Vehicle charging and discharging scheduling method, device and equipment

Abstract

The application relates to the technical field of charging control, in particular to a vehicle charging and discharging scheduling method, device and equipment. The method comprises the following steps: acquiring operation data, vehicle use data and battery data of a power grid; predicting a charging and discharging interval of the battery according to the battery data; predicting travel data of a user at a future time according to the vehicle use data; generating a target instruction according to the operation data, the travel data and the charging and discharging interval, wherein the target instruction comprises one of a charging instruction and a discharging instruction of a charging and discharging facility; controlling the charging and discharging facility to charge a target vehicle according to the charging instruction; and controlling the charging and discharging facility to provide electric energy of the target vehicle to the power grid according to the discharging instruction. Therefore, the problems of poor user experience of vehicle charging and discharging and poor battery loss control are solved.

Description

Technical Field

[0001] This application relates to the field of charging control technology, and in particular to a method, apparatus and equipment for vehicle charging and discharging scheduling. Background Technology

[0002] When implementing V2G (Vehicle-to-Grid) charging and discharging scheduling solutions, simply controlling battery charging and discharging behavior based on fixed energy thresholds makes it difficult to consider the long-term lifespan of the battery. Furthermore, the scheduling strategy fails to anticipate users' future travel needs, easily leading to situations where vehicle battery power cannot meet travel demands, resulting in a poor overall user experience and limited flexibility in matching real-time grid load changes, thus limiting the effectiveness of grid peak-valley regulation. Summary of the Invention

[0003] This application provides a vehicle charging and discharging scheduling method, device, and equipment to solve problems such as poor user experience during vehicle charging and discharging and poor battery loss control.

[0004] The first aspect of this application provides a vehicle charging and discharging scheduling method, comprising the following steps: acquiring grid operation data, vehicle usage data, and battery data; predicting the target charging and discharging range of the battery based on the battery data; predicting the user's travel data for future times based on the vehicle usage data; generating a target instruction based on the operation data, travel data, and charging and discharging range, the target instruction including either a charging instruction or a discharging instruction from the discharging facility; controlling the charging and discharging facility to charge the target vehicle based on the charging instruction; and controlling the charging and discharging facility to supply the target vehicle's electrical energy to the grid based on the discharging instruction.

[0005] Based on the aforementioned technical means, this application embodiment integrates three types of data—grid, vehicle, and battery—to achieve integrated charging and discharging scheduling. By defining suitable charging and discharging intervals based on battery-related data, reasonable charging and discharging power and capacity ranges can be limited, reducing losses caused by improper charging and discharging and better protecting the battery. By using vehicle data to predict users' future travel plans, sufficient power can be reserved for travel when formulating scheduling schemes, avoiding power shortages and improving the daily driving experience. By comprehensively generating corresponding charging and discharging instructions based on the three types of information, vehicle charging and discharging behavior can be flexibly adjusted according to grid load and electricity prices, alleviating peak-valley differences in the grid and increasing the economic benefits for car owners participating in vehicle-grid interaction.

[0006] Optionally, predicting the target charge / discharge range of the battery based on battery data includes: inputting battery data into a pre-established battery aging model, and outputting the minimum allowable discharge SOC (State of Charge), the maximum allowable charging SOC, and the maximum charge / discharge power through the battery aging model to generate the target charge / discharge range of the battery.

[0007] Based on the aforementioned technical means, this application embodiment relies on a pre-built battery aging model to calculate battery data, comprehensively outputting upper and lower limits of charge capacity and power limits to accurately define the charging and discharging range suitable for the current battery state. This method no longer relies on a fixed threshold to simply limit charging and discharging behavior, but can dynamically adjust the charging and discharging boundaries based on the actual aging degree of the battery, effectively avoiding conditions that damage the battery such as overcharging, over-discharging, and high-power charging and discharging, thus delaying battery degradation in the long term, better maintaining the battery's health, and extending its service life.

[0008] Optionally, predicting future user travel data based on user vehicle usage data includes: inputting user vehicle usage data into a pre-trained user travel prediction model, and outputting future travel time, mileage, and parking duration through the user travel prediction model.

[0009] Based on the aforementioned technical means, this application embodiment uses a trained travel prediction model to process vehicle usage data, accurately outputting the user's subsequent travel time, mileage, and parking duration, fully restoring the user's actual vehicle usage patterns. By formulating scheduling plans based on quantified travel-related parameters, it can accurately match vehicle battery demand, avoiding situations where insufficient prediction leads to battery shortages or excessive discharge damaging the battery. This balances the owner's daily travel needs with battery protection, improving the fit of vehicle-to-grid scheduling and enhancing the user's driving experience.

[0010] Optionally, before inputting user vehicle usage data into a pre-trained user travel prediction model, the method further includes at least one process: data cleaning, normalization, and feature extraction of the user vehicle usage data.

[0011] Based on the aforementioned technical means, this application embodiment pre-processes vehicle usage data through cleaning, normalization, and feature extraction before the trip prediction model is calculated. This process removes invalid and disorderly data, standardizes data, and extracts effective vehicle usage features. After the pre-processed data is input into the model, the prediction bias caused by noisy data can be significantly reduced, making the prediction results for travel time, mileage, etc., more accurate and reliable. This data can then be used as a basis for planning charging and discharging schedules, further improving the rationality of scheduling.

[0012] Optionally, the target instruction is generated based on the operation data, travel data, and charging / discharging range, including: generating a first charging / discharging constraint based on the travel data; generating a second charging / discharging constraint based on the charging / discharging range; and generating the target instruction based on the operation data, the first charging / discharging constraint, and the second charging / discharging constraint.

[0013] Based on the aforementioned technical means, this application embodiment transforms travel demand and battery status into two types of charging and discharging constraints, and then combines these with the grid operation status to generate unified charging and discharging commands. These two types of constraints respectively lock in the vehicle's power demand and the battery's safe operating boundary, preventing any scheduling situations that would encroach on travel power or damage the battery. Simultaneously, the command generation closely matches the real-time grid operating conditions, allowing bidirectional power interaction between the vehicle and the grid to take into account the needs of user use, battery protection, and grid regulation, resulting in a more stable and adaptable overall scheduling system.

[0014] Optionally, the first charge / discharge constraint includes charge / discharge time constraint and charge / discharge capacity constraint, and the second charge / discharge constraint includes charge / discharge depth constraint and charge / discharge power constraint.

[0015] Based on the aforementioned technical means, this application's embodiments define two categories of refined constraints: time and power constraints to align with user travel plans, and depth and power constraints to safeguard the battery's safe operating range. Each constraint has clear and well-defined boundaries, allowing for comprehensive limitation when generating charge / discharge commands. The scheduling process will not arbitrarily change the charging / discharge time period, power, or capacity, thus stably meeting daily driving needs while continuously avoiding various charging / discharge conditions that could damage the battery, resulting in more refined overall scheduling and control.

[0016] Optionally, generating a target instruction based on operational data, a first charge-discharge constraint, and a second charge-discharge constraint includes: constructing an objective function based on user benefits and the peak-valley difference in the power grid; using the first charge-discharge constraint and the second charge-discharge constraint as constraints of the objective function, solving the objective function based on operational data to obtain the target instruction.

[0017] Based on the aforementioned technical means, this application embodiment constructs an objective function around user benefits and the peak-valley difference in the power grid, uses two types of charging and discharging constraints as the solution boundary, and calculates the final charging and discharging command based on power grid operation data. The entire solution process takes dual needs as the optimization direction, while being constrained by travel and battery-related conditions. The final output scheduling command can both reduce the peak-valley difference in power grid load and improve the economic benefits for car owners participating in bidirectional charging and discharging. The scheduling scheme takes into account both the power grid operation needs and the user's vital interests.

[0018] Optionally, vehicle usage data includes user-entered travel plans and vehicle historical driving data; battery data includes battery SOC, battery temperature, and historical charge and discharge data; and grid operation data includes grid load, time-of-use pricing, and demand response signals.

[0019] Based on the aforementioned technical means, this application embodiment comprehensively collects multi-dimensional raw information from travel, battery, and power grid. The various data cover user driving habits, real-time battery operating conditions, and dynamic power grid operation status, with complete and abundant information sources. Relying on diverse basic data for subsequent calculations and scheduling planning can fully align with actual user driving scenarios, battery health status, and real-time power grid control needs, effectively reducing scheduling deviations caused by single data sources and making the final generated charging and discharging commands more adaptable.

[0020] A second aspect of this application provides a vehicle charging and discharging scheduling device, comprising: an acquisition module for acquiring grid operation data, vehicle usage data, and battery data; a first prediction module for predicting the battery charging and discharging range based on the battery data; a second prediction module for predicting user travel data for future times based on the vehicle usage data; and a control module for generating a target instruction based on the operation data, travel data, and charging and discharging range, the target instruction including either a charging instruction or a discharging instruction from a discharging facility, controlling the charging and discharging facility to charge the target vehicle according to the charging instruction, and controlling the charging and discharging facility to supply the target vehicle's electrical energy to the grid according to the discharging instruction.

[0021] Optionally, the first prediction module is further used to: input battery data into a pre-established battery aging model, and output the minimum allowable discharge SOC, the maximum allowable charge SOC, and the maximum charge and discharge power through the battery aging model to generate the target charge and discharge range of the battery.

[0022] Optionally, the second prediction module is further used to: input user vehicle usage data into a pre-trained user travel prediction model, and output the travel time, mileage, and parking duration for future times through the user travel prediction model.

[0023] Optionally, it also includes: a processing module for performing at least one of the following processes on the user vehicle data: data cleaning, normalization, and feature extraction, before inputting the user vehicle data into the pre-trained user travel prediction model.

[0024] Optionally, the control module is further configured to: generate a first charge / discharge constraint based on travel data; generate a second charge / discharge constraint based on the charge / discharge interval; and generate a target instruction based on the operating data, the first charge / discharge constraint, and the second charge / discharge constraint.

[0025] Optionally, the first charge / discharge constraint includes charge / discharge time constraint and charge / discharge capacity constraint, and the second charge / discharge constraint includes charge / discharge depth constraint and charge / discharge power constraint.

[0026] Optionally, the control module is further configured to: construct an objective function based on user benefits and the peak-valley difference of the power grid; and solve the objective function based on the operating data, using the first charging and discharging constraint and the second charging and discharging constraint as constraints of the objective function, to obtain the target instruction.

[0027] Optionally, vehicle usage data includes user-entered travel plans and vehicle historical driving data; battery data includes battery SOC, battery temperature, and historical charge and discharge data; and grid operation data includes grid load, time-of-use pricing, and demand response signals.

[0028] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the vehicle charging and discharging scheduling method as described in the above embodiments.

[0029] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0030] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a vehicle charging and discharging scheduling method according to an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a bidirectional intelligent charging and discharging system for electric vehicles provided according to an embodiment of this application; Figure 3 This is a flowchart of a bidirectional intelligent charging and discharging method for electric vehicles provided according to an embodiment of this application; Figure 4 This is a block diagram of a vehicle charging and discharging scheduling device according to an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0031] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0032] Currently, bidirectional charging and discharging technology for vehicles is widely used in grid load regulation and vehicle-to-grid energy interaction scenarios. However, these technologies suffer from the following shortcomings in practical applications: Most charging and discharging schemes only base their plans on grid demand, neglecting user travel needs and driving habits. This can easily lead to insufficient vehicle battery power, disrupting normal user travel and significantly reducing user participation in vehicle-grid interaction. Furthermore, the accuracy of predicting user travel behavior is low, making it difficult to accurately determine user charging duration, charging amount, and travel needs, resulting in poor execution of charging and discharging plans. There is a lack of effective dynamic scheduling and adjustment mechanisms, making it impossible to adapt and adjust charging and discharging strategies in a timely manner to sudden changes in user behavior or emergency grid conditions. Finally, insufficient consideration of battery health status and unreasonable charging and discharging depths and frequencies can continuously accelerate battery aging and shorten overall battery lifespan. In summary, these charging and discharging scheduling schemes suffer from poor adaptability, insufficient flexibility, and weak battery protection, making it difficult to simultaneously meet the multiple application requirements of grid scheduling, user experience, and battery life protection.

[0033] The following description, with reference to the accompanying drawings, outlines a vehicle charging and discharging scheduling method, apparatus, and device according to embodiments of this application. Addressing the issues of poor user experience and inadequate battery loss control during vehicle charging and discharging mentioned in the background section, this application provides a bidirectional intelligent charging and discharging scheduling method for electric vehicles based on user behavior prediction and grid peak-valley regulation. This method relies on a complete interactive system comprised of user terminals, vehicle terminals, a cloud platform, a grid dispatch center, and bidirectional charging and discharging facilities to conduct the scheduling work.

[0034] The user terminal allows users to input travel plans, view charging and discharging status and revenue data. The vehicle terminal continuously collects vehicle location, battery parameters, driving and historical charging and discharging information. The power grid dispatch center pushes relevant signals on power grid load, time-of-use pricing, and demand response to the cloud platform. The cloud platform has four functional modules: a user behavior prediction module that uses an LSTM (Long Short-Term Memory) neural network combined with historical vehicle usage data to predict travel information for the next 24 to 72 hours; a battery health management module that calculates appropriate charging and discharging depth and power limits; a power grid interaction module that completes data exchange with the dispatch center; and an intelligent charging and discharging scheduling module that integrates multi-dimensional information to generate charging and discharging plans and can dynamically adjust them in real time. Finally, the bidirectional charging and discharging facilities execute the bidirectional power flow instructions. This solves the problem that related technologies struggle to balance user travel experience, long-term battery protection, and power grid load balancing in charging and discharging scheduling.

[0035] Specifically, Figure 1 This is a flowchart of a vehicle charging and discharging scheduling method provided in an embodiment of this application.

[0036] like Figure 1 As shown, the vehicle charging and discharging scheduling method includes the following steps: In step S101, the power grid operation data, vehicle usage data, and battery data are acquired.

[0037] It is understood that the embodiments of this application simultaneously collect data from three different dimensions: power grid operating conditions, user vehicle usage, and power battery. This allows for a complete understanding of the power grid's operating status, users' daily vehicle usage patterns, and the real-time operating conditions of the battery. Sufficient and comprehensive basic data can provide a reliable basis for subsequent travel calculations, delineation of charging and discharging boundaries, and formulation of dispatch instructions, thus avoiding the deviation of the dispatch plan from the actual usage scenario due to incomplete data.

[0038] Specifically, such as Figure 2 , Figure 3 As shown, this application collects three types of data: vehicle data and battery data collected by the vehicle terminal, vehicle-related plans entered by the user terminal, and power grid information from the power grid dispatch center. Among them, vehicle data includes user-entered travel plans and historical vehicle driving data; battery data includes battery SOC, battery temperature, and historical charge and discharge data; and power grid operation data includes power grid load, time-of-use electricity price, and demand response signals. The complete collection of multi-dimensional raw data supports subsequent full-process calculations.

[0039] In step S102, the target charge / discharge range of the battery is predicted based on the battery data.

[0040] It is understood that the embodiments of this application define a dedicated charging and discharging range based on the collected battery parameters, limit the upper and lower limits of the battery's allowable capacity and the maximum charging and discharging power, avoid working modes that damage the battery cells such as overcharging, over-discharging, and high-power charging and discharging, dynamically control the charging and discharging range according to the battery's own aging state, continuously slow down the battery's degradation rate, and effectively extend the service life of the power battery.

[0041] It should be noted that the target charge / discharge range is a safe operating range for the battery calculated based on its current health status and aging level. It includes a charge threshold and a power limit and is used to constrain all charge and discharge behaviors of the battery to prevent unreasonable charge and discharge from damaging the battery cells.

[0042] Specifically, such as Figure 3 As shown in the battery health assessment stage, this application retrieves battery SOC, temperature, and historical charge and discharge data, and dynamically calculates the safe operating range based on the battery aging state to obtain the target charge and discharge range suitable for the current battery operating conditions.

[0043] In this embodiment of the application, predicting the target charge-discharge range of the battery based on battery data includes: inputting the battery data into a pre-established battery aging model, and outputting the minimum allowable discharge SOC, the maximum allowable charge SOC, and the maximum charge-discharge power through the battery aging model to generate the target charge-discharge range of the battery.

[0044] It is understood that the embodiments of this application rely on a pre-built battery aging model to calculate battery data, and comprehensively output upper and lower limits of charge capacity and power limits to accurately define the charging and discharging range suitable for the current battery state. This method no longer relies on a fixed threshold to simply limit charging and discharging behavior, but can dynamically adjust the charging and discharging boundaries based on the actual aging degree of the battery, effectively avoiding conditions that damage the battery such as overcharging, over-discharging, and high-power charging and discharging, thus delaying battery degradation in the long term, better maintaining the battery's health, and extending the battery's service life.

[0045] It should be noted that the battery aging model is a pre-built computational model that can extrapolate the degree of battery aging based on real-time battery status data and historical charge and discharge data; the minimum allowable discharge SOC is the lower limit of the battery's safe discharge capacity; the maximum allowable charging SOC is the upper limit of the battery's safe charging capacity; and the maximum charge and discharge power is the upper limit of the maximum charging and discharging power that the battery can withstand under the current state. The above three parameters together constitute the core limiting parameters of the target charge and discharge range.

[0046] Specifically, such as Figure 3 As shown, the battery's current SOC, temperature, historical charge / discharge cycles, and charge / discharge depth data are imported into the battery aging model. The model calculates and outputs three parameters: minimum allowable discharge SOC, maximum allowable charging SOC, and maximum charge / discharge power. These three parameters are then integrated to determine the battery's complete safe charge / discharge range, i.e., the target charge / discharge range.

[0047] In step S103, the user's travel data for the future is predicted based on the vehicle usage data.

[0048] It is understood that this application embodiment relies on the user's historical vehicle usage information and customized travel plans to calculate the user's subsequent travel time, mileage, and parking duration, accurately grasping the user's vehicle usage needs. When formulating subsequent charging and discharging plans, the necessary power for travel can be reserved in advance, preventing power shortages due to excessive vehicle power dissipation, and effectively optimizing the daily driving experience for car owners.

[0049] It should be noted that "future time" refers to the time span predicted by the user travel prediction model, specifically the interval between the next 24 and 72 hours.

[0050] Specifically, such as Figure 3 As shown in the user behavior prediction stage, this application uses two types of vehicle usage data—user-entered travel plans and vehicle historical driving data—combined with external characteristics such as weather and holidays, to predict user travel-related information for the next 24 to 72 hours, obtaining travel data such as travel time, mileage, and parking duration.

[0051] In this embodiment of the application, predicting the user's travel data in the future based on the user's vehicle usage data includes: inputting the user's vehicle usage data into a pre-trained user travel prediction model, and outputting the travel time, mileage and parking duration in the future through the user travel prediction model.

[0052] It is understood that the embodiments of this application use a trained travel prediction model to process vehicle usage data, accurately outputting the user's subsequent travel time, mileage, and parking duration, fully restoring the user's actual vehicle usage patterns. Based on quantified travel-related parameters, a scheduling plan can be formulated to accurately match vehicle battery demand, avoiding situations where insufficient prediction leads to battery shortages or excessive discharge damaging the battery. This balances the owner's daily travel needs with battery protection, improving the fit of vehicle-to-grid scheduling and enhancing the user's driving experience.

[0053] It should be noted that the user travel prediction model is a prediction model built and pre-trained based on an improved LSTM neural network. The model incorporates an attention mechanism and external features to analyze vehicle usage data and output user travel demand parameters.

[0054] Specifically, this application imports the preprocessed vehicle usage data into a user travel prediction model composed of an improved LSTM neural network. After the model is computed, it outputs three types of travel data for the next 24 to 72 hours: travel time, mileage, and parking duration.

[0055] In this embodiment of the application, before inputting user vehicle data into the pre-trained user travel prediction model, the method further includes at least one process of data cleaning, normalization, and feature extraction of the user vehicle data.

[0056] It is understood that, before the trip prediction model is calculated, the vehicle usage data in this embodiment is pre-cleaned, normalized, and feature extracted to remove invalid and messy data, unify data standards, and extract effective vehicle usage features. After the pre-processed data is input into the model, the prediction bias caused by noisy data can be significantly reduced, making the prediction results such as travel time and mileage more accurate and reliable. Subsequent planning of charging and discharging arrangements is based on this, further improving the rationality of scheduling.

[0057] Specifically, such as Figure 3 As shown, before inputting user vehicle usage data into the improved LSTM neural network user travel prediction model, at least one of the following preprocessing operations—data cleaning, normalization, and feature extraction—is performed on the collected raw vehicle usage data to remove invalid and messy data, unify data standards, and extract effective vehicle usage features, thereby ensuring the model's prediction accuracy.

[0058] In step S104, a target instruction is generated based on the operating data, travel data, and charging / discharging interval. The target instruction includes either a charging instruction or a discharging instruction from the discharging facility. The charging / discharging facility is controlled to charge the target vehicle based on the charging instruction, and the charging / discharging facility is controlled to supply the target vehicle's electrical energy to the power grid based on the discharging instruction.

[0059] It is understood that the embodiments of this application integrate the three conditions of real-time grid status, user travel constraints, and battery safety boundaries to generate charging and discharging instructions in a unified manner. This allows for flexible scheduling of vehicle charging and reverse power supply during peak and off-peak hours of the grid, which can not only smooth grid load fluctuations and improve grid operation stability, but also allow car owners to obtain corresponding benefits by taking advantage of electricity price differences, ultimately achieving a balance between the needs of the grid, users, and power batteries.

[0060] It should be noted that the target instruction is a scheduling instruction generated by the cloud platform's intelligent charging and discharging scheduling module, which can be either a charging instruction or a discharging instruction, and is used to send it to the bidirectional charging and discharging facility to perform power interaction; the target vehicle is an electric vehicle equipped with an on-board terminal that participates in V2G bidirectional charging and discharging scheduling.

[0061] Specifically, such as Figure 2 As shown in the system architecture, the cloud platform integrates grid operation data issued by the power grid dispatch center, travel data obtained from user travel predictions, and charging / discharging intervals output by the battery health management module to generate target instructions. When a charging instruction is issued, the bidirectional charging / discharging facility replenishes the target vehicle's power. When a discharging instruction is issued, the system controls the target vehicle's power battery to supply power to the grid.

[0062] In this embodiment of the application, generating a target instruction based on operating data, travel data, and a charging / discharging range includes: generating a first charging / discharging constraint based on the travel data; generating a second charging / discharging constraint based on the charging / discharging range; and generating a target instruction based on the operating data, the first charging / discharging constraint, and the second charging / discharging constraint.

[0063] It is understood that the embodiments of this application convert travel demand and battery status into two types of charging and discharging constraints, and then combine them with the grid operation status to generate unified charging and discharging instructions. The two types of constraints respectively lock in the vehicle's power demand and the battery's safe operation boundary, so that there will be no scheduling situation that encroaches on travel power or damages the battery. At the same time, the instruction generation is in line with the real-time operating conditions of the grid, so that the two-way power interaction of the vehicle takes into account the needs of user use, battery protection and grid regulation, and the overall scheduling is more stable and adaptable.

[0064] It should be noted that the first charge / discharge constraint is a constraint built based on user travel data, and its function is to ensure the power needs of users during normal travel; the second charge / discharge constraint is a constraint built based on the target charge / discharge range of the battery, and its function is to limit the safe charge / discharge operating range of the battery.

[0065] Specifically, this application transforms user travel prediction results into a first charge / discharge constraint and the battery safe charge / discharge range into a second charge / discharge constraint. Using these two types of constraints as boundary conditions, the application combines real-time grid operation data to calculate and solve the problem, and finally outputs the corresponding target charge / discharge command.

[0066] In the embodiments of this application, the first charge-discharge constraint includes charge-discharge time constraint and charge-discharge capacity constraint, and the second charge-discharge constraint includes charge-discharge depth constraint and charge-discharge power constraint.

[0067] It is understandable that the embodiments of this application define two types of refined constraints: time and power constraints to fit users' travel plans, and depth and power constraints to safeguard the battery's safe operating range. The boundaries of each constraint are clear and well-defined, allowing for comprehensive limitation when generating charge and discharge instructions. The scheduling process will not arbitrarily change the charging and discharging time, power, or capacity, thus stably meeting daily driving needs while continuously avoiding various charging and discharging conditions that could damage the battery, resulting in more refined overall scheduling and control.

[0068] It should be noted that time constraint and power constraint are the sub-parameters of the first charge and discharge constraint, which respectively limit the execution time period of charge and discharge and the total charge and discharge capacity; depth constraint and power constraint are the sub-parameters of the second charge and discharge constraint, which respectively limit the depth of battery charge and discharge and the upper limit of real-time charge and discharge power.

[0069] Specifically, the first charge and discharge constraint is broken down into two parts: charge and discharge time constraint and charge and discharge capacity constraint, which match the user's travel plan; the second charge and discharge constraint is broken down into two parts: charge and discharge depth constraint and charge and discharge power constraint, which match the battery's safe charge and discharge range.

[0070] In this embodiment of the application, generating a target instruction based on operating data, a first charging and discharging constraint, and a second charging and discharging constraint includes: constructing a target function based on user benefits and the peak-valley difference of the power grid; using the first charging and discharging constraint and the second charging and discharging constraint as constraints of the target function, solving the target function based on the operating data to obtain the target instruction.

[0071] It is understandable that the embodiments of this application construct an objective function around user benefits and the peak-valley difference of the power grid, use two types of charging and discharging constraints as the solution boundary, and calculate the final charging and discharging command based on power grid operation data. The entire solution process takes dual needs as the optimization direction, and is also subject to travel and battery-related conditions. The final output scheduling command can both reduce the peak-valley difference of the power grid load and improve the economic benefits of car owners participating in bidirectional charging and discharging. The scheduling scheme takes into account both the power grid operation needs and the vital interests of users.

[0072] It should be noted that the objective function is a bi-objective optimization function that simultaneously pursues maximizing user revenue and minimizing the peak-valley difference in the power grid; the constraints of the objective function are the boundary conditions that must be followed during the solution of the optimization function, namely the first charge-discharge constraint and the second charge-discharge constraint.

[0073] Specifically, such as Figure 3 As shown in the charge / discharge plan generation stage, this application constructs a dual objective function: maxF = α × (charging cost savings + discharge benefit) - β × battery aging cost minΔP=P_max-P_min Where α and β are weighting coefficients, P_max is the maximum load during peak hours, and P_min is the minimum load during off-peak hours. The first and second charge / discharge constraints are used as the boundary conditions for solving the objective function. Combined with grid operation data, an improved particle swarm optimization algorithm is employed to solve the objective function, calculating the optimal charge / discharge plan and generating the corresponding target instructions.

[0074] In this embodiment of the application, the vehicle data includes user-entered travel plans and vehicle historical driving data; the battery data includes battery SOC, battery temperature, and historical charge and discharge data; and the power grid operation data includes power grid load, time-of-use electricity price, and demand response signals.

[0075] It is understood that the embodiments of this application comprehensively collect multi-dimensional raw information on travel, battery, and power grid. Various types of data cover user driving habits, real-time battery operating conditions, and dynamic power grid operating status, with complete and rich information sources. Relying on diverse basic data to carry out subsequent calculations and scheduling plans can fully match the user's actual driving scenarios, battery health status, and real-time power grid control needs, effectively reducing scheduling deviations caused by single data points, and making the final generated charging and discharging commands more adaptable.

[0076] Specifically, such as Figure 2 , Figure 3 As shown in the data collection phase: vehicle data consists of travel plans entered by users and historical vehicle driving data uploaded by vehicle terminals; battery data consists of battery SOC, battery temperature, and historical charge and discharge data collected by vehicle terminals; and grid operation data consists of grid load, time-of-use pricing, and demand response signals issued by the grid dispatch center. All three types of data are uploaded to the cloud platform for aggregation, supporting subsequent prediction, constraint construction, and instruction solving.

[0077] The vehicle charging and discharging scheduling method proposed in this application integrates data from the power grid, vehicle usage, and battery to achieve unified charging and discharging scheduling. By defining suitable charging and discharging intervals based on battery-related data, reasonable charging and discharging power and capacity ranges can be limited, reducing losses caused by improper charging and discharging and better protecting the battery. By using vehicle usage data to predict users' future travel plans, sufficient power can be reserved for travel when formulating scheduling plans, avoiding power shortages and improving the daily driving experience. By comprehensively generating corresponding charging and discharging instructions based on the three types of information, vehicle charging and discharging behavior can be flexibly adjusted according to power grid load and electricity prices, alleviating peak-valley differences in the power grid and increasing the economic benefits for car owners participating in vehicle-grid interaction.

[0078] Next, the vehicle charging and discharging scheduling device according to the embodiments of this application is described with reference to the accompanying drawings.

[0079] Figure 4 This is a block diagram of a vehicle charging and discharging scheduling device according to an embodiment of this application.

[0080] like Figure 4 As shown, the vehicle charging and discharging scheduling device 40 includes: an acquisition module 401, a first prediction module 402, a second prediction module 403, and a control module 404.

[0081] The system includes: an acquisition module 401 for acquiring grid operation data, vehicle usage data, and battery data; a first prediction module 402 for predicting the battery's charge / discharge range based on the battery data; a second prediction module 403 for predicting future user travel data based on the vehicle usage data; and a control module 404 for generating target instructions based on the operation data, travel data, and charge / discharge range. The target instructions include either a charging instruction or a discharging instruction from the discharge facility. The charging instruction controls the charging / discharging facility to charge the target vehicle, and the discharging instruction controls the charging / discharging facility to supply the target vehicle's electrical energy to the grid.

[0082] In this embodiment of the application, the first prediction module 402 is further used to: input battery data into a pre-established battery aging model, and output the minimum allowable discharge SOC, the maximum allowable charge SOC and the maximum charge and discharge power through the battery aging model to generate the target charge and discharge range of the battery.

[0083] In this embodiment of the application, the second prediction module 403 is further used to: input user vehicle data into a pre-trained user travel prediction model, and output the travel time, mileage and parking time for future times through the user travel prediction model.

[0084] In this embodiment of the application, the apparatus 40 further includes a processing module.

[0085] The processing module is used to perform at least one of the following processes on the user vehicle data before inputting it into the pre-trained user travel prediction model: data cleaning, normalization, and feature extraction.

[0086] In this embodiment, the control module 404 is further configured to: generate a first charge / discharge constraint based on travel data; generate a second charge / discharge constraint based on the charge / discharge interval; and generate a target instruction based on the operating data, the first charge / discharge constraint, and the second charge / discharge constraint.

[0087] In the embodiments of this application, the first charge-discharge constraint includes charge-discharge time constraint and charge-discharge capacity constraint, and the second charge-discharge constraint includes charge-discharge depth constraint and charge-discharge power constraint.

[0088] In this embodiment, the control module 404 is further configured to: construct an objective function based on user benefits and the peak-valley difference of the power grid; and solve the objective function based on the operating data, using the first charging and discharging constraint and the second charging and discharging constraint as constraints of the objective function, to obtain the target instruction.

[0089] In this embodiment of the application, the vehicle data includes user-entered travel plans and vehicle historical driving data; the battery data includes battery SOC, battery temperature, and historical charge and discharge data; and the power grid operation data includes power grid load, time-of-use electricity price, and demand response signals.

[0090] It should be noted that the foregoing explanation of the vehicle charging and discharging scheduling method embodiment also applies to the vehicle charging and discharging scheduling device of this embodiment, and will not be repeated here.

[0091] The vehicle charging and discharging scheduling device proposed in this application integrates data from the power grid, vehicle usage, and battery to achieve unified charging and discharging scheduling. By defining suitable charging and discharging intervals based on battery-related data, it can limit reasonable charging and discharging power and capacity ranges, reducing losses caused by improper charging and discharging and better protecting the battery. By using vehicle usage data to predict users' future travel plans, it prioritizes reserving sufficient power for travel when formulating scheduling plans, avoiding power shortages and improving the daily driving experience. By comprehensively generating corresponding charging and discharging instructions based on the three types of information, it can flexibly adjust vehicle charging and discharging behavior according to power grid load and electricity prices, alleviating peak-valley differences in the power grid and increasing the economic benefits for car owners participating in vehicle-grid interaction.

[0092] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0093] When the processor 502 executes the program, it implements the vehicle charging and discharging scheduling method provided in the above embodiments.

[0094] Furthermore, electronic devices also include: Communication interface 503 is used for communication between memory 501 and processor 502.

[0095] The memory 501 is used to store computer programs that can run on the processor 502.

[0096] The memory 501 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0097] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0098] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0099] The processor 502 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of this application.

[0100] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0101] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0102] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0103] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0104] Those skilled in the art will understand that all or part of the steps of the methods implementing the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0105] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A vehicle charging and discharging scheduling method, characterized in that, Includes the following steps: Acquire power grid operation data, vehicle usage data, and battery data; Predict the target charge / discharge range of the battery based on the battery data; Predict future user travel data based on the aforementioned vehicle usage data; Based on the operational data, the travel data, and the charging / discharging interval, a target instruction is generated. The target instruction includes either a charging instruction or a discharging instruction from the discharging facility. The charging / discharging facility is controlled to charge the target vehicle according to the charging instruction, and the charging / discharging facility is controlled to supply the target vehicle's electrical energy to the power grid according to the discharging instruction.

2. The vehicle charging and discharging scheduling method according to claim 1, characterized in that, The step of predicting the target charge / discharge range of the battery based on the battery data includes: The battery data is input into a pre-established battery aging model, which outputs the minimum allowable discharge SOC, the maximum allowable charge SOC, and the maximum charge / discharge power to generate the target charge / discharge range for the battery.

3. The vehicle charging and discharging scheduling method according to claim 1, characterized in that, The step of predicting future user travel data based on the user's vehicle usage data includes: The user's vehicle usage data is input into a pre-trained user travel prediction model, which then outputs the travel time, mileage, and parking duration for future times.

4. The vehicle charging and discharging scheduling method according to claim 3, characterized in that, Before inputting the user vehicle usage data into the pre-trained user travel prediction model, the process also includes: The user vehicle data is subjected to at least one of the following processes: data cleaning, normalization, and feature extraction.

5. The vehicle charging and discharging scheduling method according to claim 1, characterized in that, The step of generating a target instruction based on the operational data, the travel data, and the charging / discharging range includes: The first charge / discharge constraint is generated based on travel data; A second charge / discharge constraint is generated based on the charge / discharge interval; The target instruction is generated based on the running data, the first charge / discharge constraint, and the second charge / discharge constraint.

6. The vehicle charging and discharging scheduling method according to claim 5, characterized in that, The first charge / discharge constraint includes charge / discharge time constraint and charge / discharge capacity constraint, and the second charge / discharge constraint includes charge / discharge depth constraint and charge / discharge power constraint.

7. The vehicle charging and discharging scheduling method according to claim 5, characterized in that, The generation of target instructions based on operational data, the first charge / discharge constraint, and the second charge / discharge constraint includes: Construct an objective function based on user benefits and the peak-valley difference in the power grid; Using the first charge / discharge constraint and the second charge / discharge constraint as the objective function, the objective function is solved based on the running data to obtain the target instruction.

8. The vehicle charging and discharging scheduling method according to any one of claims 1-7, characterized in that, The vehicle usage data includes user-entered travel plans and vehicle historical driving data; the battery data includes battery SOC, battery temperature, and historical charge and discharge data; and the power grid operation data includes power grid load, time-of-use electricity price, and demand response signals.

9. A vehicle charging and discharging scheduling device, characterized in that, include: The acquisition module is used to acquire power grid operation data, vehicle usage data, and battery data. The first prediction module is used to predict the target charge / discharge range of the battery based on the battery data. The second prediction module is used to predict the user's travel data in the future based on the vehicle usage data. The control module is used to generate target instructions based on the operating data, the travel data, and the charging / discharging interval. The target instructions include one of a charging instruction and a discharging instruction from the discharging facility. The module controls the charging / discharging facility to charge the target vehicle according to the charging instruction, and controls the charging / discharging facility to supply the target vehicle's electrical energy to the power grid according to the discharging instruction.

10. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the vehicle charging and discharging scheduling method according to any one of claims 1-8.

Images