Electric vehicle charging scheduling method and electronic equipment

Abstract

The invention discloses an electric vehicle charging scheduling method and electronic equipment. The method comprises the following steps: acquiring historical charging behavior data of an electric vehicle in a predetermined historical time period; prediction information corresponding to the multiple areas is determined, and the prediction information at least comprises predicted power grid loads, predicted electricity prices and weather forecast information of the corresponding areas in the prediction time period; constructing an optimization target based on the historical charging behavior data and the prediction information corresponding to the plurality of areas; and based on the optimization target, charging scheduling optimization is carried out on the electric vehicle, a target charging scheduling scheme of the electric vehicle is obtained, and the target charging scheduling scheme comprises the charging moment, the charging position and the total charging electric energy of the electric vehicle in the prediction time period. According to the invention, the technical problems of poor flexibility and low accuracy of the scheduling scheme caused by incomplete consideration factors during charging scheduling of the electric vehicle in the prior art are solved.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle scheduling technology, and more specifically, to an electric vehicle charging scheduling method and electronic device. Background Technology

[0002] In the rapidly developing electric vehicle industry, intelligent dispatching technology is increasingly becoming crucial for maintaining grid stability, optimizing energy utilization, and improving user experience. With the surge in the number of electric vehicles, the impact of disorderly charging behavior on the power grid has become significant, especially during peak hours, potentially leading to localized grid overload and power instability, increasing grid operating costs. Furthermore, due to the uncertainty of electric vehicle charging demand and the intermittent nature of renewable energy sources such as wind and solar power, effectively integrating these resources to ensure a balance between power supply and demand has become a challenge. Related technologies have significant shortcomings in the optimized dispatching of electric vehicles, mainly in the following aspects:

[0003] Currently, most electric vehicle charging scheduling methods employ centralized control systems and rule-based algorithms. While these methods can manage charging behavior to some extent, they do not comprehensively consider all factors when scheduling electric vehicle charging, making it difficult to adapt to dynamic changes in user behavior and real-time fluctuations in grid load, resulting in insufficient flexibility and accuracy in scheduling schemes.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides an electric vehicle charging scheduling method and electronic device to at least solve the technical problem that the scheduling scheme has poor flexibility and low accuracy due to the incomplete consideration of factors in the electric vehicle charging scheduling in related technologies.

[0006] According to one aspect of the present invention, an electric vehicle charging scheduling method is provided, comprising: acquiring historical charging behavior data of electric vehicles during a predetermined historical period, wherein the predetermined historical period is a period of a first predetermined duration prior to the current moment; determining prediction information corresponding to multiple regions, wherein the prediction information includes at least the predicted grid load, predicted electricity price, and weather forecast information of the corresponding region during the prediction period, the prediction period being a period of a second predetermined duration after the current moment, and the region being the region where the charging pile is located; constructing an optimization objective based on the historical charging behavior data and the prediction information corresponding to the multiple regions; and optimizing the charging scheduling of electric vehicles based on the optimization objective to obtain a target charging scheduling scheme for electric vehicles, wherein the target charging scheduling scheme includes: the charging time, charging location, and total charging energy of the electric vehicles during the prediction period.

[0007] According to another aspect of the present invention, an electric vehicle charging scheduling device is also provided, comprising: a data collection module for acquiring historical charging behavior data of electric vehicles during a predetermined historical period, wherein the predetermined historical period is a period of a first predetermined duration prior to the current moment; a prediction information generation module for determining prediction information corresponding to multiple regions, wherein the prediction information includes at least the predicted grid load, predicted electricity price, and weather forecast information of the corresponding region during the prediction period, the prediction period being a period of a second predetermined duration after the current moment, and the region being the region where the charging pile is located; an optimization target construction module for constructing an optimization target based on the historical charging behavior data and the prediction information corresponding to the multiple regions; and a charging scheduling optimization module for optimizing the charging scheduling of electric vehicles based on the optimization target to obtain a target charging scheduling scheme for electric vehicles, wherein the target charging scheduling scheme includes: the charging time, charging location, and total charging energy of the electric vehicles during the prediction period.

[0008] According to another aspect of the present invention, a non-volatile storage medium is also provided, which stores a plurality of instructions adapted for loading and executing any one of the instructions in an electric vehicle charging scheduling method by a processor.

[0009] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement any one of the electric vehicle charging scheduling methods.

[0010] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps of any one of the electric vehicle charging scheduling methods.

[0011] In this embodiment of the invention, historical charging behavior data of electric vehicles during a predetermined historical period is obtained, wherein the predetermined historical period is a period of a first predetermined duration before the current moment; prediction information corresponding to multiple regions is determined, wherein the prediction information includes at least the predicted grid load, predicted electricity price, and weather forecast information of the corresponding region during the prediction period, the prediction period is a period of a second predetermined duration after the current moment, and the region is the region where the charging pile is located; based on the historical charging behavior data and the prediction information corresponding to multiple regions, an optimization objective is constructed; based on the optimization objective, the charging scheduling of electric vehicles is optimized to obtain a target charging scheduling scheme for electric vehicles, wherein the target charging scheduling scheme includes: the charging time, charging location, and total charging energy of electric vehicles during the prediction period, achieving the goal of comprehensively and accurately scheduling electric vehicle charging by comprehensively analyzing vehicle travel data, predicting multiple factors, and combining with the target optimization algorithm, thereby achieving the technical effect of improving the accuracy and flexibility of electric vehicle charging scheduling, and thus solving the technical problem of poor scheduling scheme flexibility and low accuracy caused by the incomplete consideration of factors in electric vehicle charging scheduling in related technologies. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0013] Figure 1 This is a flowchart of an electric vehicle charging scheduling method according to an embodiment of the present invention;

[0014] Figure 2 This is a flowchart of an optional electric vehicle charging scheduling method according to an embodiment of the present invention;

[0015] Figure 3 This is a schematic diagram of an electric vehicle charging scheduling device according to an embodiment of the present invention. Detailed Implementation

[0016] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0017] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0018] According to an embodiment of the present invention, a method embodiment for electric vehicle charging scheduling is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0019] Figure 1 This is a flowchart of an electric vehicle charging scheduling method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0020] Step S102: Obtain historical charging behavior data of electric vehicles during a predetermined historical period, wherein the predetermined historical period is the period of the first predetermined duration before the current moment;

[0021] Optionally, sensors and communication devices can be installed on electric vehicles to collect historical charging behavior data for predetermined historical time periods. These predetermined historical time periods refer to the first predetermined duration preceding the current moment, such as the past week or a longer period. Analyzing charging records during this period, including charging frequency, location, time, and amount of charge, helps to establish a more accurate user energy consumption assessment model. This allows for more personalized consideration of each user's actual charging needs when formulating charging scheduling strategies, thereby improving scheduling efficiency and user satisfaction.

[0022] Step S104: Determine the forecast information corresponding to each of the multiple regions. The forecast information includes at least the forecasted grid load, forecasted electricity price and weather forecast information of the corresponding region during the forecast period. The forecast period is the second predetermined time period after the current time, and the region is the region where the charging pile is located.

[0023] Optionally, the aforementioned forecast information includes at least the forecasted grid load, forecasted electricity price, and weather forecast information for the corresponding region during the forecast period. The forecast period is defined as the second predetermined time interval after the current moment, such as the next 24 or 48 hours. The region specifically refers to the geographical area where the charging station is located. These regions may include, but are not limited to, different parts of a city, commercial areas, residential areas, etc., each with its unique electricity demand. By collecting and analyzing various real-time and historical data, such as grid load data, electricity price information, and weather data provided by weather forecast application interfaces, an electricity information forecasting model is established to predict the grid load, electricity price fluctuations, and weather conditions for each region during the forecast period. By obtaining this detailed forecast information, the electricity balance of each region can be calculated more accurately, and the charging time and location of electric vehicles can be rationally allocated, thereby providing users with more convenient charging services while ensuring grid stability. This approach not only improves the intelligence level of electric vehicle charging scheduling but also promotes the efficient utilization of electricity resources.

[0024] Step S106: Based on historical charging behavior data and prediction information corresponding to multiple regions, construct optimization objectives;

[0025] Optionally, the aforementioned optimization objective is constructed based on two major datasets: historical charging behavior data and prediction information for multiple regions. Historical charging behavior data encompasses charging records of electric vehicles over specific time periods. Analyzing this data allows us to understand users' charging habits and preferences, thereby predicting potential future charging needs. Simultaneously, the prediction information forecasts future grid load, electricity prices, and weather conditions, focusing on the power supply and demand status of each charging station's location over a future period. Based on these two sets of data, an optimization objective is constructed, which can be achieved by minimizing a multi-factor objective function that integrates charging cost, charging convenience, and regional power balance.

[0026] In one optional embodiment, an optimization objective is constructed based on historical charging behavior data and prediction information corresponding to multiple regions, including: determining the predicted unit energy consumption of electric vehicles based on historical charging behavior data, wherein the predicted unit energy consumption represents the amount of electricity consumed by electric vehicles per unit distance during the prediction period; determining the predicted electricity demand and predicted electricity consumption for each of the multiple regions based on the prediction information corresponding to each region, wherein the predicted electricity demand represents the electricity demand of the corresponding region during the prediction period, and the predicted electricity consumption represents the electricity consumption of the corresponding region during the prediction period; constructing a multi-factor objective function based on the predicted unit energy consumption, the predicted electricity demand, and the predicted electricity consumption for each of the multiple regions; and determining the optimization objective as: minimizing the function value of the multi-factor objective function.

[0027] Optionally, by analyzing historical charging data of electric vehicles, predicting their unit energy consumption and the power supply and demand of each charging area, a multi-dimensional optimization objective function can be constructed. The aim is to achieve the best balance between charging cost, charging convenience and grid stability by minimizing the value of this function, thereby achieving the goal of intelligent, efficient and economical charging scheduling.

[0028] In one optional embodiment, determining the predicted unit energy consumption of an electric vehicle based on historical charging behavior data includes: using an energy consumption assessment model based on historical charging behavior data to obtain the predicted unit energy consumption of the electric vehicle; wherein, the energy consumption assessment model is obtained through machine learning based on the charging behavior data and unit energy consumption corresponding to multiple historical time periods; the charging behavior data includes historical charging times within the corresponding historical time period, as well as the corresponding charging location and remaining power.

[0029] Optionally, predicting unit energy consumption is a crucial parameter for determining charging costs and the effectiveness of charging strategies. This parameter is determined based on rich historical charging behavior data, including specific charging times, locations, and remaining battery power after each charge. By collecting and analyzing this data, patterns in vehicle energy consumption can be identified, particularly the differences in energy consumption under varying weather conditions and driving habits. An energy consumption assessment model is employed to predict unit energy consumption. This model can utilize machine learning techniques, such as neural network algorithms (backpropagation neural networks), to train on charging behavior data and unit energy consumption for multiple historical time periods. During training, the model learns the complex relationships between historical charging times, charging locations, remaining battery power, and unit energy consumption, identifying which factors significantly impact energy consumption and how these factors interact to determine unit energy consumption. As training progresses, the model gradually optimizes its internal parameters to minimize prediction errors and improve prediction accuracy. Once the model training is complete, it can predict the energy consumption per unit distance traveled by an electric vehicle in the next predicted time period based on the latest historical charging data and real-time vehicle status, providing a reliable foundation for subsequent charging scheduling strategies.

[0030] In one optional embodiment, based on the forecast information corresponding to each of the multiple regions, the predicted electricity demand and predicted electricity consumption corresponding to each of the multiple regions are determined, including: based on the predicted grid load, predicted electricity price and weather forecast information of the corresponding region during the forecast period, an electricity information forecasting model is used to obtain the predicted electricity demand and predicted electricity consumption corresponding to each of the multiple regions. The electricity information forecasting model is obtained by machine learning algorithm based on the grid load, electricity price, weather forecast information, electricity demand and electricity consumption corresponding to each of the multiple historical periods.

[0031] Optionally, to accurately predict the electricity demand and consumption of each region, this embodiment employs an electricity information prediction model. This model is trained using machine learning algorithms, specifically utilizing predicted grid load, predicted electricity price, and weather forecast information for the corresponding region during the prediction period. By learning the inherent relationships between these data, the model can identify which factors significantly influence electricity demand and consumption, and how these factors interact. Grid load prediction helps identify peak and off-peak periods of electricity demand, thereby avoiding additional pressure on the grid from charging scheduling during peak load periods. Electricity price prediction considers optimizing user charging costs; by selecting charging periods with lower electricity prices, user charging expenses can be effectively reduced. Weather forecast prediction is based on the impact of weather on electricity demand. For example, electricity demand may increase in hot weather because people use more appliances such as air conditioners, while demand may differ in cold or rainy weather. Once the model is trained, it can generate predicted electricity demand and consumption for each region based on the latest prediction information. These predictions provide important basis for subsequent charging scheduling optimization, helping the system to formulate the optimal charging strategy based on factors such as charging cost, charging convenience and grid stability.

[0032] In one optional embodiment, based on the predicted unit energy consumption and the predicted electricity demand and consumption of each of the multiple regions, a multi-factor objective function is constructed, including: based on the predicted unit energy consumption and the predicted electricity demand and consumption of each of the multiple regions, constructing a charging cost function, a charging convenience function, and a regional power balance function; and based on the charging cost function, the charging convenience function, and the regional power balance function, constructing a multi-factor objective function.

[0033] Optionally, firstly, using predicted unit energy consumption—that is, the energy consumption of an electric vehicle per unit distance traveled within a predicted period—and combining predicted energy demand and consumption data, three sub-functions are constructed: a charging cost function, a charging convenience function, and a regional energy balance function. Subsequently, based on these three sub-functions, a multi-factor objective function is constructed. This multi-factor objective function can comprehensively evaluate the merits of charging scheduling schemes, providing a powerful quantitative tool for charging decisions. This approach not only improves the intelligence level of charging scheduling but also helps to achieve effective integration of new energy vehicle charging with grid resources, promoting efficient energy utilization and the development of green transportation.

[0034] In an optional embodiment, based on predicted unit energy consumption, predicted energy demand, and predicted energy consumption for each of multiple regions, a charging cost function, a charging convenience function, and a regional energy balance function are constructed, including: The charging cost function is constructed as follows: CD = CDE × DED + LCJ × W × PR; where CD is the charging cost of an electric vehicle during the predicted period when any charging scheduling scheme is adopted, CDE is the total charging energy of the electric vehicle when any charging scheduling scheme is adopted, DED is the predicted charging price of the region where the electric vehicle is charged when any charging scheduling scheme is adopted, LCJ is the distance from the location of the electric vehicle to the charging pile in any charging scheduling scheme, W is the predicted unit energy consumption, and PR is the historical charging price of the region where the electric vehicle was charged when any charging scheduling scheme occurred; The charging convenience function is constructed as follows: BL = SC + LC; where BL is the charging convenience of the electric vehicle when any charging scheduling scheme is adopted, SC is the total charging time of the electric vehicle when any charging scheduling scheme is adopted, and LC is the total distance from the location of the electric vehicle to the charging pile in any charging scheduling scheme; The regional energy balance function is constructed as follows: Wherein, PH represents the regional power balance when any charging scheduling scheme is adopted, GYi represents the power supply of the i-th region when any charging scheduling scheme is adopted, XYi represents the predicted power consumption of the i-th region when any charging scheduling scheme is adopted, i represents the identifier of any one of the multiple regions, and n represents the total number of multiple regions; wherein, the predicted power consumption is obtained based on the charging amount of electric vehicles and the predicted power demand of the i-th region when any charging scheduling scheme is implemented.

[0035] For example, in an electric vehicle charging scheduling system, assuming an electric vehicle requires a total charging energy (CDE) of 50 kWh, the predicted charging price (DED) is $0.2 per kWh, the distance from the electric vehicle's location to the nearest charging station (LCJ) is 10 km, the predicted energy consumption per unit (W) is 0.3 kWh / km, and the historical charging price (PR) at the time of the last charging action was $0.2 per kWh, the charging cost (CD) can be calculated as: CD = CDE × DED + LCJ × W × PR = 50 × 0.2 + 10 × 0.3 × 0.2 = 10 + 0.6 = $10.6; assuming the total charging time (S) in the electric vehicle charging area is... C) The total travel time (LC) from the location of the electric vehicle to the charging station is 0.5 hours, and the charging convenience (BL) can be calculated as: BL = SC + LC = 2 + 0.5 = 2.5 hours. Assuming that the current charging scheme involves two areas, the first area has a power supply (GY1) of 100 MW and a power consumption (XH1) of 80 MW; the second area has a power supply (GY2) of 150 MW and a power consumption (XH2) of 120 MW. The regional power balance (PH) can be calculated as: PH = |GY1-XH1| + |GY2-XH2| = |100-80| + |150-120| = 20 + 30 = 50 MW.

[0036] Optionally, constructing charging cost functions, charging convenience functions, and regional power balance functions are key steps to ensure that charging strategies are both economical and user-friendly. The design of these functions not only focuses on minimizing charging costs and maximizing charging convenience, but also strives to maintain grid stability and balance, avoiding regional power shortages or surpluses caused by a large number of electric vehicles charging simultaneously. By integrating these functions into a multi-factor objective function, a comprehensive standard for evaluating the merits of charging solutions is provided, helping to achieve the optimal balance between economics, user satisfaction, and grid stability in charging decisions. In practical applications, the specific values ​​of each function depend on the accuracy of the predicted data, such as predicted unit energy consumption, predicted energy demand, and predicted energy consumption. By continuously monitoring these parameters and dynamically adjusting them in conjunction with user behavior and grid conditions, charging strategies can be continuously optimized to better adapt to complex real-world environments, providing electric vehicle users with a better charging experience.

[0037] In one optional embodiment, a multi-factor objective function is constructed based on the charging cost function, the charging convenience function, and the regional power balance function. This includes constructing the multi-factor objective function as follows: DMB = PH × (k1 × CD + k2 × BL); where DMB is the function value of the multi-factor objective function when any charging scheduling scheme is adopted, k1 is a preset first weighting coefficient used to adjust the charging cost, and k2 is a preset second weighting coefficient used to adjust the charging convenience. For example, assuming the first weighting coefficient (k1) is 0.6 and the second weighting coefficient (k2) is 0.4, the calculated function value (DMB) of the multi-factor objective is: DMB = PH × (k1 × CD + k2 × BL) = 50 × (0.6 × 10.6 + 0.4 × 2.5) = 50 × (6.36 + 1) = 50 × 7.36 = 368 units.

[0038] Optionally, a multi-factor objective function can comprehensively reflect the impact of a charging dispatching scheme on charging costs, charging convenience, and regional power balance. The preset weighting coefficients allow the dispatching strategy to flexibly adjust priorities among different objectives. For example, when power supply is tight or electricity prices rise significantly, a greater weight may be given to k1 to prioritize reducing charging costs and grid burden. Conversely, when power is sufficient and convenience is the primary consideration, increasing the weight of k2 can better improve charging convenience and satisfaction. This ability to dynamically adjust weights enables the charging dispatching strategy of this embodiment to make more flexible and accurate dispatching decisions in the face of changing market conditions and charging demands.

[0039] Step S108: Based on the optimization objective, optimize the charging schedule of electric vehicles to obtain the target charging schedule scheme for electric vehicles. The target charging schedule scheme includes: the charging time, charging location and total charging energy of electric vehicles during the predicted period.

[0040] Optionally, regarding the selection of charging times, the target charging scheduling scheme utilizes an energy information prediction model, considering the periodic changes in electricity prices and the distribution of grid load, to ensure that electric vehicles can be charged during the time period with the greatest cost-effectiveness and the least impact on the grid. The determination of charging locations is based on user location information, driving habits, and the real-time status and availability of charging stations, intelligently recommending charging stations that are moderately far away, have high charging efficiency, and best match the energy demand balance within the predicted time period. For the total charging energy, the amount of electricity required for each charge can be accurately calculated based on real-time monitoring of the remaining battery power of electric vehicles, user trip planning, and assessment of predicted unit energy consumption. This satisfies user needs while avoiding the potential damage to battery health and grid stability caused by overcharging. Through precise calculation and prediction, the target charging scheduling scheme can provide electric vehicle users with a charging plan that is optimal in terms of time, location, and charging volume within the predicted time period. These methods not only help reduce the economic burden on users during the charging process and improve charging convenience, but also contribute to the stable operation of the grid and reduce load peaks caused by large-scale electric vehicle charging.

[0041] In one optional embodiment, based on the optimization objective, the charging schedule of the electric vehicle is optimized to obtain the target charging schedule scheme for the electric vehicle, including: determining the constraint condition that the result of multiplying the driving distance of the electric vehicle to the charging location by the predicted unit energy consumption by a predetermined multiple is less than the remaining power of the electric vehicle at the departure time, wherein the departure time is the time when the electric vehicle departs for the charging location, and the predicted unit energy consumption represents the amount of power consumed by the electric vehicle per unit distance during the predicted period; and determining the target charging schedule scheme from multiple candidate charging schedule schemes based on the optimization objective and the constraint condition.

[0042] Optionally, when determining the target charging scheduling scheme, the primary constraint must be that the energy consumed by the electric vehicle (EV) traveling from its current location to the recommended charging point cannot exceed its remaining battery power at the time of departure. Specifically, the constraint is expressed as follows: the distance the EV needs to travel to the charging location (denoted as JL), multiplied by the predicted unit energy consumption (i.e., the energy consumption per unit distance during the predicted period, denoted as W), and then multiplied by a predetermined factor (1.5), must result in a value less than the EV's remaining battery power at the time of departure (denoted as SY). This constraint ensures that the EV has sufficient battery power to reach the charging station, avoiding the risk of running out of power en route, while also considering potential energy losses and power demands in emergency situations. By screening multiple candidate charging scheduling schemes that meet the above constraints and further determining the optimization objective, a comprehensive analysis of each potential charging scheduling scheme can achieve a high degree of intelligence in EV charging scheduling. This not only ensures smooth user journeys and reduces charging costs but also effectively avoids adverse impacts on grid stability, providing strong technical support for the efficient operation of EV charging infrastructure and the application of smart grids.

[0043] In an optional embodiment, when the optimization objective is determined to be minimizing the function value of the multi-factor objective function, a target charging scheduling scheme is determined from multiple candidate charging scheduling schemes based on the optimization objective and constraints. This includes: determining, from the multiple candidate charging scheduling schemes, the one that satisfies the constraints and has the smallest function value of the multi-factor objective function as the first charging scheduling scheme; and determining, from the other candidate charging scheduling schemes, the one that satisfies the constraints and has the smallest function value of the multi-factor objective function as the second charging scheduling scheme. The other candidate charging scheduling schemes are those other than the first charging scheduling scheme among the multiple candidate charging scheduling schemes. The target charging scheduling scheme includes both the first and second charging scheduling schemes.

[0044] Optionally, multiple candidate charging scheduling schemes can be generated, each with detailed plans for the charging time, location, and amount of electricity for electric vehicles within the predicted time period. To ensure the feasibility of these schemes, a key constraint can be set. Among the candidate schemes that meet the constraint, those that minimize the multi-factor objective function value are selected as the first charging scheduling scheme, representing the optimal scheme among all eligible candidates. The second stage of selection then begins. After eliminating the optimal scheme, schemes that meet the constraint are searched again for the remaining candidates, and the one with the smallest multi-factor objective function value is selected as the second-optimal scheme. The final target charging scheduling scheme includes both the first and second schemes. This dual-scheme configuration strategy not only provides charging flexibility but also ensures the continuity and effectiveness of charging scheduling when the first scheme cannot be implemented. This approach not only meets the needs of electric vehicle users but also effectively regulates the grid load.

[0045] For example, in an electric vehicle dispatching system, the location information of all available charging stations at the current moment is obtained from a database or real-time data interface. Assume there are three selectable charging locations A, B, and C, with a threshold of 100 units. Assume the current charging location A has a travel distance (JL) of 10 kilometers, an energy consumption per unit distance (W) of 0.3 kWh / km, and a remaining energy (SY) of 20 kWh. The calculation yields JL × W × 1.5 = 4.5 units, which is less than the remaining energy (SY) of 20 kWh, indicating that the current charging location A meets the constraints. Then, the fourth formula is used for calculation, assuming the multi-source factor control target for the current charging location A is 300 units. Similarly, the current charging location B has a travel distance (JL) of 80 kilometers, an energy consumption per unit distance (W) of 0.3 kWh / km, and a remaining energy (SY) of 30 kWh. At this point, the calculated value is JL×W×1.5=80×0.3×1.5×30=36 units, which is greater than the remaining energy (SY) of 30 kWh. This indicates that the current charging position B does not meet the constraints, and the subsequent process is not continued. Assuming the current charging position C has a travel distance (JL) of 12 km, an energy consumption per unit distance (W) of 0.3 kWh / km, and a remaining energy (SY) of 15 kWh, the calculated value is JL×W×1.5=12×0.3×1.5=5.4 units, which is less than the remaining energy (SY) of 15 kWh. This indicates that the current charging position C meets the constraints. Next, the fourth formula is used for calculation, assuming the multi-source factor control target for the current charging position C is 320 units. Finally, by comparing the multi-source factor control targets of the current charging positions A and C, the charging position C with the smallest multi-source factor control target value is selected as the optimal electric vehicle charging scheduling scheme. Having determined charging location C as the optimal electric vehicle (EV) charging schedule, the EV scheduling system ranks the remaining options based on multi-source factor control target values. Assuming charging location A has the smallest multi-source factor control target value among the remaining options, it is selected as the second-best EV scheduling option. Next, the charging time, charging location, and total charging energy of the EVs in both the optimal (charging location C) and second-best (charging location A) scheduling schemes are extracted. Furthermore, once the target charging schedule is determined, it is immediately transmitted to the corresponding EV. This step is achieved through a wireless network, ensuring the timeliness and reliability of information transmission. The target charging schedule includes the EV's charging time, charging location, and charging amount within the predicted time period. Upon receiving the target charging schedule, this information is clearly presented to the driver, facilitating quick understanding and comparison of the two options. The driver can choose between the optimal and second-best charging schedule options based on personal preference, travel arrangements, or cost considerations.This selection process can be completed via the in-vehicle touchscreen or through a companion mobile application. Regardless of the method used, once the driver decides to adopt a particular option, the result is immediately fed back to the central control center via wireless network. By collecting this feedback, the effectiveness of the target charging scheduling plan can be further verified, its performance in actual implementation can be evaluated, and necessary adjustments and optimizations can be made accordingly to improve the accuracy and efficiency of subsequent charging scheduling.

[0046] Optionally, firstly, with the electric vehicle connected to the network, the optimal electric vehicle scheduling plan (charging location C) and the second-best electric vehicle scheduling plan (charging location A) are sent to the vehicle's onboard information system or mobile application via the electric vehicle scheduling system. The system then extracts the charging time, charging location, and charging amount information for each electric vehicle in the plan. For example, charging time at charging location C is 2 hours, with a total charging energy of 50 kWh; charging time at charging location A is 2.5 hours, with a total charging energy of 45 kWh. Secondly, the driver selects from the two plans. After selection, the onboard information system or mobile application sends the selection result back to the central control center via wireless network for further optimization of the scheduling strategy.

[0047] Through the above steps S102 to S108, the goal of comprehensively and accurately scheduling electric vehicle charging can be achieved by analyzing vehicle travel data, predicting multiple factors, and combining with target optimization algorithms. This achieves the technical effect of improving the accuracy and flexibility of electric vehicle charging scheduling, and solves the technical problem of poor scheduling flexibility and low accuracy caused by the incomplete consideration of factors in electric vehicle charging scheduling in related technologies.

[0048] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation method. Figure 2 This is a flowchart of an optional electric vehicle charging scheduling method according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes:

[0049] S1: Obtain historical charging behavior data of electric vehicles through sensors and communication devices on the electric vehicle. The specific implementation process is the same as the aforementioned embodiments, and will not be repeated here.

[0050] S2: Establish an energy information prediction model that comprehensively considers predicted grid load, predicted electricity price, and weather forecast information. The specific implementation process is the same as the aforementioned embodiments, and will not be repeated here.

[0051] S3: Based on historical charging behavior data and power information prediction models, a multi-factor objective function is constructed. The specific implementation process is the same as the aforementioned embodiments, and will not be repeated here.

[0052] S4: The optimal electric vehicle charging scheduling scheme is obtained by minimizing the function value of the multi-factor objective function. The specific implementation process is the same as the previous embodiment, and will not be repeated here.

[0053] S5: Obtain the suboptimal electric vehicle charging scheduling scheme, and extract two different sets of charging parameters for the optimal electric vehicle charging scheduling scheme and the suboptimal electric vehicle charging scheduling scheme. The specific implementation process is the same as the previous embodiment, and will not be repeated here.

[0054] S6: Provide users with two electric vehicle charging scheduling schemes, the optimal and the second-best, and feed back the selection results to optimize the charging scheduling strategy. The specific implementation process is the same as the previous embodiment, and will not be repeated here.

[0055] It should be noted that, compared with traditional electric vehicle scheduling methods that rely on centralized control systems and rule-based algorithms, this embodiment demonstrates significant advantages in improving the accuracy and flexibility of electric vehicle charging scheduling by using a charging scheduling method that can comprehensively analyze vehicle travel data, predict multiple factors, and combine target optimization algorithms. It solves the technical problem of poor scheduling flexibility and low accuracy caused by the incomplete consideration of factors in electric vehicle charging scheduling in related technologies.

[0056] This embodiment also provides an electric vehicle charging scheduling device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the terms "module" and "device" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0057] According to an embodiment of the present invention, an apparatus embodiment for implementing the above-described electric vehicle charging scheduling method is also provided. Figure 3 This is a schematic diagram of the structure of an electric vehicle charging scheduling device according to an embodiment of the present invention, as shown below. Figure 3 As shown, the above-mentioned electric vehicle charging scheduling device includes: a data collection module 300, a prediction information generation module 302, an optimization target construction module 304, and a charging scheduling optimization module 306, wherein:

[0058] The data collection module 300 is used to acquire historical charging behavior data of electric vehicles during a predetermined historical period, wherein the predetermined historical period is the period of the first predetermined duration before the current moment;

[0059] The prediction information generation module 302 is connected to the data collection module 300 and is used to determine the prediction information corresponding to each of the multiple regions. The prediction information includes at least the predicted grid load, predicted electricity price and weather forecast information of the corresponding region during the prediction period. The prediction period is the second predetermined time period after the current time and the region is the region where the charging pile is located.

[0060] An optimization target construction module 304 is connected to the prediction information generation module 302, and is used to construct optimization targets based on historical charging behavior data and prediction information corresponding to multiple regions.

[0061] The charging scheduling optimization module 306 is connected to the optimization target construction module 304. It is used to optimize the charging schedule of electric vehicles based on the optimization target to obtain the target charging schedule scheme of electric vehicles. The target charging schedule scheme includes: the charging time, charging location and total charging energy of electric vehicles in the predicted period.

[0062] In this embodiment of the invention, a data collection module 300 is set up to acquire historical charging behavior data of electric vehicles during a predetermined historical period, wherein the predetermined historical period is a period of a first predetermined duration before the current moment; a prediction information generation module 302, connected to the data collection module 300, is used to determine prediction information corresponding to multiple regions, wherein the prediction information includes at least the predicted grid load, predicted electricity price, and weather forecast information of the corresponding region during the prediction period, the prediction period is a period of a second predetermined duration after the current moment, and the region is the region where the charging pile is located; an optimization target construction module 304, connected to the prediction information generation module 302, is used to construct an optimization target based on the historical charging behavior data and the prediction information corresponding to multiple regions; a charging scheduling optimization module 306, connected to the optimization target construction module 304, is used to optimize the charging scheduling of electric vehicles based on the optimization target to obtain a target charging scheduling scheme for electric vehicles, wherein the target charging scheduling scheme includes: the charging time, charging location, and total charging energy of electric vehicles during the prediction period. This approach achieves the goal of comprehensively and accurately scheduling electric vehicle charging by analyzing vehicle travel data, predicting multiple factors, and combining them with target optimization algorithms. This improves the accuracy and flexibility of electric vehicle charging scheduling and solves the technical problem of poor scheduling flexibility and low accuracy caused by incomplete consideration of factors in related technologies.

[0063] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0064] It should be noted that the data collection module 300, prediction information generation module 302, optimization target construction module 304, and charging scheduling optimization module 306 mentioned above correspond to steps S102 to S108 in the embodiments. The instances and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run on a computer terminal.

[0065] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.

[0066] The electric vehicle optimization scheduling device described above may also include a processor and a memory. The data collection module 300, the prediction information generation module 302, the optimization target construction module 304, and the charging scheduling optimization module 306 are all stored in the memory as program modules. The processor executes the program modules stored in the memory to realize the corresponding functions.

[0067] The processor contains a core that retrieves the corresponding program modules from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0068] According to an embodiment of this application, an embodiment of a non-volatile storage medium is also provided. Optionally, in this embodiment, the non-volatile storage medium includes a stored program, wherein, when the program runs, it controls the device where the non-volatile storage medium is located to execute any of the electric vehicle charging scheduling methods described above.

[0069] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals, and the non-volatile storage medium includes stored programs.

[0070] Optionally, during program execution, the device containing the non-volatile storage medium is controlled to perform the following functions: acquire historical charging behavior data of electric vehicles during a predetermined historical period, wherein the predetermined historical period is a period of a first predetermined duration before the current moment; determine the prediction information corresponding to multiple regions, wherein the prediction information includes at least the predicted grid load, predicted electricity price, and weather forecast information of the corresponding region during the prediction period, the prediction period is a period of a second predetermined duration after the current moment, and the region is the region where the charging pile is located; construct an optimization objective based on the historical charging behavior data and the prediction information corresponding to multiple regions; and optimize the charging scheduling of electric vehicles based on the optimization objective to obtain a target charging scheduling scheme for electric vehicles, wherein the target charging scheduling scheme includes: the charging time, charging location, and total charging energy of electric vehicles during the prediction period.

[0071] According to an embodiment of this application, an embodiment of a processor is also provided. Optionally, in this embodiment, the processor is used to run a program, wherein the program executes any of the above-described electric vehicle charging scheduling methods.

[0072] According to an embodiment of this application, an embodiment of a computer program product is also provided. Optionally, in this embodiment, the computer program product includes a computer program that, when executed by a processor, implements the steps of any of the above-described electric vehicle charging scheduling methods.

[0073] Optionally, when the aforementioned computer program product is executed on a data processing device, it is suitable to execute an initialization program with the following method steps: acquiring historical charging behavior data of electric vehicles during a predetermined historical period, wherein the predetermined historical period is a period of a first predetermined duration before the current moment; determining the prediction information corresponding to multiple regions, wherein the prediction information includes at least the predicted grid load, predicted electricity price, and weather forecast information of the corresponding region during the prediction period, the prediction period is a period of a second predetermined duration after the current moment, and the region is the region where the charging pile is located; constructing an optimization objective based on the historical charging behavior data and the prediction information corresponding to multiple regions; and optimizing the charging scheduling of electric vehicles based on the optimization objective to obtain a target charging scheduling scheme for electric vehicles, wherein the target charging scheduling scheme includes: the charging time, charging location, and total charging energy of electric vehicles during the prediction period.

[0074] This invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring historical charging behavior data of electric vehicles during a predetermined historical period, wherein the predetermined historical period is a period of a first predetermined duration prior to the current moment; determining prediction information corresponding to multiple regions, wherein the prediction information includes at least the predicted grid load, predicted electricity price, and weather forecast information for the corresponding region during the prediction period, the prediction period being a period of a second predetermined duration after the current moment, and the region being the region where the charging pile is located; constructing an optimization objective based on the historical charging behavior data and the prediction information corresponding to the multiple regions; and optimizing the charging schedule of electric vehicles based on the optimization objective to obtain a target charging schedule scheme for electric vehicles, wherein the target charging schedule scheme includes: the charging time, charging location, and total charging energy of the electric vehicles during the prediction period.

[0075] The order of the above embodiments of the present invention is merely for description and does not represent the superiority or inferiority of the embodiments.

[0076] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0077] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of modules described above can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between modules, and may be electrical or other forms.

[0078] The modules described above as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0079] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0080] If the aforementioned integrated modules are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part 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 non-volatile storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned non-volatile storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0081] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for scheduling electric vehicle charging, characterized in that, include: Acquire historical charging behavior data of electric vehicles during a predetermined historical period, wherein the predetermined historical period is a period of a first predetermined duration prior to the current moment; Determine the forecast information corresponding to each of the multiple regions, wherein the forecast information includes at least the forecasted grid load, forecasted electricity price and weather forecast information of the corresponding region during the forecast period, the forecast period is the second predetermined time period after the current time, and the region is the region where the charging pile is located; Based on the historical charging behavior data and the prediction information corresponding to each of the multiple regions, an optimization target is constructed. Based on the optimization objective, the charging schedule of the electric vehicle is optimized to obtain the target charging schedule scheme of the electric vehicle. The target charging schedule scheme includes the charging time, charging location and total charging energy of the electric vehicle during the predicted period.

2. The method according to claim 1, characterized in that, The optimization objective, based on the historical charging behavior data and the prediction information corresponding to each of the multiple regions, includes: Based on the historical charging behavior data, the predicted unit energy consumption of the electric vehicle is determined, wherein the predicted unit energy consumption represents the amount of electrical energy consumed by the electric vehicle per unit distance during the predicted period. Based on the forecast information corresponding to each of the multiple regions, the forecasted electricity demand and forecasted electricity consumption of each of the multiple regions are determined, wherein the forecasted electricity demand represents the electricity demand of the corresponding region during the forecast period, and the forecasted electricity consumption represents the electricity consumption of the corresponding region during the forecast period. Based on the predicted unit energy consumption, the predicted electricity demand and predicted electricity consumption of each of the multiple regions, a multi-factor objective function is constructed. The optimization objective is determined to be: to minimize the function value of the multi-factor objective function.

3. The method according to claim 2, characterized in that, The step of determining the predicted unit energy consumption of the electric vehicle based on the historical charging behavior data includes: Based on the historical charging behavior data, an energy consumption assessment model is used to obtain the predicted unit energy consumption of the electric vehicle. The energy consumption assessment model is obtained through machine learning based on charging behavior data and unit energy consumption corresponding to multiple historical time periods. The charging behavior data includes historical charging times within the corresponding historical time period, as well as the corresponding charging location and remaining power.

4. The method according to claim 2, characterized in that, The step of determining the predicted electricity demand and predicted electricity consumption for each of the multiple regions based on their respective prediction information includes: Based on the predicted grid load, predicted electricity price, and weather forecast information of the corresponding regions during the prediction period, an energy information prediction model is used to obtain the predicted energy demand and predicted energy consumption of each of the multiple regions. The energy information prediction model is obtained through machine learning algorithms based on the grid load, electricity price, weather forecast information, energy demand, and energy consumption of each of the multiple historical periods.

5. The method according to claim 2, characterized in that, Based on the predicted unit energy consumption, the predicted electricity demand and predicted electricity consumption of each of the multiple regions, a multi-factor objective function is constructed, including: Based on the predicted unit energy consumption, the predicted power demand and predicted power consumption of each of the multiple regions, a charging cost function, a charging convenience function, and a regional power balance function are constructed. Based on the charging cost function, the charging convenience function, and the regional power balance function, the multi-factor objective function is constructed.

6. The method according to claim 5, characterized in that, Based on the predicted unit energy consumption, the predicted electricity demand and predicted electricity consumption of each of the multiple regions, a charging cost function, a charging convenience function, and a regional power balance function are constructed, including: The charging cost function is constructed as follows: CD = CDE × DED + LCJ × W × PR; Wherein, CD is the charging cost of the electric vehicle in the predicted period when any charging scheduling scheme is adopted, CDE is the total charging energy of the electric vehicle when any charging scheduling scheme is adopted, DED is the predicted charging electricity price of the area where the electric vehicle is charged when any charging scheduling scheme is adopted, LCJ is the distance from the location of the electric vehicle to the charging pile in any charging scheduling scheme, W is the predicted unit energy consumption, and PR is the historical charging electricity price of the area where the electric vehicle is charged when the last charging behavior occurred. The charging convenience function is constructed as follows: BL = SC + LC; Wherein, BL is the charging convenience of the electric vehicle when any of the charging scheduling schemes is adopted, SC is the total charging time of the electric vehicle when any of the charging scheduling schemes is adopted, and LC is the total travel time from the location of the electric vehicle to the charging pile in any of the charging scheduling schemes. The regional power balance function is constructed as follows: Wherein, PH represents the regional power balance when any of the above charging scheduling schemes is adopted, and GY i For the power supply of the i-th region when any of the above charging scheduling schemes are adopted, XY i The predicted energy consumption of the i-th region when any of the charging scheduling schemes is adopted is given, where i is the identifier of any one of the multiple regions and n is the total number of the multiple regions; wherein, the predicted energy consumption is obtained based on the charging amount of the electric vehicle and the predicted energy demand of the i-th region when any charging scheduling scheme is implemented.

7. The method according to claim 5, characterized in that, The multi-factor objective function is constructed based on the charging cost function, the charging convenience function, and the regional power balance function, including: The multi-factor objective function is constructed as follows: DMB = PH × (k1 × CD + k2 × BL); Wherein, DMB is the function value of the multi-factor objective function when any charging scheduling scheme is adopted, k1 is a preset first weighting coefficient used to adjust the charging cost, and k2 is a preset second weighting coefficient used to adjust the charging convenience.

8. The method according to any one of claims 1 to 7, characterized in that, The step of optimizing the charging schedule of the electric vehicle based on the optimization objective to obtain the target charging schedule scheme for the electric vehicle includes: The constraint condition is defined as follows: the result of multiplying the driving distance of the electric vehicle to the charging location by the predicted unit energy consumption by a predetermined multiple is less than the remaining battery power of the electric vehicle at the departure time, where the departure time is the time when the electric vehicle departs for the charging location, and the predicted unit energy consumption represents the amount of energy consumed by the electric vehicle per unit distance during the predicted period. Based on the optimization objective and the constraints, the target charging scheduling scheme is determined from multiple candidate charging scheduling schemes.

9. The method according to claim 8, characterized in that, Given that the optimization objective is to minimize the function value of the multi-factor objective function, the step of determining the target charging scheduling scheme from multiple candidate charging scheduling schemes based on the optimization objective and the constraints includes: From the multiple candidate charging scheduling schemes, the one that satisfies the constraints and has the smallest function value of the multi-factor objective function is selected as the first charging scheduling scheme. From other candidate charging scheduling schemes, the one that satisfies the constraints and has the smallest function value of the multi-factor objective function is selected as the second charging scheduling scheme. The other candidate charging scheduling schemes are the charging scheduling schemes other than the first charging scheduling scheme among the multiple candidate charging scheduling schemes. The target charging scheduling scheme includes the first charging scheduling scheme and the second charging scheduling scheme.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the electric vehicle charging scheduling method according to any one of claims 1 to 9.

Images