Vehicle intelligent charging control method and system, electronic equipment and storage medium

Abstract

The invention provides a vehicle intelligent charging control method and system, electronic equipment and a storage medium. The method comprises the steps that vehicle state data, environment data and operation data of a current vehicle are acquired; based on the environment data and the operation data, predicting the order demand and the charging station state of the vehicle in a future time period, and the energy consumption and the traffic condition of the vehicle running in the future time period; based on the vehicle state data, the order demand, the charging station state, the energy consumption and the traffic condition, determining an optimal charging decision, the optimal charging decision including an optimal charging opportunity and an optimal charging station; generating a power supply decision instruction based on the optimal power supply decision; and controlling the vehicle to arrive at the optimal charging station for charging at the optimal charging time based on the charging decision instruction. The vehicle is controlled to be charged based on the determined optimal charging decision. The charging cost is reduced, and the vehicle charging efficiency and the user experience are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a vehicle intelligent power supplement control method and system, an electronic device and a readable storage medium. BACKGROUND

[0002] With the maturity of automatic driving technology, automatic driving electric vehicles gradually become an important part of urban transportation. Especially in the field of automatic driving of car-hailing, taxi, logistics vehicles and other operating vehicles, the power supplement scheduling efficiency of the vehicle directly affects the operating income and resource utilization.

[0003] In related technologies, the power supplement mode of automatic driving electric vehicles depends on the experience of the driver, and the power supplement scheduling mode depends on manual judgment. Some vehicles go to charge during the peak period of orders, which may cause operating downtime and cannot accurately predict the matching relationship between vehicle endurance and order demand. Due to uneven allocation of charging station resources, some vehicles choose crowded charging stations, resulting in long waiting time of the vehicle. In addition, some vehicles may run out of power halfway due to estimation deviation of remaining power, and sudden order demand may interrupt the charging process, thereby increasing the power supplement cost of automatic driving vehicles and reducing the power supplement efficiency of automatic driving vehicles. SUMMARY

[0004] The present application provides a vehicle intelligent power supplement control method and system, an electronic device and a readable storage medium to at least solve the problem of long queuing time, increased charging cost and reduced power supplement efficiency due to the inability to accurately predict vehicle endurance time and uneven allocation of charging station resources in related technologies. The technical solutions of the present application are as follows: According to a first aspect of an embodiment of the present application, a vehicle intelligent power supplement control method is provided, comprising: obtaining vehicle state data, environment data and operation data of a current vehicle; based on the environment data and the operation data, predicting order demand, charging station state of the vehicle in a future period, and energy consumption and traffic conditions of the vehicle driving in a future time; based on the vehicle state data, the order demand, the charging station state, the energy consumption and the traffic conditions, determining an optimal power supplement decision, the optimal power supplement decision including an optimal power supplement opportunity and an optimal charging station; generating a power supplement decision instruction based on the optimal power supplement decision; controlling the vehicle to arrive at the optimal charging station for power supplement at the optimal power supplement opportunity based on the power supplement decision instruction; According to a second aspect of an embodiment of the present application, a vehicle intelligent power supplement control system is provided, comprising: An acquisition module is configured to acquire vehicle state data, environment data and operation data of a current vehicle; A prediction module is configured to predict order demand, charging station state, energy consumption and traffic condition of the vehicle in a future period based on the environment data and the operation data; A determination module is configured to determine an optimal power supplement decision based on the vehicle state data, the order demand, the charging station state, the energy consumption and the traffic condition, the optimal power supplement decision including an optimal power supplement timing and an optimal charging station; A generation module is configured to generate a power supplement decision instruction based on the optimal power supplement decision; A control module is configured to control the vehicle to reach the optimal charging station for power supplement at the optimal power supplement timing based on the power supplement decision instruction.

[0005] According to a third aspect of the embodiments of the present application, an electronic device is provided, including: The electronic device includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, and the program or instruction is executed by the processor to implement the steps of the vehicle intelligent power supplement control method.

[0006] According to a fourth aspect of the embodiments of the present application, a readable storage medium is provided, and the readable storage medium stores a program or instruction, and the program or instruction is executed by a processor of an electronic device to implement the steps of the vehicle intelligent power supplement control method.

[0007] According to a fifth aspect of the embodiments of the present application, a computer program product is provided, and the computer program product includes a computer program or instruction, and the computer program or instruction is executed by a processor of an electronic device to implement the steps of the vehicle intelligent power supplement control method.

[0008] The embodiments of the present application provide at least the following beneficial effects: In this embodiment, vehicle status data, environmental data, and operational data of the current vehicle are acquired. Based on the environmental data and operational data, the order demand, charging station status, energy consumption, and traffic conditions of the vehicle in the future are predicted. Based on the vehicle status data, order demand, charging station status, energy consumption, and traffic conditions, an optimal charging decision is determined. The optimal charging decision includes: optimal charging time and optimal charging station. A charging decision instruction is generated based on the optimal charging decision. Based on the charging decision instruction, the vehicle is controlled to arrive at the optimal charging station at the optimal charging time for charging. In other words, in this embodiment, by acquiring the vehicle status in real time and combining it with the predicted order demand and charging station resource situation in the future, the optimal charging decision is determined, and the vehicle is controlled to charge using the optimal charging decision. This effectively solves the vehicle range problem, reduces charging costs while ensuring operational efficiency, and improves vehicle charging efficiency and user experience.

[0009] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0010] The accompanying drawings, incorporated in and forming part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. They do not constitute an undue limitation of this application. To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0011] Figure 1 This is a flowchart of a vehicle intelligent power replenishment control method provided in an embodiment of this application.

[0012] Figure 2 This is a schematic diagram illustrating an optimal charging station selection method provided in an embodiment of this application.

[0013] Figure 3 This is a schematic diagram of a vehicle intelligent power replenishment decision provided in an embodiment of this application.

[0014] Figure 4 This is a block diagram of a vehicle intelligent power replenishment control system provided in an embodiment of this application.

[0015] Figure 5 This is a block diagram of a determining module provided in an embodiment of this application.

[0016] Figure 6 This is a block diagram of a power replenishment decision selection module provided in an embodiment of this application.

[0017] Figure 7 This is a hierarchical architecture block diagram of a vehicle intelligent power replenishment control system provided in an embodiment of this application.

[0018] Figure 8 This is a block diagram of an electronic device provided in an embodiment of this application.

[0019] Figure 9 This is a block diagram of a vehicle intelligent power replenishment control system provided in an embodiment of this application. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0021] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application 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 this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of systems and methods consistent with some aspects of this application as detailed in the appended claims.

[0022] Figure 1 This is a flowchart of a vehicle intelligent power replenishment control method provided in an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps: Step 101: Obtain the current vehicle status data, environmental data, and operational data.

[0023] Step 102: Based on the environmental data and the operational data, predict the order demand for the vehicle in the future, the status of charging stations, and the energy consumption and traffic conditions of the vehicle in the future.

[0024] Step 103: Based on the vehicle status data, the order demand, the charging station status, the energy consumption, and the traffic conditions, determine the optimal charging decision, which includes the optimal charging time and the optimal charging station.

[0025] Step 104: Generate a power replenishment decision instruction based on the optimal power replenishment decision.

[0026] Step 105: Based on the charging decision command, control the vehicle to arrive at the optimal charging station at the optimal charging time to charge.

[0027] In this embodiment, by acquiring vehicle status in real time and combining it with predicted order demand and charging station resource availability for future periods, the optimal charging decision is determined, and the vehicle is controlled to charge based on this optimal decision. This effectively solves the vehicle range problem, reduces charging costs while ensuring operational efficiency, and improves vehicle charging efficiency and user experience.

[0028] The intelligent vehicle power replenishment control method described in this application can be applied to vehicle-side, server-side, autonomous driving control systems, etc., without limitation. The vehicle-side implementation equipment can be an in-vehicle terminal, vehicle control platform, industrial control computer, or other electronic equipment. The server-side can be an independent server, a server cluster, or a server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, or big data and artificial intelligence platforms, etc., without limitation.

[0029] The following is combined Figure 1 The specific implementation steps of a vehicle intelligent power replenishment control method provided in the embodiments of this application will be described in detail.

[0030] In step 101, the vehicle status data, environmental data, and operational data of the current vehicle are obtained.

[0031] In this step, vehicle status data can be collected in real time through onboard sensors and the battery management system. The vehicle status data may include: the current remaining battery charge (i.e., battery SOC, State of Charge), real-time energy consumption (kWh / km), and the vehicle's current location (GPS or latitude and longitude coordinates, etc.). Of course, the vehicle status data may also include: battery health status (SOH, State of Health), battery voltage, temperature, current vehicle status (idle, carrying passengers, charging, maintenance, etc.), historical energy consumption data, remaining driving range, etc. This embodiment does not impose any limitations.

[0032] In this step, environmental data can be obtained through the charging station's cloud API. This environmental data may include: charging pile status (including the number of charging piles, type, fast charging or slow charging, number of available charging piles, etc.), real-time charging unit (i.e., real-time charging price, including peak and off-peak electricity prices), and traffic conditions (whether there is traffic congestion, etc.). Of course, this environmental data may also include the location of the charging station and the estimated queuing time (which can be predicted based on historical data and the current status).

[0033] Traffic conditions can be obtained from traffic and weather services: real-time traffic congestion and weather forecasts (temperature, precipitation, wind speed, etc., which affect vehicle energy consumption).

[0034] In this step, operational data can be obtained through the order management system. The operational data may include: order demand forecasting, which includes historical order data and real-time demand, current order distribution, and prediction of order demand in future time periods; historical operating patterns (such as which time periods are peak periods and which time periods are off-peak periods); and V2G assessment (i.e., assessment based on grid demand).

[0035] The vehicles described in this application embodiment can be applied to autonomous ride-hailing vehicles, taxis, logistics vehicles, etc., but are not limited to these. They can also be applied to other autonomous vehicles. This embodiment does not impose any restrictions.

[0036] In step 102, based on the environmental data and the operational data, the order demand for the vehicle in the future time period, the status of charging stations, and the energy consumption and traffic conditions of the vehicle in the future time period are predicted.

[0037] This step includes: 11) Preprocessing.

[0038] In this step, the environmental data and operational data are preprocessed. Preprocessing may include cleaning, denoising, and normalizing the acquired environmental and operational data, and converting the processed data into a standard format to facilitate subsequent prediction.

[0039] 12) Order demand forecasting.

[0040] In this step, based on preprocessed operational and environmental data, such as historical order patterns, real-time traffic conditions, weather conditions, holidays, and special events, order demand in the future time period (e.g., the next 24 hours) can be predicted.

[0041] Specifically, time series analysis (such as ARIMA) or machine learning models (such as LSTM) can be used to predict order demand in various regions over a future period (e.g., the next 2 hours). Alternatively, it can predict the order volume distribution, peak / off-peak hours, order origin-destination concentration, and average order mileage in the current and potential operating areas of vehicles within a preset future time period (e.g., the next 24 hours), providing support for avoiding peak order times when recharging. The specific prediction process is well-known to those skilled in the art and will not be elaborated upon here.

[0042] 13) Energy consumption prediction.

[0043] In this step, based on the vehicle's historical energy consumption data, real-time road conditions, weather conditions (temperature, wind speed, slope, etc.), and driving mode, the energy consumption of the vehicle on its future driving path is predicted. Specifically, machine learning models (such as gradient boosting trees) can be used for prediction. The specific prediction process is well-known to those skilled in the art and will not be elaborated here.

[0044] The predicted energy consumption can cover historical and real-time energy consumption data of the vehicle, including driving energy consumption, on-board equipment energy consumption, and charging loss rate under different road conditions, weather conditions, and load conditions. It can accurately calculate the energy consumption of the vehicle when going to and from the charging station and during subsequent operation.

[0045] 14) Charging station status prediction In this step, the busyness and queuing time of charging stations can be predicted over a future period. Specifically, queuing theory models or statistical models based on historical data can be used for prediction. The specific prediction process is well-known to those skilled in the art and will not be elaborated here.

[0046] The predicted charging station status can include: the real-time location of all compliant charging stations within the vehicle's preset range, the number of available charging piles, the rated charging power of the charging piles, the real-time congestion level, the time-of-use charging price, whether V2G bidirectional charging is supported, and the equipment's operational fault status, providing core indicators for the selection of candidate charging stations.

[0047] 15) Traffic forecast In this step, traffic conditions can be predicted based on historical traffic data, traffic conditions can be predicted through traffic weather stations, or weather forecasts can be queried through web pages. This embodiment does not impose any restrictions.

[0048] The predicted traffic conditions can include real-time road congestion index from the vehicle's current location to each potential charging station, estimated travel time for road segments, traffic control information, and the location and impact range of sudden traffic events (such as accidents or construction), providing a basis for calculating the time spent during charging and matching the timing.

[0049] In this embodiment, the system can access the OCPP protocol interface of a traffic weather station to obtain road surface conditions, visibility, and traffic weather warning information for the target road segment. It can also integrate real-time traffic flow and congestion data from a traffic management platform to generate a fusion signal for vehicle-network collaborative traffic-weather fusion decision-making. Based on this fusion signal, the system dynamically adjusts vehicle charging routes and V2G charging strategies to ensure driving safety and charging efficiency.

[0050] In step 103, based on the vehicle status data, the order demand, the charging station status, the energy consumption, and the traffic conditions, an optimal charging decision is determined. The optimal charging decision includes the optimal charging time and the optimal charging station.

[0051] The step includes: First, based on the vehicle status data, the order demand, the charging station status, the energy consumption, and the traffic conditions, multiple candidate charging decisions are determined. Each candidate charging decision includes a candidate charging station and a corresponding candidate charging opportunity.

[0052] In this embodiment, multiple candidate charging decisions are determined based on five dimensions of data: vehicle status data, order demand, charging station status, energy consumption, and traffic conditions. This can be explained through three steps: screening, matching, and verification, thereby ensuring the effectiveness, rationality, and diversity of the generated candidate charging decisions. Specifically, this includes: 21) Candidate charging station screening: In this embodiment, based on the current location of the vehicle, a range of a preset reasonable driving radius (e.g., 10km) is defined. Combining charging station status data, traffic data, and energy consumption data, charging stations that are faulty, overloaded, or have travel time exceeding the threshold are eliminated. Charging stations that meet the conditions of "usable, reachable, and cost controllable" are selected as initial candidate charging stations.

[0053] 22) Matching candidate charging times: In this step, for each initial candidate charging station, we can combine the peak / off-peak hours in the order demand data and the peak and valley congestion hours in the traffic conditions, and at the same time refer to the range critical node and dynamic charging threshold in the vehicle status data to match at least one suitable candidate charging time. We will give priority to the off-peak hours of orders, smooth traffic and low charging prices, and avoid the time when it will affect the vehicle's operating revenue.

[0054] 23) Multi-dimensional verification and completion: In this step, the combination of "candidate charging station + candidate charging time" is verified a second time. The energy consumption of the vehicle to and from the charging station and the charging time required under this combination are calculated by combining energy consumption data. It is confirmed that the vehicle range after charging can meet the needs of subsequent orders. Invalid combinations with insufficient range and excessive charging time are eliminated, and finally multiple qualified candidate charging decisions are formed.

[0055] It should be noted that in this embodiment, each qualified candidate charging decision is a one-to-one combination of candidate charging station and candidate charging time, and the two are related and inseparable.

[0056] In this embodiment, the candidate charging stations are compliant charging stations that have been screened and verified as described above. Each candidate charging station has a clear and unique identifier and is accompanied by key attributes such as the real-time charging power, current charging price, estimated travel time to the station, and whether it supports V2G bidirectional charging, which serve as the basis for subsequent optimization and evaluation.

[0057] In this embodiment, the candidate charging time is a precise time period (accurate to the minute) that is adapted to the corresponding candidate charging station. This time must meet three core requirements at the same time: first, avoid peak order periods; second, match the idle time of the charging station; and third, ensure that the vehicle can connect to subsequent operations after charging. In addition, the candidate charging time matched for each candidate charging station is not repeated or conflicting.

[0058] In addition, the multiple candidate charging decisions need to be differentiated, covering combinations of different charging stations and different charging times. This includes both emergency decisions that are "nearby and immediate" and benefit-oriented decisions that are "low-cost and efficient," providing ample room for selection of the optimal solution in the future.

[0059] Secondly, a multi-objective optimization function is used to evaluate the candidate charging stations and corresponding candidate charging times in each candidate charging decision, and the optimal candidate charging decision is selected as the optimal charging decision.

[0060] In this step, based on the candidate charging stations and corresponding candidate charging times in each candidate charging decision, the expected revenue, cost penalty, empty-run penalty, experience penalty, and risk penalty for each candidate charging decision are calculated according to the different weights of the set multi-objective optimization function. Based on the expected revenue, cost penalty, empty-run penalty, experience penalty, and risk penalty for each candidate charging decision, the objective function value of each candidate charging decision is calculated using the multi-objective optimization function. From all objective function values, the candidate charging station and corresponding candidate charging time corresponding to the maximum objective function value are selected as the optimal charging decision.

[0061] In other words, in this embodiment, the candidate charging decision with the highest objective function value is selected as the optimal charging decision. The content of the optimal charging decision may include: target charging station, departure time, charging amount (or charging time), whether to participate in V2G, etc. Of course, other content may be included as needed, and this embodiment does not impose any restrictions.

[0062] Specifically, based on the candidate charging stations and corresponding candidate charging times in each candidate charging decision, and according to the different weights of the set multi-objective optimization function, the corresponding expected revenue, cost penalty, empty-running penalty, experience penalty, and risk penalty are calculated. This includes: calculating expected revenue, charging cost, empty-running cost, experience compensation, and rescue cost based on the candidate charging stations and corresponding candidate charging times in each candidate charging decision; and multiplying the expected revenue, charging cost, empty-running cost, experience compensation, and rescue cost by the corresponding weights of the set multi-objective optimization function (revenue weight, charging weight, empty-running weight, experience weight, and rescue weight) to obtain the corresponding expected revenue, cost penalty, empty-running penalty, experience penalty, and risk penalty. Furthermore, the different weights of the multi-objective optimization function can be dynamically adjusted according to different time periods in the operating mode (e.g., peak, off-peak, nighttime).

[0063] In other words, in this embodiment, the general representation of the multi-objective optimization function is shown in the following formula: Total_Utility = ω1× Revenue_Utility - ω2× Cost_Penalty - ω3×Deadhead_Penalty - ω4× Experience_Penalty - ω5× Risk_Penalty In this formula, ω1, ω2, ω3, ω4, and ω5 are all weight coefficients greater than 0 and less than 1. ω1+ω2+ω3+ω4+ω5=1, and the weights can be dynamically adjusted according to the actual operational priorities.

[0064] The weights can be dynamically adjusted based on the operating mode (peak, off-peak, night). For example, during peak hours: increase ω1 (revenue weight) and decrease ω2 (cost weight); during night hours: increase ω2 (cost weight) and take advantage of off-peak electricity prices, etc.

[0065] The meanings of each component in this formula are as follows: Total Utility: This is the core evaluation metric for candidate power replenishment decisions. The higher the value, the higher the overall fit of the candidate power replenishment decision. It is the sole criterion for selecting the optimal power replenishment decision and is calculated by weighting one positive benefit term and four negative penalty terms.

[0066] Estimated Revenue (Revenue_Utility): This forecasts the expected revenue from orders received by vehicles in the area surrounding the charging station during and after the charging period, taking into account order probability and estimated vehicle fares.

[0067] Charging cost (Cost_Penalty): Charging cost (electricity × electricity price + service fee) + battery depreciation cost (calculated based on charging rate and battery temperature).

[0068] Deadhead cost (Deadhead_Penalty): empty distance × cost per unit distance.

[0069] Cancellation Compensation Cost (Experience_Penalty): A penalty is imposed if an order is cancelled or passenger waiting time is extended due to charging.

[0070] Risk_Penalty: Assess the risk that the vehicle's battery level will fall below a safe threshold after completing a follow-up order, multiplied by a high rescue cost.

[0071] In this formula, ω1 × Revenue_Utility represents the operating revenue utility.

[0072] ω2×Cost_Penalty represents the cost penalty.

[0073] ω3× Deadhead_Penalty represents the penalty for driving without a license.

[0074] ω4×Experience_Penalty represents the experience penalty.

[0075] ω5× Risk_Penalty represents the risk penalty.

[0076] Among them, ω1 to ω5 are dynamic weighting coefficients used to adjust the priority of each target under different operating scenarios (such as morning rush hour, night, and severe weather).

[0077] The definitions and calculation processes of each part of the formula are explained below.

[0078] 31) Operating revenue utility (i.e., profit utility) is a positive return.

[0079] This section is used to quantify the expected revenue that a vehicle may obtain during the decision-making process of charging, specifically calculated using the formula below.

[0080] Revenue_Utility = Σ (P_order × Fare_estimate) In this formula, P_order represents the predicted probability of receiving high-quality orders in a specific hotspot area during the power replenishment period and subsequent periods. This predicted probability can be achieved through order demand forecasting, based on factors such as historical order data, real-time events, and weather.

[0081] Fare_estimate: Represents the estimated fare for the corresponding order.

[0082] Sum of ranges: indicates the time window (e.g., within one hour) and spatial range (e.g., 5 kilometers around the charging station) for assessing the impact of the decision.

[0083] 32) Cost penalty.

[0084] This section quantifies the economic costs directly related to power replenishment, and can be calculated using the following formula: Cost_Penalty = Electricity_Cost + Station_Fee + Battery_Degradation_Cost In this formula, Electricity_Cost represents the charging amount multiplied by the real-time electricity price at the charging station. This encourages vehicles to charge during off-peak electricity pricing periods.

[0085] Station_Fee: This indicates the charging service fee or parking fee.

[0086] Battery_Degradation_Cost: Represents a function related to charging rate, battery temperature, and current battery level, used to quantify the impact of fast charging on battery life and encourage healthier charging strategies.

[0087] 33) Penalty for driving empty This section quantifies the efficiency loss caused by the vehicle running idle to recharge, and is calculated using the following formula: Deadhead_Penalty = Deadhead_Distance × Cost_Per_Kilometer In this formula, Deadhead_Distance represents the distance from the vehicle's current location to the selected charging station.

[0088] Cost_Per_Kilometer: Represents the operating cost per unit distance (including depreciation, maintenance, etc.).

[0089] 34) Experience punishment This section quantifies the negative impact of charging decisions on passenger experience, specifically calculated using the following formula: Experience_Penalty = Σ (Order_Cancellation_Penalty + Waiting_Time_Penalty) In this formula, Order_Cancellation_Penalty represents a high fixed penalty that is triggered if the current decision forces the system to cancel an order already assigned to the vehicle.

[0090] Waiting_Time_Penalty: This indicates that if the decision results in the expected demand for transportation in the surrounding area not being met in the next few minutes (i.e., passenger waiting time is extended), a penalty function that increases over time will be applied based on the predicted demand.

[0091] 35) Risk penalties.

[0092] This section is used to quantify the operational risks caused by poor power management, specifically calculated using the following formula: Risk_Penalty = Low_Battery_Risk × Emergency_Tow_Cost In this formula, Low_Battery_Risk represents a probability value that predicts the risk that the vehicle's battery level will fall below a safe threshold (e.g., 5%) after completing subsequent orders.

[0093] Emergency_Tow_Cost: Represents an extremely high fixed cost, simulating the expenses and brand reputation damage incurred when a vehicle needs roadside assistance due to a power outage. This acts as a "safety valve" to prevent the system from "risking" vehicle operation for short-term gains.

[0094] In other words, in this embodiment of the application, each potential power replenishment decision can be evaluated using a multi-objective optimization function.

[0095] Optionally, in this embodiment, the weights ω1 to ω5 are not fixed, but are dynamically adjusted according to the operational strategy and real-time status. This embodiment uses the following modes as examples, but in practical applications, it is not limited to these: 41) Peak Sprint Mode (Morning / Evening Peak): ω1 (revenue weight) can be increased and ω2 (cost weight) slightly decreased to maximize capacity supply and revenue capture.

[0096] 42) Cost-priority mode (off-peak nighttime): can increase ω2 (cost weight), prioritize low-priced charging stations, and enable V2G mode (in this case, Electricity_Cost can be negative, representing electricity sales revenue).

[0097] 43) Experience guarantee mode (after large events, inclement weather): can significantly improve ω4 (experience weight), ensure sufficient capacity, and avoid passengers being without a car for a long time even if it means sacrificing some efficiency.

[0098] 44) Risk avoidance mode (vehicle battery is generally low): can increase ω5 (risk weight) to force low battery vehicles to recharge in advance to prevent problems before they occur.

[0099] In step 104, a power replenishment decision instruction is generated based on the optimal power replenishment decision.

[0100] In this step, based on the content of the optimal charging decision (i.e., full information), standardized and structured charging decision instructions are generated according to the system's preset instruction format. The core execution instructions may include: specifying the instruction number, target vehicle identifier, optimal candidate charging station information (location, pile number, interface type, etc.), optimal charging timing (departure time, estimated arrival time, planned charging start and end time periods, target SOC value / discharge amount, etc.), driving route planning instructions (recommended optimal driving route, precautions for passing through road sections), charging execution requirements (charging power range, V2G charging and discharging mode switching instructions, charging completion confirmation criteria), and resource reservation instructions (sending charging pile reservation and locking instructions to the charging station, synchronizing the vehicle's estimated arrival time, etc.).

[0101] Of course, in this embodiment, when sending the charging decision instruction, an auxiliary reference instruction can also be issued, and the two can work together. Among them, the auxiliary reference instruction (decision support type) includes: the expected operating benefits of the optimal decision, the total cost of the charging process, the estimated empty-run loss, risk warnings (such as the time of day when the route is prone to congestion, and the warning of temporary charging station failures), and emergency handling guidelines for emergencies (such as sudden high-priority orders, charging station failures), for the system or subsequent intervention reference, etc.

[0102] In step 105, based on the charging decision command, the vehicle is controlled to arrive at the optimal charging station at the optimal charging time to charge.

[0103] In this step, based on the vehicle scheduling system, the charging decision instruction is sent to the vehicle's autonomous driving system to control the vehicle to go to the designated charging station, that is, to arrive at the optimal charging station at the optimal charging time to charge.

[0104] In this embodiment, vehicle status data, environmental data, and operational data are acquired. Based on the environmental data and operational data, the order demand, charging station status, energy consumption, and traffic conditions of the vehicle in the future are predicted. Based on the vehicle status data, order demand, charging station status, energy consumption, and traffic conditions, an optimal charging decision is determined. The optimal charging decision includes: optimal charging time and optimal charging station. A charging decision command is generated based on the optimal charging decision. Based on the charging decision command, the vehicle is controlled to arrive at the optimal charging station at the optimal charging time for charging. In other words, in this embodiment, by acquiring the vehicle status in real time and combining it with the predicted order demand and charging station resource situation in the future, the optimal charging decision is determined, and the vehicle is controlled to charge using the optimal charging decision. This effectively solves the vehicle range problem, reduces charging costs while ensuring operational efficiency, and improves vehicle charging efficiency and user experience.

[0105] Optionally, in another embodiment, based on the above embodiments, the method may further include: real-time monitoring of traffic conditions and dynamic route adjustment during the process of controlling the vehicle to travel to the designated charging station, so that the vehicle arrives at the optimal charging station at the optimal charging time for charging, thereby improving the accuracy of vehicle charging and charging efficiency.

[0106] In this step, the charging pile for vehicle charging is controlled. In this embodiment, the charging pile can be reserved through the charging station management system to ensure that the vehicle can be charged immediately after arrival, thereby improving charging efficiency.

[0107] In other words, in this embodiment, the charging station management system reserves the charging pile vehicle of the optimal charging station so that after the vehicle arrives at the optimal charging station, it can automatically connect to the reserved charging pile and perform charging according to the charging mode (normal charging or V2G) of the charging decision instruction.

[0108] Optionally, in another embodiment, based on the above embodiments, before acquiring the current vehicle status data, environmental data, and operational data, the method may further include: configuring a V2G bidirectional charging strategy for the vehicle; acquiring real-time grid demand information; and dynamically adjusting the V2G bidirectional charging strategy of the vehicle according to the real-time grid demand, thereby realizing bidirectional power interaction between the autonomous vehicle and the grid.

[0109] V2G stands for Vehicle-to-grid. It describes the relationship between an electric vehicle and the power grid. When the electric vehicle is not in use, the electrical energy from its battery is sold to the grid. If the battery needs charging, current flows from the grid back to the vehicle.

[0110] During periods of high grid demand and high electricity prices, and when vehicle battery capacity is sufficient (e.g., SOC > 60%), the V2G model can be used to power the grid as a distributed power source, generating revenue.

[0111] At this point, Revenue_Utility in the multi-objective optimization function can include electricity sales revenue, while also considering battery depreciation costs, etc.

[0112] Please participate Figure 2 This is a schematic diagram illustrating an optimal charging station selection method provided in an embodiment of this application, as shown below. Figure 2 As shown, it includes: 201: The vehicle has triggered a charging request.

[0113] In this step, the vehicle triggers a charging demand (such as when the remaining charge is lower than the dynamic charging threshold or the range cannot support the predicted demand for subsequent orders) by determining the dynamic threshold of its own battery management system or charging dispatch system, and initiates the charging decision process.

[0114] Step 202: Determine whether pre-screening of charging stations is required. If so, proceed to step 203 to obtain the shortlisted candidate charging stations.

[0115] In this step, the system conducts an initial screening of charging stations across the entire region based on basic information such as the vehicle's current location, the real-time status of charging stations (e.g., whether they are faulty or whether there are available charging piles), and traffic conditions. Charging stations that obviously do not meet the conditions (e.g., faulty stations or stations that are too far away) are eliminated, thus narrowing down the scope of subsequent evaluation.

[0116] Step 203: Evaluate candidate charging stations from multiple dimensions.

[0117] In this step, for the candidate charging stations obtained after pre-screening, this embodiment uses a multi-objective optimization function to conduct a comprehensive evaluation from six dimensions and establish a candidate station set, which includes multiple candidate charging stations. Specifically, it includes: Step 2031: Establish a candidate station set: Include the pre-screened candidate charging stations into the candidate scope; Step 2032: Distance cost, which is to calculate the driving distance and energy consumption cost from the vehicle's current location to each candidate charging station.

[0118] Step 2033: Time cost (queue prediction), which combines historical data and real-time congestion levels of each candidate charging station to predict the queuing time after a vehicle arrives.

[0119] Step 2034: Economic cost (electricity price / service fee), which is to calculate the time-of-use electricity price, charging service fee and other direct costs for each candidate charging station.

[0120] Step 2035: Operational matching degree (nearby order hot zone), which is to analyze the order demand density around each candidate charging station and evaluate the convenience of vehicle access to orders after charging.

[0121] Step 2036: Facility compatibility (fast charging / V2G), which means verifying whether each candidate charging station supports the vehicle's fast charging requirements or V2G bidirectional charging function.

[0122] Step 204: Calculate the overall score.

[0123] In this step, each candidate charging station is quantitatively scored according to the weight of each evaluation dimension (such as the weight of operational matching degree being higher than that of distance cost), and the comprehensive score of each candidate charging station is obtained, which serves as the core basis for decision-making.

[0124] Step 205: Decision-making center makes a judgment, that is, the decision-making center makes a dual judgment based on the comprehensive score and the real-time operation scenario: If there are no sudden high-priority orders in this step, proceed to step 206; if there are sudden high-priority orders, proceed to step 207.

[0125] Step 206: Select the candidate charging station with the highest comprehensive score as the best charging station (i.e., the optimal charging station), and then proceed to step 208.

[0126] Step 207: Implement the delayed charging strategy and add the vehicle to the priority dispatch queue. Then, proceed to step 208.

[0127] In other words, if there are no sudden orders: the candidate charging station with the highest comprehensive score is directly selected as the best charging station; if there are sudden orders: the current charging plan is suspended, the high-priority orders are responded to first, and the charging process is retried after the orders are completed.

[0128] Step 209: Dispatch the vehicle to and reserve a charging station.

[0129] In this step, the vehicle is dispatched to the optimal charging station and an available charging station is reserved (i.e., a charging resource is reserved).

[0130] In this step, after the final charging decision is determined, the system will send a dispatch instruction to the vehicle and send a reservation request to the available charging piles of the optimal target charging station to lock in the charging resources.

[0131] In this embodiment, for non-self-operated charging stations, a cooperation agreement can be signed to share data and permissions among the various charging stations and unify reservation rules, thereby achieving data interoperability between platforms. Specifically, this includes: 1) It can access the OCPP protocol interface of third-party charging operators to obtain real-time status information of available charging piles in non-self-operated charging stations and submit reservation requests to target available charging piles.

[0132] In this step, for example, multiple brand operators can be connected at once through an aggregation platform (such as Gaode Charging, Alipay / WeChat Charging Mini Programs, etc.) to obtain the status of each charging pile in the charging station and the reservation entry point in real time. Alternatively, the operator's OCPP / MQTT interface can be directly connected to obtain the available charging pile data and reservation permissions of the charging station, and the vehicle system / APP can be adapted to initiate requests.

[0133] 2) A prepaid / deposit mechanism can be used to lock in the reservation time slot, and identity verification can be completed by scanning a code / NFC / vehicle identification to activate the charging pile.

[0134] In this step, for example, a "time slot lock + prepayment / deposit" method can be used to reserve a charging station for a certain time slot, and a certain amount can be paid (such as a 10 yuan deposit, which can be used to offset the charging fee after charging). If the time slot is exceeded, the charging station will be automatically released and part of the deposit will be deducted to ensure that charging station resources are not wasted.

[0135] 3) Establish an anomaly handling mechanism. When a reserved charging station malfunctions or is occupied, it will automatically switch to an available charging station at the same station or recommend an alternative charging station to ensure the fulfillment of the reservation.

[0136] In this step, if the reserved charging station is faulty or occupied, an alternative charging station at the same station will be recommended first for the vehicle. The station will automatically switch and notify the reserved vehicle within a set time (e.g., 5 minutes). If no alternative charging station is available, the deposit will be fully refunded, and a corresponding compensation coupon can be sent, or an additional available charging station can be recommended.

[0137] Furthermore, this embodiment may also include: performing a charging operation, that is, the vehicle goes to a designated charging station according to the dispatch instruction, completes charging at the reserved charging pile, and reconnects to the operation order queue after the charging is completed.

[0138] Furthermore, this embodiment may also include: operational monitoring and feedback, i.e., real-time monitoring of vehicle performance status, including whether it arrives on time and whether charging is normal. If an anomaly occurs (such as a charging station malfunction or a vehicle not arriving as planned), a re-decision is triggered. Actual operational data (such as actual revenue, costs, passenger feedback, etc.) is collected to evaluate the effectiveness of the decision.

[0139] Furthermore, this embodiment may also include: a feedback learning system, which periodically (e.g., weekly) retrains the prediction model (demand forecasting, energy consumption forecasting, etc.) using collected actual data to optimize prediction accuracy; and adjusts the weight parameters in the optimization function based on actual operational results to better adapt the system to the actual operating environment.

[0140] Please also see Figure 3This is a schematic diagram of intelligent vehicle charging decision-making provided in an embodiment of this application. In this embodiment, taking an autonomous ride-hailing vehicle as an example, it illustrates the process from data collection to charging decision execution and feedback optimization. Specifically, it includes: 1) Real-time data acquisition, specifically including: vehicle status monitoring, environmental data acquisition and operational data collection, etc.

[0141] Vehicle status monitoring includes collecting core operational data such as the vehicle's current battery level (SOC, for example, 45%), real-time energy consumption (for example, 0.25Wh / km), and vehicle location (i.e., latitude and longitude coordinates). This data forms the basis for charging decisions. Of course, this embodiment is just an example, and in actual applications, it is not limited to these data.

[0142] Environmental data acquisition includes: charging station status (e.g., 3 / 10 idle charging piles), real-time electricity price (e.g., peak hour price of 1.8 yuan / kWh), and traffic conditions (e.g., congestion index of 6.8), reflecting the constraints of the external charging environment. This is just an example, but practical applications are not limited to this.

[0143] Operational data collection includes: order demand forecasting (e.g., high demand in the next 2 hours), historical operating patterns (e.g., peak hours 7-9 AM), V2G opportunity assessment (moderate grid demand), and correlation between operational revenue and grid interaction needs. This is just an example, but practical applications are not limited to this. 2) Evaluation of the decision computation layer, specifically including: multi-objective optimization computation and decision engine evaluation.

[0144] The multi-objective optimization calculation is specifically performed using a multi-objective optimization function. The calculation formula and process of the multi-objective optimization function are detailed above and will not be repeated here. The calculation results provide data support for the evaluation of the decision engine.

[0145] The decision engine evaluation can be divided into three decision directions based on the calculation results, yielding corresponding decision outcomes: One is V2G power supply, which means that when adapting to the grid demand, a reverse power supply scheme is generated and V2G scheduling is executed; then, the power replenishment command is executed in real time.

[0146] Another is immediate power replenishment, which means that when the power / operational demand is urgent, an emergency power replenishment plan is generated and an emergency dispatch is executed; then, the power replenishment command is executed in real time.

[0147] Another method is delayed power replenishment, which involves generating the optimal power replenishment plan and executing the schedule in non-emergency scenarios; then, the power replenishment command is executed in real time.

[0148] 3) Execution and Feedback Layer (Generation of Power Supplement Decision Instructions and Iterative Optimization) In this step, the actual charging command is generated and executed based on the decision results, while the execution status is monitored. It also determines whether the charging execution was successful. If it fails, a backup plan is triggered, and the actual charging command is executed again. If successful, the vehicle status is updated, operational data is collected, feedback is provided for learning and optimization, the current decision is terminated, and the process awaits the next decision cycle before returning to the start of the charging decision cycle.

[0149] In other words, the algorithm model is optimized through feedback learning. After making the current decision, it waits for the next decision cycle to form a closed loop, thereby achieving iterative optimization.

[0150] It should be noted that, in this embodiment, seamless integration of real-time data from vehicles, charging stations, the power grid, and the order platform is required to ensure data interface compatibility and guarantee the timeliness and accuracy of data collection. The weights of the multi-objective optimization function need to be dynamically adjusted according to actual operational scenarios (such as peak order periods and power grid peak shaving periods) to improve decision-making adaptability.

[0151] This embodiment also proposes a backup charging solution, covering common abnormal scenarios such as charging station failures, traffic congestion, and sudden orders, to avoid interruption of the power replenishment decision-making process and improve the emergency response mechanism.

[0152] It should be noted that, Figure 3 The examples shown are for illustrative purposes only and are not limited to these in practical applications.

[0153] In this embodiment, multi-objective optimization processing is performed based on real-time collected vehicle, environmental, and operational data, and a charging decision is determined based on the processing results. The system also supports iterative decision-making cycles to adapt to dynamically changing operational scenarios and improve vehicle charging efficiency.

[0154] Furthermore, in this embodiment, multi-scenario adaptation is performed to realize vehicle V2G power supply, emergency power replenishment, planned power replenishment, and other scenarios, taking into account grid demand, operational urgency, and optimal benefits.

[0155] Furthermore, in this embodiment, the execution results are fed back to the algorithm through feedback learning, continuously improving the accuracy of subsequent decisions and achieving closed-loop optimization.

[0156] In this embodiment, by accurately predicting and reducing operational interruptions caused by charging, vehicle utilization is increased by more than 25%, thus improving operational efficiency. Charging costs are reduced by leveraging peak-valley electricity price differences, and additional revenue is generated by combining V2G technology, achieving cost optimization. Ensuring sufficient vehicle battery power reduces order cancellation rates, improves service reliability, and enhances user experience. Intelligent scheduling balances regional grid load, supports renewable energy consumption, and enables mutual coordination between vehicles and the grid.

[0157] For ease of understanding, please refer to the following embodiment, which takes an autonomous ride-hailing vehicle as an example. The values ​​in this embodiment are for illustrative purposes only and are not limited to this in actual applications.

[0158] Assume an autonomous ride-hailing vehicle currently has 35% battery power and is operating during off-peak hours. The system makes the following decision: Data collection and order demand forecasting: The current vehicle location is in area A. The current order demand forecast shows that there will be a peak in area B in 1 hour. Charging stations C and D are near the vehicle. The electricity price at station C is 10% lower than that at station D, but it requires driving 3 kilometers more.

[0159] Energy consumption prediction: The predicted energy consumption for vehicles arriving at station C is 0.5 kWh, and the predicted energy consumption for arriving at station D is 0.2 kWh. The estimated queuing time at station C is 5 minutes, and at station D it is estimated to be 10 minutes.

[0160] Decision engine: Calculates the objective function values ​​of the two schemes using a multi-objective optimization function. Option 1: Go to Station C Income utility: Considering that the peak hours in Zone B will begin after 1 hour, vehicles can travel to Zone B after charging, resulting in higher expected income.

[0161] Cost: Electricity costs are low, but the empty driving distance is long, resulting in slightly higher costs.

[0162] Experience: Short charging queue time, ensuring you won't miss peak order times.

[0163] Option 2: Go to Station D Income utility: You can also go to Zone B, but the queuing time may cause you to miss some peak orders.

[0164] Costs: High electricity costs and short empty driving distance.

[0165] After calculation, the objective function value of Scheme 1 is higher, so Station C is selected.

[0166] Execution: The vehicle is dispatched to Station C, charged to 80%, and then proceeds to Area B to pick up orders.

[0167] Feedback: In actual operation, the vehicle successfully completed multiple orders in Zone B. The system recorded this decision as a positive example for subsequent model optimization.

[0168] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential to this application.

[0169] Please also see Figure 4 This is a block diagram of a vehicle intelligent power replenishment control system provided in an embodiment of this application. The system includes: an acquisition module 401, a prediction module 402, a determination module 403, a generation module 404, and a control module 405, wherein... The acquisition module 401 is used to acquire the current vehicle status data, environmental data, and operational data. The prediction module 402 is used to predict the order demand, charging station status, energy consumption and traffic conditions of the vehicle in the future time period based on the environmental data and the operational data. The determination module 403 is used to determine the optimal charging decision based on the vehicle status data, the order demand, the charging station status, the energy consumption and the traffic conditions. The optimal charging decision includes: the optimal charging time and the optimal charging station. Generation module 404 is used to generate a power replenishment decision instruction based on the optimal power replenishment decision; Control module 405 is used to control the vehicle to arrive at the optimal charging station for recharging at the optimal recharging time based on the recharging decision command.

[0170] Optionally, in another embodiment, based on the above embodiment, the determining module 403 includes: a candidate power replenishment determining module 501 and a power replenishment decision selection module 502, the structure of which is as follows: Figure 5 As shown, where, The candidate charging determination module 501 is used to determine multiple candidate charging decisions based on the vehicle status data, the order demand, the charging station status, the energy consumption and the traffic conditions. Each candidate charging decision includes: a candidate charging station and a corresponding candidate charging opportunity. The charging decision selection module 502 is used to evaluate the candidate charging stations and corresponding candidate charging times in each candidate charging decision using a multi-objective optimization function, and select the optimal candidate charging decision as the optimal charging decision.

[0171] Optionally, in another embodiment, based on the above embodiment, the power replenishment decision selection module 502 includes: a first calculation module 601, a second calculation module 602, and an optimal power replenishment decision selection module 603, the structure of which is as follows: Figure 6 As shown, where, The first calculation module 601 is used to calculate the expected revenue, cost penalty, empty driving penalty, experience penalty and risk penalty for each candidate charging decision based on the candidate charging station and the corresponding candidate charging timing in each candidate charging decision, according to the different weights of the set multi-objective optimization function. The second calculation module 602 is used to calculate the objective function value of each candidate charging decision based on the expected revenue, cost penalty, empty driving penalty, experience penalty and risk penalty of each candidate charging decision using a multi-objective optimization function; The optimal charging decision selection module 603 is used to select the candidate charging station and the corresponding candidate charging timing corresponding to the maximum objective function value from all objective function values, as the optimal charging decision.

[0172] Optionally, in another embodiment, based on the above embodiments, the first calculation module includes: a cost calculation module and a product calculation module, wherein, The cost calculation module is used to calculate expected revenue, charging cost, empty driving cost, experience compensation and rescue cost based on the candidate charging station and the corresponding candidate charging time in each candidate charging decision; The product calculation module is used to multiply the revenue weight, charging weight, empty driving weight, experience weight, and rescue weight of the set multi-objective optimization function by the corresponding expected revenue, charging cost, empty driving cost, experience compensation, and rescue cost to obtain the corresponding expected revenue, cost penalty, empty driving penalty, experience penalty, and risk penalty.

[0173] Optionally, in another embodiment, based on the above embodiment, the power replenishment selection module further includes: a weight adjustment module, used to dynamically adjust the different weights of the multi-objective optimization function in the first calculation module according to different time periods in the operation mode.

[0174] Optionally, in another embodiment, based on the above embodiments, the system further includes: The configuration module is used to configure a V2G bidirectional charging strategy for the vehicle before acquiring the current vehicle status data, environmental data, and operational data. The demand information acquisition module is used to acquire real-time demand information of the power grid; The charging adjustment module is used to dynamically adjust the V2G bidirectional charging strategy of the autonomous vehicle according to the real-time demand of the power grid, so as to realize bidirectional power interaction between the autonomous vehicle and the power grid.

[0175] Optionally, in another embodiment, based on the above embodiments, the system further includes: The monitoring module is used to monitor traffic conditions in real time before the control module controls the vehicle to arrive at the optimal charging station for charging at the optimal charging time based on the charging decision command. The route adjustment module is used to dynamically adjust the vehicle's driving route based on the monitored traffic conditions, so that the vehicle can reach the optimal charging station for charging at the optimal charging time.

[0176] Please also see Figure 7 This is a hierarchical architecture diagram of a vehicle intelligent power replenishment control system provided in an embodiment of this application. The system includes: a data acquisition layer, a data processing and prediction layer, an intelligent decision-making layer (core layer), an execution and feedback layer, and an external system. The module interaction process at each stage is described below: 71) Data acquisition layer: Real-time collection of multi-source data.

[0177] The data acquisition layer uses vehicle sensors, GPS / BeiDou positioning, battery management system, order management system (obtaining order data through external user ride-hailing platforms), charging station cloud API, and traffic and meteorological cloud services (this is just one example, but it is not limited to these in actual applications) to collect real-time vehicle status (battery SOC, voltage, temperature, etc.), location information, energy consumption data, order demand data, charging station status (number of charging piles, power, congestion, etc.), and traffic and meteorological data, providing full raw data support for subsequent processing and decision-making.

[0178] 72) Data processing and prediction layer: data preprocessing + multi-dimensional prediction.

[0179] 721) Data Preprocessing Engine: Cleans, integrates, and standardizes the multi-source raw data collected by the data acquisition layer, removes invalid data and unifies the data format, and generates a structured dataset that can be called by the demand forecasting module, capacity forecasting module and charging station status forecasting (i.e., charging station status forecasting module).

[0180] 722) Calculations of the demand forecasting module, capacity forecasting module, and charging station status forecasting module: The demand forecasting module, based on preprocessed order data and traffic / weather data, predicts the order demand density and peak periods in different regions in the future.

[0181] Energy consumption prediction module: Combining historical vehicle energy consumption, real-time road conditions, and weather conditions, it predicts the energy consumption of the vehicle during driving and recharging in the future.

[0182] Charging station status prediction: Based on real-time data and historical operating patterns of charging stations, predict the availability and congestion of charging piles in future periods.

[0183] 723) Prediction result output: Synchronize the prediction data of orders, energy consumption, charging station status, etc. to the power replenishment decision engine of the intelligent decision layer.

[0184] 73) Intelligent Decision Layer (Core Layer): Generation and optimization of power replenishment decisions.

[0185] 731) Dynamic weight controller: Based on real-time operating scenarios (peak / off-peak order, power grid peak shaving demand, etc.), dynamically adjust the weight coefficients of each indicator (revenue, cost, empty run, etc.) in the multi-objective optimization function.

[0186] 732) V2G Strategy Module: Connects to the power grid dispatching system of external systems to obtain real-time power grid demand (peak and valley periods, peak shaving demand, etc.), formulates charging and discharging strategies for vehicle V2G bidirectional charging, and outputs them synchronously to the power replenishment decision engine.

[0187] 733) Multi-objective optimization function: Based on dynamic weights and preset algorithms, an optimization function including expected income and various penalty terms is constructed to provide a quantitative evaluation basis for power replenishment decisions.

[0188] 7334) Recharge Decision Engine: Integrates the prediction results of the data processing and prediction layer, V2G strategy, and multi-objective optimization function to generate multiple candidate recharge decisions (candidate charging station + recharge timing). The objective function value of each decision is calculated through the optimization function. The candidate charging station with the largest objective function value and the corresponding recharge timing are selected as the optimal recharge decision. The optimal recharge decision is then output to the execution and feedback layer.

[0189] 74) Execution and feedback layer.

[0190] 741) Instruction execution: Vehicle dispatching module: Based on the optimal charging decision, it generates a charging decision instruction and sends the charging decision instruction (i.e., vehicle driving dispatch instruction) to the autonomous driving system to control the vehicle to go to the designated charging station.

[0191] Charging pile control module: Interacts with the charging station network of external systems, reserves charging pile resources and issues charging / discharging control commands (adapted to V2G scenarios).

[0192] 742) Operational monitoring and feedback: Operations monitoring dashboard: Real-time monitoring of vehicle charging status, charging station resource usage, and order operation data.

[0193] Feedback learning system: Collects the execution effects of power replenishment decisions (such as actual benefits, costs, risks, etc.), and feeds the data back to the intelligent decision-making layer to continuously optimize the parameters of the dynamic weight controller and multi-objective optimization function, thereby realizing the closed-loop iterative upgrade of the decision model.

[0194] It should be noted that the entire implementation process shown in the figure also requires data interaction and command coordination with external systems (autonomous driving system, charging station network, power grid dispatching system, user ride-hailing platform, etc.) through interfaces to ensure the seamless connection of the entire chain from data collection to execution of the power replenishment decision.

[0195] It should be noted that, Figure 7 The layers, modules, and systems shown are merely illustrative examples. The components shown may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the layers and modules can be selected to implement this embodiment according to actual needs, which will not be elaborated further here.

[0196] Optionally, embodiments of this application also provide an electronic device, including: It includes a processor, a memory; and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the vehicle intelligent power replenishment control method as described above.

[0197] Optionally, embodiments of this application also provide a readable storage medium storing a program or instructions, which, when executed by a processor of an electronic device, implement the steps of the vehicle intelligent power replenishment control method as described above.

[0198] Optionally, embodiments of this application also provide a computer program product, including a computer program or instructions, which, when executed by a processor of an electronic device, implement the steps of the vehicle intelligent power replenishment control method as described above.

[0199] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0200] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0201] Please also see Figure 8This is a block diagram of an electronic device provided in an embodiment of this application. As shown in the figure, it includes a processor 801, a communication interface 802, a memory 803, and a communication bus 804, wherein the processor 801, the communication interface 802, and the memory 803 communicate with each other through the communication bus 804; Memory 803 is used to store the processor-executable instructions; The processor 801, when executing executable instructions on memory 803, implements the method described above.

[0202] In this embodiment, the communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used to represent it in the figure, but this does not mean that there is only one bus or one type of bus.

[0203] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0204] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage system located remotely from the aforementioned processor.

[0205] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0206] In another embodiment provided in this application, a readable storage medium is also provided, on which a program or instruction is stored. When the program or instruction is executed by a processor of an electronic device, the processor is able to execute the various processes of the vehicle intelligent power replenishment control method embodiment described above, and achieve the same technical effect. To avoid repetition, it will not be described again here. For example, the readable storage medium includes computer-readable storage media, such as ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage devices.

[0207] In another embodiment provided in this application, a computer program product is also provided, including a computer program or instructions. When the computer program or instructions are executed by the processor of an electronic device, they implement the various processes of the vehicle intelligent power replenishment control method embodiment described above and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0208] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state disk (SSD)).

[0209] Please also see Figure 9 This is a block diagram of a system 900 for intelligent vehicle power replenishment control provided in an embodiment of this application. For example, system 900 can be provided as a server. (Refer to...) Figure 9System 900 includes a processing component 922, which further includes one or more processors, and memory resources represented by memory 932 for storing instructions, such as application programs, that can be executed by the processing component 922. The application programs stored in memory 932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 922 is configured to execute instructions to perform the methods described above.

[0210] System 900 may also include a power supply component 926 configured to perform power management of system 900, a wired or wireless network interface 950 configured to connect system 900 to a network, and an input / output (I / O) interface 958. System 900 can operate on an operating system stored in memory 932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or similar.

[0211] It should be noted that the external system data involved in the embodiments of this application, such as data from traffic weather stations, charging station status data, environmental data obtained through the charging station cloud API, and power grid dispatch data, are all data authorized by the relevant units or authorized by the parties.

[0212] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0213] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A vehicle intelligent power replenishment control method, characterized in that, include: Acquire current vehicle status data, environmental data, and operational data; Based on the environmental data and the operational data, predict the order demand for the vehicle in the future, the status of charging stations, and the energy consumption and traffic conditions of the vehicle in the future. Based on the vehicle status data, the order demand, the charging station status, the energy consumption, and the traffic conditions, an optimal charging decision is determined, which includes: the optimal charging time and the optimal charging station. Based on the optimal power replenishment decision, a power replenishment decision instruction is generated; Based on the charging decision command, the vehicle is controlled to arrive at the optimal charging station at the optimal charging time to recharge.

2. The intelligent vehicle power replenishment control method according to claim 1, characterized in that, The process of determining the optimal charging decision based on the vehicle status data, order demand, charging station status, energy consumption, and traffic conditions includes: Based on the vehicle status data, the order demand, the charging station status, the energy consumption, and the traffic conditions, multiple candidate charging decisions are determined. Each candidate charging decision includes: a candidate charging station and a corresponding candidate charging opportunity. A multi-objective optimization function is used to evaluate the candidate charging stations and corresponding candidate charging times in each candidate charging decision, and the optimal candidate charging decision is selected as the optimal charging decision.

3. The vehicle intelligent power replenishment control method according to claim 2, characterized in that, The process of evaluating candidate charging stations and corresponding candidate charging times for each candidate charging decision using a multi-objective optimization function, and selecting the optimal candidate charging decision as the optimal charging decision, includes: Based on the candidate charging stations and corresponding candidate charging times in each candidate charging decision, the expected revenue, cost penalty, empty driving penalty, experience penalty and risk penalty for each candidate charging decision are calculated according to the different weights of the set multi-objective optimization function. Based on the expected revenue, cost penalty, empty run penalty, experience penalty, and risk penalty for each candidate refueling decision, the objective function value for each candidate refueling decision is calculated using a multi-objective optimization function. The candidate charging station and the corresponding candidate recharging timing corresponding to the maximum objective function value are selected from all objective function values ​​as the optimal recharging decision.

4. The vehicle intelligent power replenishment control method according to claim 3, characterized in that, The process involves calculating the expected revenue, cost penalty, empty-run penalty, experience penalty, and risk penalty based on the candidate charging stations and corresponding candidate charging times in each candidate charging decision, according to the different weights of the set multi-objective optimization function. This includes: Based on the candidate charging stations and corresponding candidate charging times in each candidate charging decision, calculate the expected revenue, charging cost, empty driving cost, experience compensation and rescue cost; By multiplying the revenue weight, charging weight, empty-running weight, experience weight, and rescue weight of the multi-objective optimization function by the corresponding expected revenue, charging cost, empty-running cost, experience compensation, and rescue cost, the corresponding expected revenue, cost penalty, empty-running penalty, experience penalty, and risk penalty are obtained.

5. The intelligent vehicle power replenishment control method according to claim 3, characterized in that, Also includes: The weights of the multi-objective optimization function are dynamically adjusted according to different time periods in the operation mode.

6. The intelligent vehicle power replenishment control method according to claim 1, characterized in that, Before acquiring the current vehicle status data, environmental data, and operational data, the method further includes: Configure the vehicle with a V2G bidirectional charging strategy; Obtain real-time demand information from the power grid; The vehicle's V2G bidirectional charging strategy is dynamically adjusted according to the real-time demand of the power grid to achieve bidirectional power interaction between the autonomous vehicle and the power grid.

7. The intelligent vehicle power replenishment control method according to claim 1, characterized in that, Before controlling the vehicle to arrive at the optimal charging station for charging at the optimal charging time based on the charging decision command, the method further includes: Real-time traffic monitoring; Based on the monitored traffic conditions, the vehicle's route is dynamically adjusted so that the vehicle arrives at the optimal charging station for charging at the optimal charging time.

8. A vehicle intelligent power replenishment control system, characterized in that, include: The acquisition module is used to acquire the current vehicle status data, environmental data, and operational data. The prediction module is used to predict the order demand, charging station status, energy consumption and traffic conditions of the vehicle in the future time period based on the environmental data and the operational data. The determination module is used to determine the optimal charging decision based on the vehicle status data, the order demand, the charging station status, the energy consumption, and the traffic conditions. The optimal charging decision includes: the optimal charging time and the optimal charging station. The generation module is used to generate a power replenishment decision instruction based on the optimal power replenishment decision; The control module is used to control the vehicle to arrive at the optimal charging station for recharging at the optimal recharging time based on the recharging decision command.

9. An electronic device, characterized in that, include: Including processor and memory; And a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the vehicle intelligent power replenishment control method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor of an electronic device, implement the steps of the vehicle intelligent power replenishment control method as described in any one of claims 1 to 7.

Images