Vehicle network interaction type orderly charging scheduling method, system and device and storage medium

Abstract

The invention provides a vehicle network interaction type orderly charging scheduling method, system and device and a storage medium, and relates to the technical field of electric vehicle charging, and the method comprises the steps: predicting a target power grid load curve in a second time period through combining a historical power grid load curve and a real-time power grid load curve of a target region, determining a high load period, a stable load period and a low load period of the target power grid load curve; obtaining first reservation information of the charging pile in the target area in a high load period, second reservation information of the charging pile in a stable load period and third reservation information of the charging pile in a low load period; generating an initial charging scheduling strategy by combining the first reservation information, the second reservation information and the third reservation information; and obtaining historical vehicle performance data of the charging pile, adjusting the initial charging scheduling strategy according to the historical vehicle performance data, and generating a target charging scheduling strategy of the charging pile in the high-load period. The method has the technical effect that the risk of power grid load fluctuation is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of electric vehicle charging, and in particular to a vehicle-grid interactive orderly charging scheduling method, system, device and storage medium. Background Art

[0002] With the rapid adoption of electric vehicles, the concentrated and random nature of charging demand poses significant challenges to the safe operation of the power grid. Especially during high-load periods, the simultaneous charging of a large number of electric vehicles can lead to localized overloads on the grid, posing potential safety risks to the power supply. Therefore, an effective charging scheduling mechanism is needed to balance charging loads and ensure safe and stable grid operation.

[0003] Currently, charging scheduling methods based on historical data are commonly used. These methods analyze historical charging behavior patterns to formulate charging prices and scheduling strategies. For example, peak and off-peak hours are determined based on historical data, and differentiated peak and off-peak electricity prices are used to guide charging demand shifts. While these methods can achieve a certain degree of charging load shifting, they rely too heavily on historical data and fail to respond promptly to real-time load changes. This can lead to significant discrepancies between actual scheduling results and expectations, increasing the risk of grid load fluctuations. Summary of the Invention

[0004] The present application provides a vehicle-grid interactive orderly charging scheduling method, system, device and storage medium for reducing the risk of grid load fluctuations.

[0005] In the first aspect, the present application provides a vehicle-grid interactive orderly charging scheduling method, the method comprising: obtaining a historical grid load curve of a target area, and a real-time grid load curve of the target area in a first time period before the current moment; combining the historical grid load curve and the real-time grid load curve, predicting a target grid load curve in a second time period after the current moment, and determining a high-load period, a stable load period, and a low-load period of the target grid load curve, wherein the high-load period is a period in which the load value in the target grid load curve exceeds a preset load upper limit, the stable load period is a period in which the load value in the target grid load curve is between a preset load upper limit and a preset load lower limit, and the low-load period is a period in which the load value in the target grid load curve is between a preset load upper limit and a preset load lower limit. The time period is a time period when the load value in the target power grid load curve is lower than the preset load lower limit; the first reservation information of the charging pile in the target area during the high load period, the second reservation information during the stable load period, and the third reservation information during the low load period are obtained; the initial charging scheduling strategy for the charging pile during the high load period is generated by combining the first reservation information, the second reservation information, and the third reservation information; the historical vehicle performance data of the charging pile is obtained, and the number of vehicle defaults in the high load period is predicted based on the historical vehicle performance data; the initial charging scheduling strategy is adjusted based on the number of defaults to generate a target charging scheduling strategy for the charging pile during the high load period.

[0006] By adopting the above technical solutions, the vehicle-grid interactive orderly charging scheduling method provided in this application improves prediction accuracy by combining historical and real-time grid load curves for load forecasting. By acquiring charging reservation information by time period and formulating an initial charging scheduling strategy, it achieves refined management of charging demand. In particular, by introducing a default prediction mechanism based on historical vehicle fulfillment data to dynamically adjust the scheduling strategy, it effectively avoids the waste of charging resources caused by user defaults. This solution not only improves the utilization efficiency of charging resources but also reduces the risk of grid load fluctuations.

[0007] Optionally, combining the historical grid load curve and the real-time grid load curve to predict the target grid load curve in the second time period after the current moment includes: predicting the first grid load curve of the target area in the second time period after the current moment based on the historical grid load curve; and predicting the target grid load curve in the second time period after the current moment in combination with the first grid load curve and the real-time grid load curve.

[0008] By adopting this technical solution, a primary grid load curve is first predicted based on historical grid load curves. This is then combined with the real-time grid load curve for a secondary prediction to generate the target grid load curve. This prediction method not only preserves the long-term variation patterns in historical data but also uses real-time data to correct the prediction results, improving the accuracy and reliability of load forecasts and providing more reliable data support for the formulation of subsequent charging scheduling strategies.

[0009] Optionally, the combining of the first power grid load curve and the real-time power grid load curve to predict the target power grid load curve in the second time period after the current moment includes: predicting the second power grid load curve in the second time period after the current moment based on the real-time power grid load curve; calculating the load difference between the first power grid load curve and the second power grid load curve at each moment in the second time period; judging whether the absolute value of the load difference at each moment is greater than a preset threshold; if the absolute value at the first moment is greater than the preset threshold, obtaining a weighting coefficient of the first power grid load curve and the second power grid load curve at the first moment, and performing a weighted operation on the two load values ​​of the first power grid load curve and the second power grid load curve at the first moment according to the weighting coefficient to obtain a first target load value at the first moment; if the absolute value at the second moment is not greater than the preset threshold, using the load value of the second power grid load curve at the second moment as the second target load value at the second moment; and connecting the first target load value at the first moment and the second target load value at the second moment in the second time period in chronological order to generate a target power grid load curve in the second time period after the current moment.

[0010] By adopting the above technical solution, the solution adopts a two-step forecasting mechanism. First, the first grid load curve is predicted based on the historical grid load curve. Then, this is combined with the real-time grid load curve for a secondary forecast to generate the target grid load curve. This forecasting method not only retains the long-term variation patterns in historical data, but also corrects the forecast results with real-time data, improving the accuracy and reliability of load forecasts and providing more reliable data support for the formulation of subsequent charging scheduling strategies.

[0011] Optionally, the combination of the first reservation information, the second reservation information and the third reservation information is used to generate an initial charging scheduling strategy for the charging pile during the high load period, including: obtaining a preset load upper limit for the charging pile during the high load period; calculating the total charging load of the charging pile during the high load period based on the first reservation information; when the total charging load exceeds the preset load upper limit, calculating the target difference between the total charging load and the preset load upper limit; according to the size of the target difference, increasing the first charging cost of the vehicle during the high load period, and / or reducing the second charging cost of the vehicle during the stable load period and the low load period, to generate a charging scheduling strategy to be adjusted, wherein the first charging cost and the second charging cost are both positively correlated with the target difference; in combination with the second reservation information and the third reservation information, adjusting the charging scheduling strategy to be adjusted to generate an initial charging scheduling strategy for the charging pile during the high load period.

[0012] By adopting the above technical solution, a preset load limit is set and compared with the total charging load. When an overload occurs, the first charging fee for high-load periods and the second charging fee for other periods are dynamically adjusted based on the target difference, achieving price-based demand guidance. By establishing a positive correlation between the charging fee and the target difference, the price adjustment range can be adaptively adjusted according to the degree of load overload. Combined with the second and third reservation information for strategy optimization, a closed-loop price adjustment mechanism is formed, effectively shifting the charging load to different time periods and avoiding excessive electricity consumption pressure during high-load periods.

[0013] Optionally, the charging scheduling strategy to be adjusted is adjusted in combination with the second reservation information and the third reservation information to generate an initial charging scheduling strategy for the charging pile in the high load period, including: obtaining a first remaining charging capacity in the stable load period and a second remaining charging capacity in the low load period; based on the first remaining charging capacity and the second remaining capacity, generating a first transferable charging capacity in the stable load period and a second transferable charging capacity in the low load period according to the second reservation information and the third reservation information; adjusting the reduction rate of the second charging fee in the stable load period and the low load period respectively according to the size of the first transferable charging capacity and the second transferable charging capacity, wherein The reduction rate of the second charging fee is positively correlated with the transferable charging capacity of the corresponding time period; when the charging capacity sum of the first transferable charging capacity and the second transferable charging capacity is less than the target difference, the increase rate of the first charging fee in the high load period is adjusted, and the increase rate of the first charging fee in the high load period is positively correlated with the difference between the target difference and the charging capacity sum; when the charging capacity sum is not less than the target difference, the second charging fee in the stable load period and the low load period is reduced according to a preset ratio based on the ratio of the target difference to the charging capacity sum; based on the adjusted first charging fee and the second charging fee, an initial charging scheduling strategy for the charging pile in the high load period is generated.

[0014] By adopting the above technical solutions, the scheme establishes a complete charging capacity transfer and price dynamic adjustment mechanism. By calculating the transferable charging capacity during stable load periods and low load periods, it achieves precise price adjustment based on actual capacity. When the transferable charging capacity is insufficient, the system increases the first charging fee for high-load periods accordingly; when the transferable charging capacity is sufficient, the second charging fee for each period is adjusted according to the target difference ratio. This method of linking the charging fee adjustment range with the transferable charging capacity and the target difference ensures both the feasibility of charging load transfer and the rationality of price adjustment, forming an adaptive price adjustment mechanism that effectively improves the accuracy and reliability of charging scheduling.

[0015] Optionally, the initial charging scheduling strategy is adjusted according to the number of defaults to generate a target charging scheduling strategy for the charging pile during the high load period, including: calculating the actual releasable charging capacity during the high load period according to the number of defaults; adjusting the remaining charging capacity allocation during the high load period based on the actual releasable charging capacity; if the actual releasable charging capacity is greater than a preset capacity threshold, reducing the charging cost during the high load period, and adjusting the charging costs during the stable load period and the low load period; if the actual releasable charging capacity is not greater than the preset capacity threshold, keeping the charging cost in the initial charging scheduling strategy unchanged, and reserving corresponding spare charging capacity according to the number of defaults; and using the adjusted charging cost and charging capacity allocation scheme as the target charging scheduling strategy for the charging pile during the high load period.

[0016] By adopting the above technical solution, the actual available charging capacity is calculated by predicting the number of defaults, and differentiated adjustment strategies are adopted based on preset capacity thresholds: when the available charging capacity is large, resource utilization is optimized by adjusting the charging fees for each period; when the available charging capacity is small, the fees remain unchanged and spare capacity is reserved. This threshold-based adaptive adjustment mechanism not only avoids the waste of charging resources caused by defaults, but also ensures the reliability of the scheduling strategy through reasonable reservations, achieving efficient utilization of charging resources and dynamic optimization of the scheduling strategy, and improving the flexibility and accuracy of overall charging scheduling.

[0017] Optionally, after generating the target charging scheduling strategy for the charging pile during the high load period, the method further includes: obtaining real-time grid load data during the high load period; determining whether the real-time grid load data meets a preset load condition; if the real-time grid load data does not meet the preset load condition, calculating the deviation value between the real-time grid load data and the preset load condition; adjusting the charging cost in the target charging scheduling strategy according to a preset adjustment coefficient based on the size of the deviation value, wherein the adjustment range of the charging cost in the target charging scheduling strategy is positively correlated with the deviation value; recalculating the available charging capacity of the charging pile during the high load period based on the adjusted charging cost; and generating an updated charging capacity allocation plan based on the available charging capacity.

[0018] By adopting this technical solution, after the target charging scheduling strategy is generated, the solution monitors grid load data during high-load periods in real time and compares it with preset load conditions. When abnormal real-time load is detected, the charging fee and capacity allocation plan can be adjusted promptly, forming a real-time response mechanism. This dynamic fine-tuning mechanism based on real-time data improves the charging scheduling strategy's adaptability to sudden changes in grid load, ensures the safety and stability of grid operation, and achieves closed-loop optimization of the charging scheduling strategy.

[0019] In a second aspect, the present application provides a vehicle-grid interactive orderly charging scheduling system, the system comprising: a first acquisition module, a first combination module, a second acquisition module, a second combination module and a generation module; wherein, The first acquisition module is used to acquire the historical power grid load curve of the target area and the real-time power grid load curve of the target area in the first time period before the current moment; the first combination module is used to combine the historical power grid load curve and the real-time power grid load curve to predict the target power grid load curve in the second time period after the current moment, and determine the high load period, stable load period and low load period of the target power grid load curve, the high load period is the period when the load value in the target power grid load curve exceeds the preset load upper limit, the stable load period is the period when the load value in the target power grid load curve is between the preset load upper limit and the preset load lower limit, and the low load period is the period when the load value in the target power grid load curve is lower than the preset load The lower limit of the time period; the second acquisition module is used to obtain the first reservation information of the charging pile in the target area during the high load period, the second reservation information during the stable load period and the third reservation information during the low load period; the second combination module is used to combine the first reservation information, the second reservation information and the third reservation information to generate an initial charging scheduling strategy for the charging pile during the high load period; the generation module is used to obtain the historical vehicle performance data of the charging pile, predict the number of vehicle defaults in the high load period according to the historical vehicle performance data, adjust the initial charging scheduling strategy according to the number of defaults, and generate a target charging scheduling strategy for the charging pile during the high load period.

[0020] In a third aspect, the present application provides an electronic device that adopts the following technical solution: it includes a processor, a memory, a user interface, and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a computer program such as any of the above-mentioned vehicle-grid interactive orderly charging scheduling methods.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: storing a computer program that can be loaded by a processor and execute any of the above-mentioned vehicle-grid interactive orderly charging scheduling methods.

[0022] In summary, this application includes at least one of the following beneficial technical effects: The vehicle-grid interactive orderly charging scheduling method provided in this application improves forecasting accuracy by combining historical and real-time grid load curves. It also achieves refined management of charging demand by acquiring charging reservation information by time period and formulating an initial charging scheduling strategy. In particular, by dynamically adjusting the scheduling strategy based on a default prediction mechanism based on historical vehicle fulfillment data, it effectively avoids the waste of charging resources caused by user defaults. This solution not only improves the utilization efficiency of charging resources but also reduces the risk of grid load fluctuations. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a vehicle-grid interactive orderly charging scheduling method provided in an embodiment of the present application; Figure 2 This is a structural diagram of a vehicle-grid interactive orderly charging scheduling system provided in an embodiment of the present application; Figure 3 This is a structural diagram of an electronic device provided in an embodiment of the present application.

[0024] Description of the accompanying drawings: 1000, electronic device; 1001, processor; 1002, communication bus; 1003, user interface; 1004, network interface; 1005, memory. DETAILED DESCRIPTION

[0025] In order to enable people skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0026] In the description of the embodiments of this application, words such as "exemplary," "for example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "for example," or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0027] Figure 1 This is a flow chart of a vehicle-grid interactive orderly charging scheduling method provided in an embodiment of the present application. Figure 1 As shown, the method includes S101-S105: S101 , obtaining a historical power grid load curve of a target area and a real-time power grid load curve of the target area in a first period before a current moment.

[0028] In this embodiment, the historical grid load curve of the target area and the real-time grid load curve of the target area in the first time period before the current moment are first obtained. Among them, the target area can be a specific urban area, industrial park or residential area with multiple charging piles. The historical grid load curve represents the changes in the grid load of the target area in the past period of time (for example, the past year or the past six months), including power load data in different time periods. The first time period can be the 24 hours before the current moment, and the real-time grid load curve represents the actual power load changes in the target area during the first time period.

[0029] Specifically, load collection devices installed in the target area can be used to obtain electricity load data within the area. These load collection devices can include smart meters, electricity information collection terminals, and other devices that can monitor and record electricity load data within the area in real time. Historical grid load curves can be retrieved from the target area's power management system database, which stores historical load data for various time periods within the area. Real-time grid load curves are collected in real time by the load collection devices, with collection intervals set to, for example, 5 or 10 minutes.

[0030] The purpose of obtaining these two load curves is to analyze historical load data to understand the patterns and cyclical variations in electricity consumption in the target area, while real-time load data reflects actual current electricity consumption. The combination of these two data types provides a more accurate basis for subsequent load forecasting. Historical data reflects long-term trends, while real-time data reflects short-term fluctuations, complementing each other. For example, electricity load during certain holidays or under unusual weather conditions may deviate from historical patterns, making real-time load data particularly valuable.

[0031] By obtaining these two types of load curves, a reliable data basis can be provided for subsequent load forecasting and charging scheduling, which helps to accurately grasp the power consumption characteristics of the target area and thus formulate a more reasonable charging scheduling strategy.

[0032] S102, combining the historical grid load curve and the real-time grid load curve, predicting the target grid load curve in the second period after the current moment, and determining the high load period, stable load period and low load period of the target grid load curve.

[0033] Among them, the high load period is the period when the load value in the target power grid load curve exceeds the preset load upper limit, the stable load period is the period when the load value in the target power grid load curve is between the preset load upper limit and the preset load lower limit, and the low load period is the period when the load value in the target power grid load curve is lower than the preset load lower limit.

[0034] After obtaining the historical and real-time grid load curves, this embodiment needs to predict the target grid load curve for a second period after the current time and divide the curve into time periods. The second period can be set to 24 hours after the current time. This time period is set mainly because electric vehicle charging reservations are usually completed within a day and the load forecast within this period has high reliability.

[0035] The specific prediction process consists of two stages. First, based on historical grid load curves, a time series analysis method is used to predict a first grid load curve. This prediction process analyzes the periodic, trend, and seasonal characteristics of the historical load data to obtain preliminary load forecast results. Subsequently, using the real-time grid load curve as a correction, an online learning algorithm is used to predict a second grid load curve. The load difference between the first and second grid load curves at corresponding times is calculated to determine whether the absolute value of the difference exceeds a preset threshold (for example, a 10% load fluctuation). If the absolute value of the difference exceeds the preset threshold, it indicates that the real-time load deviates significantly from the historical load pattern. In this case, different weight coefficients are assigned to the two prediction results for weighted calculation to obtain a more accurate target grid load curve. Conversely, if the absolute value of the difference does not exceed the preset threshold, the second grid load curve predicted based on real-time data is directly used as the target grid load curve.

[0036] After obtaining the target grid load curve, the second period needs to be divided into a high-load period, a stable load period, and a low-load period. This division is based on the load level of the target grid load curve, setting two load thresholds: a preset upper load limit and a preset lower load limit. When the load level exceeds the preset upper load limit (e.g., above 85% of the daily peak load), the corresponding period is classified as a high-load period; when the load level is below the preset lower load limit (e.g., below 50% of the daily peak load), the corresponding period is classified as a low-load period; and periods between the two thresholds are classified as stable load periods.

[0037] This prediction and classification method aims to accurately grasp the load change trend over a period of time and provide a time period basis for subsequent charging scheduling. By combining historical data with real-time data for prediction, the accuracy of the prediction can be effectively improved.

[0038] Based on the above embodiment, as an optional implementation, in S102, combining the historical grid load curve and the real-time grid load curve to predict the target grid load curve in the second period after the current moment specifically includes S21-S22: S21 , predicting a first power grid load curve of the target area within a second time period after the current moment based on the historical power grid load curve.

[0039] As an optional implementation, this embodiment uses a two-step process to predict the target grid load curve. First, a first grid load curve is predicted based on historical grid load curves. Then, the first grid load curve is combined with the real-time grid load curve to generate the final target grid load curve. This two-step prediction method fully leverages the statistical laws of historical data and the dynamic characteristics of real-time data, improving prediction accuracy.

[0040] The system first preprocesses historical power grid load curves, including outlier removal and data normalization. It then analyzes the cyclical characteristics (such as daily, weekly, and seasonal cycles) and trend characteristics of the historical load data. Based on these characteristics, the system uses time series analysis methods, combined with historical load data from the same period, weather factors, and holiday information, to predict the first power grid load curve for the target area in the second period after the current time. The prediction process focuses on regular load fluctuations, such as load differences between weekdays and weekends and load changes caused by seasonal changes.

[0041] S22 , combining the first grid load curve and the real-time grid load curve to predict a target grid load curve within a second time period after the current moment.

[0042] A revised forecast is performed by combining the first grid load curve and the real-time grid load curve. Specifically, the deviation between the real-time grid load curve and historical load data for the same period is calculated, and the current load trend is analyzed. If significant differences between the real-time load and historical patterns are found, the first grid load curve needs to be revised. This is done by setting weight coefficients and taking a weighted average of the historical forecast results and the real-time trend forecast results. The weights are determined based on factors such as the deviation between the real-time load and the historical load, the duration of the load change, and the degree of change in external conditions (such as weather and temperature).

[0043] For example, if the system detects that the real-time grid load curve has recently and consistently exceeded historical levels for the same period, it will adjust the predicted value of the primary grid load curve accordingly. This adjustment isn't a simple linear adjustment, but rather is determined based on the duration and trend of the deviation. The system also sets a reasonable range for the predicted value, requiring verification of its validity if the revised predicted value exceeds this range.

[0044] Based on the above embodiment, as an optional implementation, in S22, combining the first grid load curve and the real-time grid load curve to predict the target grid load curve in the second time period after the current moment specifically includes S221-S226: S221 , predicting a second power grid load curve within a second time period after the current moment based on the real-time power grid load curve.

[0045] After obtaining the first grid load curve, this embodiment requires further forecast correction based on real-time grid load data. This is because relying solely on historical data for forecasts may not reflect actual changes in current load demand. In particular, during emergencies or unusual weather conditions, real-time loads may deviate significantly from historical patterns. Therefore, a dynamic correction mechanism is needed to rationally integrate historical and real-time forecast results to improve the accuracy of the final forecast.

[0046] Specifically, the system first predicts a second grid load curve based on the real-time grid load curve. This prediction process utilizes an online learning algorithm that captures the dynamic characteristics of recent load changes. The prediction focuses on characteristics such as the changing trend and fluctuation amplitude of real-time load data, and incorporates current external conditions such as weather conditions and temperature fluctuations. For example, if a sustained upward trend in load is detected in the near future, the predicted load value will be adjusted upward accordingly.

[0047] S222: Calculate the load difference between the first power grid load curve and the second power grid load curve at each moment in the second time period.

[0048] The system then calculates the load difference between the first and second grid load curves at each moment during the second period. Each moment can be divided into 5-minute or 10-minute intervals, resulting in a discrete series of load differences. By calculating these differences, the degree of deviation between historical and real-time forecasts can be quantified.

[0049] S223: Determine whether the absolute value of the load difference at each moment is greater than a preset threshold.

[0050] S224, if there is an absolute value at the first moment that is greater than a preset threshold, obtain the weighting coefficients of the first power grid load curve and the second power grid load curve at the first moment, and according to the weighting coefficients, perform weighted operation on the two load values ​​of the first power grid load curve and the second power grid load curve at the first moment to obtain the first target load value at the first moment.

[0051] For each moment's load difference, the system needs to determine whether its absolute value exceeds a preset threshold. The preset threshold can be set to approximately 10% of the average load, and the specific value can be adjusted based on the actual application scenario. When the absolute value of the load difference at a certain moment (referred to as the first moment) is greater than the preset threshold, it indicates that there is a significant difference between the historical forecast result and the real-time forecast result at that moment, and correction is required through weighted fusion. The system will set a corresponding weighting coefficient based on the degree of difference. For example, when the real-time load forecast value is closer to the most recent actual load, the weight of the second grid load curve can be appropriately increased. The specific weighting coefficient can be dynamically adjusted based on factors such as the size and duration of the load difference, and the sum of the two weights must be 1. Through weighted calculation, the first target load value for the first moment is obtained.

[0052] When the absolute value of the load difference at the first moment is greater than a preset threshold, the system needs to determine a reasonable weighting coefficient for the first grid load curve and the second grid load curve. Specifically, the system first obtains the actual load data for the 12 sampling points (1 hour) before the first moment and calculates the average relative errors E1 and E2 of the first grid load curve and the second grid load curve relative to the actual load, respectively. E1 represents the average relative error of the first grid load curve, calculated as E1=(1 / 12)×∑|Pactual(i)-PHistoricalPrediction(i)| / Pactual(i), where Pactual(i) and PHistoricalPrediction(i) represent the actual load value and historically predicted load value at the i-th sampling point, respectively. E2 represents the average relative error of the second grid load curve, calculated as E2=(1 / 12)×∑|Pactual(i)-PReal-TimePrediction(i)| / Pactual(i), where PReal-TimePrediction(i) represents the real-time predicted load value at the i-th sampling point.

[0053] On this basis, the weighting coefficient for the second grid load curve is W2 = E1 / (E1+E2), and the weighting coefficient for the first grid load curve is W1 = 1-W2. Through this calculation method, the load curve with a smaller prediction error will receive a larger weighting coefficient. Finally, the system weights the load values ​​of the two load curves at the first moment according to the corresponding weighting coefficients to obtain the first target load value at the first moment. When a sudden load change is detected (the load change between adjacent sampling points exceeds 20%), the system limits the value range of W2 to [0.6, 0.9] to ensure that the real-time prediction result dominates. When the load change is stable (the load change between adjacent sampling points does not exceed 5%), the value range of W2 is limited to [0.3, 0.7] to balance the impact of the two prediction results.

[0054] S225: If the absolute value at the second moment is not greater than the preset threshold, the load value of the second power grid load curve at the second moment is used as the second target load value at the second moment.

[0055] Conversely, if the absolute value of the load difference at a certain moment (referred to as the second moment) is no greater than the preset threshold, the two prediction results at that moment are relatively close. In this case, the load value of the second grid load curve at that moment is directly adopted as the second target load value for the second moment. This is because when the two prediction results are close, the real-time prediction result is generally more timely and accurate.

[0056] S226 , connecting the first target load value at the first moment in the second time period and the second target load value at the second moment in chronological order to generate a target grid load curve in the second time period after the current moment.

[0057] Finally, the system chronologically connects the target load values ​​for all moments in the second period (including the first and second target load values) to form a complete target grid load curve. This dynamic fusion method, based on difference judgment, preserves the regularity characteristics of historical data while promptly reflecting changing trends in real-time loads, thereby improving the accuracy and reliability of load forecasts. For example, during holidays or under unusual weather conditions, when real-time loads deviate significantly from historical patterns, this method can promptly adjust the forecast results to make the final target load curve more consistent with actual conditions.

[0058] S103 , obtaining first reservation information of charging piles in the target area during a high-load period, second reservation information during a stable-load period, and third reservation information during a low-load period.

[0059] After determining the load period divisions, this embodiment needs to obtain the reservation information for charging piles in the target area during different time periods. Specifically, it is necessary to obtain the first reservation information for the high-load period, the second reservation information for the stable load period, and the third reservation information for the low-load period. This reservation information contains the charging demand data submitted by the user, mainly including key parameters such as the scheduled charging time period, the required charge amount, the charging power, and the expected stay time.

[0060] Charging reservation information can be obtained through the charging pile management system within the target area. This system typically consists of a mobile app and a backend management platform. Users can submit charging reservation applications through the app, and the backend system receives and processes these reservation information in real time. In this embodiment, the charging pile management system will categorize and store the received reservation information according to the scheduled charging time period. Based on the aforementioned load period division, the reservation information will be classified as the first reservation information, the second reservation information, and the third reservation information. For example, if a user schedules charging between 7:00 and 9:00 in the morning, and this period is classified as a high-load period, the reservation information will be classified as the first reservation information.

[0061] The purpose of obtaining this reservation information is to comprehensively understand charging demand at each time period and provide a basis for formulating appropriate charging scheduling strategies. By analyzing reservation information for different time periods, we can accurately assess the charging load level in each period and adjust charging prices and capacity allocation accordingly. In particular, for the first reservation information during high-load periods, it is important to pay attention to the number of reservations and the concentration of charging load to avoid excessive charging load concentration that could increase grid load.

[0062] During the acquisition process, the system collects real-time statistics on metrics such as the total number of reservations, total charging demand, and average charging duration for each time period. These metrics can reflect user charging preferences and behavioral characteristics. For example, analysis may reveal that users tend to reserve charging during the high-load period after get off work, while reservations are less frequent during the low-load period late at night. This analysis helps develop more targeted scheduling strategies, such as using price leverage to shift charging demand from high-load periods to other times.

[0063] S104 : generating an initial charging scheduling strategy for the charging pile during a high-load period by combining the first reservation information, the second reservation information, and the third reservation information.

[0064] After obtaining the reservation information for each time period, this embodiment needs to generate an initial charging scheduling strategy for the charging piles during the high-load period. The strategy generation process is mainly based on the charging load balance and price adjustment mechanism, and optimizes the distribution of charging demand by reasonably allocating charging capacity and adjusting charging costs.

[0065] First, the system needs to obtain the preset load cap for the charging pile during the high-load period. This cap is typically determined based on the grid's safe operation requirements and the rated capacity of the charging facility. Subsequently, the total charging load during the high-load period is calculated based on the first reservation information. This calculation is performed by multiplying the charging power and charging duration of all scheduled charging requests during that period and summing the results to obtain the expected total charging load. If the total charging load exceeds the preset load cap, the system calculates the target difference between the two. This difference represents the amount of charging load that needs to be shifted through the scheduling strategy.

[0066] Based on the calculated target difference, the system uses a price adjustment mechanism to guide charging demand shifts. Specifically, this increases the primary charging fee during high-load periods while reducing the secondary charging fee during periods of stable and low loads. The fee adjustment is positively correlated with the target difference: a larger target difference increases the fee during high-load periods and reduces the fee during other periods. This price adjustment mechanism aims to use economic leverage to guide users to proactively adjust their charging schedules, thereby achieving a balanced distribution of charging load.

[0067] After initially determining the price adjustment plan, the system needs to further optimize it by combining the second and third reservation information. First, the first remaining charging capacity for the stable load period and the second remaining charging capacity for the low load period are obtained. These capacity values ​​represent the acceptable charging load for each period. Then, based on the existing reservation information, the first transferable charging capacity and the second transferable charging capacity for these two periods are calculated. These transferable capacities represent the charging load that can be transferred to these periods under the price adjustment.

[0068] The system dynamically adjusts charging fees for different time periods based on the amount of transferable charging capacity. For periods with larger transferable charging capacities, greater price discounts are offered to attract more charging demand. When the sum of the first and second transferable charging capacities is less than the target difference, charging fees for high-load periods are further increased to strengthen the price adjustment effect. Conversely, if the sum of the transferable charging capacities is not less than the target difference, charging fees for stable and low-load periods are reduced according to a preset ratio.

[0069] Based on the above embodiment, as an optional implementation, in S104, combining the first reservation information, the second reservation information, and the third reservation information to generate an initial charging scheduling strategy for the charging pile during the high-load period specifically includes S41-S44: S41, obtaining a preset upper load limit of the charging pile during a high-load period.

[0070] First, the system needs to determine the preset upper load limit for charging piles during high-load periods. This upper limit is determined based on the grid's safe operation requirements, the rated capacity of the charging facilities, and historical operating experience. It is used to ensure that the charging load does not pose a threat to grid security. The setting of the preset upper load limit requires consideration of factors such as the physical carrying capacity of the charging pile, the capacity limitations of the power supply network, and safety margins.

[0071] S42: Calculate the total charging load of the charging pile during the high-load period according to the first reservation information.

[0072] The system then calculates the total charging load of the charging pile during the high-load period based on the first reservation information. This calculation is done by multiplying the charging power and the estimated charging duration of all scheduled charging requests during that period and summing the results. For example, if a user schedules a 2-hour charging session during the high-load period at a charging power of 7 kW, the charging load generated by this reservation is 14 kWh. By summing up the charging loads of all reservations, the total charging load value for the high-load period is obtained.

[0073] S43, when the total charging load exceeds the preset load upper limit, the target difference between the total charging load and the preset load upper limit is calculated; according to the size of the target difference, the first charging cost of the vehicle in the high load period is increased, and / or the second charging cost of the vehicle in the stable load period and the low load period is reduced, and the charging scheduling strategy to be adjusted is generated, and the first charging cost and the second charging cost are both positively correlated with the target difference.

[0074] When the calculated total charging load exceeds the preset load limit, the system needs to take measures to adjust charging demand. First, the target difference between the total charging load and the preset load limit is calculated. This difference represents the amount of charging load that needs to be shifted through the scheduling strategy. Then, based on the target difference, the system designs a price adjustment plan: increasing the first charging fee for vehicles during high-load periods, while reducing the second charging fee for vehicles during stable and low-load periods. The fee adjustment is proportional to the target difference: the larger the target difference, the larger the fee adjustment. For example, when the target difference reaches 30% of the preset load limit, the system may increase the charging fee during high-load periods by 50%, while reducing the charging fee during other periods by 30%. This price adjustment mechanism forms the charging scheduling strategy to be adjusted.

[0075] S44 , combining the second reservation information and the third reservation information, adjusting the charging scheduling strategy to be adjusted, and generating an initial charging scheduling strategy for the charging pile during the high-load period.

[0076] Finally, the system optimizes the charging scheduling strategy for the charging piles to be adjusted based on the second and third reservation information. This optimization process primarily considers two aspects: first, the remaining charging capacity during stable and low-load periods to ensure these periods can accommodate charging demand shifted from high-load periods; and second, the price gradient between different periods to ensure that price differences effectively guide demand shifts without overburdening users. This optimization ultimately generates the initial charging scheduling strategy for the charging piles during high-load periods.

[0077] Based on the above embodiment, as an optional implementation, in S44, combining the second reservation information and the third reservation information, adjusting the charging scheduling strategy to be adjusted, and generating an initial charging scheduling strategy for the charging pile during the high-load period specifically include S441-S446: S441, obtaining a first remaining charging capacity during a stable load period and a second remaining charging capacity during a low load period.

[0078] First, the system obtains the first remaining charging capacity for the stable load period and the second remaining charging capacity for the low load period. The remaining charging capacity refers to the amount of charging load that can be accepted in each period, taking into account existing reservations. This is calculated by subtracting the reserved charging capacity from the total capacity for the period. The total capacity for the period needs to take into account the physical limitations of the charging facilities and grid security constraints.

[0079] S442 : Based on the first remaining charging capacity and the second remaining capacity, and according to the second reservation information and the third reservation information, a first transferable charging capacity for the stable load period and a second transferable charging capacity for the low load period are generated accordingly.

[0080] Based on the remaining charging capacity, the system combines the second and third reservation information to calculate the first transferable charging capacity for the stable load period and the second transferable charging capacity for the low-load period. Transferable charging capacity refers to the capacity that can actually be used to meet the transfer demand during the high-load period, while ensuring that the reservation demand for the current period is met. A certain safety margin must be reserved during the calculation to cope with possible temporary charging needs. For example, if the remaining charging capacity for a certain period is 100 kWh, after considering a 20% safety margin, the transferable charging capacity is 80 kWh.

[0081] S443, adjusting the reduction rate of the second charging fee in the stable load period and the low load period respectively according to the size of the first transferable charging capacity and the second transferable charging capacity, wherein the reduction rate of the second charging fee is positively correlated with the transferable charging capacity in the corresponding period.

[0082] The system then adjusts the second charging fee reduction for both smooth and low-load periods based on the size of the first and second transferable charging capacities. The greater the transferable charging capacity, the greater the reduction in charging fees, effectively attracting charging demand from high-load periods. For example, if the transferable charging capacity during smooth load periods is twice that of low-load periods, the reduction in charging fees should also be approximately twice as large.

[0083] S444, when the sum of the charging capacities of the first transferable charging capacity and the second transferable charging capacity is less than the target difference, adjusting the increase in the first charging fee during the high load period, the increase in the first charging fee during the high load period is positively correlated with the difference between the target difference and the sum of the charging capacities.

[0084] When the combined charging capacity of the first and second transferable charging capacities is less than the target difference, simply reducing charging fees during other periods cannot fully offset the excess charging demand during high-load periods. In this case, the system needs to further increase the first charging fee during high-load periods, with the increase proportional to the difference between the target difference and the combined charging capacity. This two-way regulation mechanism can more effectively curb charging demand during high-load periods.

[0085] S445 , when the sum of the charging capacities is not less than the target difference, the second charging fee for the stable load period and the low load period is reduced according to a preset ratio based on the ratio of the target difference to the sum of the charging capacities.

[0086] When the total charging capacity is no less than the target difference, it indicates that there is sufficient capacity in other time periods to accommodate the transferred charging demand. At this point, the system reduces the secondary charging fee for periods of stable and low loads by a preset ratio based on the ratio of the target difference to the total charging capacity. The setting of the preset ratio requires consideration of user acceptance and the actual effectiveness of charging demand shifting. A stepped ratio structure is typically used, meaning that the larger the target difference percentage, the greater the fee reduction.

[0087] S446 , generating an initial charging scheduling strategy for the charging pile during the high-load period according to the adjusted first charging fee and the second charging fee.

[0088] Finally, the system generates an initial charging scheduling strategy for the charging piles during high-load periods based on the adjusted first and second charging costs. This strategy includes information such as specific charging cost standards for each period and expected charging capacity allocation.

[0089] S105, obtaining historical vehicle performance data of the charging pile, predicting the number of vehicle defaults during the high-load period based on the historical vehicle performance data, adjusting the initial charging scheduling strategy based on the number of defaults, and generating a target charging scheduling strategy for the charging pile during the high-load period.

[0090] After generating the initial charging scheduling strategy, this embodiment also needs to consider the impact of user defaults on the scheduling strategy. To do this, it first needs to obtain historical vehicle fulfillment data for the charging pile. This data records the actual execution of past charging reservations, including information such as reservation time, actual arrival time, fulfillment, and reasons for default. Historical vehicle fulfillment data is typically derived from historical records in the charging pile management system and can reflect users' reservation compliance and default patterns.

[0091] Based on historical vehicle performance data, the system uses machine learning to predict the number of vehicle defaults during high-load periods. The prediction process primarily considers factors such as historical default rates during the same period, weather conditions, weekend or holiday effects, and pre-booked charging fees. By building a predictive model, the system calculates the likely number of defaults during high-load periods. For example, if historical data shows a significant increase in default rates during rainy days or holidays, more room for default handling will be required during high-load periods under similar conditions.

[0092] After acquiring historical vehicle compliance data for charging stations, the system needs to build a prediction model to predict the number of defaults that may occur during high-load periods. This embodiment uses the random forest algorithm to build the prediction model. This algorithm has strong nonlinear fitting and anti-interference capabilities, making it suitable for multi-feature prediction problems.

[0093] First, the system preprocesses historical vehicle performance data. This preprocessing step involves dividing the historical data for three consecutive months into 30-minute intervals. Feature vectors are extracted from the data within each interval. These feature vectors contain the following dimensions: default rate for the same period (the number of defaults in the previous week, two weeks, or four weeks divided by the total number of reservations), weather conditions (one-hot encoding for sunny, cloudy, rainy, and snowy), temperature values, time features (one-hot encoding for weekdays / weekends, and marking holidays), and scheduled charging fees (the charging electricity price for the current period). Missing data is filled using the mean of the period, and outliers (such as data with a default rate exceeding 95%) are removed.

[0094] The processed dataset was then randomly split into a training set and a test set in an 8:2 ratio. The training set was used for model training, and the test set was used to evaluate model performance. During the model training phase, the key parameters of the random forest algorithm were set as follows: the number of decision trees was set to 100, the maximum tree depth was set to 8, the number of features considered for each node split was the square root of the total number of features, and the minimum number of leaf node samples was set to 5. These parameters were selected based on cross-validation results to balance the model's fit and generalization capabilities.

[0095] The training process uses the following steps: for each record in the training set, the above feature vector is used as input, and the actual number of defaults is used as the output label; the random forest algorithm trains 100 decision trees in parallel, and each tree is trained using a randomly sampled subset of the data; during the partitioning process of each node, the algorithm selects the best splitting feature from the candidate features so that the split child node has the smallest mean squared error.

[0096] After the model training is completed, the prediction effect is evaluated using the test set. When the root mean square of the prediction error is less than the preset threshold (such as 0.1), the model is considered to be usable.

[0097] During the prediction phase, the system first obtains a feature vector for the predicted time period, including the previous default rate, the current day's weather forecast, temperature forecast, time characteristics, and the planned charging costs. These features are then fed into a trained random forest model, where each decision tree generates a prediction. The final default prediction is the average of all the decision tree predictions. For example, if the model predicts five defaults during a high-load period, the system will appropriately increase the number of charging reservations for that period based on the existing scheduling strategy. The increase is 1.2 times the predicted number of defaults (i.e., six reservations) to fully utilize the charging resources left idle due to defaults.

[0098] After obtaining the predicted number of defaults, the system first calculates the actual releasable charging capacity during the high-load period. This capacity value is equal to the sum of the charging load corresponding to the predicted number of defaults. The initial charging scheduling strategy is then adjusted based on this releasable charging capacity. The specific adjustment process is divided into two cases: When the actual releasable charging capacity exceeds a preset capacity threshold (for example, 15% of the total charging capacity), it indicates that the default situation may significantly affect the charging scheduling effect. In this case, the charging fee during the high-load period needs to be reduced, while the charging fee during the stable load and low-load periods needs to be adjusted accordingly to balance the actual charging demand in each period. If the actual releasable charging capacity does not exceed the preset capacity threshold, the charging fee in the initial charging scheduling strategy remains unchanged, but a corresponding amount of spare charging capacity is reserved based on the number of defaults. This spare capacity can be used for temporary charging needs or to respond to emergencies.

[0099] The adjusted charging fee and charging capacity allocation plan will serve as the target charging scheduling strategy for charging piles during high-load periods. This default prediction-based adjustment mechanism aims to improve the practicality and reliability of charging scheduling. By predicting defaults and reserving appropriate adjustment space, it can reduce the waste of charging resources caused by user defaults and improve the actual utilization rate of charging facilities.

[0100] Based on the above embodiment, as an optional implementation, in S105, adjusting the initial charging scheduling strategy according to the number of defaults and generating a target charging scheduling strategy for the charging pile during the high-load period specifically includes S51-S55: S51, calculating the actual releasable charging capacity during the high load period according to the number of defaults.

[0101] First, the system calculates the actual available charging capacity during the high-load period based on the predicted number of defaults. This calculation is done by multiplying the scheduled charging power and charging duration for each predicted defaulter, and then summing the total available charging capacity. For example, if three users are predicted to default, and their original plans were to charge for 2 hours, 3 hours, and 1.5 hours, respectively, all at 7 kW, the actual available charging capacity is (2 + 3 + 1.5) × 7 = 45.5 kWh.

[0102] S52: Based on the actual releasable charging capacity, adjust the allocation of the remaining charging capacity during the high-load period.

[0103] After determining the actual available charging capacity, the system adjusts the remaining charging capacity allocation during high-load periods. This adjustment process takes into account temporal distribution characteristics, specifically the specific distribution of default predictions within high-load periods. For example, if defaults are concentrated in a particular time period, the remaining charging capacity during that time period will be increased accordingly. This refined adjustment based on temporal distribution allows for better utilization of released charging resources.

[0104] S53: If the actual releasable charging capacity is greater than the preset capacity threshold, the charging fee in the high-load period is reduced, and the charging fee in the stable load period and the low-load period is adjusted.

[0105] When the actual available charging capacity exceeds the preset capacity threshold, it indicates that the default situation may significantly affect the charging scheduling effect, and the charging demand needs to be rebalanced through the price adjustment mechanism. The system first reduces the charging fee during high-load periods, and the reduction is proportional to the amount of available charging capacity. At the same time, to maintain a reasonable price gradient between time periods, the charging fee during stable load periods and low load periods is adjusted accordingly. For example, when the available charging capacity reaches twice the preset capacity threshold, the charging fee during high-load periods may be reduced by 30%, while the charging fee during other periods may be slightly increased by 10%.

[0106] S54: If the actual releasable charging capacity is not greater than the preset capacity threshold, the charging cost in the initial charging scheduling strategy is kept unchanged, and corresponding spare charging capacity is reserved according to the number of defaults.

[0107] If the actual available charging capacity is no greater than the preset capacity threshold, the impact of defaults on charging scheduling is relatively small. In this case, the system maintains the charging costs set in the initial charging scheduling strategy, but reserves a corresponding amount of backup charging capacity based on the number of defaults. This backup charging capacity is set using a tiered reservation mechanism: more capacity is reserved for periods with a higher probability of default, and less capacity is reserved for periods with a lower probability of default. This mechanism ensures that defaults can be addressed while avoiding excessive idle charging resources.

[0108] Specifically, based on historical vehicle performance data, a statistical analysis of the default rate for each hour during high-load periods was conducted. The ratio of the number of historical defaults to the total number of appointments per hour was used as the historical default rate for that period. High-load periods were then sorted from high to low by historical default rate. Periods with a historical default rate greater than 15% were considered high default risk periods, those with a historical default rate between 5% and 15% were considered medium default risk periods, and those with a historical default rate less than 5% were considered low default risk periods.

[0109] For periods of high default risk, the reserved capacity is the product of the predicted number of defaults in that period and the average charging power of each vehicle, multiplied by the high risk coefficient of 1.2; for periods of medium default risk, the reserved capacity is the product of the predicted number of defaults in that period and the average charging power of each vehicle, multiplied by the medium risk coefficient of 1.1; for periods of low default risk, the reserved capacity is the product of the predicted number of defaults in that period and the average charging power of each vehicle, multiplied by the low risk coefficient of 1.0.

[0110] For example, a high-load period between 5:00 PM and 6:00 PM has a historical default rate of 20%, making it a high-default risk period. The current forecast for defaults is 5 vehicles, and the average charging power per vehicle is 7 kW. Therefore, the reserved capacity for this period is calculated as 5 × 7 × 1.2 = 42 kW. This tiered reservation mechanism based on historical data allows for targeted reserve capacity for periods with varying default risk levels, ensuring preparedness for potential defaults while avoiding resource waste caused by excessive reservations. Furthermore, the reservation coefficient provides room for adjustment, allowing for optimization based on actual operational conditions.

[0111] S55: Using the adjusted charging cost and charging capacity allocation plan as a target charging scheduling strategy for the charging pile during the high-load period.

[0112] Finally, the system integrates the adjusted charging fee standards and charging capacity allocation plan into a target charging scheduling strategy for charging piles during high-load periods. This strategy not only includes specific charging fee and capacity allocation data, but also includes rules for using spare capacity and operational guidance such as how to handle temporary charging requests.

[0113] Based on the above embodiment, as an optional implementation manner, after generating the target charging scheduling strategy for the charging pile during the high-load period, the following steps are specifically further included: Obtain real-time grid load data during high-load periods; determine whether the real-time grid load data meets preset load conditions; if the real-time grid load data does not meet the preset load conditions, calculate the deviation between the real-time grid load data and the preset load conditions; based on the size of the deviation, adjust the charging cost in the target charging scheduling strategy according to a preset adjustment coefficient, wherein the adjustment range of the charging cost in the target charging scheduling strategy is positively correlated with the deviation; based on the adjusted charging cost, recalculate the available charging capacity of the charging pile during the high-load period; and generate an updated charging capacity allocation plan based on the available charging capacity.

[0114] In this embodiment, in order to further improve the real-time adaptability of the charging scheduling strategy, after generating the target charging scheduling strategy, it is also necessary to monitor and dynamically adjust the real-time operating status of the power grid.

[0115] Specifically, first obtain the real-time grid load data during the high-load period, wherein the real-time grid load data can be collected in real time by a load monitoring device set in the distribution network. The preset load condition in this embodiment refers to the load threshold range for safe and stable operation of the power grid, and the threshold range can be determined based on historical operating experience and the carrying capacity of the power grid equipment. The system compares the acquired real-time grid load data with the preset load condition and sets the threshold range of the preset load condition: 85% of the rated capacity of the transformer is used as the lower threshold and 95% is used as the upper threshold. The system compares the acquired load data with the threshold range in real time. When the real-time grid load data is not within the threshold range of the preset load condition (i.e., the real-time load is higher than the upper threshold of 95% or lower than the lower threshold of 85%), it is determined that the current grid load state is abnormal and it is necessary to dynamically adjust the charging scheduling strategy in a timely manner.

[0116] The specific adjustment process is as follows: First, the deviation between the real-time grid load data and the preset load conditions is calculated. Taking the upper limit of the preset load condition as an example, if the real-time grid load data exceeds the upper limit, the deviation value is the difference between the two. The system dynamically adjusts the charging fee based on the calculated deviation value and a pre-set adjustment coefficient. The adjustment coefficient can be determined based on historical control experience and is used to map the deviation value to a specific fee adjustment range. The adjustment range of the charging fee is positively correlated with the deviation value. That is, the larger the deviation value, the larger the adjustment range. This setting can more effectively guide users to change their charging behavior.

[0117] After adjusting charging fees, the system reassesses the available charging capacity of charging piles during high-load periods. Available charging capacity refers to the maximum charging power a charging pile can provide while ensuring safe grid operation. This capacity is calculated based on the adjusted charging fees and a user price sensitivity model. Finally, based on the updated available charging capacity, the system generates a new charging capacity allocation plan to rationally allocate limited charging resources to individual charging users.

[0118] First, the user price sensitivity model is established by analyzing historical data.

[0119] The specific steps are as follows: Collect charging cost change data and corresponding charging demand change data for each period in the past 6 months; plot these data points in a coordinate system, with the horizontal axis representing the charging cost change rate and the vertical axis representing the charging demand change rate; use the least squares method to perform linear regression on these data points to obtain the linear relationship equation between price and demand changes: demand change rate = -0.8 × price change rate.

[0120] The available charging capacity is calculated as follows: Assume the original available charging capacity is C0; calculate the charging cost adjustment ratio ΔP: ΔP = (adjusted cost - original cost) / original cost × 100%; calculate the demand change rate ΔD based on the sensitivity model: ΔD = -0.8 × ΔP; calculate the new available charging capacity C: C = C0 × (1 + ΔD).

[0121] For example: the original available charging capacity C0 = 100kW in a certain period, the original cost is 1 yuan / kWh, and the adjusted cost is 1.072 yuan / kWh; calculate the price change rate: ΔP = (1.072-1) / 1×100% = 7.2%; calculate the demand change rate: ΔD = -0.8×7.2% = -5.76%; calculate the new available charging capacity: C = 100×(1-5.76%) = 94.24kW.

[0122] Through this dynamic adjustment mechanism, this embodiment can rapidly respond to abnormal grid load conditions, regulating user charging behavior through price leverage to prevent grid overload. Furthermore, the dynamically adjusted charging capacity allocation scheme ensures optimal utilization of charging resources, guaranteeing both safe and stable grid operation and satisfying user charging needs.

[0123] Based on the above method, this application also discloses a vehicle-grid interactive orderly charging scheduling system, such as Figure 2 As shown, Figure 2 This is a structural diagram of a vehicle-grid interactive orderly charging scheduling system provided by an embodiment of the present application. The system includes: a first acquisition module, a first combination module, a second acquisition module, a second combination module and a generation module; wherein, The first acquisition module is used to obtain the historical power grid load curve of the target area and the real-time power grid load curve of the target area in the first time period before the current moment; the first combination module is used to combine the historical power grid load curve and the real-time power grid load curve to predict the target power grid load curve in the second time period after the current moment, and determine the high load period, stable load period and low load period of the target power grid load curve. The high load period is the period when the load value in the target power grid load curve exceeds the preset load upper limit, the stable load period is the period when the load value in the target power grid load curve is between the preset load upper limit and the preset load lower limit, and the low load period is the period when the target power grid load curve The medium load value is lower than the preset load lower limit during the period; the second acquisition module is used to obtain the first reservation information of the charging piles in the target area during the high load period, and the second reservation information during the stable load period and the third reservation information during the low load period; the second combination module is used to combine the first reservation information, the second reservation information and the third reservation information to generate an initial charging scheduling strategy for the charging piles during the high load period; the generation module is used to obtain the historical vehicle performance data of the charging piles, predict the number of vehicle defaults in the high load period based on the historical vehicle performance data, adjust the initial charging scheduling strategy based on the number of defaults, and generate a target charging scheduling strategy for the charging piles during the high load period.

[0124] It should be noted that the above embodiments provide systems that implement their functions using only the division of the above functional modules as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0125] See Figure 3 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0126] The communication bus 1002 is used to implement the connection and communication between these components.

[0127] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0128] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0129] Processor 1001 may include one or more processing cores. Using various interfaces and circuits, processor 1001 connects to various components within the server. It executes instructions, programs, code sets, or instruction sets stored in memory 1005, as well as accesses data stored in memory 1005, to perform various server functions and process data. Optionally, processor 1001 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). Processor 1001 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display; and the modem handles wireless communications. It is understood that the modem may not be integrated into processor 1001 but implemented as a separate chip.

[0130] Among them, the memory 1005 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may optionally be at least one storage device located away from the aforementioned processor 1001. As Figure 3 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a vehicle-grid interactive orderly charging scheduling method.

[0131] exist Figure 3In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 1001 can be used to call an application program stored in the memory 1005 for a vehicle-grid interactive orderly charging scheduling method. When executed by one or more processors, the electronic device executes one or more methods described in the above embodiments.

[0132] An electronic device readable storage medium stores instructions, which, when executed by one or more processors, enable the electronic device to execute one or more of the methods described in the above embodiments.

[0133] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0134] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0135] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of the devices or units can be electrical or other forms.

[0136] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0137] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0138] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this application. The aforementioned memory includes various media that can store program code, such as USB flash drives, mobile hard drives, magnetic disks, or optical disks.

[0139] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure herein, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A vehicle-grid interactive orderly charging scheduling method, characterized in that: The method comprises: Obtaining a historical power grid load curve of a target area and a real-time power grid load curve of the target area within a first period before a current moment; combining the historical power grid load curve and the real-time power grid load curve, predicting a target power grid load curve within a second time period after the current moment, and determining a high-load period, a stable load period, and a low-load period of the target power grid load curve, wherein the high-load period is a period during which the load value in the target power grid load curve exceeds a preset upper load limit, the stable load period is a period during which the load value in the target power grid load curve is between a preset upper load limit and a preset lower load limit, and the low-load period is a period during which the load value in the target power grid load curve is lower than a preset lower load limit; Acquire first reservation information of charging piles in the target area during the high-load period, second reservation information during the stable-load period, and third reservation information during the low-load period; generating an initial charging scheduling strategy for the charging pile during the high-load period by combining the first reservation information, the second reservation information, and the third reservation information; Obtain historical vehicle performance data for the charging pile, predict the number of vehicle defaults during the high-load period based on the historical vehicle performance data, adjust the initial charging scheduling strategy based on the number of defaults, and generate a target charging scheduling strategy for the charging pile during the high-load period.

2. The vehicle-grid interactive orderly charging scheduling method according to claim 1, characterized in that: The step of combining the historical power grid load curve and the real-time power grid load curve to predict a target power grid load curve within a second time period after the current moment includes: Predicting a first power grid load curve of the target area within a second time period after the current moment based on the historical power grid load curve; The first power grid load curve and the real-time power grid load curve are combined to predict a target power grid load curve within a second time period after the current moment.

3. The vehicle-grid interactive orderly charging scheduling method according to claim 2, characterized in that: The step of combining the first power grid load curve and the real-time power grid load curve to predict a target power grid load curve within a second time period after the current moment includes: Predicting a second power grid load curve within a second time period after the current moment based on the real-time power grid load curve; Calculating a load difference between the first power grid load curve and the second power grid load curve at each moment in the second time period; Determining whether the absolute value of the load difference at each moment is greater than a preset threshold; If the absolute value at the first moment is greater than the preset threshold, obtaining a weighting coefficient of the first power grid load curve and the second power grid load curve at the first moment, and performing a weighted operation on the two load values ​​of the first power grid load curve and the second power grid load curve at the first moment according to the weighting coefficient to obtain a first target load value at the first moment; If the absolute value at the second moment is not greater than the preset threshold, the load value of the second power grid load curve at the second moment is used as the second target load value at the second moment; The first target load value at the first moment in the second time period and the second target load value at the second moment are connected in chronological order to generate a target power grid load curve in a second time period after the current moment.

4. The vehicle-grid interactive orderly charging scheduling method according to claim 1, characterized in that: The generating an initial charging scheduling strategy for the charging pile during the high-load period by combining the first reservation information, the second reservation information, and the third reservation information includes: Obtaining a preset load upper limit of the charging pile during the high load period; Calculating the total charging load of the charging pile during the high-load period according to the first reservation information; When the total charging load exceeds the preset load upper limit, calculating a target difference between the total charging load and the preset load upper limit; According to the size of the target difference, a first charging fee for vehicles in the high-load period is increased, and / or a second charging fee for vehicles in the stable load period and the low-load period is decreased, to generate a charging scheduling strategy to be adjusted, wherein both the first charging fee and the second charging fee are positively correlated with the target difference; The charging scheduling strategy to be adjusted is adjusted in combination with the second reservation information and the third reservation information to generate an initial charging scheduling strategy for the charging pile during the high-load period.

5. The vehicle-grid interactive orderly charging scheduling method according to claim 4, characterized in that: The adjusting the charging scheduling strategy to be adjusted in combination with the second reservation information and the third reservation information to generate an initial charging scheduling strategy for the charging pile during the high-load period includes: Obtaining a first remaining charging capacity during the stable load period and a second remaining charging capacity during the low load period; Based on the first remaining charging capacity and the second remaining capacity, and according to the second reservation information and the third reservation information, a first transferable charging capacity for the stable load period and a second transferable charging capacity for the low load period are generated accordingly; adjusting the reduction rate of the second charging fee during the stable load period and the low load period respectively according to the size of the first transferable charging capacity and the second transferable charging capacity, wherein the reduction rate of the second charging fee is positively correlated with the transferable charging capacity during the corresponding period; When the sum of the charging capacities of the first transferable charging capacity and the second transferable charging capacity is less than the target difference, adjusting the increase in the first charging fee during the high-load period, wherein the increase in the first charging fee during the high-load period is positively correlated with the difference between the target difference and the sum of the charging capacities; When the sum of the charging capacities is not less than the target difference, the second charging fee for the stable load period and the low load period is reduced according to a preset ratio based on a ratio of the target difference to the sum of the charging capacities; An initial charging scheduling strategy for the charging pile during the high-load period is generated according to the adjusted first charging fee and the second charging fee.

6. The vehicle-grid interactive orderly charging scheduling method according to claim 1, characterized in that: The adjusting the initial charging scheduling strategy according to the number of defaults to generate a target charging scheduling strategy for the charging pile during the high-load period includes: Calculating the actual releasable charging capacity during the high-load period according to the number of defaults; Based on the actual releasable charging capacity, adjusting the allocation of the remaining charging capacity during the high-load period; If the actual releasable charging capacity is greater than the preset capacity threshold, the charging fee during the high-load period is reduced, and the charging fees during the stable load period and the low-load period are adjusted; If the actually releasable charging capacity is not greater than the preset capacity threshold, the charging fee in the initial charging scheduling strategy is kept unchanged, and corresponding spare charging capacity is reserved according to the number of defaults; The adjusted charging cost and charging capacity allocation plan is used as the target charging scheduling strategy for the charging pile during the high load period.

7. The vehicle-grid interactive orderly charging scheduling method according to claim 1, characterized in that: After generating the target charging scheduling strategy for the charging pile during the high-load period, the method further includes: Acquiring real-time grid load data during the high-load period; Determining whether the real-time grid load data meets a preset load condition; If the real-time grid load data does not meet the preset load condition, calculating a deviation value between the real-time grid load data and the preset load condition; According to the size of the deviation value, the charging cost in the target charging scheduling strategy is adjusted according to a preset adjustment coefficient, wherein the adjustment range of the charging cost in the target charging scheduling strategy is positively correlated with the deviation value; The available charging capacity of the charging pile during the high-load period is recalculated based on the adjusted charging fee; and an updated charging capacity allocation plan is generated based on the available charging capacity.

8. A vehicle-grid interactive orderly charging scheduling system, characterized by: The system includes: a first acquisition module, a first combination module, a second acquisition module, a second combination module and a generation module; wherein, The first acquisition module is used to acquire a historical power grid load curve of a target area and a real-time power grid load curve of the target area within a first period before a current moment; The first combining module is configured to combine the historical power grid load curve and the real-time power grid load curve to predict a target power grid load curve within a second time period after the current moment, and determine a high-load period, a stable load period, and a low-load period of the target power grid load curve, wherein the high-load period is a period during which the load value in the target power grid load curve exceeds a preset upper load limit, the stable load period is a period during which the load value in the target power grid load curve is between a preset upper load limit and a preset lower load limit, and the low-load period is a period during which the load value in the target power grid load curve is lower than a preset lower load limit; The second acquisition module is configured to acquire first reservation information of charging piles in the target area during the high-load period, second reservation information during the stable-load period, and third reservation information during the low-load period; The second combining module is configured to combine the first reservation information, the second reservation information, and the third reservation information to generate an initial charging scheduling strategy for the charging pile during the high-load period; The generation module is used to obtain historical vehicle performance data of the charging pile, predict the number of vehicle defaults during the high-load period based on the historical vehicle performance data, adjust the initial charging scheduling strategy based on the number of defaults, and generate a target charging scheduling strategy for the charging pile during the high-load period.

9. An electronic device, characterized in that: The electronic device comprises a processor, a memory, a user interface and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 7.

Images