Pricing method, device and storage medium of charging station

Abstract

This application discloses a pricing method, equipment, and storage medium for charging stations, relating to the field of data processing technology. The method includes: decomposing charging demand into basic charging demand and flexible charging demand; using flexible charging demand to quantify the relationship between service fee adjustments and the marginal impact on charging demand; generating multiple charging demand prediction curves with different confidence levels based on the superposition of basic and flexible charging demand to accurately characterize the uncertainty of charging demand; determining charging revenue based on these multiple prediction curves, reflecting fluctuations in charging revenue at different confidence levels, thus transforming the evaluation of each candidate pricing curve from a single charging revenue to encompassing charging revenue under different conditions; and finally, optimizing the pricing strategy based on the charging revenue under different conditions, selecting the optimal pricing strategy by fully considering the uncertainty of charging demand and revenue risk, thereby improving the pricing accuracy of charging stations.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to pricing methods, equipment and storage media for charging stations. Background Technology

[0002] Currently, setting excessively high service fees for charging stations leads to decreased customer traffic, while setting too low fees results in insufficient profits. Therefore, determining a reasonable and optimal service fee has become a challenge for the industry. In related technologies, charging station operators set service fees based on experience, and then determine the final price of the charging station based on the service fee and electricity prices. However, manual service fee setting is inaccurate, resulting in insufficient precision in the final pricing of the charging station. Summary of the Invention

[0003] The main purpose of this application is to provide a pricing method, device and storage medium for charging stations, which aims to improve the pricing accuracy of charging stations.

[0004] To achieve the above objectives, this application proposes a pricing method for charging stations, including: Based on the range of electricity prices and service fees for charging stations at different times, at least two candidate pricing curves should be determined. For each candidate pricing curve, the basic charging demand and elastic charging demand corresponding to the candidate pricing curve are determined. Based on the basic charging demand and elastic charging demand, multiple charging demand prediction curves corresponding to different confidence levels are determined. Among them, elastic charging demand represents the amount of change in charging demand caused by changes in service fees. Based on multiple charging demand forecast curves, determine the charging revenue corresponding to the candidate pricing curve. The optimal pricing strategy for charging stations is determined by optimizing the charging revenue corresponding to each candidate pricing curve.

[0005] In one embodiment, determining the basic charging demand and flexible charging demand corresponding to the candidate pricing curve includes: Determine the change in service fees for each time period based on the service fees for each time period. The service fee change corresponding to each time period is input into the elastic charging demand prediction model to predict the elastic charging demand corresponding to each time period. The elastic charging demand prediction model is trained based on the relationship between historical service fee change samples and historical elastic charging demand samples. The electricity price and meteorological data corresponding to each time period are input into the basic charging demand prediction model to predict the basic charging demand corresponding to each time period at different confidence levels. The basic charging demand prediction model is trained by the mapping relationship between historical electricity price samples, historical meteorological data samples and historical basic charging demand samples at different confidence levels.

[0006] In one embodiment, determining the change in service fees for each time period based on the service fees for each time period includes: Determine the historical average service fee based on the service fees for different historical periods; The change in service fees for each current time period is obtained by comparing the current service fee with the historical average service fee.

[0007] In one embodiment, it further includes: Based on the charging demand corresponding to each historical period, determine the historical average charging demand; based on the difference between the charging demand corresponding to each historical period and the historical average charging demand, obtain the elastic charging demand corresponding to each historical period; construct a historical elastic charging demand sample based on the elastic charging demand corresponding to each historical period. The historical basic charging demand sample is determined based on the difference between the historical real charging demand sample and the historical elastic charging demand sample.

[0008] In one embodiment, determining multiple charging demand prediction curves corresponding to different confidence levels based on basic charging demand and flexible charging demand includes: Based on the flexible charging demand and the basic charging demand corresponding to different confidence levels, determine the charging demand corresponding to different confidence levels. Based on the charging demand corresponding to different confidence levels, multiple charging demand prediction curves are generated. Each charging demand prediction curve corresponds to a different confidence level, and each charging demand prediction curve consists of the charging demand corresponding to at least two time periods.

[0009] In one embodiment, determining the charging revenue corresponding to a candidate pricing curve based on multiple charging demand forecast curves includes: Based on multiple charging demand prediction curves corresponding to different confidence levels, the photovoltaic-storage-charging joint optimization model is solved to obtain the optimal, worst, and average revenues corresponding to the candidate pricing curves. Among them, charging revenue includes optimal revenue, worst-case revenue, and average revenue; The objective function of the photovoltaic-storage-charging joint optimization model includes a charging demand variable and a revenue objective. The objective function aims to maximize both the charging demand variable and the revenue objective. The constraints used in solving the photovoltaic-storage-charging joint optimization model include: charging demand range constraints. When calculating the optimal benefit, the charging demand range constraint is: the charging demand corresponding to time period t is equal to the charging demand at the first confidence level. When calculating the worst-case benefit and the average benefit, the charging demand range constraint is: the charging demand corresponding to time period t is greater than or equal to the charging demand at the second confidence level and less than or equal to the charging demand at the first confidence level.

[0010] In one embodiment, optimizing the pricing strategy based on the charging revenue corresponding to each candidate pricing curve to determine the optimal pricing strategy for the charging station includes: Based on charging revenue, the evaluation indicators corresponding to the candidate pricing curves are determined, whereby the evaluation indicators are used to characterize the balance between revenue and risk. With the goal of maximizing the evaluation index, the candidate pricing curves are iteratively updated until the set convergence condition is met, and the candidate pricing curve with the highest evaluation index is output as the optimal pricing strategy for the charging station.

[0011] In one embodiment, the evaluation metrics for determining the candidate pricing curve based on charging revenue include: Based on the optimal return, worst return, and average return, determine the Sharpe ratio corresponding to the candidate pricing curve, and use the Sharpe ratio as the evaluation indicator for the candidate pricing curve. Among them, charging revenue includes optimal revenue, worst revenue, and average revenue; both optimal and worst revenue are negatively correlated with the Sharpe ratio, while average revenue is positively correlated with the Sharpe ratio.

[0012] In one embodiment, with the maximization of the evaluation index as the optimization objective, each candidate pricing curve is iteratively updated until a set convergence condition is met, and the candidate pricing curve with the highest evaluation index is output as the optimal pricing strategy for the charging station, including: Treat each candidate pricing curve as an individual to obtain the current population; The fitness of each individual in the current population is evaluated to obtain the fitness value of each individual, where the fitness value is used to characterize the evaluation index. If the set convergence condition is met, the candidate pricing curve with the largest fitness value in the current population will be taken as the optimal pricing strategy for the charging station. If the set convergence condition is not met, target individuals are selected from the current population based on the fitness values ​​of each individual, and crossover and mutation operations are performed on the target individuals to generate offspring individuals; based on the offspring individuals and the target individuals, a new generation population is constructed; the new generation population is used as the new current population, and the steps of evaluating the fitness of each individual in the current population are returned to obtain the fitness values ​​of each individual. The convergence conditions include: the number of iterations is greater than the preset number of iterations, or the maximum fitness value obtained by a consecutive preset number of iterations remains unchanged.

[0013] In one embodiment, based on the range of electricity prices and service fees corresponding to different time periods at the charging station, at least two candidate pricing curves are determined, including: The service fee range for each time period is determined based on the number of people charging at the charging station and the electricity price for each time period. The pricing range for each time period is determined based on the electricity price and service fee range for each time period. Based on the pricing range corresponding to each time period, at least two candidate pricing curves are initialized.

[0014] In addition, to achieve the above objectives, this application also proposes a pricing device for a charging station, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the pricing method for the charging station as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the charging station pricing method described above.

[0016] The one or more technical solutions proposed in this application have at least the following technical effects: By decomposing charging demand into basic charging demand and flexible charging demand, the relationship between the adjustment of service fees and the marginal impact on charging demand is quantified using flexible charging demand; on this basis, multiple charging demand prediction curves with different confidence levels are generated based on the superposition of basic charging demand and flexible charging demand, which can accurately characterize the uncertainty of charging demand, thereby expanding the single charging demand estimate into a probabilistic assessment of multiple scenarios; then, charging revenue is determined based on these multiple charging demand prediction curves with different confidence levels to reflect the fluctuation of charging revenue under different confidence levels, so that the evaluation of each candidate pricing curve changes from a single charging revenue expectation to a charging revenue that covers different situations; finally, the pricing curve is optimized based on the charging revenue that covers different situations, which can screen out the optimal pricing strategy on the basis of fully considering the uncertainty of charging demand and revenue risk, thereby effectively avoiding the evaluation bias caused by manual experience pricing, improving the evaluation accuracy of charging demand and charging revenue, and thus improving the pricing accuracy of charging stations. Attached Figure Description

[0017] 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.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating the pricing method for the charging station in this application (first embodiment). Figure 2 This diagram illustrates the relationship between the change in service fees for this application and the flexible charging demand. Figure 3 A detailed flowchart illustrating an embodiment of the pricing method for charging stations in this application; Figure 4 This is a schematic diagram of the pricing equipment for the charging station in this application.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] In related technologies, charging station operators set service fees based on experience, and then determine the final price of the charging station based on the service fee and electricity price. However, manual service fee pricing is inaccurate, resulting in insufficient precision in the final pricing of the charging station.

[0024] To address this issue, this application proposes a pricing method for charging stations. The main technical solution includes: determining at least two candidate pricing curves based on the electricity price and service fee range corresponding to each time period; for each candidate pricing curve, determining the basic charging demand and elastic charging demand corresponding to the candidate pricing curve, and determining multiple charging demand prediction curves with different confidence levels based on the basic charging demand and elastic charging demand, wherein elastic charging demand represents the amount of charging demand change caused by changes in service fees; determining the charging revenue corresponding to the candidate pricing curve based on the multiple charging demand prediction curves; and optimizing the pricing strategy based on the charging revenue corresponding to each candidate pricing curve to determine the optimal pricing strategy for the charging station.

[0025] By breaking down charging demand into basic charging demand and flexible charging demand, the relationship between service fee adjustments and the marginal impact of charging demand is quantified using flexible charging demand. Based on this, multiple charging demand prediction curves with different confidence levels are generated by superimposing basic and flexible charging demand, accurately depicting the uncertainty of charging demand. This expands the single charging demand estimate into a probabilistic assessment across multiple scenarios. Furthermore, charging revenue is determined based on these multiple charging demand prediction curves with different confidence levels, reflecting the fluctuation of charging revenue under different confidence levels. This transforms the evaluation of each candidate pricing curve from a single expected charging revenue to encompassing charging revenue under different conditions. Finally, pricing curve optimization is performed based on charging revenue covering different conditions. This allows for the selection of the optimal pricing strategy while fully considering the uncertainty of charging demand and revenue risks, effectively avoiding evaluation biases caused by manual experience-based pricing, improving the accuracy of charging demand and charging revenue assessments, and ultimately improving the pricing accuracy of charging stations.

[0026] It should be noted that the executing entity in this embodiment can be the pricing device of the charging station. The pricing device of the charging station is a computing service device with data processing, network communication and program running functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device that can realize the above functions.

[0027] Based on this, embodiments of this application provide a pricing method for charging stations, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the pricing method for the charging station according to this application. In this embodiment, the pricing method for the charging station includes steps S10 to S40: Step S10: Determine at least two candidate pricing curves based on the range of electricity prices and service fees corresponding to each time period at the charging station.

[0028] The electricity price for each time period refers to the price charged by the power grid company to the charging station for electricity consumption, which is usually determined by the electricity market pricing mechanism; therefore, the electricity price for each time period is known. The service fee range for each time period can be determined by the charging station's operation and maintenance personnel, based on the electricity price and the number of people charging during different time periods. The aforementioned time periods can be divided into peak and off-peak periods based on the distribution of electricity prices; they can also be divided into peak, off-peak, and flat periods. The candidate pricing curve is generated from each time period and its corresponding price. For example, mapping this candidate pricing curve to a coordinate system, the horizontal axis can represent the time period, and the vertical axis can represent the price corresponding to each time period.

[0029] In one alternative approach, the electricity price for each time period at the charging station can be divided into peak, normal, and off-peak periods based on the electricity price distribution. A corresponding service fee range can then be set for each of these periods. Based on the electricity price and service fee range for each period, at least two candidate pricing curves can be determined. Since the electricity price for each time period is known and defined, while the service fee is uncertain, different service fees can be applied within the corresponding service fee range for each period. These service fees can then be added to the electricity price for that period to obtain the pricing for that period under different service fee values. The pricing for each period under different service fee values ​​can be arbitrarily combined to obtain at least two candidate pricing curves.

[0030] For example, a day has 24 time periods, and the time-of-use electricity price for each period is as follows: [0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3]. Here, 0.2 yuan per kilowatt-hour is the price for the off-peak period, and 1.3 yuan per kilowatt-hour is the price for the peak period. Assume the service fee for the off-peak period ranges from 0.1 yuan per kilowatt-hour to 0.3 yuan per kilowatt-hour, and the service fee for the peak period ranges from 0.1 yuan per kilowatt-hour to 0.2 yuan per kilowatt-hour. When the service fee for off-peak hours is set at 0.1 yuan per kilowatt-hour and the service fee for peak hours is set at 0.1 yuan per kilowatt-hour, the resulting candidate pricing curve is: [0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 1.4 ... When the service fee for off-peak hours is set at 0.2 yuan per kilowatt-hour and the service fee for peak hours is set at 0.1 yuan per kilowatt-hour, the resulting candidate pricing curve is: [0.4, 0.4, 0.4, 0.4, 0.4, 0.4, 0.4, 0.4, 0.4, 0.4, 1 ...

[0031] Step S20: For each candidate pricing curve, determine the basic charging demand and flexible charging demand corresponding to the candidate pricing curve, and determine multiple charging demand prediction curves corresponding to different confidence levels based on the basic charging demand and flexible charging demand. Among them, the flexible charging demand represents the amount of change in charging demand caused by the change in service fee.

[0032] After initializing and obtaining multiple candidate pricing curves, the corresponding charging demand for each curve must be predicted. Considering the varying sensitivity of charging customers to charging prices under different time-of-use (TOU) electricity prices, such as lower prices during off-peak hours (even with significant adjustments to service fees), the overall electricity price remains low, resulting in low customer sensitivity. Conversely, during peak hours (higher electricity prices), even small adjustments to service fees can cause significant changes in customer demand, leading to high customer sensitivity. Based on this, charging demand can be divided into basic charging demand and elastic charging demand. Basic charging demand refers to the charging volume determined by factors such as electricity prices at different times, weather data, and user habits, without considering the impact of service fee changes; it reflects the rigid portion of charging demand. Elastic charging demand refers to the change in charging demand caused by changes in service fees relative to a benchmark level, reflecting the user's sensitivity to price adjustments. Increased service fees typically lead to decreased charging demand, while decreased service fees typically lead to increased charging demand; it reflects the elastic portion of charging demand. The benchmark level here can be the average service fee.

[0033] Confidence level refers to the degree of reliability of charging demand forecast results, reflecting the probability that the forecast results fall within the actual demand range. A higher confidence level indicates stronger reliability of the charging demand forecast results. The confidence level can be categorized according to specific circumstances.

[0034] A charging demand forecast curve is a curve formed by connecting the predicted charging demand values ​​for each time period of the day in chronological order, at a certain confidence level. It is used to characterize the trend and magnitude of charging demand changes over time at that confidence level. Since there are corresponding charging demand forecast results at different confidence levels, there are multiple charging demand forecast curves corresponding to different confidence levels, used to simulate operational performance under different market environments.

[0035] For example, multiple charging demand prediction curves corresponding to different confidence levels could be: charging demand prediction curves at the 95th quantile, the 50th quantile, and the 5th quantile, or other confidence levels. These curves are used to describe the uncertainty of charging demand prediction. The charging demand prediction curve at the 95th quantile indicates that there is a 95% probability that actual charging demand will not exceed the value corresponding to this curve; there is only a 5% probability that demand will be higher. It represents a slightly optimistic or extreme demand scenario, which can be understood as a situation with very strong demand and many users. The charging demand prediction curve at the 50th quantile indicates that there is a 50% probability that actual charging demand will be higher than this curve and a 50% probability that it will be lower than this curve. It is the median of the probability distribution, representing the most likely normal demand level, which is a typical expected scenario. The charging demand forecast curve at the 5th percentile indicates that there is a 95% probability that the actual charging demand will not be lower than the value corresponding to this curve; there is only a 5% probability that the demand will be lower than it; it represents a pessimistic or extreme demand scenario, which can be understood as a situation where the demand is very poor and no one comes to charge.

[0036] In one optional approach, average service fees and average charging demand are calculated based on historical data. For the current candidate pricing curve, the difference between the service fee and the average service fee for each time period is calculated to obtain the service fee change for each time period. Based on the service fee change and the pre-determined relationship between the service fee change and elastic charging demand, elastic charging demand is determined. Here, historical data can include historical electricity prices and historical charging demand. Historical electricity prices include historical time-of-use electricity prices and historical service fees. The relationship between service fee changes and elastic charging demand can be pre-fitted using historical service fee change samples and historical elastic charging demand samples. For example, the service fee change (corresponding to...) Figure 2 The difference in charging electricity prices and flexible charging demand (corresponding to) Figure 2 The relationship between the charging load difference in the middle is as follows: Figure 2 As shown. At the same time, current data is acquired, and the basic charging demand for each time period is predicted based on this current data. This current data may include information such as the current electricity price for each time period and current weather data.

[0037] After obtaining the basic charging demand and flexible charging demand for each time period using the above method, the basic charging demand and flexible charging demand can be added together by time period to obtain the charging demand for each time period. Specifically, the basic charging demand for each time period at different confidence levels can be predicted using this historical data. The basic charging demand and flexible charging demand at the corresponding confidence level can be added together by time period to obtain the charging demand for each time period at the corresponding confidence level. Connecting the charging demands for each time period at the corresponding confidence level in chronological order yields the charging demand prediction curve for that confidence level. Thus, the charging demand prediction curves corresponding to different confidence levels can be obtained through the above method.

[0038] Understandably, by breaking down charging demand into basic charging demand and flexible charging demand, the impact of service fee changes on demand can be accurately quantified. Furthermore, by using multi-confidence prediction curves to characterize demand uncertainty, the accuracy and comprehensiveness of demand assessment can be improved, providing reliable data support for subsequent revenue optimization and pricing decisions.

[0039] Step S30: Based on multiple charging demand forecast curves, determine the charging revenue corresponding to the candidate pricing curve.

[0040] Charging revenue refers to the economic benefit obtained by a charging station in providing charging services. This revenue can be categorized into optimal, worst-case, and average revenue. Each type of revenue is primarily derived from charging revenue and grid connection revenue, minus grid disconnection revenue and energy storage operating costs. Due to the existence of charging demand forecast curves with varying confidence levels, different charging revenues exist. For example, the charging revenue corresponding to the charging demand forecast curve at the 95th percentile is optimal, the charging revenue corresponding to the charging demand forecast curve at the 50th percentile is average, and the charging revenue corresponding to the charging demand forecast curve at the 5th percentile is worst. For each candidate pricing curve, there are multiple charging demand forecast curves corresponding to different confidence levels. The charging revenue corresponding to each confidence level of the charging demand forecast curve can be determined separately. Finally, the charging revenue determined by each confidence level of the charging demand forecast curve is taken as the charging revenue corresponding to that candidate pricing curve. Each candidate pricing curve can be used to determine its corresponding charging revenue in the above manner, which can reflect the fluctuation of charging revenue under different confidence levels, so that the evaluation of each candidate pricing curve is transformed from a single charging revenue expectation to a charging revenue that covers different situations.

[0041] Step S40: Optimize the pricing strategy based on the charging revenue corresponding to each candidate pricing curve to determine the optimal pricing strategy for the charging station.

[0042] Pricing strategy optimization refers to the process of selecting the best-performing pricing strategy from an existing set of candidate pricing curves based on a certain evaluation metric. The optimal pricing strategy is the candidate pricing curve with the highest evaluation metric.

[0043] In one optional approach, an evaluation metric is calculated for each candidate pricing curve. Subsequently, a heuristic optimization algorithm is used to iteratively update the candidate pricing curves with the objective of maximizing the evaluation metric. In each iteration, selection, crossover, and mutation operations are performed based on the evaluation metric ranking of individuals in the current population to generate a new generation of candidate pricing curves. An elite retention strategy ensures that historical optimal solutions are not lost. When the change in the optimal evaluation metric across multiple generations is less than a preset threshold or the maximum number of iterations is reached, the optimization process stops, and the candidate pricing curve with the highest evaluation metric is determined as the optimal pricing strategy.

[0044] In another alternative approach, a particle swarm optimization (PSO) algorithm is used for optimization. Each candidate pricing curve is mapped to a particle, where its position represents the value of the candidate pricing curve, and its velocity represents the update direction and step size. In each iteration, the particle's velocity and position are updated according to its evaluation metrics, and the globally optimal position is recorded. When the algorithm converges, the candidate pricing curve corresponding to the globally optimal position is output as the optimal pricing strategy.

[0045] In this embodiment, charging demand is broken down into basic charging demand and flexible charging demand. The relationship between service fee adjustments and the marginal impact of flexible charging demand on charging demand is quantified. Based on this, multiple charging demand prediction curves with different confidence levels are generated by superimposing basic and flexible charging demand. This accurately portrays the uncertainty of charging demand, expanding a single charging demand estimate into a probabilistic assessment across multiple scenarios. Charging revenue is then determined based on these multiple charging demand prediction curves with different confidence levels to reflect the fluctuations in charging revenue under different confidence levels. This transforms the evaluation of each candidate pricing curve from a single expected charging revenue to encompassing charging revenue under different conditions. Finally, pricing curve optimization is performed based on the charging revenue covering different conditions. This allows for the selection of the optimal pricing strategy while fully considering the uncertainty of charging demand and revenue risks, effectively avoiding evaluation biases caused by manual experience-based pricing, improving the accuracy of charging demand and charging revenue assessments, and ultimately improving the pricing accuracy of charging stations.

[0046] In one feasible implementation, step S10 may include steps S11 to S13: Step S11: Determine the service fee range for each time period based on the number of people charging and the electricity price at each time period.

[0047] The electricity price for each time period refers to the price charged by the power grid company to the charging station for electricity consumption, which is usually determined by the electricity market pricing mechanism; therefore, the electricity price for each time period is known. The number of people charging in each time period varies. The service fee range for each time period can be determined by the charging station's operation and maintenance personnel. The basis for setting the service fee range for each time period can be: when the number of people charging increases and the electricity price decreases, the service fee range for that time period increases; when the number of people charging decreases and the electricity price increases, the service fee range for that time period decreases; and when the number of people charging increases and the electricity price increases, the service fee range for that time period decreases. These time periods can be divided into peak and off-peak periods based on the distribution of electricity prices. For example, a day has 24 time periods, and the time-of-use electricity price for each time period is: [0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3, 1.3]; where 0.2 is the off-peak price and 1.3 is the peak price. It can also be divided into peak hours, off-peak hours, and flat hours.

[0048] In one alternative approach, a mapping relationship can be pre-established between different preset charging user numbers, preset electricity prices, and preset service fee ranges. During actual use, the service fee range for each time period can be obtained by matching the mapping relationship between the charging user numbers and electricity prices for each time period.

[0049] Step S12: Determine the pricing range for each time period based on the electricity price and service fee range for each time period.

[0050] The pricing for each time period equals the sum of the electricity price and service fee for that time period. The electricity price for each time period is known and definite, while the service fee is what this application needs to determine; it is unknown but has a range, and the service fee calculated subsequently needs to satisfy the corresponding service fee range. Therefore, by using the electricity price for the corresponding time period and the service fee range for that time period, the pricing range for that time period can be determined.

[0051] In one alternative approach, the lower limit of the pricing range for a given time period is obtained by adding the electricity price for that period to the lower limit of the service fee range for that period, and the upper limit of the pricing range for that time period is obtained by adding the electricity price for that period to the upper limit of the service fee range for that period. Then, the pricing range for that time period is determined based on both the lower and upper limits. The pricing range for each time period can be determined using the above method. For example, if the electricity price for a certain time period is 1.5 yuan per kilowatt-hour, and the service fee range for that time period is 0.5 to 0.9 yuan per kilowatt-hour, then the pricing range for that time period is 2 yuan to 2.4 yuan per kilowatt-hour.

[0052] Step S13: Based on the pricing range corresponding to each time period, initialize at least two candidate pricing curves.

[0053] In one alternative approach, the electricity price corresponding to each time period at the charging station can be divided into peak, normal, and off-peak periods based on the electricity price distribution. A corresponding service fee range can be set for each of the peak, normal, and off-peak periods. Then, based on the electricity price and service fee ranges corresponding to the peak, normal, and off-peak periods, a pricing range can be determined for each of the peak, normal, and off-peak periods. Based on these pricing ranges, at least two candidate pricing curves can be initialized.

[0054] For example, time-of-use electricity price data for a charging station connected to the power grid shows that peak hours are from 10:00 to 14:00 and from 18:00 to 22:00, with a price of 1.5 yuan per kilowatt-hour; off-peak hours are from 00:00 to 08:00 the next day, with a price of 0.3 yuan per kilowatt-hour; and the remaining hours are normal hours, with a price of 0.8 yuan per kilowatt-hour. The service fee range for peak hours can be set at 0.8 yuan to 1.2 yuan per kilowatt-hour, the service fee range for normal hours at 0.5 yuan to 0.9 yuan per kilowatt-hour, and the service fee range for off-peak hours at 0.3 yuan to 0.7 yuan per kilowatt-hour. This results in a pricing range of 1.8 yuan to 2.7 yuan per kilowatt-hour during peak hours and a price range of 0.8 yuan to 2.7 yuan per kilowatt-hour during normal hours. The pricing range is 1.3 to 1.7 yuan per kilowatt-hour, and the pricing range during off-peak hours is 0.6 to 1 yuan per kilowatt-hour. Then, prices are randomly selected within the above-mentioned pricing ranges for each time period, and candidate pricing curves covering different peak-valley price difference strategies are generated. For example, the first curve takes the upper limit of the pricing range during peak hours and the lower limit of the pricing range during off-peak hours to pursue high returns, while the second curve takes the lower limit of the pricing range during peak hours and the upper limit of the pricing range during off-peak hours to attract customers. Since there is a corresponding pricing range for each time period, different prices can be taken for each time period by taking values ​​within the corresponding pricing range for each time period, so as to form at least two candidate pricing curves.

[0055] In this embodiment, by combining the number of charging users with the electricity price, the service fee range for each time period can be determined. This allows for the accurate capture of supply and demand characteristics and differences in user price sensitivity during different time periods. For example, during peak charging periods with high user numbers, a relatively conservative upper limit for the service fee can be set in conjunction with a high electricity price to avoid customer churn. During off-peak charging periods with low user numbers, a relatively aggressive lower limit for the service fee can be set in conjunction with a low electricity price to improve resource utilization. This overcomes the problem of one-size-fits-all pricing based on human experience. Based on this, the electricity price and service fee range are coupled to form the pricing range for each time period, constructing a reasonable range for the pricing strategy. Then, multiple candidate pricing curves are initialized within this pricing range, providing a diverse initial solution set that conforms to actual operational logic for subsequent charging demand prediction and optimization.

[0056] In one feasible implementation, determining the basic charging demand and flexible charging demand corresponding to the candidate pricing curve in step S20 may include steps S21 to S23: Step S21: Determine the change in service fees for each time period based on the service fees for each time period.

[0057] The historical average service fee refers to the arithmetic mean of service fees for all time periods within a historical statistical period. It represents the charging station's charging level over a past period and serves as a price benchmark for measuring the relative level of the current service fee. The service fee for each time period can include the service fee for each historical time period as well as the service fee for each current time period. The change in the service fee for each time period can be the change in the service fee for each current time period.

[0058] In one optional approach, the change in service fees for each current period can be determined based on the service fees for each historical period and the service fees for each current period. Specifically, the historical average service fee can be determined based on the service fees for each historical period; the change in service fees for each current period is then obtained by calculating the difference between the service fees for each current period and the historical average service fee. This can be achieved by averaging the service fees for each historical period; after obtaining the historical average service fee, the change in service fees for each current period is subtracted from this historical average service fee to obtain the change in service fees for each current period. By comparing the service fees for each current period with the historical average service fee, the change in service fees for each period can be accurately calculated, providing a basis for quantifying the impact of service fee fluctuations on charging demand.

[0059] Step S22: Input the service fee change corresponding to each time period into the elastic charging demand prediction model to predict the elastic charging demand corresponding to each time period.

[0060] The elastic charging demand forecasting model can be trained based on the relationship between historical service fee change samples and historical elastic charging demand samples. This model can be a least squares model or a machine learning model, etc. The historical service fee change samples can include historical service fee changes across multiple time periods. The historical service fee change for each time period can be determined by: determining the historical average service fee based on the service fees for each historical time period; and obtaining the service fee change for each historical time period based on the difference between the service fees for each historical time period and the historical average service fee. Similarly, the historical elastic charging demand samples can include historical elastic charging demand across multiple time periods. The historical elastic charging demand for each time period can be determined by: determining the historical average charging demand based on the charging demand for each historical time period; and obtaining the elastic charging demand for each historical time period based on the difference between the charging demand for each historical time period and the historical average charging demand. After obtaining the elastic charging demand for each historical time period, a historical elastic charging demand sample can be constructed based on this historical elastic charging demand.

[0061] In one alternative approach, the change in service fees for each current time period can be input into the elastic charging demand forecasting model. By analyzing the relationship between the change in service fees and the elastic charging demand in the elastic charging demand forecasting model, the elastic charging demand for each current time period can be determined.

[0062] Step S23: Input the electricity price and meteorological data corresponding to each time period into the basic charging demand prediction model to predict the basic charging demand corresponding to each time period under different confidence levels.

[0063] The basic charging demand prediction model can be trained by mapping historical electricity price samples, historical meteorological data samples, and historical basic charging demand samples with different confidence levels. This initial basic charging demand prediction model can be ngboost (a machine learning model that outputs a complete probability distribution), IGBM (LightGBM, an open-source, efficient gradient boosting framework), XGBM (an efficient machine learning algorithm, short for Extreme Gradient Boosting, used for structured data prediction), etc. The historical basic charging demand samples can be determined based on the difference between historical real charging demand samples and historical elastic charging demand samples. These historical basic charging demand samples include historical basic charging demand corresponding to different time periods. For each time period, the historical basic charging demand for that time period can be obtained based on the difference between the historical real charging demand and the historical elastic charging demand for that time period. Finally, the historical basic charging demand samples are formed based on the historical basic charging demand for each time period.

[0064] In one alternative approach, the basic charging demand forecasting model is obtained by inputting the electricity price and meteorological data corresponding to each time period into the basic charging demand forecasting model. By using the mapping relationship between the electricity price, meteorological data and basic charging demand at different confidence levels in the basic charging demand forecasting model, the basic charging demand corresponding to each time period at different confidence levels can be determined.

[0065] In this embodiment, by applying a pre-trained elastic charging demand forecasting model, the rapid and accurate quantification of demand fluctuations caused by changes in service fees is achieved. This effectively solves the problem that human experience is insufficient to accurately measure price sensitivity, providing a basis for charging stations to formulate dynamic pricing strategies. By applying a pre-trained basic charging demand forecasting model, the forecasting of rigid charging demand unaffected by price is achieved. This effectively solves the problem that traditional forecasting methods can only provide single-point estimates and cannot quantify uncertainty, providing data support for charging stations to make decisions in complex environments.

[0066] In one feasible implementation, after obtaining the basic charging demand and flexible charging demand through the above method, determining multiple charging demand prediction curves corresponding to different confidence levels based on the basic charging demand and flexible charging demand includes: determining the charging demand corresponding to different confidence levels based on the flexible charging demand and the basic charging demand corresponding to different confidence levels; generating multiple charging demand prediction curves based on the charging demand corresponding to different confidence levels. Each charging demand prediction curve corresponds to a different confidence level, and each charging demand prediction curve consists of the charging demand corresponding to at least two time periods.

[0067] In one alternative approach, the elastic charging demand can be superimposed onto the base charging demand corresponding to different confidence levels to obtain the charging demand at each confidence level. Multiple charging demand prediction curves are then generated based on the charging demand at different confidence levels. Specifically, for a single charging demand prediction curve, the elastic charging demand for each time period is added to the base charging demand for that time period to obtain the charging demand for that time period; the charging demand for each time period is then concatenated in chronological order to obtain the single charging demand prediction curve. Each confidence level can have its corresponding charging demand prediction curve determined using the above method. Thus, charging demand prediction curves corresponding to different confidence levels can be determined using this method. For example, multiple charging demand prediction curves corresponding to different confidence levels could be: a charging demand prediction curve at the 95th percentile, a charging demand prediction curve at the 50th percentile, and a charging demand prediction curve at the 5th percentile.

[0068] Understandably, by determining the basic charging demand and the flexible charging demand, and then superimposing these two demands, a charging demand prediction curve can be obtained. Furthermore, since there are basic charging demands corresponding to different confidence levels, multiple charging demand prediction curves with different confidence levels can be accurately obtained, providing a data foundation for determining subsequent charging revenue.

[0069] In one feasible implementation, step S30 includes: based on multiple charging demand prediction curves corresponding to different confidence levels, solving the photovoltaic-storage-charging joint optimization model respectively to obtain the optimal revenue, worst revenue and average revenue corresponding to the candidate pricing curve.

[0070] The charging revenue includes optimal revenue, worst-case revenue, and average revenue. The objective function of the photovoltaic-storage-charging joint optimization model includes a charging demand variable and a revenue objective term, with the objective function aiming to maximize both the charging demand variable and the revenue objective term. For example, the objective function can be expressed as: .

[0071] in, Let be the charging demand variable, representing the total charging power demand of the charging station at time t. For revenue targets. This represents the charging demand at time t; This represents the revenue target at time t (charging revenue + grid connection revenue - offline revenue - energy storage operation cost). . This represents the service fee at time t; This represents the on-grid electricity price at time t; This represents the power consumed at time t. This represents the on-grid electricity price at time t; This represents the downlink power at time t; This represents the energy storage discharge power at time t; This represents the cost per kilowatt-hour of energy storage; in the above formula... This represents a normalization operation because the unit of charging demand is kilowatts, while the range of charging revenue is yuan, thus avoiding the impact of the difference in units on the optimization objective.

[0072] The constraints used in solving the photovoltaic-storage-charging joint optimization model include charging demand range constraints, which differ when calculating different charging benefits. Specifically, the charging demand range constraint used when calculating the optimal benefit is that the charging demand corresponding to time period t is equal to the charging demand at the first confidence level; the charging demand range constraint used when calculating the worst-case and average benefits is that the charging demand corresponding to time period t is greater than or equal to the charging demand at the second confidence level and less than or equal to the charging demand at the first confidence level.

[0073] In solving the photovoltaic-storage-charging joint optimization model, in addition to the charging demand range constraints mentioned above, the following constraints can also be used, including but not limited to:

[0074] Among them, constraints 1, 2, and 3 are energy storage capacity constraints; constraint 4 is an electricity balance constraint; constraint 5 is that energy storage charging and discharging cannot coexist; constraint 6 is that grid connection and energy storage discharge cannot coexist; constraint 7 is that grid connection and energy storage discharge cannot coexist. Constraint 8 is a reverse current prevention and overload prevention constraint; constraint 9 is negative for grid connection; constraint 10 is positive for grid connection; constraint 11 is an energy storage charging power constraint; constraint 12 is an energy storage discharging power constraint; constraint 13 is an actual photovoltaic power output constraint; and constraint 14 describes the uncertainty range of charging demand.

[0075] Where SOC_t represents the state of charge of the stored energy at time t. The initial value of the state of charge of the energy storage. and These are the lower limit and upper limit of its safe state of charge operation, respectively; Cap is the rated capacity of energy storage. and These represent the energy storage charging and discharging efficiency, respectively. and These represent the charging and discharging power of the energy storage system at time t; This indicates the energy conversion efficiency of the charging station; Let t be the actual photovoltaic output power at time t. Let be the predicted photovoltaic power output at time t; For auxiliary loads within the station; and These are the overload and backflow protection power limits for the power grid connection lines, respectively. This indicates the maximum allowable charging power of the energy storage system; This indicates the maximum allowable discharge power of the energy storage system.

[0076] Since the revenue of a charging station mainly comes from charging revenue, the higher the charging demand, the higher the revenue, and the lower the charging demand, the lower the revenue. Therefore, when solving for the optimal revenue, we only need to change the 14th constraint to: ,in This represents the charging demand forecast curve at the 95th percentile, where the 95th percentile indicates the first confidence level. This represents the charging demand forecast curve at the 5th percentile, where the 5th percentile represents the second confidence level.

[0077] In this embodiment, the photovoltaic-storage-charging joint optimization model is solved based on multiple charging demand prediction curves corresponding to different confidence levels to obtain the optimal, worst-case, and average revenues corresponding to the candidate pricing curves. Each candidate pricing curve can have its corresponding charging revenue determined using the above method, reflecting the fluctuations in charging revenue under different confidence levels. This transforms the evaluation of each candidate pricing curve from a single expected charging revenue to encompassing charging revenues under different conditions.

[0078] Based on the above, in one feasible implementation, step S40 includes steps S41 and S42: Step S41: Based on charging revenue, determine the evaluation index corresponding to the candidate pricing curve, wherein the evaluation index is used to characterize the balance between revenue and risk.

[0079] In one alternative approach, charging revenue includes optimal revenue, worst-case revenue, and average revenue. The Sharpe ratio corresponding to a candidate pricing curve can be determined based on these three metrics, and used as an evaluation indicator for the candidate pricing curve. Optimal and worst-case revenues are negatively correlated with the Sharpe ratio, while average revenue is positively correlated. Determining the Sharpe ratio for a candidate pricing curve involves dividing the average revenue by the difference between the optimal and worst-case revenues. This Sharpe ratio measures the excess return per unit of risk; a higher Sharpe ratio indicates greater excess return per unit of risk, and a better candidate pricing curve. By considering the uncertainty of charging demand forecasting and determining the charging revenue and Sharpe ratio corresponding to candidate pricing curves, a more accurate and objective evaluation of the candidate pricing curves can be achieved, balancing revenue and risk.

[0080] Step S42: With the maximization of evaluation index as the optimization objective, iteratively update each candidate pricing curve until the set convergence condition is met, and output the candidate pricing curve with the highest evaluation index as the optimal pricing strategy for the charging station.

[0081] In one optional approach, each candidate pricing curve is treated as an individual to obtain the current population; fitness evaluation is performed on each individual in the current population to obtain the corresponding fitness value, where the fitness value is used to characterize the evaluation index; if the set convergence condition is met, the candidate pricing curve with the largest fitness value in the current population is taken as the optimal pricing strategy for the charging station; if the set convergence condition is not met, target individuals are selected from the current population according to the fitness values ​​of each individual, and crossover and mutation operations are performed on the target individuals to generate offspring individuals; a new generation population is constructed based on the offspring individuals and the target individuals; the new generation population is used as the new current population, and the step of performing fitness evaluation on each individual in the current population to obtain the corresponding fitness value is returned; wherein, the set convergence condition includes: the number of iterations is greater than the preset number of iterations, or the maximum fitness value obtained by consecutive preset number of iterations remains unchanged.

[0082] In this embodiment, an evaluation index corresponding to the candidate pricing curve is determined based on charging revenue. With maximizing the evaluation index as the optimization objective, each candidate pricing curve is iteratively updated until a set convergence condition is met. The candidate pricing curve with the highest evaluation index is then output as the optimal pricing strategy for the charging station. By considering the uncertainty of charging demand forecasting, the charging revenue and Sharpe ratio corresponding to the candidate pricing curve are determined, enabling a more accurate and objective evaluation of the candidate pricing curve and achieving a balance between revenue and risk. Optimizing the pricing strategy with the maximum Sharpe ratio as the objective improves the accuracy of the optimal pricing strategy.

[0083] For example, to help understand the implementation process of the charging station pricing method obtained in this embodiment combined with the above embodiment one, please refer to... Figure 3 , Figure 3 A simplified flowchart illustrating a pricing method for charging stations is provided, specifically: (1) Step S101: Obtain basic data, including historical predicted load data, historical actual load data, historical predicted electricity price data, and historical actual electricity price data. This basic data is used to predict the elastic charging demand and basic charging demand corresponding to each time period.

[0084] (2) Step S102: Use a heuristic algorithm to optimize the pricing strategy. First, initialize N pricing curves, that is, users set the upper and lower limits of service fee adjustment for different time periods according to the time-of-use electricity price, thereby obtaining the optimization range of the pricing curve. This corresponds to step S10 and its specific technical means.

[0085] (3) Step S103: For each candidate pricing curve, use the charging demand prediction technology based on a semi-parametric structural model to output the charging demand prediction results at different confidence levels, reflecting the uncertainty of the prediction. This corresponds to step S20 and its specific technical means.

[0086] (3) Step S104: After obtaining the charging demand prediction results (charging demand prediction curves) under different confidence levels, the optimal revenue, average revenue, and worst revenue corresponding to each candidate pricing curve are output based on the operation research optimization model of photovoltaic energy storage and charging. This corresponds to step S30 and its specific technical means.

[0087] (4) Step S105: Evaluation of pricing strategies considering return and risk value. That is, after obtaining the optimal return, average return, and worst return corresponding to the candidate pricing curve, the Sharpe ratio is used to calculate the evaluation index corresponding to the pricing curve. This corresponds to step S41 and its specific technical means.

[0088] (5) Step S106: Return the evaluation indicators to the heuristic algorithm for iterative updating of the pricing curve. Finally, output the optimal pricing. This corresponds to step S40 and its specific technical means.

[0089] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the pricing method of the charging station in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0090] Based on the same inventive concept, this application provides a pricing device for a charging station, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute the pricing method for the charging station in the above embodiments.

[0091] like Figure 4As shown, the pricing device of the charging station may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The random access memory 1004 also stores various programs and data required for the operation of the charging station's pricing device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the charging station's pricing equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a charging station pricing equipment with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0092] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0093] The pricing device for charging stations provided in this application, employing the pricing method for charging stations described in the above embodiments, can improve the pricing accuracy of charging stations. Compared with the prior art, the beneficial effects of the pricing device for charging stations provided in this application are the same as those of the pricing method for charging stations provided in the above embodiments, and other technical features in the pricing device for charging stations are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0094] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0095] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0096] Based on the same inventive concept, this application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the pricing method of the charging station in the above embodiments.

[0097] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory (EPROM), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0098] The aforementioned computer-readable storage medium may be included in the pricing device of the charging station; or it may exist independently and not be installed in the pricing device of the charging station.

[0099] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the pricing device of the charging station, cause the pricing device of the charging station to implement the steps of the aforementioned pricing method for the charging station.

[0100] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0102] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0103] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the pricing method of the charging station described above, which can improve the pricing accuracy of the charging station. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the pricing method of the charging station provided in the above embodiments, and will not be repeated here.

[0104] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A pricing method for charging stations, characterized in that, The method includes: Based on the range of electricity prices and service fees for each time period at the charging station, at least two candidate pricing curves are determined; For each candidate pricing curve, the basic charging demand and elastic charging demand corresponding to the candidate pricing curve are determined, and multiple charging demand prediction curves corresponding to different confidence levels are determined based on the basic charging demand and the elastic charging demand, wherein the elastic charging demand represents the amount of change in charging demand caused by changes in service fees. Based on multiple charging demand forecast curves, the charging revenue corresponding to the candidate pricing curve is determined. The optimal pricing strategy for the charging station is determined by optimizing the charging revenue corresponding to each candidate pricing curve.

2. The pricing method for charging stations as described in claim 1, characterized in that, Determining the basic charging demand and flexible charging demand corresponding to the candidate pricing curve includes: Determine the change in service fees for each time period based on the service fees for each time period. The service fee change corresponding to each time period is input into the elastic charging demand prediction model to predict the elastic charging demand corresponding to each time period. The elastic charging demand prediction model is trained based on the relationship between historical service fee change samples and historical elastic charging demand samples. The electricity price and meteorological data corresponding to each time period are input into the basic charging demand prediction model to predict the basic charging demand corresponding to each time period at different confidence levels. The basic charging demand prediction model is trained by the mapping relationship between historical electricity price samples, historical meteorological data samples and historical basic charging demand samples at different confidence levels.

3. The pricing method for charging stations as described in claim 2, characterized in that, The determination of the change in service fees for each time period based on the service fees for each time period includes: Determine the historical average service fee based on the service fees for different historical periods; The change in service fees for each current time period is obtained by comparing the current service fee with the historical average service fee.

4. The pricing method for charging stations as described in claim 2, characterized in that, Also includes: Determine the historical average charging demand based on the charging demand corresponding to each historical period. The elastic charging demand for each historical period is obtained by comparing the charging demand for each historical period with the historical average charging demand. A sample of historical elastic charging demand is then constructed based on the elastic charging demand for each historical period. The historical basic charging demand sample is determined based on the difference between the historical real charging demand sample and the historical flexible charging demand sample.

5. The pricing method for charging stations as described in claim 2, characterized in that, The step of determining multiple charging demand prediction curves corresponding to different confidence levels based on the basic charging demand and the flexible charging demand includes: Based on the aforementioned flexible charging demand and the basic charging demand corresponding to different confidence levels, determine the charging demand corresponding to different confidence levels. Based on the charging demand corresponding to different confidence levels, multiple charging demand prediction curves are generated. Each charging demand prediction curve corresponds to a different confidence level, and each charging demand prediction curve consists of charging demand corresponding to at least two time periods.

6. The pricing method for charging stations as described in claim 1, characterized in that, The process of determining the charging revenue corresponding to the candidate pricing curve based on multiple charging demand forecast curves includes: Based on multiple charging demand prediction curves corresponding to different confidence levels, the photovoltaic-storage-charging joint optimization model is solved to obtain the optimal revenue, worst revenue, and average revenue corresponding to the candidate pricing curves. The charging revenue includes the optimal revenue, the worst-case revenue, and the average revenue. The objective function of the photovoltaic-storage-charging joint optimization model includes a charging demand variable and a revenue objective, and the objective function aims to maximize the charging demand variable and the revenue objective. The constraints used in solving the photovoltaic-storage-charging joint optimization model include: charging demand range constraints. When calculating the optimal benefit, the charging demand range constraint is that the charging demand corresponding to time period t is equal to the charging demand at the first confidence level. When calculating the worst benefit and the average benefit, the charging demand range constraint is that the charging demand corresponding to time period t is greater than or equal to the charging demand at the second confidence level and less than or equal to the charging demand at the first confidence level.

7. The pricing method for charging stations as described in any one of claims 1 to 6, characterized in that, The step of optimizing the pricing strategy based on the charging revenue corresponding to each candidate pricing curve to determine the optimal pricing strategy for the charging station includes: Based on the charging revenue, an evaluation index corresponding to the candidate pricing curve is determined, wherein the evaluation index is used to characterize the balance between revenue and risk. With the maximization of the evaluation index as the optimization objective, each candidate pricing curve is iteratively updated until the set convergence condition is met, and the candidate pricing curve with the highest evaluation index is output as the optimal pricing strategy for the charging station.

8. The pricing method for charging stations as described in claim 7, characterized in that, The evaluation metrics for determining the candidate pricing curve based on the charging revenue include: Based on the optimal return, worst return, and average return, the Sharpe ratio corresponding to the candidate pricing curve is determined, and the Sharpe ratio is used as the evaluation index corresponding to the candidate pricing curve. The charging benefits include optimal benefits, worst-case benefits, and average benefits; the optimal benefits and the worst-case benefits are both negatively correlated with the Sharpe ratio, while the average benefits are positively correlated with the Sharpe ratio.

9. The pricing method for charging stations as described in claim 7, characterized in that, The step of iteratively updating each candidate pricing curve with the goal of maximizing the evaluation index until a set convergence condition is met, and outputting the candidate pricing curve with the highest evaluation index as the optimal pricing strategy for the charging station includes: Each of the candidate pricing curves is treated as an individual to obtain the current population; A fitness assessment is performed on each individual in the current population to obtain a fitness value for each individual, wherein the fitness value is used to characterize the assessment index; If the set convergence condition is met, the candidate pricing curve with the largest fitness value in the current population will be taken as the optimal pricing strategy for the charging station. If the set convergence condition is not met, then target individuals are selected from the current population based on the fitness values ​​of each individual, and crossover and mutation operations are performed on the target individuals to generate offspring individuals; based on the offspring individuals and the target individuals, a new generation population is constructed; using the new generation population as the new current population, the step of evaluating the fitness of each individual in the current population to obtain the fitness value of each individual is returned; The convergence conditions include: the number of iterations is greater than the preset number of iterations, or the maximum fitness value obtained by a consecutive preset number of iterations remains unchanged.

10. The pricing method for charging stations as described in claim 1, characterized in that, The step of determining at least two candidate pricing curves based on the electricity price and service fee range corresponding to each time period of the charging station includes: The service fee range for each time period is determined based on the number of people charging at the charging station and the electricity price for each time period. The pricing range for each time period is determined based on the electricity price and service fee range for each time period. Based on the pricing range corresponding to each time period, at least two candidate pricing curves are initialized.

11. A pricing device for a charging station, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the pricing method for the charging station as claimed in any one of claims 1 to 10.

12. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the pricing method for the charging station as described in any one of claims 1 to 10.

Images