A charging station power purchase method and device, electronic equipment and storage medium

Abstract

The application provides a charging station electricity purchasing method and device, electronic equipment and a storage medium, which are applied to a charging system. The charging system comprises at least one charging station for charging electric vehicles of users. For each charging station, a photovoltaic power station and a power storage device are arranged. The power stored in the power storage device comprises power purchased from a power grid by the charging station and power generated by the photovoltaic power station. The method comprises the following steps: establishing a power purchasing strategy mathematical model; constructing a reward function of the power purchasing strategy mathematical model; solving the power purchasing strategy mathematical model based on the reward function to obtain action variables at different times, i.e., power purchasing strategies of each charging station at different times; and for each charging station, controlling the charging station to purchase power from the power grid according to the power purchasing strategy of the charging station at different times. The application can control the charging station to purchase power with the goal of maximizing operation returns.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrical engineering, in particular to a charging station power purchasing method and device, electronic equipment and storage medium. BACKGROUND

[0002] With the development of the times and the progress of science and technology, electric vehicles are increasingly appearing in people's daily life. Therefore, the corresponding charging stations and charging piles for charging electric vehicles have also gradually increased.

[0003] A good energy management strategy of an electric vehicle charging station can not only balance the charging and discharging peak of electric vehicles, reduce the idle rate of charging piles of the charging station, and relieve traffic congestion during peak hours, but also can expand the operation return of the charging station, attract more companies to enter the operation market, form a benign competition, speed up the construction of a smart interconnected city. However, at present, the energy management strategy of the charging station is mostly determined by experience. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a charging station power purchasing method and device, electronic equipment and storage medium, which can control the charging station to purchase power with the goal of maximizing operation return.

[0005] In a first aspect, the embodiments of the present application provide a charging station power purchasing method, applied to a charging system, the charging system comprising at least one charging station for charging electric vehicles of users, each charging station being provided with a photovoltaic power station and a power storage device, the amount of electricity stored in the power storage device including the amount of electricity purchased by the charging station from the power grid and the amount of electricity generated by the photovoltaic power station; the method comprising:

[0006] The electric vehicle charging load of each charging station at different times predicted by a charging load prediction model, the amount of electricity generated by the photovoltaic power station of each charging station at different times predicted by the charging load prediction model, the amount of electricity stored by the power storage device of each charging station at different times, the electricity price of the power grid at different times, and the operation return of each charging station at different times are constructed as state variables, and the amount of electricity purchased by each charging station from the power grid at different times is constructed as an action variable, and a power purchase strategy mathematical model is established;

[0007] An reward function of the power purchase strategy mathematical model is constructed;

[0008] Based on the reward function, the power purchase strategy mathematical model is solved to obtain the action variable at different times, i.e., the power purchase strategy of each charging station at different times;

[0009] For each of the charging stations, the charging station is controlled to purchase electricity from the power grid according to a purchase electricity strategy of the charging station at different time points.

[0010] In a possible implementation, the reward function is an operation return of each of the charging stations at different time points.

[0011] In a possible implementation, based on the reward function, the purchase electricity strategy mathematical model is solved to obtain the action variable at different time points, that is, the purchase electricity strategy of each of the charging stations at different time points, including:

[0012] Based on the reward function, the purchase electricity strategy mathematical model is solved by using a double-delay deep deterministic policy gradient algorithm to obtain the action variable at different time points, that is, the purchase electricity strategy of each of the charging stations at different time points.

[0013] In a possible implementation, in the process of solving the purchase electricity strategy mathematical model, the method further includes:

[0014] For each of the action variables, target noise is added to the action variable to obtain a noise action variable, and the noise action variable is used as the action variable, wherein the target noise is obtained by target sampling of noise conforming to a beta distribution of a probability density function, and the target sampling is any one of the following: Thompson sampling, importance sampling, marginal importance sampling, and Monte Carlo sampling.

[0015] In a second aspect, the embodiments of the present application further provide a charging station electricity purchasing device applied to a charging system, the charging system including at least one charging station for charging an electric vehicle of a user, and for each of the charging stations, the charging station is provided with a photovoltaic power station and a power storage device, and the amount of electricity stored in the power storage device includes the amount of electricity purchased by the charging station from a power grid and the amount of electricity generated by the photovoltaic power station; the device includes:

[0016] A model establishing module is configured to construct a state variable by using the electric vehicle charging load of each of the charging stations at different time points predicted by a charging load prediction model, the amount of electricity generated by the photovoltaic power station of each of the charging stations at different time points predicted by the charging load prediction model, the amount of electricity stored in the power storage device of each of the charging stations at different time points, the electricity price of the power grid at different time points, and the operation return of each of the charging stations at different time points, construct an action variable by using the amount of electricity purchased by each of the charging stations from the power grid at different time points, and establish a purchase electricity strategy mathematical model.

[0017] A function constructing module is configured to construct a reward function of the purchase electricity strategy mathematical model.

[0018] a solving module configured to solve the electricity-buying strategy mathematical model based on the reward function, and obtain the action variable at different time points, i.e., the electricity-buying strategy of each charging station at different time points;

[0019] a control module configured to control each charging station to buy electricity from the power grid according to the electricity-buying strategy of the charging station at different time points.

[0020] In a possible implementation, the reward function is the operation return of each charging station at different time points.

[0021] In a possible implementation, the solving module is specifically configured to:

[0022] use a double-delay deep deterministic policy gradient algorithm to solve the electricity-buying strategy mathematical model based on the reward function, and obtain the action variable at different time points, i.e., the electricity-buying strategy of each charging station at different time points.

[0023] In a possible implementation, the apparatus further includes:

[0024] a noise adding module configured to, in the process of solving the electricity-buying strategy mathematical model, for each action variable, add target noise to the action variable to obtain a noise action variable, and use the noise action variable as the action variable, wherein the target noise is obtained by target sampling of noise conforming to a beta distribution of a probability density function, and the target sampling is any one of the following: Thompson sampling, importance sampling, marginal importance sampling, and Monte Carlo sampling.

[0025] In a third aspect, an electronic device is provided, including a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium through the bus. The processor executes the machine-readable instructions to perform the steps of the charging station electricity-buying method according to any one of the first aspect.

[0026] In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. When the computer program is run by a processor, the steps of the charging station electricity-buying method according to any one of the first aspect are performed.

[0027] The charging station electricity-buying method, apparatus, electronic device, and storage medium provided by the embodiments of the present application can control the charging station to buy electricity with the goal of maximizing operation return. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be regarded as limiting the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0029] Figure 1 A flow chart of a charging station electricity purchasing method provided by an embodiment of the present application is shown;

[0030] Figure 2 A flow chart of another charging station electricity purchasing method provided by an embodiment of the present application is shown;

[0031] Figure 3 A flow chart of another charging station electricity purchasing method provided by an embodiment of the present application is shown;

[0032] Figure 4 A structural schematic diagram of a charging station electricity purchasing device provided by an embodiment of the present application is shown;

[0033] Figure 5 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. It should be understood that the drawings in the present application only play the purpose of illustration and description, and are not used to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn according to the actual proportion. The flow chart shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow chart can not be implemented in sequence, and the steps without logical context relationship can be reversed in sequence or implemented simultaneously. In addition, one or more other operations can be added to the flow chart or removed from the flow chart under the guidance of the content of the present application by those skilled in the art.

[0035] In addition, the described embodiments are only some of the embodiments of the present application, not all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0036] It should be noted that the term "comprising" will be used in the embodiments of the present application to specify the presence of the features subsequently stated, but not to exclude the addition of further features.

[0037] To facilitate the understanding of the present embodiment, a charging station electricity purchasing method, device, electronic equipment and storage medium provided by the present application are introduced in detail.

[0038] Referring to Figure 1 The flow chart of a charging station electricity purchasing method provided by the present application is shown in FIG. 1. The method is applied to a charging system, which includes at least one charging station for charging electric vehicles of users. For each charging station, a photovoltaic power station and a power storage device are provided. The power stored in the power storage device includes the power purchased from a power grid and the power generated by the photovoltaic power station. The method includes the following steps.

[0039] S101, the state variables are constituted by the electric vehicle charging load of each charging station at different time points predicted by a charging load prediction model, the power generated by the photovoltaic power station of each charging station at different time points predicted by the charging load prediction model, the power stored in the power storage device of each charging station at different time points, the electricity price of the power grid at different time points, and the operation return of each charging station at different time points. The action variables are constituted by the power purchased from the power grid by each charging station at different time points. A power purchase strategy mathematical model is established.

[0040] For example, the operation return of each charging station at time t (t is a certain time point in different time points) can be obtained in the following manner:

[0041]

[0042] wherein, is the sum of the power sold by each charging station at time t; is the electricity price at time t (as specified); is the sum of the environmental benefits generated by each charging station; is the sum of the fixed load power consumption of each charging station at time t; SOE t is the sum of the power storage of the power storage device of each charging station at time t; is the power generated by the photovoltaic power station of each charging station at time t; is the electricity price of the power grid at time t (as specified).

[0043] S102, a reward function of the power purchase strategy mathematical model is constructed.

[0044] The reward function can be an operation return of each charging station at different time points.

[0045] S103, based on the reward function, solving the buying electricity strategy mathematical model to obtain the action variable at different time points, i.e., the buying electricity strategy of each charging station at different time points.

[0046] The buying electricity strategy of each charging station at different time points is the amount of electricity that each charging station needs to purchase from the power grid at different time points.

[0047] S104, for each charging station, controlling the charging station to purchase electricity from the power grid according to the buying electricity strategy of the charging station at different time points.

[0048] That is, for each time point, controlling the charging station to purchase electricity from the power grid according to the buying electricity strategy at the time point (the amount of electricity that needs to be purchased from the power grid at the time point).

[0049] In a possible implementation, the reward function is an operation return of each charging station at different time points.

[0050] Referring to Figure 2 Fig. 4 is a flowchart of another method for charging station electricity purchase provided by an embodiment of the present application. In a possible implementation, based on the reward function, the buying electricity strategy mathematical model is solved to obtain the action variable at different time points, i.e., the buying electricity strategy of each charging station at different time points, including:

[0051] S201, based on the reward function, using a double-delay deep deterministic policy gradient algorithm to solve the buying electricity strategy mathematical model to obtain the action variable at different time points, i.e., the buying electricity strategy of each charging station at different time points.

[0052] The double-delay deep deterministic policy gradient algorithm (TD3, Twin Delayed Deep Deterministic Policy Gradient) adds a Critic network to the DDPG algorithm. The TD3 has two Critic networks and an Actor network on the main network, and the Target target network also has a backup of the main network.

[0053] Referring to Figure 3 Fig. 5 is a flowchart of another method for charging station electricity purchase provided by an embodiment of the present application. In a possible implementation, in the process of solving the buying electricity strategy mathematical model, the method further includes:

[0054] S301, for each of the action variables, appending a target noise to the action variable to obtain a noise action variable, and taking the noise action variable as the action variable, wherein the target noise is obtained by target sampling of noise conforming to a beta distribution of a probability density function, and the target sampling is any one of the following: Thompson sampling, importance sampling, marginalization importance sampling, and Monte Carlo sampling.

[0055] By appending the target noise to the action variable, the action variable can be more stable.

[0056] Preferably, the target sampling is Thompson sampling.

[0057] The charging station electricity purchasing method provided by the embodiment of the application can control the charging station to purchase electricity with the goal of maximizing operation returns.

[0058] Referring to Figure 4 FIG. 1 shows a structure schematic diagram of a charging station electricity purchasing device provided by an embodiment of the application, which is applied to a charging system including at least one charging station for charging electric vehicles of users. For each of the charging stations, the charging station is provided with a photovoltaic power station and a power storage device, and the amount of electricity stored in the power storage device includes the amount of electricity purchased by the charging station from a power grid and the amount of electricity generated by the photovoltaic power station. The device includes:

[0059] A model establishing module 401 is configured to establish a buy electricity strategy mathematical model by taking the electric vehicle charging load of each of the charging stations at different time instants predicted by a charging load prediction model, the amount of electricity generated by the photovoltaic power station of each of the charging stations at different time instants predicted by the charging load prediction model, the amount of electricity stored by the power storage device of each of the charging stations at different time instants, the electricity price of the power grid at different time instants, and the operation returns of each of the charging stations at different time instants as state variables, and taking the amount of electricity purchased by each of the charging stations from the power grid at different time instants as action variables.

[0060] A function constructing module 402 is configured to construct a reward function of the buy electricity strategy mathematical model.

[0061] A solving module 403 is configured to solve the buy electricity strategy mathematical model based on the reward function to obtain the action variables at different time instants, i.e., the buy electricity strategies of each of the charging stations at different time instants.

[0062] A control module 404 is configured to control each of the charging stations to purchase electricity from the power grid according to the buy electricity strategy of the charging station at different time instants.

[0063] In a possible implementation, the reward function is an operation return of each charging station at different time points.

[0064] In a possible implementation, the solving module 403 is specifically configured to:

[0065] Based on the reward function, the mathematical model of the electricity purchasing strategy is solved using a double-delay deep deterministic policy gradient algorithm, and an action variable at different time points is obtained, i.e., an electricity purchasing strategy of each charging station at different time points.

[0066] In a possible implementation, the apparatus further includes:

[0067] The noise adding module is configured to, in the process of solving the mathematical model of the electricity purchasing strategy, for each action variable, add a target noise to the action variable to obtain a noise action variable, and use the noise action variable as the action variable, wherein the target noise is obtained by target sampling of a noise conforming to a beta distribution of a probability density function, and the target sampling is any one of the following: Thompson sampling, importance sampling, marginal importance sampling, and Monte Carlo sampling.

[0068] The charging station electricity purchasing apparatus provided by the embodiments of the present application can control the charging station to purchase electricity with the goal of maximizing operation return.

[0069] Referring to Figure 5 The electronic device 500 provided by the embodiments of the present application includes a processor 501, a memory 502, and a bus. The memory 502 stores machine readable instructions executable by the processor 501. When the electronic device is running, the processor 501 and the memory 502 communicate through the bus. The processor 501 executes the machine readable instructions to perform the steps of the charging station electricity purchasing method.

[0070] Specifically, the memory 502 and the processor 501 can be general memory and processor, which are not specifically limited here. When the processor 501 runs the computer program stored in the memory 502, the charging station electricity purchasing method can be performed.

[0071] Corresponding to the charging station electricity purchasing method, the embodiments of the present application further provide a computer readable storage medium, which stores a computer program. When the computer program is run by a processor, the steps of the charging station electricity purchasing method are performed.

[0072] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the system and the device described above can refer to the corresponding process in the method embodiment, and will not be repeated in the present application. In the several embodiments provided in the present application, it should be understood that the disclosed system, system and method can be implemented by other means. The above-described device embodiments are only schematic, for example, the division of the modules is only a logical function division, and in actual implementation, there can be another division manner, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed mutual ones can be indirect coupling or communication connection through some communication interfaces, devices or modules, and can be electrical, mechanical or other forms.

[0073] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical units, i.e., can be located in one place or distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0074] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0075] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, and various program code storage media.

[0076] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for purchasing electricity for charging stations, characterized in that, The method is applied to a charging system, the charging system including at least one charging station for charging users' electric vehicles, each of the charging stations being equipped with a photovoltaic power station and an energy storage device, the energy stored in the energy storage device including electricity purchased by the charging station from the grid and electricity generated by the photovoltaic power station; the method includes: The electric vehicle charging load of each charging station predicted by the charging load prediction model at different times, the electricity generated by the photovoltaic power generation station of each charging station at different times predicted by the charging load prediction model at different times, the electricity stored by the energy storage device of each charging station at different times, the electricity price of the power grid at different times, and the operating return of each charging station at different times constitute state variables, and the electricity purchased by each charging station from the power grid at different times constitutes action variables to establish a mathematical model for electricity purchase strategy. Construct the reward function for the mathematical model of the electricity purchase strategy; Based on the reward function, the mathematical model of the electricity purchase strategy is solved to obtain the action variables at different times, which are the electricity purchase strategies of each charging station at different times. For each of the aforementioned charging stations, the station is controlled to purchase electricity from the power grid according to its electricity purchase strategy at different times.

2. The method for purchasing electricity for a charging station according to claim 1, characterized in that, The reward function represents the operational return for each charging station at different times.

3. The method for purchasing electricity for charging stations according to claim 1, characterized in that, Based on the reward function, the mathematical model of the electricity purchase strategy is solved to obtain the action variables at different times, which are the electricity purchase strategies of each charging station at different times, including: Based on the reward function, the mathematical model of the electricity purchase strategy is solved using the double-delay deep deterministic policy gradient algorithm, and the action variables at different times are the electricity purchase strategies of each charging station at different times.

4. The method for purchasing electricity for charging stations according to claim 1, characterized in that, In solving the mathematical model of the electricity purchase strategy, the method further includes: For each action variable, target noise is added to the action variable to obtain a noisy action variable, and the noisy action variable is used as the action variable. The target noise is obtained by target sampling of noise whose probability density function conforms to the beta distribution. The target sampling is any of the following: Thompson sampling, importance sampling, marginal importance sampling, and Monte Carlo sampling.

5. A power purchase device for a charging station, characterized in that, An application to a charging system, the charging system including at least one charging station for charging users' electric vehicles, each of the charging stations being equipped with a photovoltaic power station and an energy storage device, the energy stored in the energy storage device including electricity purchased by the charging station from the grid and electricity generated by the photovoltaic power station; the device includes: The model building module is used to establish a mathematical model for electricity purchase strategy by taking the electric vehicle charging load of each charging station predicted by the charging load prediction model at different times, the electricity generated by the photovoltaic power generation station of each charging station at different times predicted by the charging load prediction model at different times, the electricity stored by the energy storage device of each charging station at different times, the electricity price of the power grid at different times, and the operating return of each charging station at different times as state variables, and taking the electricity purchased by each charging station from the power grid at different times as action variables. The function construction module is used to construct the reward function of the mathematical model of the electricity purchase strategy; The solution module is used to solve the mathematical model of the electricity purchase strategy based on the reward function, and obtain the action variables at different times, which are the electricity purchase strategies of each charging station at different times. The control module is used to control each charging station to purchase electricity from the power grid according to its electricity purchase strategy at different times.

6. The charging station power purchase device according to claim 5, characterized in that, The reward function represents the operational return for each charging station at different times.

7. The charging station power purchase device according to claim 5, characterized in that, The solution module is specifically used for: Based on the reward function, the mathematical model of the electricity purchase strategy is solved using the double-delay deep deterministic policy gradient algorithm, and the action variables at different times are the electricity purchase strategies of each charging station at different times.

8. The charging station power purchase device according to claim 5, characterized in that, The device further includes: The noise addition module is used to, during the process of solving the mathematical model of the electricity purchase strategy, add target noise to each action variable to obtain a noise action variable, and use the noise action variable as the action variable. The target noise is obtained by target sampling of noise whose probability density function conforms to the beta distribution. The target sampling is any of the following: Thompson sampling, importance sampling, marginal importance sampling, and Monte Carlo sampling.

9. An electronic device, characterized in that, include: The device includes a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the charging station power purchase method as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, performs the steps of the charging station electricity purchase method as described in any one of claims 1 to 4.

Images