge balance evaluation system of the present invention.

First, step S1: the user 201 provides the vehicle remaining circuits, the user's vehicle current location information (or the user's current location information), and the destination information to the application 203 of his user device.

Step S1 may be implemented by the input of the user 201, or may be automatically obtained by the application 203 of the user equipment from a positioning module or other application with navigation function, which is not limited by the present invention.

Step S2: the application 203 sends the vehicle remaining circuits, the user vehicle current position information (or the user current position information), and the destination information to the network management platform 206.

Step S3: the network management platform 206 sends the remaining circuits of the vehicle, the current position information of the vehicle of the user (or the current position information of the user) and the destination information to the user information obtaining module 207.

Step S4: the user information acquisition module 207 transmits the current position information of the user vehicle (or the current position information of the user) and the destination information to the driving route acquisition module 208.

Step S5: the driving route obtaining module 208 sends a driving route obtained according to the current position information of the vehicle of the user (or the current position information of the user) and the destination information to the state distribution information obtaining module 209 of the charging pile.

Step S6: the charging pile state distribution information acquisition module 209 transmits charging pile state distribution information along and around the formation route to the charging pile acquisition module 210.

Step S7: the charging pile obtaining module 210 sends available and idle charging piles as candidate charging piles to the network management platform 206 according to the charging pile state distribution information.

Step S8: the network management platform 206 pushes the candidate charging pile information to the application 203.

Step S9: the application 203 displays the candidate charging pile information to the user 201.

Step S10: the user 201 selects a charging pile to be evaluated from the candidate charging pile information in the application 203, determines to generate a charging remaining amount evaluation request, and inputs or automatically acquires the position information of the charging pile to be evaluated by the application 203.

Step S11: the application 203 determines the time when the user is expected to reach the charging pile to be evaluated according to the position information of the charging pile to be evaluated, and sends the charging allowance evaluation request, the position information of the charging pile and the time when the user is expected to reach the charging pile to be evaluated to the network management platform 206.

The position information of the charging post and the time when the user expects to arrive at the charging post to be evaluated may be included in the charging remaining amount evaluation request, for example.

Step S12: the network management platform 206 sends the position information of the charging pile to be evaluated to the telecommunication network element equipment 204 at the door side of the power department.

Step S13: the telecommunication network element equipment 204 on the electric power department side sends the position information of the charging pile to be evaluated to the electric power department 202.

Step S14: the power department 202 sends the historical power information of the charging area where the position information of the charging pile to be evaluated is located to the telecommunication network element equipment 204.

In some embodiments, the charging area may be divided in advance, for example, so that when the position information of the charging pile to be evaluated is obtained, the charging area where the charging pile to be evaluated is located may be determined according to the charging area where the position information of the charging pile to be evaluated falls. In other embodiments, the charging area may be set as an area within a set distance range of the position information of the charging pile to be evaluated, so that the charging area dynamically changes according to the position of the charging pile to be evaluated, which is not limited in the present invention.

The historical power information includes power information at different times of day for the most recent set time period (e.g., 6 months, 1 year, 2 years, 3 years, etc., but the present invention is not limited thereto).

Step S15: the telecommunication network element device 204 sends the historical power information of the charging area where the position information of the charging pile to be evaluated is located to the network management platform 206.

Step S16: the network management platform 206 sends the historical power information of the charging area where the position information of the charging pile to be evaluated is located to the conventional power evaluation module 211.

Step S17: the telecommunication network element equipment 205 at the charging pile side is used for counting the total number m of the idle charging piles in the charging area_{Free up}And a single charging pile power P_{Charging pile}And sent to the network management platform 206.

Specifically, the telecommunication network element device 205 on the charging post side may also send the use state information of each charging post a-N in the charging area to the network management platform 206.

Step S18: the network management platform 206 charges the total number m of the idle charging piles in the charging area_{Free up}And a single charging pile power P_{Charging pile}(and the usage status information for each charging post a-N) to the power supply load assessment module 212.

Step S19: the conventional power evaluation module 211 predicts the total conventional power consumption of the charging area according to the power-versus-time power prediction model, detects and optimizes the total conventional power consumption P of the power prediction model output at the optimal designated time according to the same-ratio power information of the historical power information_{General assembly}And sent to the power supply load evaluation module 212.

Step S20: the network management platform 206 calculates and obtains the maximum power P of the charging area according to the transformer rated capacity information and the actual power factor information of the charging area obtained from the network element device 204 at the door side of the power supply department_{Maximum of}And sent to the power supply load evaluation module 212.

Step S21: the power supply load evaluation module 212 evaluates the maximum power P of the charging area_{Maximum of}And the total normal electric power P_{General assembly}The difference is used as the estimated power supply margin P_{Power supply allowance}＝P_{Maximum of}-P_{General assembly}And the total number m of the idle charging piles according to the charging area_{Free up}And a single charging pile power P_{Charging pile}Calculating total power data P of idle charging piles in the charging area_{Free up}＝m_{Free up}*P_{Charging pile}And obtaining total power data P of idle charging piles in the charging area_{Free up}Estimated power supply margin P to the charging area_{Power supply allowance}Using the small data of the medium value as a reference margin, and calculating charging margin information m of the charging area according to the reference margin_{Charge margin}＝min(P_{Free up}，P_{Power supply allowance})/P_{Charging pile}Charging margin information m of the charging area_{Charge margin}And sent to the network management platform 206.

Step S22: the network management platform 206 sends the charging allowance informationMessage m_{Charge margin}Push to application 203.

The application 203 may display the charge remaining amount information m to the user_{Charge margin}. Further, when the user selects a plurality of different charging piles to be evaluated, the above steps S10 to S21 may be repeated to push the charging amount information of the plurality of different charging piles to be evaluated to the user, respectively, whereby the user may charge to a charging area having a sufficient charging amount (number of vehicles) according to the obtained charging amount information.

The above description is only illustrative of specific implementations of the present invention, and the present invention is not limited thereto, and the steps of splitting, merging, changing the execution sequence, splitting, merging, and information transmission are all within the protection scope of the present invention.

Fig. 4 is a schematic diagram of the total conventional power usage of an implementation charging area of the present invention. The method adopts a power prediction model comprising a plurality of regression models, and estimates the conventional power consumption at the set moment of the charging area by establishing the functional relation between the whole power information (kilowatt) of the charging area and the time. As shown in fig. 4, the cyclic power data 301 and the power-on-load data 302 in the historical power information of the charging area obtained from the power department are provided as a training data set and a test data set, respectively, to different regression models in the power prediction model.

As shown in fig. 4, the power prediction model includes a plurality of regression models having different time attributes (e.g., a first regression model 303 having a first time attribute, a second regression model 305 having a second time attribute, a third regression model 307 having a third time attribute, etc.). In one specific implementation, the power prediction model may include 6 regression models with different time attributes (power regression model at different times of day, power regression model at different times of day for holidays, power regression model at different times of day for non-holidays, power regression model at different times of day for summer, power regression model at different times of day for winter, power regression model at different times of day for spring festival), so that the specific power data 301 and the specific power data 302 in the historical power information of the charging area may be divided into 6 data sets with different time attributes, respectively: the power data sets of different moments of the day, the power data sets of different moments of the day on holidays, the power data sets of different moments of the day on non-holidays, the power data sets of different moments of the day in summer, the power data sets of different moments of the day in winter and the power data sets of different moments of the day in spring festival.

In fig. 2, the ring ratio power data (solid arrows) in each type of data set is used to train the corresponding regression models (first to third regression models 303 to 307), such as the different time of day power data set is used to train the daily power regression model. By analogy, the six data sets respectively correspond to an electric regression model, a resting day daily power regression model, a non-resting day daily power regression model, a summer daily power regression model, a winter daily power regression model and a spring festival daily power regression model at different times every day. Each regression model estimates the power (kilowatt) data at a set time, and the data are respectively marked as P_{General 1i}、P_{Conventional 2i}、P_{Conventional 3i}、P_{Conventional 4i}、P_{Conventional 5i}、P_{Conventional 6i}。

The power data (dotted arrows) of the same proportion in each data set is used as test data to verify the accuracy of the regression model corresponding to each data set, and is the power data randomly obtained through the steps of randomly obtaining the power data 304, 306 and 308, which can be respectively marked as P_{Test 1i}、P_{Test 2i}、P_{Test 3i}、P_{Test 4i}、P_{Test 5i}、P_{Test 6i}。

In conjunction with the conventional power prediction results of the previous section, model evaluation module 309 of FIG. 4 verifies the validity of various regression models, such as R₁(P_{Test 1i}，P_{General 1i}) The fit of the daily power regression model was compared. The specific formula is as follows:

i in the formula represents the number of training iterations, and n represents the number of test samples, which can be adjusted manually. When tested, i is an integer between 1 and n. Similarly, the spring festival daily power regression model corresponds to a fitting function of:

wherein R is₆The degree of fit of the spring festival daily power regression model was compared. By analogy, other 4 fitting values R can be obtained₂～R₅. The normal range for each fit value is between 0.4 and 0.8 (which can be set as needed), where the i training iteration number and the n sample number can be adjusted manually.

The power prediction model adjusts the weights of the regression models in the weighted average calculation step 311 according to whether the fitting value exceeds the range 310, and may perform weight adjustment 312 and iterate the next round of model training, for example, to decrease the weights of the models outside the normal range. The weights of the regression models are initially the same and are then adjusted based on the test results. Wherein each weight value a_jThe relation to the fitting function may be when 0.8<R_jR is less than or equal to 1 or less than or equal to 0_j<0.4，a_j＝M/R_j ²I.e., an inverse correlation relationship; a is_j＝M*R_j ²When R is 0.4. ltoreq_jLess than or equal to 0.8. The whole estimation method is circulated until the fitting value is within the acceptable range (0.4-0.8). Result P of the weighted average calculation step_{General assembly}As a conventional power utilization prediction result of the conventional power evaluation module at the set moment, the formula is as follows:

the above is merely an illustrative description of one implementation of the present invention and the present invention is not limited thereto.

In the invention, after training, checking and optimizing by referring to the ring ratio power data (kilowatt) and the same ratio power data (kilowatt) of the power department at different times every day, compared with the prior art, the fitting degree of each regression model of the power prediction model is stable in a set range (for example, the fitting degree can be set to be 0.4 to 0.65 as required), so that the problems of over-fitting under-fitting and under-fitting are avoided; the final weighted average calculation step of the power prediction model emphasizes that real-time variables such as temperature, time and the like can be introduced into the scene of the scheme to correct the prediction result by adjusting the weight of the prediction value of each regression model, so that the prediction accuracy can reach 93 percent, and is improved by 5 to 10 percent compared with the accuracy of the existing prediction model; the invention depends on the coverage rate of the operator network, can more comprehensively predict and analyze data, and reduces the time for a user to find the actual available charging service by 40-50 minutes on average.

Therefore, the invention can realize the following beneficial effects:

1) the probability that the charging service is not opened after the new energy vehicle owner arrives at the public charging pile according to the recommendation information is reduced, the new energy vehicle owner is further guided to avoid the electricity consumption peak of the charging area where the recommended charging pile is located, and the charging service of the charging area is used in a staggered mode.

2) The charging recommendation information acquired by the user is supplemented, the user is assisted to verify the credibility of the application program charging service recommendation information, and the viscosity of the operator user is further increased.

3) The data interface between the operator partner server including the power department, the charging area property department and the operator user and the equipment is provided, and high-added-value and differentiated data analysis service is provided for the user after more comprehensive data is obtained.

The following provides a number of specific embodiments of the invention:

example 1: insufficient charging allowance of mall house armor in winter

In winter, at 3 pm after a certain week, 2 electric vehicles need to be charged in one household. The user acquires the recommended charging pile a information provided by the charging service recommendation application program, and intends to verify the charging allowance of the shopping mall a where the charging pile a is located (several vehicles are allowed to charge the charging area at the same time). After the user submits the position information of the charging pile A, the network management platform acquires the business from the telecommunication network element equipment at the door side of the electric power department according to the position informationThe power information of different moments of the day in recent years of the field armor is provided to a conventional power evaluation module. The module selects the ring ratio power data of the previous months to train each regression model in the power prediction model, and selects the year-round data to verify the accuracy of each regression model in the power prediction model. After testing, the fitting function R of the daily power regression model of the rest day is found₂And fitting function R of winter daily power regression model₅All values of (A) are in the interval 0.4 and 0.8, the rest of R₁、R₃、R₄、R₆All values of (a) are greater than 0.8.

In view of R₁、R₃、R₄、R₆Weight a of each regression model_jWith corresponding fitting function R_jThe square value of (A) is inversely proportional to (see figure 4), and the predicted value (i.e. P) corresponding to the daily power regression model, the non-holiday daily power regression model, the spring daily power regression model, and the spring festival daily power regression model_{General No. 1}、P_{Conventional No. 3}、P_{Conventional 4}、P_{Conventional 6}) The weight of (c) will be adjusted downward accordingly. After the power prediction model structure randomly selects the power data sets at different moments again for training and testing, R is found₁～R₆All values of (a) are in the interval 0.4 to 0.8. And the power prediction model carries out weighted average calculation according to the existing weight to obtain the conventional power prediction value of the current time point.

And the power supply load evaluation module obtains the maximum power of the market A according to the rated capacity information and the actual power factor information of the transformer obtained by the power department. After the difference value between the maximum power and the conventional power estimation value is obtained, the power supply load evaluation module compares the maximum power and the conventional power according to the total power data of the field idle charging pile transmitted from the telecommunication network element node at the market A side and then obtains the smaller value of the total power and the conventional power; after dividing by the power value of a single charging pile on site, the user is prompted to allow 1 vehicle to be charged, namely the charging allowance is 1. The user adjusts the destination immediately, seeks the idle stake of charging in other charging area.

Example 2: the charging margin of the mall B is enough

At 11 am on a certain wednesday in 3 months, a user has 1 automobile to be charged, and a charging allowance evaluation request of a market B where the charging pile A is located is submitted after the position and the information of the charging pile A provided by the charging service recommendation application program. The network management platform acquires power information of different days in recent years of the market B from a telecommunication network element node at the electric power department according to the position information of the charging pile A, trains each regression model by taking ring ratio data of previous months, and then predicts the conventional power value of the market B at the current moment.

The network management platform tests the prediction results of the models through the comparation data in the data set acquired from the power department, and finds the fitting function R of the non-holiday daily power regression model and the daily power regression model₃(P_{Test 3i}，P_{Conventional 3i}) And R₁(P_{Test 1i}，P_{General 1i}) Is in the interval 0.4 and 0.8. Predicted values R of the remaining 4 models₂(P_{Test 2i}，P_{Conventional 2i})、R₅(P_{Test 5i}，P_{Conventional 5i}) Less than 0.4, R₆(P_{Test 6i}，P_{Conventional 6i})、R₄(P_{Test 4i}，P_{Conventional 4i}) Greater than 0.8. Due to R₂、R₄、R₅、R₆The value of the fitting function and the weight a of the predicted power value_jIn an inverse relationship, and R₁And R₃Fitting value of (a) to_jIn a proportional relationship. Thus, P_{General No. 2}、P_{Conventional 4}、P_{Conventional 5}、P_{Conventional 6}Corresponding weight a₂、a₄、a₅、a₆Will be down-regulated, and a₁And a₃The relative increase. After the power prediction model structure randomly selects the power data sets at different moments again to train and test for a plurality of times, R is found₁～R₆All values of (a) are in the interval 0.4 to 0.8. The final weighted average is used as the conventional power prediction result.

The power supply load evaluation module respectively acquires the total power value of the on-site idle charging pile and the maximum power value of the market B through the network element node on the charging area side and the network element node on the power department door side. And combining the conventional power predicted value and the maximum power value of the market B, the power supply load evaluation module obtains the power supply allowance of the market B, comparing the power supply allowance with the total power of the idle charging piles of the market B, and dividing the smaller value of the power supply allowance and the total power of the idle charging piles of the market B by the power value of a single field charging pile to obtain that the charging allowance of the market B is 3. The user goes to the market B for charging immediately, and does not pay attention to the charging allowance information of the market B regularly on the way.

Thus, the difference between the present invention and the prior art is mainly that:

the prior art is limited by a network, an established user charging behavior model is only suitable for a specific charging station, power data related to a power department and a charging area are not considered, and the method acquires power data of the power department related to different charging areas at different moments every day one by one according to user requirements to train and test each regression model.

In the prior art, a Monte Carlo method, a random forest and other classification and clustering algorithms are used for establishing and optimizing a possible future charging behavior model of a user, and then prediction is carried out. The optimal solution is obtained according to the fitting degree of each regression model in the power prediction model for training, checking and optimizing the ring specific power data (kilowatt) and the similar specific power data (kilowatt) in the power data of the power department.

The prior art does not adjust the weights of the regression models according to the fitness range. According to the invention, through inspection, when the fitting degree setting range (such as 0.4 and 0.8) of each regression model in the power prediction model is out of the range, the power prediction model is inversely proportional to the weight of the regression model; otherwise, it is proportional. The weight of each model when calculating the predicted power value is adjusted according to the rule.

None of the prior art provides charge remaining amount (vehicle) information. The invention compares the power supply allowance of the charging area with the total idle charging pile power, obtains the charging allowance information (vehicle) after dividing the smaller value by the power value of the single charging pile, and then pushes the information to the user.

Fig. 5 is a block diagram of a charging area charging allowance evaluation system according to an embodiment of the invention. The charging area charge remaining capacity evaluation system 400 of the present invention, as shown in fig. 5, includes but is not limited to:

the obtaining module 410 is configured to obtain historical power information of a charging area where a charging pile to be evaluated is located.

The power prediction module 420 is configured to train a power prediction model according to the historical power information, and obtain a total regular power consumption of the charging area predicted to be output by the power prediction model.

The margin estimation module 430 is configured to calculate an estimated power supply margin for the charging area based on the maximum power of the charging area and the total regular power usage.

The implementation principle of the above modules is described in the charging area charging allowance evaluation method, and is not described herein again.

The charging area charging allowance evaluation system can train a power prediction model according to historical power information of a charging area where a charging pile to be evaluated is located, obtain total conventional power consumption of the charging area predicted and output by the power prediction model, and calculate the estimated power supply allowance of the charging area according to the total conventional power consumption. Therefore, on one hand, the problem that the charging pile in the charging area is not opened after the user arrives at the charging area according to the recommendation information is solved by considering the power load of the charging area where the charging pile is located; on the other hand, the comprehensive analysis of the charging service of the charging area can be realized through the historical power information of the charging area where the charging pile to be evaluated is located; on the other hand, the estimation of the charging allowance information which is allowed to be charged in the current or future period of the charging area can be carried out, so that the charging allowance information can be conveniently pushed to the user, and the charging experience of the user is improved.

Fig. 6 is a block diagram of another embodiment of the charging area charging margin evaluation system of the present invention. As shown in fig. 6, based on the embodiment of the apparatus shown in fig. 4, the charging area charging margin evaluation system 400' of the present invention includes, but is not limited to: a receiving module 401, a first obtaining module 410, a power predicting module 420, a margin estimating module 430, a second obtaining module 440, a total idle power calculating module 450, a reference margin determining module 460, and a margin information calculating module 470.

The receiving module 401 is configured to receive a charge margin evaluation request.

The first obtaining module 410 is configured to obtain historical power information of a charging area where a charging pile to be evaluated is located.

The power prediction module 420 is configured to train a power prediction model according to the historical power information, and obtain a total regular power consumption of the charging area predicted to be output by the power prediction model.

The margin estimation module 430 is configured to calculate an estimated power supply margin for the charging area based on the maximum power of the charging area and the total regular power usage.

The second obtaining module 440 is configured to obtain the total number of idle charging piles and the power of a single charging pile in a charging area where the charging pile to be evaluated is located.

The total idle power calculating module 450 is configured to calculate total power data of the idle charging piles of the charging area according to the total number of the idle charging piles of the charging area and the power of each charging pile.

The reference margin determination module 460 is configured to use the total power data of the idle charging piles in the charging area and the data with a smaller value in the estimated power supply margin in the charging area as the reference margin.

The margin information calculation module 470 is configured to calculate the charging margin information of the charging area according to the reference margin.

The implementation principle of the above modules is described in the charging area charging allowance evaluation method, and is not described herein again.

Fig. 5 and 6 are merely schematic diagrams respectively illustrating the charging area charging allowance evaluation systems 400 and 400' provided by the present invention, and the splitting, combining and adding of modules are within the protection scope of the present invention without departing from the concept of the present invention. The charging area charging remaining amount evaluation systems 400 and 400' provided by the present invention can be implemented by software, hardware, firmware, plug-in and any combination thereof, which is not limited to the present invention.

The embodiment of the invention also provides charging area charging allowance evaluation equipment which comprises a processor. A memory having stored therein executable instructions of the processor. Wherein the processor is configured to perform the steps of the charging area charge balance assessment method via execution of executable instructions.

As described above, the charging area charge remaining amount evaluation system of this embodiment of the present invention can make a prediction of estimating the supply remaining amount in conjunction with the historical power information of the charging area.

As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" platform.

Fig. 7 is a schematic structural diagram of a charging area charge remaining amount evaluation device of the present invention. An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 7. The electronic device 600 shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 7, the electronic device 600 is embodied in the form of a general purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one memory unit 620, a bus 630 connecting the different platform components (including the memory unit 620 and the processing unit 610), a display unit 640, etc.

Wherein the storage unit stores program code which is executable by the processing unit 610 to cause the processing unit 610 to perform the steps according to various exemplary embodiments of the present invention described in the above-mentioned charging area charge remaining amount evaluation method section of the present specification. For example, processing unit 610 may perform the steps as shown in fig. 1.

The storage unit 620 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)6201 and/or a cache memory unit 6202, and may further include a read-only memory unit (ROM) 6203.

The memory unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 630 may be one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 600, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 600 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 650. Also, the electronic device 600 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via the bus 630. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, to name a few.

An embodiment of the present invention further provides a computer-readable storage medium for storing a program, where the program implements the steps of the method for estimating the charge remaining capacity of the charge area when executed. In some possible embodiments, the various aspects of the present invention may also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps according to various exemplary embodiments of the present invention described in the above-mentioned charging area charge remaining amount evaluation method section of this description, when the program product is run on the terminal device.

As described above, the charging area charge remaining amount evaluation system of this embodiment of the present invention can make a prediction of estimating the supply remaining amount in conjunction with the historical power information of the charging area.

Fig. 8 is a schematic structural diagram of a computer-readable storage medium of the present invention. Referring to fig. 8, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

In conclusion, according to the historical power information of the charging area where the charging pile to be evaluated is located, a power prediction model is trained, the total conventional power consumption of the charging area predicted and output by the power prediction model is obtained, and the estimated power supply allowance of the charging area is calculated according to the total conventional power consumption. Therefore, on one hand, the problem that the charging pile in the charging area is not opened after the user arrives at the charging area according to the recommendation information is solved by considering the power load of the charging area where the charging pile is located; on the other hand, the comprehensive analysis of the charging service of the charging area can be realized through the historical power information of the charging area where the charging pile to be evaluated is located; on the other hand, the estimation of the charging allowance information which is allowed to be charged in the current or future period of the charging area can be carried out, so that the charging allowance information can be conveniently pushed to the user, and the charging experience of the user is improved.

The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.