A method, apparatus, equipment, medium, and product for determining a charging station configuration scheme.

Abstract

This application provides a method, apparatus, device, medium, and product for determining a charging station configuration scheme, relating to the field of charging equipment. The method acquires historical charging behavior data from multiple vehicles and, based on this data reflecting actual charging patterns, plots a charging load curve for a future second time period. This replaces the fixed or typical day load curve input in existing technologies, aligning with the dynamic characteristics of load changes and avoiding scenario adaptation bias caused by static assumptions. Furthermore, it integrates a photovoltaic output model, multiple energy storage system parameters, and multiple preset optimization objectives to construct a multi-objective optimization model that comprehensively covers energy supply, energy storage, and demand-side characteristics. This eliminates the need for manual supplementation of scenario adaptation parameters. Finally, through automatic solving of this multi-objective optimization model, it directly outputs a target configuration scheme that can guide adjustments to charging station configuration information, reducing the tedious process of manually verifying model parameters and repeatedly iterating and correcting, thus improving the efficiency of scheme determination.

Description

Technical Field

[0001] This invention belongs to the field of charging equipment, and specifically relates to a method, apparatus, equipment, medium and product for determining a charging station configuration scheme. Background Technology

[0002] With the widespread adoption of electric vehicles, the demand for charging infrastructure is growing rapidly. As a core node in energy replenishment, charging stations are facing severe challenges in their large-scale deployment and efficient operation. How to scientifically determine the configuration scheme of charging stations to achieve efficient energy utilization and stable and reliable operation has become a key issue in promoting the development of electric vehicles, making the confirmation of charging station configuration schemes particularly important.

[0003] In existing technologies, charging station configuration schemes are usually based on the charging load curve of a typical day. Using a static model and the assumption that the charging pile load is a constant value or can be predicted to fluctuate periodically, the required photovoltaic capacity and energy storage capacity of the charging station are calculated, and then the charging station configuration scheme is determined.

[0004] However, existing technologies suffer from low efficiency in determining charging station configuration schemes. These technologies rely on fixed or typical daily load curves as core input, using static models to calculate the capacity and layout of photovoltaic, energy storage, and charging piles. This approach fails to adequately consider the real-time dynamic changes in load and requires manual verification of model parameters and scenario adaptability, resulting in low efficiency in determining charging station configuration schemes. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, medium, and product for determining a charging station configuration scheme, in order to solve the problem of low efficiency in determining charging station configuration schemes in the prior art.

[0006] In a first aspect, embodiments of this application provide a method for determining a charging station configuration scheme, including:

[0007] The system acquires a photovoltaic output model, multiple energy storage system parameters, multiple optimization targets, and multiple charging behavior data of a target vehicle. The photovoltaic output model represents the ability of a preset charging station to convert solar energy into electrical energy. The multiple energy storage system parameters represent the state of the preset energy storage systems within the charging station. The target vehicle refers to any one of the preset multiple vehicles. The multiple charging behavior data represent the charging status of the target vehicle within a preset first time period, where the end time of the first time period is earlier than the current time.

[0008] A charging load curve is obtained by plotting multiple charging behavior data of multiple vehicles; wherein, the charging load curve is used to represent the change of the load of the charging station over time within a preset second time period, the start time of the second time period is later than the current time, and the charging station is used to charge the multiple vehicles.

[0009] Based on the photovoltaic output model, the multiple energy storage system parameters, the multiple optimization objectives, and the charging load curve, a multi-objective optimization model is constructed.

[0010] The multi-objective optimization model is solved to obtain the target configuration scheme; wherein, the target configuration scheme is used to guide the charging station to adjust its configuration information so that the operating state of the charging station meets the multiple optimization objectives.

[0011] Secondly, embodiments of this application provide a device for determining a charging station configuration scheme, comprising:

[0012] The acquisition module is used to acquire a photovoltaic output model, multiple energy storage system parameters, multiple optimization targets, and multiple charging behavior data of a target vehicle; wherein, the photovoltaic output model is used to represent the ability of a preset charging station to convert solar energy into electrical energy, the multiple energy storage system parameters are used to represent the state of the preset energy storage system in the charging station, the target vehicle refers to any one of the preset multiple vehicles, and the multiple charging behavior data are used to represent the charging status of the target vehicle within a preset first time period, the end time of the first time period being earlier than the current time;

[0013] A plotting module is used to plot curves based on multiple charging behavior data of multiple vehicles to obtain a charging load curve; wherein, the charging load curve is used to represent the change of the load of the charging station over time within a preset second time period, the start time of the second time period is later than the current time, and the charging station is used to charge the multiple vehicles.

[0014] The construction module is used to construct a multi-objective optimization model based on the photovoltaic output model, the multiple energy storage system parameters, the multiple optimization objectives, and the charging load curve;

[0015] The solution module is used to solve the multi-objective optimization model to obtain the target configuration scheme; wherein, the target configuration scheme is used to guide the charging station to adjust the configuration information so that the operating state of the charging station meets the multiple optimization objectives.

[0016] Thirdly, embodiments of this application provide an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0017] The memory stores computer-executed instructions;

[0018] When the processor executes the computer execution instructions stored in the memory, it is used to implement the method for determining the charging station configuration scheme as described in any of the first aspects.

[0019] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method for determining a charging station configuration scheme as described in any of the first aspects.

[0020] Fifthly, embodiments of this application provide a computer program product, including a computer program, which, when executed by a processor, is used to implement the method for determining a charging station configuration scheme as described in any of the first aspects.

[0021] This application provides a method, apparatus, device, medium, and product for determining a charging station configuration scheme. By acquiring historical charging behavior data from multiple vehicles, it plots a charging load curve for a future second time period based on this data, which reflects actual charging patterns. This replaces the fixed or typical day load curve input in the prior art, aligning with the dynamic changes in load and avoiding scenario adaptation deviations caused by static assumptions. Furthermore, it integrates a photovoltaic output model, multiple energy storage system parameters, and multiple preset optimization objectives to construct a multi-objective optimization model that comprehensively covers energy supply, energy storage, and demand-side characteristics. This eliminates the need for manual supplementation of scenario adaptation parameters. Finally, through the automatic solution of this multi-objective optimization model, it directly outputs a target configuration scheme that can guide the adjustment of charging station configuration information. This process reduces the tedious process of manually verifying model parameters and iteratively correcting them, improving the automation and efficiency of scheme determination and solving the problem of low efficiency in determining charging station configuration schemes in the prior art. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0023] Figure 1 A schematic diagram illustrating an application scenario of the method for determining a charging station configuration scheme provided in this application embodiment;

[0024] Figure 2 A flowchart illustrating the method for determining the charging station configuration scheme provided in the embodiments of this application. Figure 1 ;

[0025] Figure 3 A flowchart illustrating the method for determining the charging station configuration scheme provided in the embodiments of this application. Figure 2 ;

[0026] Figure 4 A Monte Carlo flowchart for predicting electric vehicle charging load is provided for embodiments of this application.

[0027] Figure 5 A flowchart of the coordinated optimization configuration of photovoltaic and energy storage based on the improved ant colony algorithm for dynamic load of charging piles is provided for the embodiments of this application.

[0028] Figure 6 A typical daily charging load curve of a charging station provided in the embodiments of this application;

[0029] Figure 7 Regional illumination intensity maps provided for embodiments of this application;

[0030] Figure 8 Regional temperature curves provided for embodiments of this application;

[0031] Figure 9 A typical daily power output curve of a single photovoltaic array over 12 months is provided for an embodiment of this application.

[0032] Figure 10 This is a schematic diagram of the iterative process of the improved ant colony algorithm provided in the embodiments of this application;

[0033] Figure 11 The following is a simulation result diagram of photovoltaic power consumption on a typical day in spring, provided in the embodiments of this application;

[0034] Figure 12 The following is a simulation result diagram of photovoltaic power consumption on a typical summer day provided in the embodiments of this application;

[0035] Figure 13 The following is a simulation result diagram of photovoltaic power consumption on a typical autumn day provided in the embodiments of this application;

[0036] Figure 14 The following is a simulation result diagram of photovoltaic power consumption on a typical winter day provided in the embodiments of this application;

[0037] Figure 15 A typical daily state of charge variation curve for spring provided in the embodiments of this application;

[0038] Figure 16 A typical daily state of charge variation curve for summer provided in the embodiments of this application;

[0039] Figure 17 A typical daily state of charge variation curve for autumn provided in the embodiments of this application;

[0040] Figure 18 A typical daily state of charge variation curve for winter provided in the embodiments of this application;

[0041] Figure 19A schematic diagram of the structure of the device for determining the charging station configuration scheme provided in the embodiments of this application;

[0042] Figure 20 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application.

[0043] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0044] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0045] In the embodiments of this application, the terms "first" and "second" are used to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that "first" and "second" do not necessarily imply difference. It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner. In the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more.

[0046] It should be noted that the phrase "at...time" in the embodiments of this application can refer to the instant at which a certain situation occurs, or to a period of time after the occurrence of a certain situation. The embodiments of this application do not specifically limit this. In addition, the method, apparatus, equipment, medium and product for determining a charging station configuration scheme provided in the embodiments of this application are only examples. A method, apparatus, equipment, medium and product for determining a charging station configuration scheme may also include more or fewer contents.

[0047] To facilitate a clear description of the technical solutions in the embodiments of this application, some terms and technologies involved in the embodiments of this application will be briefly introduced below:

[0048] Dynamic load refers to the collective term for electrical equipment or user groups whose power demand changes over time. Its core characteristics are time-varying and uncertainty. Unlike static load, the power of dynamic load is not a fixed value but a variable influenced by multiple factors. In the context of microgrids, understanding and predicting dynamic load is crucial for achieving stable, economical, and efficient operation.

[0049] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0050] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0051] To clearly understand the technical solution of this application, the solutions of existing technologies will first be described in detail. How to scientifically determine the configuration scheme of charging stations has become a key issue in promoting the development of electric vehicles, and how to confirm the configuration scheme of charging stations is particularly important.

[0052] In existing technologies, charging station configuration schemes are typically based on the charging load curve of a typical day. Using a static model and assuming that the charging pile load is constant or exhibits predictable periodic fluctuations, the required photovoltaic and energy storage capacities for the charging station are calculated to determine the configuration scheme. However, existing technologies rely on fixed or typical daily load curves as core input, using static models to calculate the capacity and layout of photovoltaic, energy storage, and charging piles. This approach fails to adequately consider the real-time dynamic changes in load and requires manual verification of model parameters and scenario adaptability, resulting in low efficiency in determining charging station configuration schemes. Therefore, existing technologies suffer from low efficiency in determining charging station configuration schemes.

[0053] Therefore, addressing the issue of low efficiency in determining charging station configuration schemes in existing technologies, this research found that to solve this problem, the efficiency of determining charging station configuration schemes can be improved by dynamically generating future load curves based on historical electricity consumption data of target electrical equipment, combining energy supply and storage parameters with multiple optimization objectives to construct an optimization model and automatically solve it: ① Historical operating data of electrical equipment under power supply scenarios can be collected to uncover the dynamic patterns and personalized characteristics of load changes over time, replacing traditional fixed or typical daily load curves. Based on this historical data reflecting actual demand, accurate load forecast results adapted to future periods can be generated. ② A comprehensive multi-objective optimization model covering the entire chain can be constructed by integrating energy supply-side output characteristic models, energy storage system state parameters, demand-side load characteristics, and multi-dimensional optimization objectives. The model automatically matches parameters of each dimension through preset parameter mapping rules, eliminating the need for manual supplementation of scenario-adaptive parameters and reducing the manual cost and time consumption of model construction. ③ Intelligent optimization algorithms such as genetic algorithms and particle swarm optimization algorithms can be introduced into the constructed multi-objective optimization model. Through the adaptive search, iterative evolution, and global optimization capabilities of these algorithms, the optimal solution satisfying all optimization objectives can be automatically found. The algorithm can automatically handle constraints such as power balance, equipment capacity, and grid interaction, and directly output a scheme that can guide the configuration of power supply facilities.

[0054] Specifically, by collecting historical operating data of electrical equipment in power supply scenarios, we can uncover the dynamic changes in load, generate load curves adapted to future periods, integrate the power supply output model, energy storage system state parameters, and multi-dimensional optimization objectives to construct a multi-objective optimization model, and use intelligent algorithms to automatically solve the model to output a scheme that can guide the configuration of power supply facilities. This reduces the manual parameter verification and iterative correction steps throughout the process, improving the efficiency and adaptability of the configuration scheme determination.

[0055] This application discloses a method, apparatus, device, medium, and product for determining a charging station configuration scheme. By acquiring historical charging behavior data from multiple vehicles, it plots a charging load curve for a future second time period based on this data, which reflects actual charging patterns. This replaces the fixed or typical day load curve input in the prior art, aligning with the dynamic changes in load and avoiding scenario adaptation deviations caused by static assumptions. Furthermore, it integrates a photovoltaic output model, multiple energy storage system parameters, and multiple preset optimization objectives to construct a multi-objective optimization model that comprehensively covers energy supply, energy storage, and demand-side characteristics. This eliminates the need for manual supplementation of scenario adaptation parameters. Finally, by automatically solving this multi-objective optimization model, it directly outputs a target configuration scheme that can guide the adjustment of charging station configuration information. This process reduces the tedious process of manually verifying model parameters and iteratively correcting them, improving the automation and efficiency of scheme determination and solving the problem of low efficiency in determining charging station configuration schemes in the prior art.

[0056] Based on the above-mentioned inventive discovery, the technical solution of this application is proposed.

[0057] The following describes the application scenarios of the method for determining the charging station configuration scheme provided in the embodiments of the present invention. Figure 1 This is a schematic diagram illustrating an application scenario of the method for determining a charging station configuration scheme provided in an embodiment of this application. For example... Figure 1 As shown, this application scenario includes a mobile terminal 101 and a server 102. The mobile terminal 101 collects multiple energy storage system parameters and multiple charging behavior data of the target vehicle, and sends them to the server 102. The server 102 obtains the photovoltaic output model and multiple optimization objectives. The server 102 plots curves based on the multiple charging behavior data of multiple vehicles to obtain the charging load curve. The server 102 constructs a multi-objective optimization model based on the photovoltaic output model, multiple energy storage system parameters, multiple optimization objectives and charging load curve. The server 102 solves the multi-objective optimization model to obtain the target configuration scheme.

[0058] The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0059] Figure 2 A flowchart illustrating the method for determining the charging station configuration scheme provided in the embodiments of this application. Figure 1 .like Figure 2 As shown, in this embodiment, the execution entity of this invention is a server. Therefore, the method for determining the charging station configuration scheme provided in this embodiment includes the following steps:

[0060] S201. Acquire photovoltaic output model, multiple energy storage system parameters, multiple optimization targets, and multiple charging behavior data of the target vehicle; wherein, the photovoltaic output model is used to represent the ability of the preset charging station to convert light energy into electrical energy, the multiple energy storage system parameters are used to represent the state of the preset energy storage system in the charging station, the target vehicle refers to any one of the preset multiple vehicles, and the multiple charging behavior data are used to represent the charging status of the target vehicle in a preset first time period, the end time of the first time period is earlier than the current time.

[0061] Specifically, a photovoltaic power output model can be obtained by collecting historical data on solar resources and photovoltaic module characteristic parameters of a preset area, combining them with energy conversion laws to construct or call a preset model. Multiple energy storage system parameters can be obtained by collecting inherent attributes and operating status data such as rated capacity, charging and discharging efficiency, and remaining power of energy storage devices. Multiple optimization objectives can be determined by combining preset standards such as power supply scenario requirements, cost control requirements, and resource utilization efficiency. Information such as charging duration, charging power, and charging period in the first time period can be collected through charging station charging records and vehicle terminal feedback to obtain multiple charging behavior data of the target vehicle. This step is used to provide comprehensive and effective basic data support for drawing the charging load curve of the second time period based on the charging behavior data of multiple vehicles and integrating relevant parameters to construct a multi-objective optimization model.

[0062] Several optimization objectives are set around the goals of efficient, stable, and safe operation of charging stations and meeting user charging needs. These mainly include improving the absorption rate of renewable energy such as photovoltaics, ensuring the continuity of power supply to charging stations, maintaining the safe operation of energy storage systems, reducing the impact of charging load on the power grid, and ensuring the user charging experience, so as to achieve synergistic optimization of energy utilization, system operation, and user needs. For example, a charging station can set multiple optimization objectives such as a photovoltaic absorption rate of ≥80%, a power shortage rate of ≤5%, and energy storage charging and discharging power not exceeding 85% of the rated power.

[0063] S202. Based on multiple charging behavior data of multiple vehicles, a curve is plotted to obtain a charging load curve; wherein, the charging load curve is used to represent the change of the load of the charging station with time within a preset second time period, the start time of the second time period is later than the current time, and the charging station is used to charge multiple vehicles.

[0064] Specifically, the charging behavior data of multiple vehicles in the first time period can be cleaned, integrated, and feature extracted to extract key information such as charging power, charging duration, and charging time distribution. Combined with time series analysis or load forecasting algorithms, the trend of charging station load change over time in the second time period can be obtained, and then a charging load curve can be drawn. This step is used to provide core input data that accurately reflects future power supply demand for the subsequent construction of a multi-objective optimization model, ensuring that the model can fully fit the dynamic characteristics of load change and laying a reliable foundation for solving the target configuration scheme.

[0065] S203. Based on the photovoltaic output model, multiple energy storage system parameters, multiple optimization objectives, and charging load curves, construct a multi-objective optimization model.

[0066] Specifically, the core inputs can be the energy supply capacity reflected by the photovoltaic output model, the energy storage operation boundaries corresponding to multiple energy storage system parameters, the quantitative indicators corresponding to multiple optimization objectives, and the future demand characteristics reflected by the charging load curve. The mathematical mapping relationship between each input is clarified, and constraints such as power balance and equipment capacity limits are set. The matching requirements of energy supply, energy storage and demand are transformed into quantifiable mathematical expressions, and then a multi-objective optimization model is constructed. This step is used to systematically integrate the scattered technical parameters and demand objectives to form a solvable mathematical framework, which provides the core carrier for obtaining a charging station configuration scheme that meets the multi-objective requirements through model solving.

[0067] S204. Solve the multi-objective optimization model to obtain the target configuration scheme; wherein, the target configuration scheme is used to guide the charging station to adjust the configuration information so that the operating state of the charging station meets multiple optimization objectives.

[0068] Specifically, a suitable multi-objective solution algorithm can be selected, and the photovoltaic output model, energy storage system parameters, optimization objectives, and quantitative data corresponding to the charging load curve can be input. Combined with preset constraints such as power balance and equipment operating boundaries, the algorithm iteratively searches to obtain the optimal solution set that fits all optimization objectives. From this set, the target configuration scheme containing the key configuration parameters of the charging station is selected and determined. This step is used to transform the mathematical solution of the multi-objective optimization model into a practical and operable configuration guide, directly providing a clear basis for adjusting the configuration information of the charging station, ensuring that the operating status of the charging station meets multiple preset optimization objectives, and completing the determination of the configuration scheme.

[0069] This embodiment provides a method for determining a charging station configuration scheme. By acquiring historical charging behavior data from multiple vehicles, a charging load curve for a future second time period is plotted based on this data, which reflects actual charging patterns. This replaces the fixed or typical day load curve input in existing technologies, aligning with the dynamic changes in load and avoiding scenario adaptation bias caused by static assumptions. Furthermore, by integrating a photovoltaic output model, multiple energy storage system parameters, and multiple preset optimization objectives, a multi-objective optimization model is constructed that comprehensively covers energy supply, energy storage, and demand-side characteristics. No manual supplementation of scenario adaptation parameters is required. Finally, by automatically solving this multi-objective optimization model, a target configuration scheme that can guide the adjustment of charging station configuration information is directly output. The entire process reduces the tedious process of manually verifying model parameters and repeatedly iterating and correcting, improving the automation and efficiency of scheme determination, and solving the problem of low efficiency in determining charging station configuration schemes in existing technologies.

[0070] In one possible design, the target vehicle's multiple charging behavior data includes multiple dimensions. S202, Based on the multiple charging behavior data of multiple vehicles, curves are plotted to obtain the charging load curve, including:

[0071] S2021. Extract parameters from multiple charging behavior data of the target vehicle to obtain values ​​for each dimension; among which, multiple dimensions include starting charging time, daily driving mileage, battery state of charge and power demand.

[0072] Specifically, the raw charging behavior data of the target vehicle can be cleaned, deduplicated, and filtered. From each charging record, the specific time of the start of charging, the cumulative value of daily mileage, the battery state of charge data at different stages of the charging process, and the corresponding power demand parameters can be extracted to clarify the effective numbers in each dimension. This step is used to provide accurate and standardized basic data for subsequently determining the probability density function of each dimension and sampling the preset variables to obtain the predicted charging behavior data of the target vehicle in the second time period.

[0073] S2022. Based on the values ​​of each dimension, determine the probability density function of each dimension; whereby the probability density function of each dimension is used to represent the distribution characteristics of the values ​​of each dimension.

[0074] Specifically, the distribution characteristics, central tendency, and dispersion of values ​​in each dimension can be analyzed. A probability distribution model that matches the characteristics can be selected, and the key parameters of the model can be determined through data fitting. Then, the probability density function corresponding to each dimension can be constructed. This step is used to provide a mathematical basis for sampling the preset variables to obtain the predicted charging behavior data of the target vehicle in the second time period, ensuring that the predicted data fits the distribution law of the actual charging behavior, and laying the premise for accurately calculating the charging load value and reliably drawing the charging load curve.

[0075] S2023. Sample the preset variables in the probability density function of each dimension to obtain the predicted charging behavior data of the target vehicle in the second time period; wherein, the predicted charging behavior data of the target vehicle in the second time period refers to the data of the target vehicle in multiple dimensions in the second time period.

[0076] Specifically, based on the numerical distribution patterns reflected by the probability density functions of each dimension, an appropriate sampling method can be selected to extract values ​​that fit the distribution characteristics from preset variables in each dimension, such as starting charging time, daily mileage, battery state of charge, and power demand. The extracted values ​​from each dimension are then integrated to form complete data for each dimension of the target vehicle in the second time period, thus obtaining the predicted charging behavior data. This step is used to provide specific input data that fits the actual distribution characteristics for subsequent calculations of the charging load values ​​of multiple vehicles at any time in the second time period.

[0077] S2024. Based on the predicted charging behavior data of the target vehicle in the second time period, calculate the charging load value of multiple vehicles at any time in the second time period.

[0078] Specifically, based on the predicted charging behavior data of each target vehicle in the second time period, the charging time period and the corresponding power demand of each vehicle can be determined. The second time period is divided into multiple consecutive time nodes. For any given moment, vehicles in the charging state are selected, and the power demand values ​​of these vehicles are summarized to obtain the charging load value at that moment. This step provides numerical support for subsequent curve plotting based on the charging load values ​​of multiple vehicles at any time in the second time period, ensuring that the charging load curve can truly reflect the load changes in future periods.

[0079] S2025. Based on the charging load values ​​of multiple vehicles at any time during the second time period, a curve is plotted to obtain the charging load curve.

[0080] Specifically, a coordinate system can be established with the time of the second time period as the horizontal axis and the charging load value as the vertical axis. The charging load values ​​of multiple vehicles at each moment in the second time period are mapped to the coordinate system in chronological order. By smoothly connecting the load value points at each moment, a complete charging load curve is formed. This step is used to transform the load change pattern of multiple vehicles in future time periods into an intuitive curve form, providing input for the subsequent integration of photovoltaic power output model, energy storage system parameters and optimization objectives to build a multi-objective optimization model, ensuring that the model can accurately adapt to the dynamic change characteristics of future load.

[0081] The technical effect of this solution in this embodiment is that by extracting charging behavior data from multiple dimensions and establishing probability density functions for random sampling, a high-precision random simulation of the future charging behavior of vehicles is achieved. The resulting charging load curve can fully characterize the spatiotemporal randomness and dynamic change characteristics of the load, providing a more realistic and predictive data foundation for subsequent multi-objective optimization, and improving the adaptability of the configuration solution to real operating scenarios and decision-making efficiency.

[0082] In one possible design, S203, based on the photovoltaic output model, multiple energy storage system parameters, multiple optimization objectives, and charging load curves, constructs a multi-objective optimization model, including:

[0083] S2031. Obtain multiple modeling constraints; among which, the multiple modeling constraints include photovoltaic output constraints, energy storage charging and discharging constraints, and power balance constraints. Photovoltaic output constraints are used to represent the degree to which the charging station's ability to convert light energy into electrical energy is affected by light intensity and temperature. Energy storage charging and discharging constraints are used to represent the boundary of safe operation of the energy storage system. Power balance constraints are used to represent the dynamic balance requirements between the energy supply and load demand of the charging station.

[0084] Specifically, photovoltaic output constraints can be determined by combining the technical parameters of photovoltaic modules with the influence of light intensity and temperature on light energy conversion capabilities. Energy storage charging and discharging constraints can be clarified based on the equipment specifications and safe operation standards of the energy storage system. Power balance constraints can be set based on the supply and demand interaction logic of the charging station's energy supply side, energy storage side, and load side, thereby obtaining multiple modeling constraints. This step is used to provide clear operating boundaries and adaptation requirements for the subsequent construction of a multi-objective optimization model based on the photovoltaic output model, energy storage system parameters, optimization objectives, and charging load curves, ensuring that the constructed model conforms to the operating rules of the actual application scenario.

[0085] S2032. Based on multiple modeling constraints, a multi-objective optimization model is constructed according to the photovoltaic power output model, multiple energy storage system parameters, multiple optimization objectives, and charging load curves.

[0086] Specifically, the energy supply capacity represented by the photovoltaic output model, the operating status corresponding to multiple energy storage system parameters, the quantitative indicators corresponding to multiple optimization objectives, and the demand characteristics reflected by the charging load curve can be transformed into model input variables. The photovoltaic output constraints, energy storage charging and discharging constraints, and power balance constraints can be transformed into mathematical boundary conditions. The correlation equation between the input variables and the optimization objectives can be established, and then a multi-objective optimization model can be constructed. This step is used to systematically integrate the characteristics and constraints of energy supply, energy storage, and demand sides, as well as the optimization objectives, into a solvable mathematical framework. This provides a core carrier for obtaining a charging station configuration scheme that fits the actual operating rules and multi-objective requirements through model solving, ensuring that the configuration scheme is feasible and adaptable.

[0087] The technical effect of this scheme in this embodiment is that by introducing photovoltaic output constraints, energy storage charging and discharging constraints, and power balance constraints, a multi-objective optimization model that closely fits the actual physical operating boundary is constructed. This ensures that the configuration scheme not only meets optimization objectives such as economic efficiency, but also strictly complies with the characteristics of photovoltaic power generation, the safe operation requirements of the energy storage system, and the real-time energy supply and demand balance, thereby improving the feasibility and practicality of the configuration scheme.

[0088] In one possible design, S204, the multi-objective optimization model is solved to obtain the objective configuration scheme, including:

[0089] S2041. Solve the multi-objective optimization model to obtain multiple configuration schemes.

[0090] Specifically, an appropriate multi-objective intelligent solution algorithm can be selected. The input includes the photovoltaic output model, energy storage system parameters, optimization objectives, and quantitative data corresponding to the charging load curve. Combined with preset modeling constraints, the algorithm iteratively searches and optimizes to obtain multiple feasible configuration schemes that meet all optimization objectives and constraints, forming a set of schemes with different parameter combinations. This step provides sufficient candidates for subsequent scheme selection based on the user's emphasis on each optimization objective, ensuring that the selection process can accurately match user needs from a variety of feasible schemes, and providing multiple scheme foundations for the final determination of the target configuration scheme.

[0091] S2042. Based on preset filtering rules, multiple configuration schemes are filtered to obtain the target configuration scheme; wherein, the filtering rules are used to indicate the degree of importance that users attach to each optimization objective.

[0092] Specifically, the preset screening rules can be transformed into weight allocation or priority ranking standards corresponding to each optimization goal. The degree of satisfaction of multiple configuration schemes under each optimization goal is compared. Through weight superposition calculation or priority progressive screening, the scheme with the best overall performance that meets the user's needs is selected as the target configuration scheme. This step is used to accurately match multiple feasible configuration schemes with the user's emphasis on each optimization goal, determine the final configuration scheme that fits the actual application needs from the candidate schemes, and provide personalized operation guidance for adjusting the configuration information of charging stations.

[0093] The technical effect of this solution in this embodiment is that by first solving for multiple configuration schemes that satisfy the constraints, and then filtering them based on the user's emphasis on each optimization objective, user preferences are flexibly incorporated into the multi-objective optimization framework, thereby outputting configuration schemes that fit the user's actual needs and value judgments, enhancing the personalization and practicality of the solution decision.

[0094] Figure 3 A flowchart illustrating the method for determining the charging station configuration scheme provided in the embodiments of this application. Figure 2 In this embodiment, in Figure 2 Based on the provided embodiments, the method for determining the charging station configuration scheme is further explained. The method for determining the charging station configuration scheme includes:

[0095] S301. Acquire photovoltaic output model, multiple energy storage system parameters, multiple optimization targets, and multiple charging behavior data of the target vehicle; wherein, the photovoltaic output model is used to represent the ability of the preset charging station to convert light energy into electrical energy, the multiple energy storage system parameters are used to represent the state of the preset energy storage system in the charging station, the target vehicle refers to any one of the preset multiple vehicles, and the multiple charging behavior data are used to represent the charging status of the target vehicle in a preset first time period, the end time of the first time period is earlier than the current time.

[0096] S302. Based on multiple charging behavior data of multiple vehicles, a curve is plotted to obtain a charging load curve; wherein, the charging load curve is used to represent the change of the load of the charging station with time in a preset second time period, the start time of the second time period is later than the current time, and the charging station is used to charge multiple vehicles.

[0097] S303. Based on the photovoltaic output model, multiple energy storage system parameters, multiple optimization objectives, and charging load curves, construct a multi-objective optimization model.

[0098] S304. Solve the multi-objective optimization model to obtain the target configuration scheme; wherein, the target configuration scheme is used to guide the charging station to adjust the configuration information so that the operating state of the charging station meets multiple optimization objectives.

[0099] S301-S304 are similar to S201-S204, and will not be described again in this embodiment.

[0100] S305. Execute the target configuration scheme to obtain multiple execution result data; among which, the multiple execution result data are used to represent the operating status of the charging station after executing the target configuration scheme.

[0101] Specifically, the photovoltaic output adaptation parameters, energy storage system operation parameters, and charging-related configuration information of the charging station can be adjusted according to the target configuration scheme. During the operation of the charging station according to the adjusted configuration, information reflecting the operating status, such as energy supply efficiency, load matching, energy consumption data, and optimization target achievement, is collected in real time to form multiple execution result data. This step is used to provide real and effective actual operation data support for subsequent optimization of the multi-objective optimization model based on actual operation feedback, ensuring that the optimized model can better fit the actual operation scenario of the charging station and improve the accuracy and adaptability of subsequent configuration schemes.

[0102] S306. Optimize the multi-objective optimization model based on multiple execution result data to obtain the optimized multi-objective optimization model.

[0103] Specifically, it can analyze the degree of fit between multiple execution result data and preset optimization objectives, identify the deviation between model output and actual operating state, and combine the actual operating scenario characteristics of charging stations to adjust the parameter mapping relationship, constraint boundary or objective quantification method in the multi-objective optimization model, thereby obtaining the optimized multi-objective optimization model. This step is used to build a data-driven closed-loop optimization mechanism, so that the model continuously fits the actual operating characteristics of charging stations and improves the accuracy and adaptability of subsequent configuration schemes.

[0104] For example, in a charging station scenario, after implementing the target configuration scheme for one month, the following execution results were collected: an average daily curtailment rate of 22%, an energy storage charging and discharging efficiency of 82%, and an average user charging wait time of 18 minutes. These results were compared with the preset optimization targets (curtailment rate ≤ 15%, charging and discharging efficiency ≥ 85%, and waiting time ≤ 10 minutes). Deviations were found, including excessive curtailment rate, substandard charging and discharging efficiency, and excessively long user waiting time. Further analysis revealed that the deviations stemmed from the temperature influence coefficient of the photovoltaic output constraint in the model not being in line with the actual high summer temperatures in the region, the upper limit of energy storage charging and discharging power not considering the initial battery degradation characteristics, and insufficient weighting of user experience during target quantification. Accordingly, the temperature coefficient of the photovoltaic output constraint in the model was adjusted from -0.35 to -0.38, the upper limit of energy storage charging and discharging power was dynamically reduced by 5% to match battery degradation, and the target quantification weight of user charging wait time was increased from 0.2 to 0.3, forming an optimized multi-objective optimization model.

[0105] The technical effect of this solution in this embodiment is that by feeding back the execution result data generated by the actual operation to the optimization model after implementing the target configuration scheme and performing dynamic optimization, a closed-loop improvement mechanism of optimization-execution-feedback-re-optimization is established, which can continuously correct model deviations, make subsequent configuration scheme decisions closer to the actual operation effect, and enhance the system's adaptability and long-term optimization capability.

[0106] In one possible design, S305 executes the target configuration scheme and obtains multiple execution result data, including:

[0107] S3051. Obtain multiple first environmental data and multiple second environmental data; wherein, the multiple first environmental data are used to represent the environmental state of the charging station when the target configuration scheme is obtained, and the multiple second environmental data are used to represent the environmental state of the charging station when the target configuration scheme is executed.

[0108] Specifically, when the target configuration plan is obtained, environmental information related to the operation of the charging station, such as light intensity, temperature, humidity, and power grid operation status, can be collected through environmental sensing devices deployed at the charging station and power grid data interaction channels as multiple first environmental data. When preparing to execute the target configuration plan, the same type of environmental information can be obtained in real time through similar sensing devices and data acquisition channels as multiple second environmental data. This step is used to provide an accurate basis for comparing environmental states for subsequent calculations of environmental changes, ensuring that the target configuration plan can be optimized based on actual environmental differences, making the optimized plan more suitable for the environmental conditions of the execution stage, and ensuring the effectiveness of the execution results.

[0109] S3052. Calculate the environmental changes based on multiple first environmental data and multiple second environmental data.

[0110] Specifically, multiple first environmental data and multiple second environmental data can be compared according to the same environmental indicator dimension. By calculating the numerical difference, change range or state difference of the corresponding indicators, the environmental changes of the charging station at different times can be quantified. This step is used to provide a clear basis for subsequent optimization of the target configuration scheme based on environmental differences, ensuring that the optimized scheme can adapt to the actual environmental state during the execution phase and improve the authenticity and reliability of the execution result data.

[0111] S3053. Optimize the target configuration scheme according to the changes in the environment to obtain the optimized target configuration scheme.

[0112] Specifically, by taking into account the specific changes in indicators such as light intensity, temperature, and grid operation status in the environment, the core configuration items in the target configuration scheme, such as photovoltaic output adaptation parameters, energy storage charging and discharging control parameters, and charging resource adjustment parameters, can be adjusted in a targeted manner. This ensures that the various parameters of the scheme are adapted to the actual environmental conditions during the execution phase, thereby obtaining an optimized target configuration scheme. This step is used to eliminate the impact of environmental changes on the execution effect of the original target configuration scheme, ensuring that the optimized scheme has stronger environmental adaptability and providing a reliable guarantee for subsequent execution of the scheme and obtaining real and effective execution result data.

[0113] For example, when a charging station formulated its target configuration plan in spring, the first environmental data showed that the peak daily solar irradiance was 800W per square meter, the average temperature was 25 degrees Celsius, and the power grid's midday transmission limit was 500kW. When the plan was implemented, it was summer, and the second environmental data showed that the peak daily solar irradiance had risen to 1200W per square meter, the average temperature had reached 35 degrees Celsius, and the power grid had reduced the midday transmission limit to 450kW due to summer load constraints. In light of this environmental change, the target configuration scheme was optimized as follows: the maximum power tracking threshold in the photovoltaic output adaptation parameters was adjusted from 900W per square meter to 1300W per square meter to avoid wasting photovoltaic output; the charging period in the energy storage charging and discharging control parameters was advanced from 11:00-13:00 to 9:00-11:00, and the maximum charging power was reduced from 150kW to 120kW to adapt to the grid transmission limit; the peak period (14:00-16:00) single-pile power limit of the charging pile in the charging resource adjustment parameters was dynamically adjusted from 30kW to 25kW to balance the grid load and user charging demand, resulting in an optimized target configuration scheme that adapts to summer high temperatures, strong sunlight, and grid load changes.

[0114] S3054. Execute the optimized target configuration scheme to obtain multiple execution result data.

[0115] Specifically, according to the optimized target configuration scheme, the core configuration items of the charging station, such as photovoltaic output control parameters, energy storage system operation parameters, and charging resource allocation parameters, can be adjusted. During the execution of the scheme, information reflecting the operating status of the charging station, such as power supply stability, load adaptation effect, energy consumption data, and the actual achievement of each optimization target, can be collected in real time and integrated to form multiple execution result data. This step is used to provide real execution data support that fits the current environmental conditions for subsequent optimization of the multi-objective optimization model based on actual operation feedback, ensuring that the optimized model can more accurately adapt to the dynamic operation scenario of the charging station and improve the feasibility and adaptation effect of subsequent configuration schemes.

[0116] The technical effect of this solution in this embodiment is that by comparing the differences in environmental data between the time the configuration solution is formulated and the time of actual execution, and optimizing and adjusting the initial solution accordingly, the configuration solution achieves real-time response and adaptive optimization to dynamic environmental changes, effectively reduces the deviation in solution execution caused by fluctuations in environmental conditions, and improves the robustness of charging station operation and energy utilization efficiency.

[0117] It should be noted that:

[0118] The purpose of this application is to provide a method for determining the configuration scheme of charging stations. By accurately predicting and analyzing the dynamic load of charging stations, and combining the characteristics of photovoltaic power generation and energy storage systems, the method achieves optimized configuration and coordinated operation of photovoltaic and energy storage systems, improves energy utilization efficiency, reduces the impact on the power grid, ensures stable power supply to charging piles, and reduces operating costs. The process of Example 1 is as follows:

[0119] 1. Build an electric vehicle charging load prediction model and use the Monte Carlo simulation method to predict the charging load in the charging station.

[0120] The mileage of an electric vehicle on a single trip generally does not exceed its battery's maximum range, and the number of charging times per day is generally one to two. According to relevant department surveys, for electric vehicles operating in urban areas, the driving time on weekdays is mostly between 7:00-9:00 and 12:00-14:00, while parking time is concentrated between 9:00-11:30, 14:30-17:30, and 19:00-7:00. They are in a state of inactivity for most of the day, and the inactivity rate may be even higher on holidays. For electric vehicles charging in western highway service areas, due to the influence of time difference, catering, rest and other environmental factors, there are two obvious charging concentration points during two peak load periods (11:00-15:00 and 18:00-21:00). Through the study of the starting charging time pattern of electric vehicles in highway service areas throughout the day, it was found that it follows a normal distribution and has obvious "bimodal" characteristics. Its probability density function is shown in Equation (1), which is:

[0121]

[0122] In the formula, The start of charging. Standard deviation, The expected value is the value at the start of charging. When the charging start time is between 5:00 and 17:00, the expected value is... =14, standard deviation =2.8, when the charging start time is between 17:00 and 6:00 the next day, the expected value is =19, standard deviation =4.3.

[0123] The daily mileage of an electric vehicle directly affects its usage and the user's charging choices. Its power consumption is directly proportional to the mileage, while if the charging power remains constant, the charging time and power consumption show a linear relationship. Furthermore, due to differences in user habits, the daily mileage will vary. Assuming the daily mileage of a vehicle follows a log-normal distribution, its distribution function is shown in equation (2), which is:

[0124]

[0125] In the formula, Daily mileage, in km =4.1 and =0.8 represents the expected value and standard deviation of the probability distribution function of daily mileage of electric vehicles, respectively.

[0126] Build a model of charging characteristics and charging time:

[0127] Electric vehicle battery state of charge ( () refers to the ratio of the battery's current remaining capacity to its capacity in a fully charged state, satisfying a value range of 0-1, i.e. >0 indicates that the battery is depleted. =1 indicates that the battery is fully charged. Factors such as the battery's state of charge, battery capacity, and charging power at the start and end of charging all affect the charging time of an electric vehicle.

[0128] State of charge of an electric vehicle when it begins charging The relationship between the daily mileage and the driving distance is shown in equation (3), which is:

[0129]

[0130] In the formula, This represents the battery's state of charge before the car is driven. To reduce battery charging losses, a maximum value of 90% is used. For electric vehicle battery capacity, kWh, This refers to the car's driving range, measured in kilometers. Electricity consumption per 100 kilometers for a car, in kWh / 100km.

[0131] Factors such as the daily driving range, battery charging efficiency, and charging power of electric vehicles all affect the charging time. The functional relationship is shown in equation (4), which is:

[0132]

[0133] In the formula, For charging time, The charging efficiency for electric vehicles is generally no less than 90%. The rated charging power for electric vehicles is kW. Considering that the users of the charging stations are all electric vehicle users in highway service areas, this application sets all electric vehicles to use fast charging mode.

[0134] Build a charging load prediction model:

[0135] This application uses the Monte Carlo method to calculate the charging load of electric vehicles, taking into account factors such as battery charging time, initial state of charge, number of charging vehicles, charging power, and daily mileage. The probability density distribution function is randomly sampled to obtain the charging load of all electric vehicles. The overall solution time is 24 hours, and the model computation resolution is 1 hour. The formula for calculating the total charging load is shown in equation (5), which is:

[0136]

[0137] In the formula, The total charging power of an electric vehicle in one day, in kW. Let be the number of electric vehicles entering the charging station in the i-th unit of time. The percentage of electric vehicle users who need charging.

[0138] Figure 4 The Monte Carlo flowchart for predicting electric vehicle charging load provided in this application embodiment is as follows: Figure 4 As shown, the specific implementation steps can be described as follows:

[0139] (1) Initialize the number of electric vehicles Battery capacity Electricity consumption per 100 kilometers , driving range Charging power and transmission efficiency Parameters such as these.

[0140] (2) Let n=1, which means starting the simulation from the first electric vehicle with charging needs.

[0141] (3) Using the Monte Carlo algorithm, combined with the above probability density function, the daily mileage of electric vehicles is extracted. Calculate the initial state of charge wait.

[0142] The starting charging time was extracted based on the travel patterns of electric vehicles. Combined with the daily driving mileage of electric vehicles Calculate charging time .

[0143] (4) Accumulate the charging load of the electric vehicle at each moment and determine the value of n. If Let n = n + 1, return to 2 and continue the calculation, otherwise output the total charging load curve.

[0144] 2. Construct a photovoltaic power generation output model:

[0145] The output power of a photovoltaic array is mainly affected by factors such as solar radiation intensity and temperature, exhibiting a certain degree of fluctuation and regularity. Output power at time As shown in equation (6), equation (6) is:

[0146]

[0147] In the formula, The rated output power of a unit photovoltaic array is expressed in kW. For the installed capacity of the photovoltaic array, Areas where photovoltaic power generation is planned (latitude: ) No. Month, First Heavenly The hourly average of surface solar radiation intensity at that time. , For standard irradiation intensity, take , Let be the power temperature coefficient of the photovoltaic array, and take . T is the operating temperature of the photovoltaic array. , The reference temperature for the photovoltaic array is taken as... .

[0148] 3. Energy storage system charging and discharging energy management model:

[0149] Energy storage system charge / discharge power balance analysis:

[0150] (1) The energy storage system is in a charging state:

[0151] When the output power of photovoltaic power generation is greater than the charging load power of electric vehicle, the energy storage system is in a charging state, and its functional relationship is shown in equation (7). Equation (7) is:

[0152]

[0153] In the formula, The power generated by the photovoltaic array per unit time t, in kW. Let be the charging load power of the electric vehicle within a unit time t, taken as a positive value, kW. Let be the charging power of the energy storage system of the charging station within a unit time t, taken as a positive value, in KW.

[0154] Among them, when At this time, light wastage occurs. The power of light wasted at this time... As shown in equation (8), equation (8) is:

[0155]

[0156] In the formula, The maximum charging power allowed by the energy storage system of the charging station per unit time t is expressed in kW.

[0157] (2) The energy storage system is in a discharging state:

[0158] When the output power of photovoltaic power generation is less than the charging load power of electric vehicle, the energy storage system is in a discharging state, and its functional relationship is shown in equation (9). Equation (9) is:

[0159]

[0160] In the formula, Let be the discharge power of the charging station's energy storage system within a unit time t, taken as a negative value, in KW.

[0161] Among them, when At this time, a defect phenomenon occurs. The power shortage at this time is shown in equation (10), which is:

[0162]

[0163] In the formula, The maximum charging power allowed by the energy storage system of the charging station per unit time t is expressed in kW.

[0164] In order to maximize the absorption of photovoltaic power generation, reduce curtailment, and ensure the overall power supply reliability of the charging station system, the photovoltaic array and energy storage system should be rationally configured, and the charging and discharging power of the energy storage system should be fully adjusted to meet the difference between the photovoltaic power generation and the charging load demand.

[0165] Energy storage system power balance analysis:

[0166] The energy storage system for charging stations needs to have advantages such as high charging and discharging efficiency and long lifespan. Its power conversion mode is as follows:

[0167] (1) The charging demand of electric vehicles is equal to the photovoltaic power generation. At this time, the energy storage battery is affected by self-discharge energy, and the energy storage capacity is as shown in equation (11). Equation (11) is:

[0168]

[0169] In the formula, The self-discharge rate of the energy storage system. Let t be the real-time energy level of the energy storage system at time t, in kWh.

[0170] (2) The charging demand of electric vehicles is lower than that of photovoltaic power generation. In this case, the charging status of the energy storage system needs to be determined based on its state of charge. Analysis:

[0171] 1) If the energy storage system reaches its maximum charging depth, the energy storage battery stops receiving power, and its stored power is as shown in equation (12), which is:

[0172]

[0173] In the formula, The theoretical maximum capacity of the energy storage unit is kWh. The theoretical maximum capacity of the energy storage system is kWh. The maximum depth of charging for the energy storage system is 0.9, which is used in this application to extend the service life of the energy storage batteries in the charging station.

[0174] At this point, light wastage occurs within a unit of time t.

[0175] 2) If the energy storage system has not yet reached its maximum charging depth, i.e. Then the energy storage system continues to input energy until it reaches the maximum depth of charge, and the stored energy is shown in equation (13), which is:

[0176]

[0177] In the formula, The charging efficiency of energy storage systems is generally no more than 90%. The maximum charging power that the energy storage system is allowed to accept per unit time t is expressed in kW.

[0178] If the energy storage system reaches its maximum charging depth within a unit of time, but the photovoltaic power generation is still higher than the charging demand of electric vehicles, then curtailment of solar power will occur after the maximum charging depth is reached.

[0179] (3) The charging demand of electric vehicles is higher than that of photovoltaic power generation. In this case, the discharge status of the energy storage system needs to be determined based on its state of charge. Analysis:

[0180] 1) If the energy storage system reaches its maximum depth of discharge, the energy storage battery will stop outputting power, and its stored power will be as shown in equation (14), which is:

[0181]

[0182] In the formula, The maximum depth of discharge for the energy storage system is 0.9.

[0183] At this time, a power shortage occurs within a unit of time t.

[0184] 2) If the energy storage system has not yet reached its maximum depth of discharge, i.e. Then the energy storage system continues to output, and its stored electricity is as shown in equation (15), which is:

[0185]

[0186] In the formula, For the discharge efficiency of the energy storage system, we take 90%. The maximum depth of discharge for the energy storage system is 0.9 in this application.

[0187] If the energy storage system reaches its maximum depth of discharge within a unit of time, but the photovoltaic power generation is still lower than the charging demand of electric vehicles, then a power shortage will occur after the maximum depth of discharge is reached.

[0188] Energy storage system charge and discharge model:

[0189] In summary, the operating model of the energy storage device considering self-discharge and charge / discharge power is shown in Equation (16), which is:

[0190]

[0191] In the formula, Let t be the real-time energy storage capacity of the energy storage system at time t, in kWh. It is related to the energy stored in the battery at the previous time and the net input and output power and charging and discharging efficiency at the current time.

[0192] Energy storage system state of charge The model is shown in equation (17), which is:

[0193]

[0194] In the formula, The capacity of the energy storage system battery is expressed in kWh.

[0195] 5. Optimization model for coordinated configuration of photovoltaic and energy storage capacity in charging stations:

[0196] The objective function is:

[0197] (1) Analysis of annual investment costs for charging stations, etc.

[0198] The annual investment cost of charging stations, etc., is shown in equation (18), which is:

[0199]

[0200] In the formula, Annual investment costs for charging stations, etc. The discount rate is set at 5%. These refer to the lifespan of the photovoltaic array, energy storage unit, and charging pile, respectively. , Rated output power of photovoltaic arrays and energy storage units, in kW. , The cost per unit rated power of photovoltaic arrays and energy storage units. , , The number of photovoltaic arrays, energy storage units, and charging piles to be installed. This refers to the unit price of a charging pile.

[0201] Considering that the charging pile installation capacity is closely related to the user's charging demand, this application uses the maximum charging demand of electric vehicles per unit time to effectively estimate the charging pile installation capacity, as shown in equation (19). Equation (19) is:

[0202]

[0203] In the formula, The maximum charging demand of electric vehicles per unit time, in kWh. Charging time per unit, in hours. The probability of parallel charging is set to 1 in this application.

[0204] (2) Analysis of annual operation and maintenance costs of charging stations:

[0205] The annual operation and maintenance cost of the charging station is shown in equation (20), which is:

[0206]

[0207] In the formula, The annual operation and maintenance cost of the charging station, , The unit rated power operation and maintenance cost of photovoltaic arrays and energy storage systems. This refers to the ratio of charging pile operation and maintenance.

[0208] (3) Analysis of annual curtailment revenue loss at charging stations:

[0209] The annual curtailment revenue loss of the charging station is shown in equation (21), which is:

[0210]

[0211] In the formula, The annual revenue loss from curtailment of solar power at charging stations This represents the coefficient for lost revenue from wasted light.

[0212] The curtailment rate can effectively measure the utilization of photovoltaic power generation in the photovoltaic-storage system of a charging station. The annual average curtailment rate of a charging station is [data missing]. As shown in equation (22), equation (22) is:

[0213]

[0214] In the formula, denoted as kWh, representing the amount of light wasted per unit time t.

[0215] In summary, the annual economic benefit model for charging stations is shown in equation (23), which is:

[0216]

[0217] Constraints: The optimization model for the photovoltaic-storage capacity configuration of the charging station mainly considers factors such as photovoltaic array output, energy storage system charging and discharging, system power balance, and power supply reliability.

[0218] (1) The constraints related to photovoltaic output are shown in equation (24), which is:

[0219]

[0220] In the formula, This represents the maximum output power of a single photovoltaic array.

[0221] (2) Energy storage system charge and discharge constraints:

[0222] 1) The state of charge constraint of the energy storage system is shown in equation (25), which is:

[0223]

[0224] In the formula, , These are the upper and lower limits of the state of charge of the energy storage system, respectively, and are set to 0.1 and 0.9.

[0225] 2) The discharge power constraint of the energy storage system is shown in equation (26), where equation (26) is:

[0226]

[0227] In the formula, This represents the maximum discharge power of the energy storage unit.

[0228] 3) The charging power constraint of the energy storage system is shown in equation (27), which is:

[0229]

[0230] In the formula, This represents the maximum charging power of the energy storage unit.

[0231] (3) The system power balance constraint is shown in equation (28), which is:

[0232]

[0233] In the formula, , They do not exist simultaneously.

[0234] (4) The power shortage rate constraint of the photovoltaic-storage system is shown in equation (29), which is:

[0235]

[0236] In the formula, The energy deficit per unit time t, in kWh. The electric vehicle load per unit time t, in kWh. The power shortage rate of charging stations.

[0237] 6. A coordinated optimization strategy for photovoltaic and energy storage configuration based on an improved ant colony algorithm for dynamic load of charging piles:

[0238] (1) Ant colony optimization algorithm: The ant colony optimization algorithm was first used to solve the Traveling Salesman Problem (TSP). Its basic idea is to use walking paths to represent the feasible solutions to the problem to be optimized. All paths of the entire ant colony constitute the solution space of the problem to be optimized.

[0239] Assuming that it contains In a directed graph of nodes, by An ant colony consisting of only a few ants For nodes With nodes The distance between them Path at time t On the pheromones, Let be a heuristic function, representing the ant's path from node 1. Transfer to node The level of expectation, take , , They are respectively and The relative importance, Let be the set of nodes that ant k can choose at time t. What is the probability that ant k selects the next node j from node i during its search? As shown in equation (30), equation (30) is:

[0240]

[0241] Ants release pheromones along their paths, but previously left pheromones gradually evaporate over time. Let ρ (0 < ρ < 1) represent the pheromone evaporation rate. After traversing all nodes, the ant updates the remaining pheromones in the environment using equations (31) and (32). Equations (31) and (32) are respectively:

[0242]

[0243]

[0244] In the formula, For ant k on the path The concentration of pheromones released on the surface For the ant colony on the path The concentration of pheromones released, Q, is the total amount of pheromones. Let be the total length of the path traversed by ant k in this loop.

[0245] (2) Improved Ant Colony Algorithm:

[0246] 1) State transition rule. In the ant colony optimization algorithm, ants perform probabilistic path search based on random proportion rules, resulting in low optimization efficiency and poor performance. However, in the improved ant colony optimization algorithm, the state transition rule is used for searching, which tends to select shorter paths rich in pheromones as the direction of progress. Let the current node i be the node that ant k is currently in, then the next node j to be visited is shown in equation (33), which is:

[0247]

[0248] In the formula, q is a random number in (0, 1).

[0249] when At that time, the ants used The probability is used to select the next node to be visited to develop a new region for optimization, according to equation (33). At that time, the ants used The probability is used to search for the optimal solution using the probabilistic formula of the ant colony optimization algorithm.

[0250] By adjusting The balance between improving the ant colony optimization algorithm and the ant colony optimization algorithm's search for optimization can be adjusted to determine whether the algorithm should continue to search for optimization near the current optimal path or explore new areas for optimization in the next step.

[0251] 2) Pheromone Local Update Rule: In the ant colony optimization algorithm, a local update is performed on all paths after each loop. In the improved ant colony optimization algorithm, the layout information is updated according to Equation (34) after each ant traverses an edge, so as to ensure the balance of pheromones remaining in each ant, reflect the balanced contribution of individuals to the search and mutual cooperation, thereby improving the convergence speed. Equation (34) is:

[0252]

[0253] In the formula, Let x be a large constant, and let x be the number of ants. The number of edges traversed in this iteration. For path Updated pheromone concentration The pheromone evaporation coefficient, For path The pheromone concentration before the update For path The increase in pheromones in this cycle This represents the total length of the edges traversed by all ants in this cycle. This represents the total number of ants participating in the search. For ant k, the number of times it has traversed in this loop is... The length of the side of the strip.

[0254] 3) Figure 5 A flowchart illustrating the coordinated optimization configuration of photovoltaic and energy storage based on an improved ant colony algorithm for dynamic loads of charging piles, provided in this application embodiment. Figure 5 As shown, the algorithm steps for the coordinated optimization configuration of light and energy storage based on the improved ant colony algorithm are as follows:

[0255] ① Input the original network data and set the number of ants.

[0256] ② Initialize parameters. In the initialization algorithm... , A series of key parameters are calculated, and the number of possible power supply capacities n, i.e. the number of paths, for each node is calculated based on the minimum installed capacity of the photovoltaic power supply and the load value of the node. The pheromone on each path is initialized to the same value.

[0257] ③ Based on the expected value of each path of the corresponding node i and the pheromone on the path, the transition probability of ant k at that node is calculated using equation (30), and the forward path is selected. The expected value of the path is inversely proportional to the total operating cost of the distributed power source. The higher the total operating cost of the photovoltaic-storage power source, the smaller the expected value, and vice versa. Here, it is assumed that the total operating cost of the photovoltaic-storage power source is proportional to the capacity of the distributed power source and is a fixed constant.

[0258] ④ Whenever an ant completes a search and determines the capacity of the distributed power supply installed on a certain node, it uses equation (31) to perform a local update of the pheromone.

[0259] ⑤ If all ants have completed a full path search and determined the capacity of the photovoltaic power storage system to be installed at each node, then proceed to ⑥; otherwise, proceed to ③.

[0260] ⑥ Calculate the objective function value of all solutions obtained by the ants, and select the optimal solution of this iteration to compare with the historical optimal solution. Save the best of the two as the new optimal solution.

[0261] ⑦ Adjust according to formula (33) The value of .

[0262] ⑧ Update the pheromones on the path globally according to formula (34).

[0263] ⑨ Repeat steps ③-⑧ until the given iteration termination condition is met.

[0264] ⑩ Terminate the algorithm and output the optimal solution.

[0265] By updating and searching pheromones across multiple generations of ant colonies, the global optimal solution is gradually approached, ultimately outputting a photovoltaic-storage coordinated configuration scheme that balances economy and reliability.

[0266] The process of Example 2 is as follows:

[0267] (1) Set the model parameters. The relevant parameters of electric vehicles are shown in Table 1.

[0268] Table 1. Relevant parameters of electric vehicles

[0269]

[0270] Table 2 shows the parameter settings for the photovoltaic, energy storage and charging piles configured in the integrated photovoltaic-energy storage-charging electric vehicle charging station, including their prices, working efficiency and service life.

[0271] Table 2. Relevant parameters for charging station equipment configuration

[0272]

[0273] The remaining parameter settings are shown in Table 3:

[0274] Table 3 Other parameter settings

[0275]

[0276] (2) Set the algorithm parameters: The experimental parameters are set as follows: =0.2, =0.2, =3, =20000, =50000, =0.75, =10, =35.

[0277] (3) Electric vehicle load analysis at charging stations:

[0278] In this embodiment, 14:00 and 19:00 each afternoon are selected as the two peak periods for electric vehicle charging load. Based on the electric vehicle charging load prediction model established in the technical solution and the above parameter settings, the Monte Carlo simulation method is used to predict the electric vehicle load at highway service area charging stations. Figure 6 A typical daily charging load curve of a charging station provided in the embodiments of this application.

[0279] Furthermore, based on formula (19) and the calculation of the maximum charging demand of electric vehicles per unit time, the required charging pile installation capacity within the charging station can be determined. It is 18.

[0280] (4) Power output analysis of photovoltaic array in charging station:

[0281] Based on the actual annual meteorological information data of the region published by the meteorological bureau, the photovoltaic power output of the charging station was predicted using the established photovoltaic power generation output model. Figure 7 This application provides a regional illumination intensity map for its embodiments. Figure 8 The regional temperature curve provided for the embodiments of this application. By setting the standard radiation intensity to 1 kW / m², the power temperature coefficient of the photovoltaic array is... The reference temperature is The simulation step size is 1 hour, and the simulation time is set to 576 hours. Taking a photovoltaic power supply model with a rated power of 2kW as an example, the output power curve of a single photovoltaic array over 12 months of typical daily operation is shown below. Figure 9 As shown, Figure 9A typical daily power output curve of a single photovoltaic array over 12 months, provided for an embodiment of this application.

[0282] Based on the above model, constraints, solution algorithm and parameter settings, simulation experiments were conducted under the premise of no curtailment rate constraint and ensuring 100% power supply reliability of the charging station, and the optimal configuration of the photovoltaic-storage capacity in the photovoltaic-storage-charging integrated electric vehicle charging station was obtained. Figure 10 This is a schematic diagram illustrating the iterative process of the improved ant colony algorithm provided in the embodiments of this application. The simulation results of typical daily photovoltaic power consumption in all four seasons under the optimal configuration of the photovoltaic-storage capacity of the charging station without curtailment rate constraints are as follows: Figures 11 to 14 As shown, Figure 11 The figure shows the simulation results of photovoltaic power consumption on a typical day in spring, as provided in the embodiments of this application. Figure 12 The figure shows the simulation results of photovoltaic power consumption on a typical summer day provided in the embodiments of this application. Figure 13 The figure provided here is a simulation result of photovoltaic power consumption on a typical autumn day, as shown in the embodiments of this application. Figure 14 The figure shows the simulation results of photovoltaic power consumption on a typical winter day, as provided in the embodiments of this application.

[0283] To facilitate the analysis of the charging and discharging of the energy storage system at the charging station, typical daily state of charge curves for each of the four seasons are presented, as shown below. Figures 15 to 18 As shown, Figure 15 The typical daily state of charge variation curves for spring provided in this application embodiment are shown below. Figure 16 This application provides a typical daily state of charge variation curve for summer, as shown in the embodiments. Figure 17 The typical daily state of charge variation curves for autumn provided in this application embodiment are shown below. Figure 18 The typical daily state of charge variation curves provided for embodiments of this application during winter, combined with Figures 11 to 18 It can be seen that when the photovoltaic output is high, the excess photovoltaic power cannot be absorbed, and the energy storage system will charge it, but it may still not be able to absorb all the power, thus resulting in some curtailment. When the photovoltaic output weakens or stops, the energy storage will discharge to meet the charging needs of electric vehicles. Curtailment generally occurs in summer, and in spring and autumn when the photovoltaic output is high, there is partial curtailment, while curtailment is less common in winter.

[0284] Based on the above analysis, it is possible to improve the photovoltaic absorption capacity of charging stations and reduce the curtailment rate by increasing photovoltaic capacity or energy storage capacity, while ensuring the reliability of system power supply and the charging needs of electric vehicles. Therefore, simulation analysis was conducted on the optimal configuration of photovoltaic-storage capacity of charging stations under different curtailment rate constraints:

[0285] Considering the rationality of photovoltaic-storage capacity configuration under different curtailment rates, this embodiment analyzes and compares the photovoltaic-storage capacity configuration, annual investment and operation and maintenance costs of charging stations, annual curtailment revenue loss, and curtailment rate to select an economically reasonable configuration method. The optimal photovoltaic-storage capacity configuration under different curtailment rate constraints is shown in Table 4.

[0286] Table 4 Comparison of Optimal Light-Storage Capacity Configuration Results under Different Light Curtailment Rate Constraints

[0287]

[0288] As shown in Table 4, the optimal configuration of photovoltaic-storage capacity and the costs of charging station economic benefits differ under different curtailment rate constraints. From the configuration results, as the curtailment rate requirement increases, the photovoltaic array capacity decreases, and the annual curtailment revenue loss also decreases due to the peak-valley arbitrage benefit of energy storage. However, to meet the demand for photovoltaic power consumption, the energy storage unit capacity increases accordingly, and the increase is relatively large compared to the photovoltaic array. At this point, the annual investment cost and total economic benefit cost of the charging station begin to increase continuously. Simulation results show that reducing the curtailment rate requires sacrificing some economic benefits.

[0289] Based on economic considerations, and under the premise of meeting the charging load demand of electric vehicles and ensuring power supply reliability, the optimal configuration of light-storage capacity without curtailment rate constraints is selected as the research basis for the analysis of the "most economically efficient" operation of charging stations.

[0290] Based on the spatiotemporal distribution characteristics of electric vehicle charging load, photovoltaic power output characteristics, and energy management analysis of charging station energy storage system in a certain region, this embodiment establishes a collaborative configuration optimization model for the photovoltaic-storage capacity of charging stations, taking the photovoltaic-storage capacity of charging stations as the optimization decision variable and the highest economic benefit of integrated photovoltaic-storage-charging electric vehicle charging stations as the optimization objective.

[0291] Secondly, taking this region as an example, we conducted a case study analysis. Based on the improved ant colony algorithm, we solved the model and achieved the optimal configuration of the photovoltaic-storage capacity of the charging station under the premise of meeting the charging demand of electric vehicles and the reliability index of the system power supply, thus achieving higher socio-economic benefits.

[0292] Based on this, a comparative analysis of the optimal configuration results of the photovoltaic-storage capacity of charging stations under different curtailment rates was completed, and an optimal capacity configuration scheme based on economic considerations was given.

[0293] The improvement of this embodiment compared to the prior art lies in the fact that this application establishes a collaborative optimization framework that integrates capacity configuration with charging and discharging strategies and charging adjustments for joint optimization, seeking a global optimum rather than a local optimum. This accurately characterizes and predicts the randomness, intermittency, and impact of electric vehicle charging behavior.

[0294] This embodiment utilizes high-precision dynamic load modeling and prediction technology for charging piles. It employs a Monte Carlo load model algorithm that comprehensively considers factors such as battery charging time, initial state of charge, number of charging vehicles, charging power, and daily mileage. The probability density distribution function of these factors is randomly sampled to obtain the charging load for all electric vehicles. This model takes into account multiple factors, including user behavior, battery state of charge, and charging transmission efficiency.

[0295] This embodiment establishes a photovoltaic-energy storage-charging pile model and a photovoltaic-energy storage capacity collaborative configuration optimization model for charging stations. This model places input decision variables and operational decision variables on the same time scale for synchronous optimization, ensuring the optimality of the configuration scheme in actual operation and achieving true global optimization.

[0296] This embodiment improves upon the principles and shortcomings of the ant colony optimization algorithm, ensuring the optimality of the configuration scheme in actual operation and achieving true global optimization.

[0297] This embodiment accurately characterizes and predicts the randomness, intermittency, and impulsiveness of electric vehicle charging behavior using a Monte Carlo load model algorithm. It fully considers the charging and discharging characteristics of electric vehicles, randomly sampling their probability density distribution function to obtain the charging load of all electric vehicles. This embodiment establishes an accurate and near-realistic charging station load model, providing a reliable basis for optimizing the configuration of photovoltaic, energy storage, and charging capacity. The traditional model of isolated design of photovoltaic configuration, energy storage configuration, and charging load adjustment is based on an integrated photovoltaic-energy storage-charging energy management model. With maximizing the economic benefits of the charging station as the optimization objective and the photovoltaic-energy storage capacity of the charging station as the optimization decision variable, an improved ant colony algorithm is used to solve the problem. This achieves the optimal configuration of the photovoltaic-energy storage capacity of the charging station while meeting the system power supply reliability index and the charging demand of electric vehicles. This embodiment, fully considering uncertainties, ultimately presents an optimal photovoltaic-energy storage system configuration and operation scheme across multiple dimensions of economic reliability.

[0298] Figure 19 This is a schematic diagram of the device for determining a charging station configuration scheme provided in an embodiment of this application. Figure 19 As shown, the device for determining the configuration scheme of the charging station includes:

[0299] The acquisition module 1901 is used to acquire photovoltaic output model, multiple energy storage system parameters, multiple optimization targets, and multiple charging behavior data of the target vehicle. Among them, the photovoltaic output model is used to represent the ability of the preset charging station to convert light energy into electrical energy, the multiple energy storage system parameters are used to represent the state of the preset energy storage system in the charging station, the target vehicle refers to any one of the preset multiple vehicles, and the multiple charging behavior data are used to represent the charging status of the target vehicle in a preset first time period, the end time of the first time period is earlier than the current time.

[0300] The plotting module 1902 is used to plot curves based on multiple charging behavior data of multiple vehicles to obtain a charging load curve. The charging load curve is used to represent the change of the charging station load over time within a preset second time period. The start time of the second time period is later than the current time, and the charging station is used to charge multiple vehicles.

[0301] Module 1903 is used to construct a multi-objective optimization model based on the photovoltaic output model, multiple energy storage system parameters, multiple optimization objectives, and charging load curves.

[0302] The solver module 1904 is used to solve the multi-objective optimization model to obtain the target configuration scheme. The target configuration scheme is used to guide the charging station to adjust its configuration information so that the operating state of the charging station meets multiple optimization objectives.

[0303] In one possible design, the target vehicle's multiple charging behavior data include multiple dimensions, and the mapping module 1902 includes:

[0304] The parameter extraction unit is used to extract parameters from multiple charging behavior data of the target vehicle to obtain values ​​for each dimension; among which, multiple dimensions include starting charging time, daily driving mileage, battery state of charge, and power demand.

[0305] The first determining unit is used to determine the probability density function of each dimension based on the values ​​of each dimension; wherein the probability density function of each dimension is used to represent the distribution characteristics of the values ​​of each dimension.

[0306] The sampling unit is used to sample the preset variables in the probability density function of each dimension to obtain the predicted charging behavior data of the target vehicle in the second time period; wherein, the predicted charging behavior data of the target vehicle in the second time period refers to the data of the target vehicle in multiple dimensions in the second time period.

[0307] The first calculation unit is used to calculate the charging load value of multiple vehicles at any time during the second time period based on the predicted charging behavior data of the target vehicle during the second time period.

[0308] The plotting unit is used to plot the charging load curve based on the charging load values ​​of multiple vehicles at any time during the second time period.

[0309] In one possible design, building module 1903 includes:

[0310] The first acquisition unit is used to acquire multiple modeling constraints. These constraints include photovoltaic output constraints, energy storage charging and discharging constraints, and power balance constraints. The photovoltaic output constraints represent the degree to which the charging station's ability to convert light energy into electrical energy is affected by light intensity and temperature. The energy storage charging and discharging constraints represent the boundary for the safe operation of the energy storage system. The power balance constraints represent the dynamic balance requirements between the charging station's energy supply and load demand.

[0311] The building unit is used to construct a multi-objective optimization model based on multiple modeling constraints, photovoltaic power output model, multiple energy storage system parameters, multiple optimization objectives, and charging load curves.

[0312] In one possible design, solver module 1904 includes:

[0313] The solver unit is used to solve the multi-objective optimization model and obtain multiple configuration schemes.

[0314] The filtering unit is used to filter multiple configuration schemes based on preset filtering rules to obtain the target configuration scheme; wherein, the filtering rules are used to indicate the degree of importance that users attach to each optimization goal.

[0315] In one possible design, the device for determining the charging station configuration scheme also includes:

[0316] The execution module is used to execute the target configuration scheme and obtain multiple execution result data; among them, the multiple execution result data are used to represent the operating status of the charging station after executing the target configuration scheme.

[0317] The optimization module is used to optimize the multi-objective optimization model based on multiple execution result data to obtain the optimized multi-objective optimization model.

[0318] In one possible design, the execution module includes:

[0319] The second acquisition unit is used to acquire multiple first environmental data and multiple second environmental data; wherein, the multiple first environmental data are used to represent the environmental state of the charging station when the target configuration scheme is obtained, and the multiple second environmental data are used to represent the environmental state of the charging station when the target configuration scheme is executed.

[0320] The second calculation unit is used to calculate environmental changes based on multiple first environmental data and multiple second environmental data.

[0321] The optimization unit is used to optimize the target configuration scheme according to changes in the environment, and obtain the optimized target configuration scheme.

[0322] The execution unit is used to execute the optimized target configuration scheme and obtain multiple execution result data.

[0323] The charging station configuration scheme determination device provided in this embodiment can execute... Figure 2 and Figure 3 The technical solution of the embodiment of the method for determining a charging station configuration scheme shown herein, its implementation principle and technical effects are similar to those of... Figure 2 and Figure 3 The method for determining the configuration scheme of the charging station shown is similar to the embodiment, and will not be described in detail here.

[0324] Figure 20 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application. Figure 20 As shown, the electronic device 200 includes at least one processor 2001 and a memory 2002. The electronic device 200 also includes a communication component 2003. The processor 2001, memory 2002, and communication component 2003 are connected via a bus 2004.

[0325] In the specific implementation process, at least one processor 2001 executes computer execution instructions stored in memory 2002, so that at least one processor 2001 is used to implement a method for determining a charging station configuration scheme according to the above embodiment.

[0326] The specific implementation process of processor 2001 can be found in the above method embodiments, and its implementation principle and technical effect are similar, so it will not be repeated here.

[0327] In the above embodiments, it should be understood that the processor 2001 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0328] The memory 2002 may include high-speed RAM memory, and may also include non-volatile memory NVM, such as at least one disk storage.

[0329] Bus 2004 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Bus 2004 can be divided into address bus, data bus, control bus, etc. For ease of illustration, the bus 2004 in the accompanying drawings of this application is not limited to only one bus or one type of bus.

[0330] The above description of the functions implemented by electronic devices and main control devices has introduced the solutions provided by the embodiments of the present invention. It is understood that, in order to implement the above functions, the electronic device or main control device includes hardware structures and / or software modules corresponding to the execution of each function. By combining the units and algorithm steps of the various examples described in the embodiments of the present invention, the embodiments of the present invention can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the technical solutions of the embodiments of the present invention.

[0331] This application also provides a computer-readable storage medium storing computer-executable instructions. When executed by a processor, these instructions are used to implement a method for determining a charging station configuration scheme as described in the above embodiments. In the specific implementation of the aforementioned method for determining a charging station configuration scheme, each module can be implemented as a processor.

[0332] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0333] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in application-specific integrated circuits (ASICs). Alternatively, the processor and the readable storage medium can exist as discrete components in an electronic device or a host device.

[0334] This application also provides a computer program product, including a computer program, which, when executed by a processor, is used to implement a method for determining a charging station configuration scheme as described in the above embodiments.

[0335] The computer program is stored in a readable storage medium, and at least one processor can read the computer program from the readable storage medium and execute the computer program to perform the scheme provided in any of the above embodiments.

[0336] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disk, or optical disk.

[0337] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for determining a charging station configuration scheme, characterized in that, include: The system acquires a photovoltaic output model, multiple energy storage system parameters, multiple optimization targets, and multiple charging behavior data of a target vehicle. The photovoltaic output model represents the ability of a preset charging station to convert solar energy into electrical energy. The multiple energy storage system parameters represent the state of the preset energy storage systems within the charging station. The target vehicle refers to any one of the preset multiple vehicles. The multiple charging behavior data represent the charging status of the target vehicle within a preset first time period, where the end time of the first time period is earlier than the current time. A charging load curve is obtained by plotting multiple charging behavior data of multiple vehicles; wherein, the charging load curve is used to represent the change of the load of the charging station over time within a preset second time period, the start time of the second time period is later than the current time, and the charging station is used to charge the multiple vehicles. A multi-objective optimization model is constructed based on the photovoltaic output model, the multiple energy storage system parameters, the multiple optimization objectives, and the charging load curve. The multi-objective optimization model is solved to obtain the target configuration scheme; wherein, the target configuration scheme is used to guide the charging station to adjust its configuration information so that the operating state of the charging station meets the multiple optimization objectives.

2. The method for determining the charging station configuration scheme according to claim 1, characterized in that, The target vehicle's multiple charging behavior data includes multiple dimensions. The process of plotting curves based on the multiple charging behavior data from multiple vehicles to obtain a charging load curve includes: Parameters are extracted from multiple charging behavior data of the target vehicle to obtain values ​​for each dimension; wherein, the multiple dimensions include starting charging time, daily driving mileage, battery state of charge, and power demand. Based on the values ​​of each dimension, determine the probability density function of each dimension; wherein, the probability density function of each dimension is used to represent the distribution characteristics of the values ​​of each dimension; By sampling the preset variables in the probability density function of each dimension, the predicted charging behavior data of the target vehicle in the second time period is obtained; wherein, the predicted charging behavior data of the target vehicle in the second time period refers to the data of the target vehicle in multiple dimensions in the second time period. Based on the predicted charging behavior data of the target vehicle in the second time period, calculate the charging load value of multiple vehicles at any time in the second time period. The charging load curve is obtained by plotting the charging load values ​​of multiple vehicles at any time during the second time period.

3. The method for determining the charging station configuration scheme according to claim 1, characterized in that, The step of constructing a multi-objective optimization model based on the photovoltaic output model, the multiple energy storage system parameters, the multiple optimization objectives, and the charging load curve includes: Multiple modeling constraints are obtained; wherein, the multiple modeling constraints include photovoltaic output constraints, energy storage charging and discharging constraints, and power balance constraints. The photovoltaic output constraints are used to represent the degree to which the charging station's ability to convert light energy into electrical energy is affected by light intensity and temperature. The energy storage charging and discharging constraints are used to represent the boundary of the safe operation of the energy storage system. The power balance constraints are used to represent the dynamic balance requirements between the energy supply and load demand of the charging station. Based on the aforementioned modeling constraints, a multi-objective optimization model is constructed according to the photovoltaic output model, the aforementioned energy storage system parameters, the aforementioned optimization objectives, and the aforementioned charging load curve.

4. The method for determining the charging station configuration scheme according to claim 1, characterized in that, Solving the multi-objective optimization model to obtain the target configuration scheme includes: Solving the multi-objective optimization model yields multiple configuration schemes; The multiple configuration schemes are filtered based on preset filtering rules to obtain the target configuration scheme; wherein, the filtering rules are used to indicate the degree of importance that users attach to each of the optimization goals.

5. The method for determining the configuration scheme of charging stations according to claim 1, characterized in that, After solving the multi-objective optimization model to obtain the target configuration scheme, the method further includes: The target configuration scheme is executed to obtain multiple execution result data; wherein, the multiple execution result data are used to represent the operating status of the charging station after the target configuration scheme is executed; The multi-objective optimization model is optimized based on the multiple execution result data to obtain the optimized multi-objective optimization model.

6. The method for determining the charging station configuration scheme according to claim 5, characterized in that, The execution of the target configuration scheme yields multiple execution result data, including: Acquire multiple first environmental data and multiple second environmental data; wherein, the multiple first environmental data are used to represent the environmental state of the charging station when the target configuration scheme is obtained, and the multiple second environmental data are used to represent the environmental state of the charging station when the target configuration scheme is executed; Based on the plurality of first environmental data and the plurality of second environmental data, calculate the environmental changes; The target configuration scheme is optimized based on the environmental changes to obtain an optimized target configuration scheme; The optimized target configuration scheme is executed to obtain the multiple execution result data.

7. A device for determining a charging station configuration scheme, characterized in that, include: The acquisition module is used to acquire a photovoltaic output model, multiple energy storage system parameters, multiple optimization targets, and multiple charging behavior data of a target vehicle; wherein, the photovoltaic output model is used to represent the ability of a preset charging station to convert solar energy into electrical energy, the multiple energy storage system parameters are used to represent the state of the preset energy storage system in the charging station, the target vehicle refers to any one of the preset multiple vehicles, and the multiple charging behavior data are used to represent the charging status of the target vehicle within a preset first time period, the end time of the first time period being earlier than the current time; A plotting module is used to plot curves based on multiple charging behavior data of multiple vehicles to obtain a charging load curve; wherein, the charging load curve is used to represent the change of the load of the charging station over time within a preset second time period, the start time of the second time period is later than the current time, and the charging station is used to charge the multiple vehicles. The construction module is used to construct a multi-objective optimization model based on the photovoltaic output model, the multiple energy storage system parameters, the multiple optimization objectives, and the charging load curve; The solution module is used to solve the multi-objective optimization model to obtain the target configuration scheme; wherein, the target configuration scheme is used to guide the charging station to adjust the configuration information so that the operating state of the charging station meets the multiple optimization objectives.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; When the processor executes the computer execution instructions stored in the memory, it is used to implement the method for determining the charging station configuration scheme as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method for determining a charging station configuration scheme as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The system includes a computer program, which, when executed by a processor, is used to implement the method for determining a charging station configuration scheme as described in any one of claims 1 to 6.

Images