A vehicle charging system based on dynamic energy usage data analysis

Abstract

The present invention provides a vehicle charging system based on dynamic energy usage data analysis, and relates to the technical field of power optimization. The system includes a controller and a switch device, and the switch device is used to adjust the access position of the charging pile in the three-phase power supply circuit; the controller is used to obtain the load power, access position and power consumption of the i-th control cycle of the current date; obtain the charging time of the charging pile being used; obtain the historical load power, historical access position and historical power consumption, and then obtain the predicted community load power and predicted power consumption, and predict the predicted access position of each charging pile in the i+1-th control cycle of the current date, so as to generate a switch device adjustment instruction. According to the present invention, the access position of each charging pile in the three-phase power supply circuit can be optimized, the surplus power of the power supply circuit can be fully utilized, power can be provided to the charging pile, and the probability of insufficient power supply can be reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of power optimization, and in particular to a vehicle charging system based on dynamic energy usage data analysis. Background Art

[0002] In the relevant technology, installing charging piles in the community can greatly improve the convenience of charging electric vehicles for community users. However, the power capacity in the community is limited. Installing charging piles on the basis of the community’s original power supply circuit may cause insufficient power supply, which may have an adverse impact on the normal electricity use of the community and users who use charging piles to charge.

[0003] The information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0004] The present invention provides a vehicle charging system based on dynamic energy usage data analysis, which can solve the technical problem that installing charging piles on the basis of the original power supply circuit of the community may cause insufficient power supply.

[0005] According to a first aspect of the present invention, there is provided a vehicle charging system based on dynamic energy usage data analysis, comprising: a controller and a switch device;

[0006] Wherein, the switch device includes a plurality of regulating switches, and the regulating switches are used to adjust the access position of the charging pile in the three-phase power supply circuit;

[0007] The controller is used to:

[0008] At multiple moments of the i-th control cycle of the current date, the load power of each phase power supply line in the three-phase power supply circuit of the community, the connection position of each charging pile in the three-phase power supply circuit, and the power consumption of each charging pile are obtained;

[0009] Obtain the charging time of a charging pile currently in use among multiple charging piles;

[0010] Obtain multiple moments of the i-th control cycle and multiple moments of the i+1-th control cycle on the previous date, the historical load power of each phase power supply line in the three-phase power supply circuit, the historical access position of each charging pile in the three-phase power supply circuit, and the historical power consumption of each charging pile;

[0011] According to the historical load power, the historical access position, the historical power consumption, the access position of each charging pile in the three-phase power supply circuit, the power consumption and the load power, the predicted community load power of each phase power supply line in the three-phase power supply circuit is obtained at multiple moments of the i+1th control cycle of the current date;

[0012] According to the charging time, the predicted power consumption of each charging pile is obtained at multiple moments of the (i+1)th control cycle of the current date;

[0013] Determine the predicted access position of each charging pile in the (i+1)th control cycle of the current date according to the predicted community load power and the predicted power consumption;

[0014] generating a switch device adjustment instruction according to the predicted access position;

[0015] The switch device adjustment instruction is sent to the switch device, so that in the (i+1)th control cycle of the current date, the access position of each charging pile in the three-phase power supply circuit is consistent with the predicted access position.

[0016] Technical effect: According to the present invention, the predicted power consumption of the charging piles and the predicted community load power in the next control cycle can be predicted based on the historical data of the power supply circuit and the charging piles in the community, so as to optimize and adjust the access position of each charging pile in the three-phase power supply circuit, so as to make full use of the surplus power of the power supply circuit, provide power to the charging piles, reduce the probability of insufficient power supply, and do not need to transform the power supply circuit, reduce reinvestment in power facilities, and reduce power supply costs. When determining the historical community load power, the historical data of the power consumption provided for the community's power load after removing the power provided for the charging piles can be defined, and the charging piles connected to each phase of the power supply line can be screened by means of conditional functions, and the sum of the historical power consumption of these charging piles can be determined, so as to accurately solve the historical community load power and provide an accurate data basis for subsequent predictions and optimizations. When updating the community load power prediction model, after training the community load power prediction model with the historical community load power of multiple historical dates, the trained community load power prediction model can be updated and trained with the historical community load power of the i-th control cycle and the i+1-th control cycle of the previous date, so that the updated community load power prediction model is more suitable for predicting the community load power at multiple moments in the i+1-th control cycle, further improving the prediction accuracy. When determining the predicted power consumption of the charging pile, the total usage time of each charging pile in the i+1-th control cycle can be estimated by the average usage rate, and then compared with the predicted usage time of the s-th charging pile in the i+1-th control cycle to determine the time period in which the s-th charging pile is used and the time period in which it is not used in the i+1-th control cycle, and then determine the predicted power consumption at each moment, which can improve the objectivity and accuracy of the predicted power consumption. When solving the predicted access position of the charging pile, by setting the objective function and constraints, in the process of solving the predicted access position of the charging pile, it is possible to achieve the goals of balancing the three-phase load as much as possible, meeting the electricity demand of the community and the charging pile as much as possible, and reducing the probability of circuit damage caused by sudden and large changes in circuit load, while adjusting the access position as little as possible, thereby improving the rationality and accuracy of the predicted access position.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only and do not limit the present invention. Other features and aspects of the present invention will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other embodiments can be obtained based on these drawings without creative work.

[0019] Figure 1 A schematic diagram of a vehicle charging system based on dynamic energy usage data analysis according to an embodiment of the present invention is exemplarily shown. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0022] Figure 1 A schematic diagram of a vehicle charging system based on dynamic energy usage data analysis according to an embodiment of the present invention is exemplarily shown, the system comprising: a controller and a switch device;

[0023] Wherein, the switch device includes a plurality of regulating switches, and the regulating switches are used to adjust the access position of the charging pile in the three-phase power supply circuit;

[0024] The controller is used to:

[0025] At multiple moments of the i-th control cycle of the current date, the load power of each phase power supply line in the three-phase power supply circuit of the community, the connection position of each charging pile in the three-phase power supply circuit, and the power consumption of each charging pile are obtained;

[0026] Obtain the charging time of a charging pile currently in use among multiple charging piles;

[0027] Obtain multiple moments of the i-th control cycle and multiple moments of the i+1-th control cycle on the previous date, the historical load power of each phase power supply line in the three-phase power supply circuit, the historical access position of each charging pile in the three-phase power supply circuit, and the historical power consumption of each charging pile;

[0028] According to the historical load power, the historical access position, the historical power consumption, the access position of each charging pile in the three-phase power supply circuit, the power consumption and the load power, the predicted community load power of each phase power supply line in the three-phase power supply circuit is obtained at multiple moments of the i+1th control cycle of the current date;

[0029] According to the charging time, the predicted power consumption of each charging pile is obtained at multiple moments of the (i+1)th control cycle of the current date;

[0030] Determine the predicted access position of each charging pile in the (i+1)th control cycle of the current date according to the predicted community load power and the predicted power consumption;

[0031] generating a switch device adjustment instruction according to the predicted access position;

[0032] The switch device adjustment instruction is sent to the switch device, so that in the (i+1)th control cycle of the current date, the access position of each charging pile in the three-phase power supply circuit is consistent with the predicted access position.

[0033] According to the vehicle charging system based on dynamic energy usage data analysis of an embodiment of the present invention, the predicted power consumption of the charging piles and the predicted community load power in the next control cycle can be predicted based on the historical data of the power supply circuit and the charging piles in the community, so as to optimize and adjust the access position of each charging pile in the three-phase power supply circuit to make full use of the surplus power of the power supply circuit, provide power for the charging piles, reduce the probability of insufficient power supply, and do not need to modify the power supply circuit, reduce reinvestment in power facilities, and reduce power supply costs.

[0034] According to one embodiment of the present invention, each phase power supply line in the three-phase power supply circuit of the community is connected to a different load, and the connection method of the original load of the community in the three-phase power supply circuit is relatively fixed. The access position of the charging pile in the three-phase power supply circuit can be adjusted by adjusting the switch, that is, adjusting which power supply circuit of each phase power supply line the charging pile is connected to. The surplus power of each phase power supply line can be used to provide power for the charging pile, which can also be beneficial to the load balancing of the three-phase circuit.

[0035] According to one embodiment of the present invention, the switch device includes multiple regulating switches, each regulating switch can adjust the access position of a charging pile in the three-phase power supply circuit, and the controller can use historical data and predicted data to determine the adjustment method of each regulating switch, and generate a switch device adjustment instruction, so that the switch device adjusts each regulating switch according to the switch device adjustment instruction.

[0036] According to one embodiment of the present invention, the controller can obtain historical data, including at the end of the i-th control cycle of the current date, the load power of each phase power supply line in the three-phase power supply circuit at multiple moments of the i-th control cycle of the current date, the access position of each charging pile in the three-phase power supply circuit, and the power consumption of each charging pile. The controller can also obtain historical data from the previous date, including multiple moments of the i-th control cycle of the previous date and multiple moments of the i+1-th control cycle, the historical load power of each phase power supply line in the three-phase power supply circuit, the historical access position of each charging pile in the three-phase power supply circuit, and the historical power consumption of each charging pile. The duration of each control cycle can be one hour, which is not limited by the present invention.

[0037] According to one embodiment of the present invention, the controller can predict the predicted community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i+1th control cycle of the current date based on the above historical data, that is, the power provided for the community's power load after removing the power provided for the charging pile.

[0038] According to one embodiment of the present invention, the predicted community load power of each phase power supply line in the three-phase power supply circuit is obtained at multiple moments of the i+1th control cycle of the current date based on the historical load power, the historical access position, the historical power consumption, the access position of each charging pile in the three-phase power supply circuit, the power consumption and the load power, including: determining the predicted community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle and the i+1th control cycle of the previous date based on the historical load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle and the i+1th control cycle of the previous date, the historical access position of each charging pile in the three-phase power supply circuit in the i-th control cycle and the i+1th control cycle of the previous date, and the historical power consumption of each charging pile in the i-th control cycle and the i+1th control cycle of the previous date the historical community load power at multiple moments in the i-th control cycle of the current date; determine the community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle of the current date according to the load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle of the current date, the access position of each charging pile in the three-phase power supply circuit in the i-th control cycle of the current date, and the power consumption of each charging pile in the i-th control cycle of the current date; obtain the predicted community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle of the current date according to the historical community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle of the previous date and the i+1-th control cycle.

[0039] According to one embodiment of the present invention, according to the historical load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle and the i+1-th control cycle of the previous date, the historical access position of each charging pile in the three-phase power supply circuit in the i-th control cycle and the i+1-th control cycle of the previous date, and the historical power consumption of each charging pile in the i-th control cycle and the i+1-th control cycle of the previous date, the historical community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle and the i+1-th control cycle of the previous date is determined, including: determining the historical community load power P of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the i-th control cycle of the previous date according to formula (1): c,i,j,k,Y ,

[0040]

[0041] Among them, P i,j,k,Y is the historical load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the ith control cycle on the previous date, P p,i,AYs(i),,, is the historical power consumption of the sth charging pile at the kth moment in the ith control cycle of the previous date, AYs(i) is the access position of the sth charging pile in the ith control cycle of the previous date, m is the number of charging piles, if is the conditional function, which means that if the access position of the sth charging pile in the ith control cycle of the previous date is the jth phase power supply line, then the conditional function value is P p,i,AYs(i),,, , otherwise the conditional function value is 0; according to formula (2), determine the historical community load power P of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the i+1-th control cycle of the previous date c,i+1,j,k,Y ,

[0042]

[0043] Among them, P i+1,j,k,Y is the historical load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the i+1-th control cycle on the previous date, P p,i+1,AYs(i+1),,, is the historical power consumption of the sth charging pile at the kth moment in the i+1th control cycle of the previous date, AYs(i+1) is the access position of the sth charging pile in the i+1th control cycle of the previous date, m is the number of charging piles, if is the conditional function, which means that if the access position of the sth charging pile in the i+1th control cycle of the previous date is the jth phase power supply line, then the conditional function value is P p,i+1,AYs(i+1),,s, , otherwise the conditional function value is 0.

[0044] According to one embodiment of the present invention, the historical community load power is the historical data of the power provided to the community's power load after removing the power provided to the charging pile. Therefore, the historical community load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the i-th control cycle of the previous date is equal to the historical load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the i-th control cycle of the previous date, minus the sum of the historical power consumption of multiple charging piles whose access position in the i-th control cycle of the previous date is the j-th phase power supply line at the k-th moment. Therefore, the conditional function can be used to screen out the charging piles whose access position in the i-th control cycle of the previous date is the j-th phase power supply line from all the charging piles, that is, the function value of the conditional function is equal to P when the access position in the i-th control cycle of the previous date is the j-th phase power supply line. p,i,AYs(i),,, , otherwise it is equal to 0. Therefore, the conditional functions corresponding to each charging pile can be summed to obtain the sum of the historical power consumption of multiple charging piles whose access position is the j-phase power supply line in the i-th control cycle of the previous date at the k-th moment. Similarly, the historical community load power of the j-phase power supply line in the three-phase power supply circuit at the k-th moment in the i+1-th control cycle of the previous date is equal to the historical load power of the j-phase power supply line in the three-phase power supply circuit at the k-th moment in the i+1-th control cycle of the previous date, minus the sum of the historical power consumption of multiple charging piles whose access position is the j-phase power supply line in the i+1-th control cycle of the previous date at the k-th moment. And, similar to the above, the conditional function can also be used to determine the sum of the historical power consumption of multiple charging piles whose access position is the j-phase power supply line in the i+1-th control cycle of the previous date at the k-th moment.

[0045] In this way, based on the definition of historical data of power consumption provided for the community's power load after deducting the power provided for the charging piles, the charging piles connected to each phase of the power supply line can be screened by means of conditional functions, and the sum of the historical power consumption of these charging piles can be determined, so as to accurately solve the historical community load power and provide an accurate data basis for subsequent prediction and optimization.

[0046] According to one embodiment of the present invention, the community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle of the current date can also be obtained in a similar manner to the above, that is, the load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the i-th control cycle of the current date is subtracted from the sum of the power consumption of multiple charging piles whose access position is the j-th phase power supply line in the i-th control cycle of the current date at the k-th moment, to obtain the community load power of the j-th phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle of the current date.

[0047] According to one embodiment of the present invention, based on the historical community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle and the i+1-th control cycle of the previous date, and the community load power at multiple moments in the i-th control cycle of the current date, the predicted community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i+1-th control cycle of the current date is obtained, including: training a community load power prediction model through the historical community load power at multiple moments in the control cycles of multiple historical dates before the previous date, and obtaining a trained community load power prediction model; inputting the historical community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle of the previous date into the trained community load power prediction model, and obtaining a three-phase The training community load power of each phase power supply line in the power supply circuit in the i+1th control cycle of the previous date; obtaining an updated training loss function of the trained community load power prediction model according to the historical community load power at multiple moments in the i+1th control cycle of each phase power supply line in the three-phase power supply circuit on the previous date and the training community load power; updating the trained community load power prediction model according to the updated training loss function to obtain an updated community load power prediction model; inputting the community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i+1th control cycle of the current date into the updated community load power prediction model to obtain the predicted community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i+1th control cycle of the current date.

[0048] According to one embodiment of the present invention, more historical data, including historical community load power, can be collected in multiple historical dates before the previous date, and the collected historical community load power can be used to train the load power prediction model. For example, the historical community load power at multiple moments of a control cycle in the historical date can be input into the community load power prediction model, so that the community load power prediction model outputs the predicted community load power at each moment of the next control cycle, and then the deviation between the measured community load power at each moment of the next control cycle and the predicted community load power is used to determine the loss function, and the loss function is reduced by the gradient descent method, so as to train the community load power prediction model. The community load power prediction model can be a deep learning neural network model, a time series model, etc., and the present invention does not limit this.

[0049] According to one embodiment of the present invention, after training the community load power prediction model multiple times using the historical community load power at multiple moments in the control cycle of multiple historical dates, the prediction accuracy of the community load power prediction model is improved. After the accuracy reaches a certain accuracy requirement, the training is completed to obtain the trained community load power prediction model.

[0050] According to one embodiment of the present invention, the trained community load power prediction model has a certain universality for using the community load power at multiple moments in one control cycle to predict the community load power at multiple moments in the next control cycle, that is, the trained community load power prediction model is the global optimal solution for predicting the community load power within multiple control cycles within a day, but it may not be able to achieve maximum accuracy for predicting the community load power within a specific control cycle, that is, the trained community load power prediction model is not the local optimal solution for predicting the community load power for a specific control cycle.

[0051] According to one embodiment of the present invention, for a specific control cycle, that is, using the community load power at multiple moments in the i-th control cycle within a day to predict the community load power at multiple moments in the i+1-th control cycle, the trained community load power prediction model can be updated using historical data of these two specific control cycles on the previous date, thereby maximizing the prediction accuracy of the updated community load power prediction model for the community load power at multiple moments in the i+1-th control cycle.

[0052] According to one embodiment of the present invention, in the above-mentioned updating process, the historical community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle of the previous date can be used to input the trained community load power prediction model, and the training community load power of each phase power supply line in the three-phase power supply circuit in the i+1-th control cycle of the previous date can be output, and then the training community load power can be compared with the measured historical community load power, that is, the deviation between the two can be solved, and the updated training loss function can be obtained by using the deviation. And the updated training loss function is reduced by the gradient descent method, so as to update the above-mentioned trained community load power prediction model and obtain the updated community load power prediction model, so that the updated community load power prediction model is more suitable for predicting the community load power at multiple moments in the i+1-th control cycle. In this case, the community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle of the current date can be input into the updated community load power prediction model to obtain the predicted community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i+1-th control cycle of the current date, so that the predicted community load power has a higher prediction accuracy.

[0053] In this way, after the community load power prediction model is trained by the historical community load power of multiple historical dates, the trained community load power prediction model can be updated and trained by the historical community load power of the i-th control cycle and the i+1-th control cycle of the previous date, so that the updated community load power prediction model is more suitable for predicting the community load power at multiple moments in the i+1-th control cycle, further improving the prediction accuracy.

[0054] According to one embodiment of the present invention, the charging piles being used at the end of the i-th control cycle of the current date can be determined, and the charging time of these charging piles can be determined, and then the predicted power consumption of each charging pile at multiple moments in the i+1-th control cycle of the current date can be predicted.

[0055] According to one embodiment of the present invention, the average charging time is determined based on the charging time of multiple charging piles in multiple historical dates; the average usage rate of the charging piles at each moment of the i+1th control cycle in multiple historical dates is obtained; the predicted usage time of the charging piles being used in the i+1th control cycle is determined based on the average charging time and the charged time; the predicted power consumption of each charging pile at multiple moments of the i+1th control cycle of the current date is obtained based on the average usage rate and the predicted usage time of the charging piles being used in the i+1th control cycle.

[0056] For example, the charging time of each charging pile used each time on multiple historical dates may be determined, and then these charging times may be summed up, and then the summed value may be divided by the total number of charging times of all charging piles to obtain the above average charging time.

[0057] For example, the average utilization rate of the charging piles at each moment in the i+1th control cycle of multiple historical dates can be counted. For example, the ratio between the number of charging piles being used at the first moment of the i+1th control cycle of multiple historical dates to the total number of charging piles can be counted as the utilization rate of the charging piles at the first moment of the i+1th control cycle of multiple historical dates. After averaging, the average utilization rate of the charging piles at the first moment of the i+1th control cycle of multiple historical dates can be obtained. Furthermore, the average utilization rate of the charging piles at each moment of the i+1th control cycle of multiple historical dates can be obtained in the above manner. After averaging the average utilization rate of the charging piles at each moment, the average utilization rate of the charging piles at each moment of the i+1th control cycle in multiple historical dates can be obtained.

[0058] For example, after obtaining the average charging time, the predicted usage time of the charging pile being used in the (i+1)th control cycle can be obtained by subtracting the average usage time from the charged time.

[0059] According to one embodiment of the present invention, based on the average usage rate and the predicted usage time of the charging pile being used in the i+1th control cycle, the predicted power consumption of each charging pile at multiple moments of the i+1th control cycle of the current date is obtained, including: if the sth charging pile is the charging pile being used, then when the ratio of the predicted usage time of the sth charging pile in the i+1th control cycle to the total duration of the control cycle is less than or equal to the average usage rate, determine the time from the 1st moment to the nth moment in the i+1th control cycle of the sth charging pile; p The predicted power consumption at a given moment is P p , No. The predicted power consumption from moment to moment n is P p , nth p From time to The predicted power consumption at the moment is 0, where n p Δt≤Δt p , and (n p +1)Δt>Δt p , Δt is the interval between adjacent moments, Δt p is the predicted usage time, P p is the preset charging power of the charging pile, ΔT is the duration of the control cycle, R aveis the average usage rate; when the ratio of the predicted usage time of the sth charging pile in the i+1th control cycle to the total duration of the control cycle is greater than the average usage rate, determine the time from the first moment to the nth moment of the sth charging pile in the i+1th control cycle p The predicted power consumption at a given moment is P p , nth p +1 moment to the nth moment is 0; if the sth charging pile is not the charging pile in use, determine the sth charging pile in the i+1th control cycle The predicted power consumption from moment to moment n is P p , from the first moment to the The predicted power consumption at this moment is 0.

[0060] According to one embodiment of the present invention, since the above-mentioned average usage rate is determined, it can be assumed that the total usage time of the charging pile in the i+1th control cycle is the product of the total duration of the control cycle and the average usage rate. Therefore, for the sth charging pile among multiple charging piles, if the charging pile is the charging pile being used at the end of the i-th control cycle, then the remaining time of the use of the charging pile this time is the predicted usage time of the sth charging pile in the i+1th control cycle. If the ratio of the predicted usage time to the total duration of the control cycle is less than or equal to the average usage rate, that is, the predicted usage time is less than or equal to the total usage time of the charging pile in the i+1th control cycle, then the usage time of the charging pile in the i+1th control cycle can be supplemented to the total usage time at the end of the i+1th control cycle. Therefore, it can be predicted that the sth charging pile from the 1st moment to the nth moment in the i+1th control cycle p moments are used, that is, from the 1st moment to the nth moment p The usage time at the moment is the predicted usage time. The duration from the first moment to the nth moment is also used, that is, at the end of the i+1th control cycle, the duration of use of the charging pile in the i+1th control cycle is supplemented to the total duration of use. In other words, ΔTR is used again at the end of the i+1th control cycle. ave -Δt p If the charging pile is used, the predicted power consumption is the preset charging power of the charging pile, otherwise it is 0.

[0061] According to one embodiment of the present invention, if the sth charging pile is the charging pile being used at the end of the i-th control cycle, and the ratio of the predicted usage time in the i+1-th control cycle to the total usage time of the control cycle is greater than the average usage rate, that is, the predicted usage time is greater than the total usage time of the charging pile in the i+1-th control cycle, then it is determined that the charging pile is only used at the time within the predicted usage time, and is not used at other times, that is, from the 1st moment to the nth moment in the i+1-th control cycle p The time is used and the other time is not used.

[0062] According to one embodiment of the present invention, if the sth charging pile is not the charging pile in use, it is assumed that at the end of the i+1th control cycle, the charging pile has been used for the above total usage time, that is, The charging pile is used from the first moment to the nth moment, and is not used at other moments. Of course, any time period in the (i+1)th control cycle (the length of the time period is equal to the total usage time) can also be selected as the time period for the charging pile to be used, and the present invention does not limit this.

[0063] In this way, the total usage time of each charging pile in the i+1th control cycle can be estimated by the average usage rate, which can be compared with the predicted usage time of the sth charging pile in the i+1th control cycle to determine the time period in which the sth charging pile is used and the time period in which it is not used in the i+1th control cycle, and then the predicted power consumption at each moment can be determined, which can improve the objectivity and accuracy of the predicted power consumption.

[0064] According to one embodiment of the present invention, after determining the predicted community load power and the predicted power consumption of the charging pile in the (i+1)th control cycle, the predicted access position of each charging pile may be determined.

[0065] According to one embodiment of the present invention, the predicted access position of each charging pile in the i+1th control cycle of the current date is determined according to the predicted community load power and the predicted power consumption, including: determining the constraints of the optimization model according to the predicted community load power and the predicted power consumption; determining the objective function of the optimization model according to the predicted community load power and the predicted power consumption, and the access position of each charging pile in the i+1th control cycle of the current date; solving the optimal solution of the optimization model according to the objective function and the constraints, and obtaining the predicted access position of each charging pile in the i+1th control cycle of the current date.

[0066] According to one embodiment of the present invention, the optimization model may be a nonlinear programming model, a genetic algorithm model, etc., which can be used to solve the optimal solution based on a given objective function and constraints, that is, to solve the solution that can satisfy the objective function to the greatest extent under the constraints.

[0067] According to an embodiment of the present invention, the constraint conditions of the optimization model are determined according to the predicted community load power and the predicted power consumption, including: determining the constraint conditions of the optimization model according to formulas (3), (4), (5) and (6),

[0068]

[0069] P i+1,j,k ≤P up (4)

[0070] max j∈[1,3] (P i+1,j,k )-in j∈[1,3] (P i+1,j,k )≤αP up (5)

[0071]

[0072] Among them, P i+1,j,k is the predicted load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the i+1-th control cycle on the current date, P c,i+1,j,k is the predicted community load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the i+1-th control cycle on the current date, P p,i+1,As(i+1),, is the predicted power consumption of the sth charging pile at the kth moment in the i+1th control cycle of the current date, As(i+1) is the access position of the sth charging pile in the i+1th control cycle of the current date, As(i) is the access position of the sth charging pile in the i-th control cycle of the current date, P up is the load power upper limit of each phase power supply line in the three-phase power supply circuit, α is the first preset ratio, β is the second preset ratio, max is the maximum value function, min is the minimum value function, m is the number of charging piles, and if is the conditional function.

[0073] According to one embodiment of the present invention, formula (3) describes the relationship between the predicted load power of each phase power supply line in the three-phase power supply circuit at each moment in the i+1th control cycle, the predicted community load power and the predicted power consumption of each charging pile, that is, the predicted load power of a phase power supply line at the kth moment is equal to the sum of the predicted community load power at the kth moment and the predicted power consumption of the charging pile connected to the phase power supply line at the kth moment.

[0074] According to one embodiment of the present invention, formula (4) describes the limitation of the predicted load power of each phase power supply line in the three-phase power supply circuit at each moment in the (i+1)th control cycle, that is, the load power upper limit of each phase power supply line cannot be exceeded.

[0075] According to one embodiment of the present invention, formula (5) describes the load balancing of each phase power supply line in the three-phase power supply circuit at each moment, that is, the difference between the maximum predicted load power and the minimum predicted load power of each phase power supply line in the three-phase power supply circuit at each moment is constrained, that is, it cannot exceed aP up , thereby ensuring that the loads of the three power supply lines are relatively balanced, thereby protecting the power supply lines.

[0076] According to one embodiment of the present invention, formula (6) describes the restriction on changing the access position of the charging pile, that is, if [As (i + 1) ≠ As (i), 1, 0] means that if the sth charging pile changes the access position, the conditional function value is 1, otherwise it is 0. By summing the conditional function values, the number of charging piles that change the access position can be obtained. This condition can limit the ratio between the number of charging piles that change the access position and the total number of charging piles to be less than or equal to a second preset ratio, thereby avoiding large-scale changes in the access position of the charging piles, resulting in unbalanced three-phase loads, and sudden and drastic changes in the circuit load, resulting in easy damage to the circuit.

[0077] According to one embodiment of the present invention, the objective function of the optimization model is determined according to the predicted community load power and the predicted power consumption, as well as the access location of each charging pile in the i-th control cycle of the current date, including: determining the objective function of the optimization model according to formulas (7) and (8).

[0078]

[0079]

[0080] According to one embodiment of the present invention, formula (7) is the sum of the differences between the maximum predicted load power and the minimum predicted load power of each phase power supply line in the three-phase power supply circuit at each moment, that is, the sum of the imbalance levels of the three loads in the i+1th control cycle. Minimizing the sum of the imbalance levels of the three-phase loads can be used as an optimization goal, that is, as an item in the objective function, so that the access position of the optimized charging pile can make the three-phase load as balanced as possible.

[0081] According to an embodiment of the present invention, formula (8) represents minimizing the number of charging piles that change access positions, that is, using the least number of adjustments to achieve the goal of balancing the three-phase load as much as possible and satisfying the power consumption of the community and the charging piles as much as possible. This minimizes the number of adjustments and reduces the probability of circuit damage caused by sudden and significant changes in circuit load.

[0082] According to one embodiment of the present invention, after setting the above objective function and constraints, the unknown quantities therein (i.e., the predicted access positions of each charging pile) can be optimized and solved, so as to obtain the access positions of the charging piles that maximize the degree of satisfaction of the objective function under the constraints, as the predicted access positions of each charging pile.

[0083] In this way, by setting the objective function and constraints, in the process of solving the predicted access position of the charging pile, it is possible to achieve the goals of balancing the three-phase load as much as possible, meeting the electricity demand of the community and the charging pile as much as possible, and reducing the probability of circuit damage caused by sudden and large changes in circuit load, while adjusting the access position as little as possible, thereby improving the rationality and accuracy of the predicted access position.

[0084] According to one embodiment of the present invention, after obtaining the predicted access positions of the above-mentioned charging piles, the predicted access positions can be used to generate switch device adjustment instructions, that is, instructions for adjusting the adjustment switches corresponding to the charging piles that need to change the access positions, and send them to the switch devices. The switch devices can operate the adjustment switches so that in the i+1th control cycle of the current date, the access positions of the charging piles in the three-phase power supply circuit are consistent with the predicted access positions.

[0085] According to the vehicle charging system based on the analysis of dynamic energy usage data of the embodiment of the present invention, the predicted power consumption of the charging piles and the predicted community load power of the next control cycle can be predicted based on the historical data of the power supply circuit and the charging piles in the community, so as to optimize and adjust the access position of each charging pile in the three-phase power supply circuit, so as to make full use of the surplus power of the power supply circuit, provide power for the charging piles, reduce the probability of insufficient power supply, and do not need to transform the power supply circuit, reduce the reinvestment of power facilities, and reduce the power supply cost. When determining the historical community load power, the historical data of the power consumption provided for the community's power load after removing the power provided for the charging piles can be defined, and the charging piles connected to each phase of the power supply line can be screened by means of conditional functions, and the sum of the historical power consumption of these charging piles can be determined, so as to accurately solve the historical community load power and provide an accurate data basis for subsequent prediction and optimization. When updating the community load power prediction model, after training the community load power prediction model with the historical community load power of multiple historical dates, the trained community load power prediction model can be updated and trained with the historical community load power of the i-th control cycle and the i+1-th control cycle of the previous date, so that the updated community load power prediction model is more suitable for predicting the community load power at multiple moments in the i+1-th control cycle, further improving the prediction accuracy. When determining the predicted power consumption of the charging pile, the total usage time of each charging pile in the i+1-th control cycle can be estimated by the average usage rate, and then compared with the predicted usage time of the s-th charging pile in the i+1-th control cycle to determine the time period in which the s-th charging pile is used and the time period in which it is not used in the i+1-th control cycle, and then determine the predicted power consumption at each moment, which can improve the objectivity and accuracy of the predicted power consumption. When solving the predicted access position of the charging pile, by setting the objective function and constraints, in the process of solving the predicted access position of the charging pile, it is possible to achieve the goals of balancing the three-phase load as much as possible, meeting the electricity demand of the community and the charging pile as much as possible, and reducing the probability of circuit damage caused by sudden and large changes in circuit load, while adjusting the access position as little as possible, thereby improving the rationality and accuracy of the predicted access position.

[0086] It should be understood by those skilled in the art that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may be deformed or modified in any way without departing from the principles.

[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle charging system based on dynamic energy usage data analysis, characterized in that: include: Controllers and switchgear; Wherein, the switch device includes a plurality of regulating switches, and the regulating switches are used to adjust the access position of the charging pile in the three-phase power supply circuit; The controller is used to: At multiple moments of the i-th control cycle of the current date, the load power of each phase power supply line in the three-phase power supply circuit of the community, the connection position of each charging pile in the three-phase power supply circuit, and the power consumption of each charging pile are obtained; Obtain the charging time of a charging pile currently in use among multiple charging piles; Obtain multiple moments of the i-th control cycle and multiple moments of the i+1-th control cycle on the previous date, the historical load power of each phase power supply line in the three-phase power supply circuit, the historical access position of each charging pile in the three-phase power supply circuit, and the historical power consumption of each charging pile; According to the historical load power, the historical access position, the historical power consumption, the access position of each charging pile in the three-phase power supply circuit, the power consumption and the load power, the predicted community load power of each phase power supply line in the three-phase power supply circuit is obtained at multiple moments of the i+1th control cycle of the current date; According to the charging time, the predicted power consumption of each charging pile is obtained at multiple moments of the (i+1)th control cycle of the current date; Determine the predicted access position of each charging pile in the (i+1)th control cycle of the current date according to the predicted community load power and the predicted power consumption; generating a switch device adjustment instruction according to the predicted access position; The switch device adjustment instruction is sent to the switch device, so that in the (i+1)th control cycle of the current date, the access position of each charging pile in the three-phase power supply circuit is consistent with the predicted access position.

2. The vehicle charging system based on dynamic energy usage data analysis according to claim 1, characterized in that: According to the historical load power, the historical access position, the historical power consumption, the access position of each charging pile in the three-phase power supply circuit, the power consumption and the load power, the predicted community load power of each phase power supply line in the three-phase power supply circuit is obtained at multiple moments of the i+1th control cycle of the current date, including: According to the historical load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle and the i+1-th control cycle of the previous date, the historical access position of each charging pile in the three-phase power supply circuit in the i-th control cycle and the i+1-th control cycle of the previous date, and the historical power consumption of each charging pile in the i-th control cycle and the i+1-th control cycle of the previous date, determine the historical community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle and the i+1-th control cycle of the previous date; Determine the community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle of the current date according to the load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle of the current date, the access position of each charging pile in the three-phase power supply circuit in the i-th control cycle of the current date, and the power consumption of each charging pile in the i-th control cycle of the current date; According to the historical community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle and the i+1-th control cycle of the previous date, and the community load power at multiple moments in the i-th control cycle of the current date, the predicted community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i+1-th control cycle of the current date is obtained.

3. The vehicle charging system based on dynamic energy usage data analysis according to claim 2, characterized in that: According to the historical load power of each phase power supply line in the three-phase power supply circuit at multiple times in the i-th control cycle and the i+1-th control cycle of the previous date, the historical access position of each charging pile in the three-phase power supply circuit in the i-th control cycle and the i+1-th control cycle of the previous date, and the historical power consumption of each charging pile in the i-th control cycle and the i+1-th control cycle of the previous date, the historical community load power of each phase power supply line in the three-phase power supply circuit at multiple times in the i-th control cycle and the i+1-th control cycle of the previous date is determined, including: According to the formula Determine the historical community load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the ith control cycle on the previous date ,in, is the historical load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the ith control cycle on the previous date, is the historical power consumption of the sth charging pile at the kth moment in the ith control cycle on the previous date, is the access position of the sth charging pile in the i-th control cycle of the previous date, m is the number of charging piles, if is the conditional function, which means that if the access position of the sth charging pile in the i-th control cycle of the previous date is the j-th phase power supply line, then the conditional function value is , otherwise the conditional function value is 0; According to the formula Determine the historical community load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the i+1-th control cycle on the previous date ,in, is the historical load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the i+1-th control cycle on the previous date, is the historical power consumption of the sth charging pile at the kth moment in the i+1th control cycle on the previous date, is the access position of the sth charging pile in the i+1th control cycle of the previous date, m is the number of charging piles, if is the conditional function, which means that if the access position of the sth charging pile in the i+1th control cycle of the previous date is the jth phase power supply line, then the conditional function value is , otherwise the conditional function value is 0.

4. The vehicle charging system based on dynamic energy usage data analysis according to claim 2, characterized in that: According to the historical community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle and the i+1-th control cycle of the previous date, and the community load power at multiple moments in the i-th control cycle of the current date, the predicted community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i+1-th control cycle of the current date is obtained, including: The community load power prediction model is trained by using the historical community load power at multiple moments in the control period of multiple historical dates before a previous date to obtain a trained community load power prediction model; The trained community load power prediction model is input with the historical community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle on the previous date to obtain the trained community load power of each phase power supply line in the three-phase power supply circuit in the i+1-th control cycle on the previous date; Obtaining an updated training loss function of a trained community load power prediction model according to the historical community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the (i+1)th control cycle of the previous date and the training community load power; According to the updated training loss function, the trained community load power prediction model is updated to obtain an updated community load power prediction model; The community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i-th control cycle of the current date is input into the updated community load power prediction model to obtain the predicted community load power of each phase power supply line in the three-phase power supply circuit at multiple moments in the i+1-th control cycle of the current date.

5. The vehicle charging system based on dynamic energy usage data analysis according to claim 1, characterized in that: According to the charging time, the predicted power consumption of each charging pile at multiple moments of the (i+1)th control cycle of the current date is obtained, including: Determine the average charging time based on the charging time of multiple charging piles on multiple historical dates; Obtain the average usage rate of the charging pile at each moment of the (i+1)th control cycle in multiple historical dates; Determine the predicted usage time of the charging pile being used in the (i+1)th control cycle according to the average charging time and the charged time; According to the average usage rate and the predicted usage time of the charging pile being used in the (i+1)th control cycle, the predicted power consumption of each charging pile at multiple moments of the (i+1)th control cycle of the current date is obtained.

6. The vehicle charging system based on dynamic energy usage data analysis according to claim 5, characterized in that: According to the average usage rate and the predicted usage time of the charging pile being used in the i+1th control cycle, the predicted power consumption of each charging pile at multiple moments of the i+1th control cycle of the current date is obtained, including: If the sth charging pile is a charging pile being used, then when the ratio of the predicted usage time of the sth charging pile in the i+1th control cycle to the total duration of the control cycle is less than or equal to the average usage rate, determine the usage time of the sth charging pile from the first moment to the first moment in the i+1th control cycle. The predicted power consumption at a given moment is equal to , No. The predicted power consumption from moment to moment n is equal to , No. From time to The predicted power consumption at the moment is 0, where ,and , is the interval between adjacent moments, The duration used for the prediction, is the preset charging power of the charging pile. is the duration of the control cycle, is the average utilization rate; When the ratio of the predicted usage time of the sth charging pile in the i+1th control cycle to the total duration of the control cycle is greater than the average usage rate, determine the time from the first moment to the first moment of the sth charging pile in the i+1th control cycle. The predicted power consumption at a given moment is equal to , No. The predicted power consumption from the moment to the nth moment is 0; If the sth charging pile is not a charging pile in use, determine the sth charging pile in the i+1th control cycle. The predicted power consumption from moment to moment n is equal to , from the first moment to the The predicted power consumption at this moment is 0.

7. The vehicle charging system based on dynamic energy usage data analysis according to claim 1, characterized in that: Determining the predicted access position of each charging pile in the (i+1)th control cycle of the current date according to the predicted community load power and the predicted power consumption, including: Determining the constraint conditions of the optimization model according to the predicted community load power and the predicted power consumption; Determine the objective function of the optimization model according to the predicted community load power and the predicted power consumption, as well as the access location of each charging pile in the i-th control cycle of the current date; According to the objective function and the constraint conditions, the optimal solution of the optimization model is solved to obtain the predicted access position of each charging pile in the (i+1)th control cycle of the current date.

8. The vehicle charging system based on dynamic energy usage data analysis according to claim 7, characterized in that: According to the predicted community load power and the predicted power consumption, the constraints of the optimization model are determined, including: According to the formula Determine the constraints of the optimization model, where is the predicted load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the i+1-th control cycle on the current date, is the predicted community load power of the j-th phase power supply line in the three-phase power supply circuit at the k-th moment in the i+1-th control cycle on the current date, is the predicted power consumption of the sth charging pile at the kth moment in the i+1th control cycle on the current date, is the access position of the sth charging pile in the i+1th control cycle on the current date, is the access position of the sth charging pile in the i-th control cycle on the current date, is the upper limit of the load power of each phase of the three-phase power supply circuit. is the first preset ratio, is the second preset ratio, max is the maximum value function, min is the minimum value function, m is the number of charging piles, and if is the conditional function.

9. The vehicle charging system based on dynamic energy usage data analysis according to claim 8, characterized in that: According to the predicted community load power and the predicted power consumption, and the access location of each charging pile in the i-th control cycle of the current date, the objective function of the optimization model is determined, including: According to the formula Determine the objective function of the optimization model, where n is the total number of moments included in the i+1th control cycle.

Images