Charging load prediction method and device of simulation vehicle, computer equipment and storage medium

Abstract

The invention relates to a charging load prediction method and device of a simulation vehicle, computer equipment and a storage medium. The method comprises the steps of detecting charge state information and vehicle position information of a simulation vehicle in a process that the simulation vehicle runs in a preset simulation traffic road network, and judging whether the simulation vehicle needs to be charged or not; during charging, first power consumption resource information of power supply of the simulation power distribution network in different time steps, second power consumption resource information matched with respective charging loads of the plurality of simulation charging stations in the same time step, and driving consumption resource information and time consumption resource information of charging of the simulation vehicle to the plurality of simulation charging stations are acquired; obtaining target consumption resource information of each simulation charging station; and screening the target simulation charging station with the lowest target resource consumption information, and obtaining predicted charging load information of the simulation vehicle after the simulation vehicle is controlled to run to the target simulation charging station for charging. By adopting the method, the simulation vehicle can be accurately charged.

Description

Technical Field

[0001] This application relates to the field of smart grid technology, and in particular to a method, apparatus, computer equipment and storage medium for predicting the charging load of a simulated vehicle. Background Technology

[0002] With the widespread adoption of electric vehicles, the proportion of their charging load in the power distribution network is also increasing rapidly. The uncertainty of electric vehicle charging and the ever-increasing charging demand have led to a series of problems, including increased volatility in power distribution network operation, decreased voltage quality, and reduced economic efficiency of power distribution network operation. Therefore, the problem of electric vehicle charging load forecasting has become a pressing challenge that urgently needs to be addressed.

[0003] Currently, the common approach to addressing the disorderly charging problem of electric vehicles in real-world production and daily life involves simulating the charging process of electric vehicles. When simulating the charging processes of multiple electric vehicles, this typically involves first acquiring historical data on traditional gasoline vehicles, navigation software surveys of vehicle travel, and factors influencing user charging behavior. Then, using Monte Carlo extraction to obtain relevant historical parameters, the charging process of electric vehicles in the current time period is simulated to obtain the optimal charging solution and thus predict the charging load of the simulated vehicles. However, current methods for predicting the charging load of simulated vehicles suffer from inaccuracies. Summary of the Invention

[0004] Therefore, it is necessary to provide an accurate method, device, computer equipment, computer-readable storage medium, and computer program product for predicting the charging load of simulated vehicles, addressing the aforementioned technical problems.

[0005] Firstly, this application provides a method for predicting the charging load of a simulated vehicle, including:

[0006] During the process of the simulated vehicle driving in the preset simulated traffic network, the charge state information and vehicle position information of the simulated vehicle are detected.

[0007] Based on the state of charge information and vehicle location information, determine whether the simulated vehicle needs to be charged;

[0008] When the simulated vehicle needs to be charged, the system obtains the first power consumption resource information of the simulated power distribution network connected to multiple simulated charging stations in the preset simulated traffic network at different time steps, the second power consumption resource information of matching the charging load of multiple simulated charging stations at the same time step, and the driving consumption resource information and time consumption resource information of the simulated vehicle going to multiple simulated charging stations for charging.

[0009] The first power consumption resource information, the second power consumption resource information, the driving consumption resource information, and the time consumption resource information are weighted and processed to obtain the target consumption resource information for each simulated charging station.

[0010] The target simulated charging station with the lowest resource consumption information is selected from multiple simulated charging stations. After the simulated vehicle is controlled to drive to the target simulated charging station for charging, the predicted charging load information of the simulated vehicle is obtained.

[0011] Secondly, this application also provides a charging load prediction device for a simulated vehicle, comprising:

[0012] The information detection module is used to detect the charge state information and vehicle position information of the simulated vehicle while it is driving in a preset simulated traffic network.

[0013] The charging determination module is used to determine whether the simulated vehicle needs to be charged based on the state of charge information and the vehicle's location information.

[0014] The resource consumption acquisition module is used to acquire, when the simulated vehicle needs to be charged, the first power consumption resource information of the simulated power distribution network connected to multiple simulated charging stations in the preset simulated traffic network at different time steps, the second power consumption resource information of matching the charging load of multiple simulated charging stations at the same time step, and the driving resource consumption information and time consumption resource information of the simulated vehicle going to multiple simulated charging stations for charging.

[0015] The resource consumption analysis module is used to perform weighted processing on the first power consumption resource information, the second power consumption resource information, the driving consumption resource information, and the time consumption resource information to obtain the target resource consumption information for each simulated charging station.

[0016] The charging module is used to select the target simulated charging station with the lowest resource consumption information from multiple simulated charging stations, and obtain the predicted charging load information of the simulated vehicle after controlling the simulated vehicle to drive to the target simulated charging station for charging.

[0017] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method steps.

[0018] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method steps.

[0019] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method steps.

[0020] The aforementioned method, device, computer equipment, computer-readable storage medium, and computer program product for predicting the charging load of simulated vehicles make real-time judgments during the vehicle's journey through a pre-set simulated traffic network. They consider both the vehicle's state of charge and its location information to accurately determine whether charging is necessary. If charging is required, the method considers the following: first, the first power consumption resource information from the simulated power distribution network connected to multiple simulated charging stations within the pre-set simulated traffic network at different time steps; second, the second, the power consumption resource information matching the charging load of each of the multiple simulated charging stations within the same time step; and third, the second, the driving and time consumption resource information of the vehicle traveling to multiple simulated charging stations. This comprehensive consideration of which simulated charging station minimizes the power consumption resource information ultimately instructs the vehicle to travel to the target simulated charging station that minimizes the power consumption resource information. This accurately obtains the predicted charging load information for the simulated vehicle. Furthermore, it effectively mitigates various phenomena such as increased operational volatility and voltage drops caused by disorderly charging of large numbers of vehicles entering the simulated traffic network. Therefore, the charging load prediction method for simulated vehicles in this application can be applied to real-world situations and is more accurate than existing charging load prediction methods. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a diagram illustrating the application environment of a charging load prediction method for a simulated vehicle in one embodiment.

[0023] Figure 2 This is a flowchart illustrating a method for predicting the charging load of a simulated vehicle in one embodiment.

[0024] Figure 3 This is a flowchart illustrating the charging load prediction method for a simulated vehicle in another embodiment.

[0025] Figure 4 This is a schematic diagram of a simulated traffic network topology in one embodiment;

[0026] Figure 5 This is a schematic diagram illustrating the simulated transportation network topology in one embodiment;

[0027] Figure 6This is a schematic diagram of the membership function of the state of charge information in one embodiment;

[0028] Figure 7 This is a schematic diagram of the membership function for charging distance information in one embodiment;

[0029] Figure 8 This is an example diagram illustrating the pricing of time-of-use electricity rates for the power grid according to different pricing methods in one embodiment;

[0030] Figure 9 This is an example diagram illustrating the electricity price for a simulated charging station service in one embodiment;

[0031] Figure 10 This is a schematic diagram of the load prediction results for each simulated charging station in one embodiment without considering any electricity price effect;

[0032] Figure 11 This is a schematic diagram of the load prediction results for each simulated charging station when considering the time-of-use pricing of the power grid in one embodiment;

[0033] Figure 12 This is a schematic diagram of the load forecast results for each simulated charging station, considering both the grid time-of-use tariff and the simulated charging station service tariff in one embodiment.

[0034] Figure 13 This is a flowchart illustrating the charging load prediction method for a simulated vehicle in a detailed embodiment.

[0035] Figure 14 This is a structural block diagram of a charging load prediction device for a simulated vehicle in one embodiment;

[0036] Figure 15 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application.

[0038] The charging load prediction method for simulated vehicles provided in this application embodiment can be applied to, for example... Figure 1The application environment is shown. Terminal 101 is equipped with simulation software 102, which includes components such as a preset simulated traffic network 103 and a simulated vehicle 104. The simulated vehicle travels within the preset simulated traffic network. Furthermore, the simulation software 102 has a built-in control module 105. The control module 105 communicates with the components in the simulation software 102, such as the simulated traffic network 103 and the simulated vehicle 104, and the simulation process in the simulation software 102 is controlled by the control module 105. While the simulated vehicle 104 is traveling within the preset simulated traffic network 103, the control module 105 monitors the charge state information and vehicle position information of the simulated vehicle 104 in real time. Based on the state of charge information and vehicle location information, it is determined whether the simulated vehicle 104 needs charging. If the simulated vehicle 104 needs charging, the first power consumption resource information of the simulated power distribution network connected to multiple simulated charging stations in the preset simulated traffic network 103 at different time steps, and the second power consumption resource information matching the charging load of each of the multiple simulated charging stations at the same time step are detected. The driving resource information and time resource information of the simulated vehicle 104 going to multiple simulated charging stations for charging are obtained, and the first power consumption resource information, the second power consumption resource information, the driving resource information, and the time resource information are weighted to obtain the target power consumption resource information of each simulated charging station. Based on the target power consumption resource information of multiple simulated charging stations, the target simulated charging station 106 with the lowest target power consumption resource information is selected from the simulated charging stations, and the selection result of the simulated charging station is pushed to the vehicle. The selection result is used to instruct the simulated vehicle 104 to drive to the target simulated charging station 106 for charging, thereby obtaining the predicted charging load information of the simulated vehicle 104. It should be noted that although this application is applied in a simulation environment, under ideal conditions, the vehicle charging load prediction method of this application can also be directly applied to the vehicle charging load prediction process in a real-world environment. However, the real-world environment presents more unexpected situations, such as power outages, real-time changes in electricity prices, and limitations on the number of charging piles in the simulation charging station. Therefore, the simulation results cannot completely replace reality. Thus, this application obtains an overall ideal situation through simulation. In actual production and daily life, this vehicle charging load prediction method can be referenced and further improved to make the vehicle charging load prediction process in a real-world environment more accurate.

[0039] In one exemplary embodiment, such as Figure 2 As shown, a method for predicting vehicle charging load in simulation is provided, and this method is applied to... Figure 1 The control module 105 in the example will be used for explanation. Specifically:

[0040] S100 detects the charge state information and vehicle position information of the simulated vehicle while it is driving in a preset simulated traffic network.

[0041] In this application, the vehicle is generally an electric vehicle, i.e., a vehicle driven by electricity. State of Charge (SoC) is a key parameter for measuring the remaining capacity of energy storage devices (such as batteries and supercapacitors), reflecting the remaining usable amount of active material inside the battery. Generally, SoC = (rated capacity / remaining usable capacity) × 100%.

[0042] Specifically, the simulation software includes pre-set simulated traffic networks and simulated vehicles. The simulated vehicles travel within these networks, and their location information is updated in real time. Furthermore, since the simulated vehicles consume electricity during operation, their state of charge (SBC) information is also updated in real time. The simulation software's built-in control module can detect these real-time SBC and vehicle location information.

[0043] In one embodiment, before the simulation begins, it is necessary to determine the relevant driving parameters of the simulated vehicle and assume that these parameters satisfy a certain probability distribution and range, including the electric vehicle's charging capacity information C and initial state of charge information SOC. start 1. Trip origin (usually the vehicle owner's residence) 2. Trip start time t start and the end time of the trip t end Expected State of Charge (SOC) exp Charging power P charge In practical applications, the relevant driving parameters of the simulated vehicle can be determined by random sampling using the Monte Carlo method.

[0044] The relevant driving parameters of the simulated vehicle follow a certain distribution, and the probability density functions and ranges of each parameter are as follows, where μ and σ are the mean and variance of the relevant vehicle parameters, indicating that these variables follow a normal distribution: Regarding the vehicle's charging capacity information C: , , Regarding the initial state of charge (SOC) information start : , , Regarding the travel start time t start : , , Regarding the trip end time t end : , , ; Regarding the expected state of charge (SOC) information exp : , , Regarding the charging power P charge : The above formulas provide the distribution of relevant driving parameters for the simulated vehicle; SOC exp，max This represents the upper limit of the expected state of charge (SOC). exp，min This represents the expected state of charge limit. Parameters for each vehicle were extracted using Monte Carlo methods, and P... charge The selection of a charging station is generally based on its own state of charge, choosing a suitable charging station and charging with the corresponding charging power.

[0045] In one embodiment, a simulated traffic network is pre-constructed, forming an adjacency matrix D of multiple roads. This adjacency matrix provides the connection relationships and distances between road nodes. Simultaneously, the locations of simulated charging stations are also marked within the simulated traffic network. Within the simulated traffic network, nodes such as simulated charging stations and roads are divided into residential areas, work areas, and commercial areas. Generally, simulated vehicles start from a residential area and return to it, forming a complete daily travel chain. Simulated vehicles can travel throughout the simulated traffic network for a day according to this travel chain. The method for representing the topology of the simulated traffic network using the adjacency matrix D is as follows:

[0046] ,

[0047] In the formula, the elements d in the adjacency matrix D ij G represents the distances and connections between nodes such as charging stations and roads in the simulation; G represents the set of all roads; l ij This represents the distance between adjacent nodes; an element in D that is 0 represents the current node. ij The meaning is as follows:

[0048]

[0049] In one embodiment, after obtaining information such as the simulated traffic network and related driving parameters, the travel of each vehicle can be simulated. First, the destination of a segment of each vehicle's journey is extracted, and the shortest path to the destination is planned. The destination can be a residence or another location. The planning method can be Dijstra's shortest path algorithm. Specifically: , In the formula, the objective functions are to find the optimal path with the shortest distance and the shortest time respectively (depending on the type of vehicle being simulated, the shortest time is generally considered more important, but in practice, both time and distance are considered to determine the path). Indicates road The average speed is related to the type of road.

[0050] Furthermore, considering the congestion encountered during travel, the free travel time of a road segment can be calculated using the BPR (Bureau of Public Roads Function, a classic mathematical model used in traffic engineering to describe the relationship between travel time and traffic flow) function. The BPR function is defined as follows:

[0051]

[0052] In the formula, t ij t0 represents the actual time required to travel on the road, q represents the free travel time on the road, and t0 represents the free travel time on the road. ij c represents the traffic volume of road ij at that time. ij Indicates the actual traffic capacity of the road. and The resistance coefficient can be calculated from regression analysis of actual data.

[0053] Therefore, after planning the shortest driving route to the destination according to the above method, the vehicle can travel along the shortest driving route in the preset simulated traffic network. During the journey, the charge status information and vehicle location information of the simulated vehicle are updated in real time according to time segments. Furthermore, the load status of each simulated charging station can be updated in real time according to the charging status of each vehicle at each time segment. For example, at a certain time segment, if a vehicle leaves, a new vehicle enters, or the charging power of a vehicle changes, it will affect the load status of the simulated charging station. The corresponding addition or subtraction of the load of the simulated charging station is the update process.

[0054] S200 determines whether the simulated vehicle needs charging based on its state of charge information and vehicle location information.

[0055] Specifically, after updating the simulated vehicle's state of charge (SOC) and location information, a decision is made regarding whether to charge the vehicle, based on these information. If charging is not desired, the SOC and location information continue to be updated until a preset destination is reached. If the preset destination is not the residence, a decision is made regarding ending the day's journey. If the journey is ended, the final destination is set as the residence, and a return route is planned. During the return journey, the SOC and location information are updated in real time. If the journey is not ended, the current destination is used as the starting point for the next segment, and the destination is randomly selected or defined using a Monte Carlo method. This process is repeated until the day's journey ends or a charging decision is made. If a charging decision is made, the vehicle proceeds to a simulated charging station for charging.

[0056] S300, when the simulated vehicle needs to be charged, detects the first power consumption resource information of the simulated power distribution network connected to multiple simulated charging stations in the preset simulated traffic network at different time steps, the second power consumption resource information of matching the charging load of multiple simulated charging stations at the same time step, and the driving resource information and time consumption resource information of the simulated vehicle going to multiple simulated charging stations for charging.

[0057] Specifically, the simulated charging station is connected to a simulated power distribution network. When it's determined that a simulated vehicle needs charging, the system needs to determine the resource consumption required to reach the simulated charging station based on charging resource consumption, driving resource consumption, and time-consuming resource consumption information. Therefore, it's first necessary to detect the charging resource consumption, driving resource consumption, and time-consuming resource consumption information when the simulated vehicle travels to each simulated charging station. It should be noted that after determining that a simulated vehicle needs charging, the current road travel process is generally completed before selecting a suitable simulated charging station.

[0058] The charging resource consumption information consists of the first power consumption resource information of the simulated power distribution network connected to multiple simulated charging stations within the preset simulated traffic network, supplied at different time steps, and the second power consumption resource information matching the charging load of each of the multiple simulated charging stations within the same time step. In simpler terms, the first power consumption resource information is the time-of-use electricity price when the simulated power distribution network supplies power. The time-of-use price can vary at different times, but it remains consistent across different simulated charging stations within the same time period. The second power consumption resource information is the service price determined by the load of each simulated charging station itself; the second power consumption resource information differs for different simulated charging stations within the same time period. Furthermore, the grid price is determined by the day-ahead base load and the day-ahead charging load of the simulated charging stations. The service price of each simulated charging station at each moment is determined by the load situation of each simulated charging station at the previous moment, and the service price of the simulated charging stations is calculated in real time using a rolling method. It should be noted that "history" in this application includes "day-ahead," but each time step refers to the time step in the current simulation process and is not included in the historical information. Furthermore, the driving resource consumption information refers to the driving cost of the simulated vehicle when it travels to each simulated charging station for charging, while the time resource consumption information refers to the time cost of the simulated vehicle when it travels to each simulated charging station for charging.

[0059] By combining the above information on first-level electricity consumption, second-level electricity consumption, travel consumption, and time consumption, the total resource consumption required to charge at each simulated charging station can be accurately detected.

[0060] S400 performs weighted processing on the first power consumption resource information, the second power consumption resource information, the driving consumption resource information, and the time consumption resource information to obtain the target consumption resource information for each simulated charging station.

[0061] Specifically, based on the first power consumption resource information, the second power consumption resource information, the driving resource information, and the time consumption resource information, the total resource consumption information required to go to each simulated charging station is considered in order to select a suitable simulated charging station. At this time, the target resource consumption information of each simulated charging station can be obtained by weighting the first power consumption resource information, the second power consumption resource information, the driving resource information, and the time consumption resource information.

[0062] Furthermore, in the weighted processing of the first power consumption resource information, the second power consumption resource information, the driving consumption resource information, and the time consumption resource information, the charging consumption resource information can be obtained first from the first power consumption resource information and the second power consumption resource information, and then the weighted processing of the charging consumption resource information, driving consumption resource information, and time consumption resource information can be performed. The expression can be: Let the driving consumption resource information be... Time consumption resource information is The first electricity consumption resource information is price, grid; the second electricity consumption resource information is... The charging resource consumption information for the simulated vehicle from the arrival time step of arriving at the simulated charging station to the departure time step of leaving the simulated charging station is as follows: Target resource consumption information for each simulated charging station Where m is the m-th simulated charging station, t arrive To reach the time step, t leave To leave the time step, in this embodiment This is the duration of the interval between the arrival time step and the departure time step.

[0063] S500 selects the target simulated charging station with the lowest resource consumption information from multiple simulated charging stations, and obtains the predicted charging load information of the simulated vehicle after controlling the simulated vehicle to drive to the target simulated charging station for charging.

[0064] Specifically, the target resource consumption information of multiple simulated charging stations is compared, and the lowest target resource consumption information is selected from among them. The target simulated charging station corresponding to this lowest target resource consumption information is then determined. The control module controls the simulated vehicle to change its original driving path and head to the target simulated charging station for charging. Charging continues until the simulated vehicle's state of charge information reaches the expected state of charge information. Charging then stops, and the charging load information of the simulated vehicle during the charging process is used as the predicted charging load information for the simulated vehicle to continue charging at the target simulated charging station. The vehicle then continues to its original destination.

[0065] In one embodiment, continuing to the original destination includes: obtaining the planned driving route of the simulated vehicle in a preset simulated traffic network, the planned driving route including at least the starting point location information and the destination location information; after the simulated vehicle arrives at the target simulated charging station for charging, using the location information of the target simulated charging station as the updated starting point location information, and obtaining the updated planned driving route based on the updated starting point location information and destination location information; and instructing the simulated vehicle to drive to the destination according to the updated planned driving route. Further, if the destination is not a residence, it can be determined whether to continue to the next segment of the journey. If to continue, a destination is randomly selected or customized, and the above process is repeated until the decision to end the journey is made. When the decision to end the journey is made, the destination of the last segment of the journey for the day is determined as a residence, and the planned driving route is updated again to complete the final state update process, forming a complete travel chain.

[0066] In one embodiment, upon returning to the residence in the residential area, the system can also determine whether to continue charging based on the current state of charge information and the user's psychology. If charging is to continue, the system will charge slowly because the simulated vehicle has been at the residence for a relatively long time; otherwise, the charging process will end.

[0067] In the aforementioned method for predicting the charging load of simulated vehicles, the decision to charge the simulated vehicle is made in real time while it is driving in a pre-set simulated traffic network. It considers both the vehicle's state of charge and its location to accurately determine whether charging is necessary. If charging is required, the method considers the following: first, the power consumption resource information of the simulated power distribution network connected to multiple simulated charging stations within the pre-set simulated traffic network at different time steps; second, the power consumption resource information matching the charging load of each of the multiple simulated charging stations within the same time step; and third, the driving and time consumption resource information of the simulated vehicle traveling to multiple simulated charging stations. This comprehensive consideration determines which simulated charging station minimizes the power consumption resource information. Ultimately, the method directs the simulated vehicle to the target simulated charging station that minimizes the power consumption resource information, thus accurately predicting the charging load information of the simulated vehicle traveling to the target simulated charging station. Furthermore, it effectively alleviates various phenomena such as increased operational volatility and voltage drop caused by disorderly charging of large numbers of vehicles entering the simulated traffic network. Therefore, the charging load prediction method for simulated vehicles in this application can be applied to real-world situations and is more accurate than existing charging load prediction methods.

[0068] In an exemplary embodiment, S100 includes: during the process of the simulated vehicle traveling in a preset simulated traffic network, when the simulated vehicle is traveling on any target road in the preset simulated traffic network, obtaining the road type of the target road and detecting the road speed matching the road type; based on the road speed, detecting the unit state of charge consumption information and travel distance information of the simulated vehicle traveling on the target road; based on the unit state of charge consumption information, updating the historical state of charge information of the simulated vehicle in the previous time step to obtain the state of charge information of the simulated vehicle in the current time step; based on the travel distance information, updating the historical vehicle position information of the simulated vehicle in the previous time step to obtain the vehicle position information of the simulated vehicle in the current time step.

[0069] Road types can be classified by technical grade, such as expressway, first-class highway, second-class highway, etc.; or by functional grade, such as expressway, main road, secondary road, local road, etc. Different road types have different permissible driving speeds.

[0070] Specifically, as the simulated vehicle travels within the pre-set simulated traffic network, its state of charge and location information are updated in real time. Therefore, it is necessary to monitor these two constantly updated parameters. Specifically, when the simulated vehicle travels on any target road within the pre-set simulated traffic network, the road type of the target road is obtained, and the road speed matching the road type is detected. For example, the road speed on an uphill road is slower than the road speed on a downhill road. Then, by using the road speed and the simulation duration between the previous and current time steps, the distance traveled by the simulated vehicle on the target road is obtained. Based on the distance traveled, the unit state of charge consumption information of the simulated vehicle on the target road is further detected. Finally, for updating the state of charge information, the historical state of charge information of the simulated vehicle in the previous time step is updated based on the unit state of charge consumption information. That is, the historical state of charge information of the simulated vehicle in the previous time step is subtracted from the unit state of charge consumption information to obtain the state of charge information of the simulated vehicle in the current time step. For updating the vehicle position information, the historical vehicle position information of the simulated vehicle in the previous time step is updated based on the distance traveled to obtain the vehicle position information of the simulated vehicle in the current time step.

[0071] The process involves several steps: First, the distance traveled by the simulated vehicle on the target road is obtained using the road speed and the simulation duration between the previous and current time steps. This includes multiplying the road speed by the simulation duration between the previous and current time steps to determine the distance traveled by the simulated vehicle. Second, based on the distance traveled, the vehicle's state of charge consumption per unit distance on the target road is detected. This includes acquiring the vehicle's charging capacity and energy consumption per unit distance, and then using these information to determine the vehicle's state of charge consumption per unit distance. Third, based on the distance traveled, the vehicle's historical position information from the previous time step is updated. This includes acquiring the starting and ending points of the target road, limiting the vehicle's position to be between these points, and then using the ratio between the distance traveled and the length of the target road to determine the vehicle's position at the current time step.

[0072] Taking the following expression as an example, the update process of the vehicle's state of charge information and vehicle position information during vehicle operation is as follows:

[0073]

[0074]

[0075]

[0076] In the formula, This indicates the charge status information of the nth vehicle at the current time step. This represents the state of charge consumption of the nth vehicle per unit time on road ij, i.e., the unit state of charge consumption information, where w represents the vehicle's power consumption per unit distance. Indicates the simulation time interval. The charging capacity information for the nth electric vehicle is obtained through sampling using the Monte Carlo method. This indicates the location of the nth electric vehicle at the current time step, specifically its position within a road. This indicates the starting position information of road ij. This represents the endpoint location information of road ij, where k represents the number of time intervals passed. This represents the simulation duration, which consists of multiple simulation time intervals between the previous time step and the current time step.

[0077] In the above embodiments, by accurately detecting the state of charge information and vehicle location information of the simulated vehicle, the state of charge information and vehicle location information of the simulated vehicle can be updated in real time, making the simulated driving process of the simulated vehicle accurate, and the subsequent charging judgment based on the real-time updated state of charge information and vehicle location information is also more accurate.

[0078] In one exemplary embodiment, such as Figure 3 As shown, S200 includes:

[0079] S220, when the state of charge information is within the preset state of charge information range, the state of charge information is processed by a membership function to obtain the first charging probability corresponding to the state of charge information. The preset state of charge information range represents whether the simulated vehicle needs to be charged. When the state of charge information is less than the preset state of charge information range, the simulated vehicle needs to be charged. When the state of charge information is greater than the preset state of charge information range, the simulated vehicle does not need to be charged.

[0080] S240, when the first charging probability is the first preset value, the charging distance information between the simulated vehicle and multiple simulated charging stations is detected based on the vehicle location information.

[0081] S260, when there is charging distance information within the preset charging distance information range and no charging distance information less than the preset charging distance information range, the membership function is processed on the charging distance information to obtain the second charging probability corresponding to the charging distance information. Here, the preset charging distance information range represents whether the simulated vehicle needs to be charged. When there is charging distance information less than the preset charging distance information range, the simulated vehicle needs to be charged. When all charging distance information is greater than the preset charging distance information range, the simulated vehicle does not need to be charged.

[0082] S280, when the second charging probability is the second preset value, it is determined that the simulated vehicle needs to be charged.

[0083] Specifically, the decision of whether to charge the simulated vehicle is primarily related to the vehicle's current state of charge (SOC) and location information; more specifically, it is related to the SOC and the charging distance from the simulated charging station. However, directly assigning a fixed value or a specific mathematical expression to the charging decision is inaccurate. Therefore, fuzzy reasoning is used to describe the user's charging decision. Membership functions considering SOC and charging distance information represent the user's intention to charge the simulated vehicle, with SOC having higher priority than charging distance. Furthermore, the charging distance between the simulated vehicle and the simulated charging station can be determined using the vehicle's location information.

[0084] First, it is determined whether the state of charge information is within the preset state of charge information range. When the state of charge information is less than the preset state of charge information range, the simulated vehicle needs to be charged. When the state of charge information is greater than the preset state of charge information range, the simulated vehicle does not need to be charged. When determining whether the state of charge information is within the preset state of charge information range, it is uncertain whether the simulated vehicle needs to be charged.

[0085] At this point, a first charging probability corresponding to the state of charge (SOC) information can be obtained by processing the SOC information with a membership function. When the first charging probability is a first preset value (i.e., 1), it is considered that the simulated vehicle needs to be charged, taking into account the SOC information. However, it is also necessary to further consider the charging distance information between the simulated vehicle and multiple simulated charging stations. That is, it is necessary to determine whether there are simulated charging stations whose charging distance information is within the preset charging distance information range. When there are simulated charging stations whose charging distance information is less than the preset charging distance information range, it means that the simulated vehicle can be charged in time and the simulated vehicle needs to be charged. When the charging distance information is greater than the preset charging distance information range, it means that the distance between the simulated vehicle and each simulated charging station is far and the simulated vehicle does not need to be charged. When there are charging distance information within the preset charging distance information range and no charging distance information less than the preset charging distance information range, a second charging probability corresponding to the charging distance information can be obtained by processing the charging distance information with a membership function. When the second charging probability is a second preset value (i.e., 1), it is determined that the simulated vehicle needs to be charged.

[0086] For example, during the simulation, when the State of Charge (SOC) is ≤ 0.2, charging is required, and the nearest simulated charging station is selected. If it is greater than 0.6, charging is not required. If the SOC is between 0.2 and 0.6, the membership function is used to calculate the charging probability. A random value is selected based on this probability. If the probability is 1, the charging distance information is considered for further judgment. If there is a simulated charging station less than 3km away, charging is performed. In this case, when selecting simulated charging stations based on resource consumption information, the selection is also based on the simulated charging stations less than 3km away. If all simulated charging stations are greater than 10km away, charging is not considered. When the charging distance is between 3km and 10km, the membership function is first used to process the charging distance information, and a random value is selected based on the probability. If the probability is 1, charging is confirmed. At this time, the impact of the grid electricity price is analyzed, the theoretical charging service cost is calculated, and finally, the distance and service cost are combined to quantify the distance into a cost. The cost is calculated comprehensively, and the simulation charging station with the lowest cost is selected for charging. Furthermore, when calculating the probability that charging will not proceed if a value of 1 is not obtained, the labeled 1 is affected by the charging distance information when the membership function is used to process the charging distance information. The probability of charging distance information in the middle range is obtained according to the distance, and the probability of taking 1 is smaller the farther away it is.

[0087] In one embodiment, the membership functions for state of charge information and charging distance information are:

[0088]

[0089]

[0090] In the formula, This indicates the probability that the vehicle will make the decision to charge. For the first charging probability, This is the second charging probability; This indicates the current state of charge of the nth vehicle. and These are the mean and variance of the membership function corresponding to the state of charge information, respectively. This represents the charging distance information of the nth vehicle from the mth simulated charging station; and These are the mean and variance of the membership function corresponding to the charging distance information, respectively.

[0091] In the above embodiments, the user's charging intention is described by considering fuzzy reasoning. That is, the user's charging idea is represented by the membership function that considers the state of charge information and the membership function that considers the charging distance information. In this process, the priority of the state of charge information is greater than the priority of the charging distance information, which can more accurately determine whether the simulated vehicle needs to be charged.

[0092] In an exemplary embodiment, obtaining the first power consumption resource information of the simulated power distribution network connected to multiple simulated charging stations within a preset simulated traffic network at different time steps includes: for each simulated charging station, obtaining historical charging load information, basic load information of the simulated power distribution network connected to the simulated charging station, and initial power consumption resource information of the connected simulated power distribution network supplying power to the simulated charging station at each time step; and detecting the first power consumption resource information of the simulated power distribution network supplying power to the simulated charging station at different time steps based on the historical charging load information, basic load information, and initial power consumption resource information.

[0093] Among them, historical charging load information refers to the additional electricity load generated by the simulated vehicle during charging within a historical time period, such as the day-ahead charging load information; basic load information refers to other loads besides the load generated by the simulated vehicle charging, such as daily electricity consumption load information, and basic load information is the load that all distribution network nodes have.

[0094] Specifically, for each simulated charging station, the first power consumption resource information is the time-of-use electricity price for the power supply from the distribution network to the simulated charging station. The time-of-use electricity price can be determined based on historical charging load information, which can be the charging load information from the previous day. The initial power consumption resource information is, simply put, the initial electricity price for each stage of the time-of-use electricity price. More specifically, firstly, for each simulated charging station, historical charging load information and the basic load information of the simulated distribution network are obtained. These are then superimposed to generate historical total charging load information for the power supply from the simulated distribution network to the simulated charging station. The maximum and minimum values ​​of the historical total charging load information are obtained. Based on these values, the number of segments in the first power consumption resource information, and the influence weight of the initial power consumption resource information, the initial power consumption resource information is updated. This yields the first power consumption resource information for the power supply from the simulated distribution network to the simulated charging station at each time step.

[0095] It should be noted that the charging load information of the simulated charging station refers to the sum of the charging load information generated by all simulated vehicles charging in that simulated charging station; the basic load information is the load other than the load generated by simulated vehicle charging, such as the basic load value obtained from daily electricity consumption, and the historical charging load information is the load value obtained from the previous day. This is equivalent to the load situation of vehicles charging haphazardly in each simulated charging station when the first method of calculating electricity consumption resource information in this embodiment is not used, and can be used to eliminate interference. In simpler terms, when the power grid sets time-of-use pricing, it needs to consider the total load result, which includes the charging load. However, the real-time charging load causes the electricity price to constantly change. Therefore, the time-of-use pricing is calculated by summing the previous day's charging load information, i.e., the result of haphazard charging load, with the basic load information.

[0096] For each simulated charging station, the expression for obtaining the first power consumption resource information is: ,in, This indicates the first power consumption resource information at time step t; This represents the base load plus the day-ahead charging load. This represents the minimum total load value for the current day; This represents the maximum daily load; K represents the number of electricity price segments. Indicates rounding down. This indicates the initial power consumption information at different time steps.

[0097] In the above embodiments, by combining basic load information with historical charging load information, the initial power consumption resource information of the simulated distribution network supplying power to the simulated charging station at each time step can be updated, and the first power consumption resource information of the simulated distribution network supplying power to the simulated charging station at different time steps can be accurately determined.

[0098] In an exemplary embodiment, obtaining second power consumption resource information that matches the charging load of multiple simulated charging stations within the same time step includes:

[0099] Acquire the initial second power consumption resource information of each of the multiple simulated charging stations, the pre-allocation charging load information when no load allocation was performed in the previous time step, and the post-allocation charging load information after load allocation was performed in the previous time step; based on the multiple initial second power consumption resource information, the multiple pre-allocation charging load information, and the multiple post-allocation charging load information, detect the second power consumption resource information that matches the charging load of each of the multiple simulated charging stations in the current time step.

[0100] Specifically, firstly, the initial second power consumption resource information of each of the multiple simulated charging stations, the pre-allocation charging load information when no load allocation was performed in the previous time step, and the post-allocation charging load information after load allocation was performed in the previous time step are obtained. The post-allocation charging load information refers to the charging load information of the simulated charging station after load allocation according to the minimum voltage deviation of the distribution network. Furthermore, based on the multiple initial second power consumption resource information, the multiple pre-allocation charging load information, and the multiple post-allocation charging load information, second power consumption resource information matching the charging load of each of the multiple simulated charging stations in the current time step can be generated.

[0101] Second electricity consumption resource information The specific expression can be: In the formula, This is the charging load information after allocation; It contains the charging load information of all simulated charging stations before allocation; M represents the number of simulated charging stations, and m is the m-th simulated charging station; This represents the initial second power consumption resource information. In simpler terms, the second power consumption resource information refers to the service electricity price of each simulated charging station. This service electricity price differs from the time-of-use electricity price of the distribution network. At the same time step, the time-of-use electricity price is the same for different simulated charging stations; the difference in charging service electricity price is what causes the differences between different simulated charging stations at the same time step. The service electricity price of each simulated charging station is set based on the load conditions of each simulated charging station at the previous time step.

[0102] It should be explained that setting the service price based on the load of the simulated charging station at the previous moment is to guide users to choose the simulated charging station and time reasonably and to balance the load distribution. For example, increasing the service price when the load is high can encourage some users to go to other simulated charging stations or charge later; decreasing the service price when the load is low can attract users to charge and improve the utilization rate of the simulated charging station.

[0103] In one embodiment, the allocated charging load information refers to the charging load information of the simulated charging station after the load is allocated according to the minimum distribution network voltage deviation. The allocation method can be as follows: the allocated charging load is applied as a variable to the standard distribution network test system IEEE 33 nodes and superimposed on the original system base load. With the total load balance and the upper and lower limits of the load of each simulated charging station as constraints, and with the minimum distribution network voltage deviation as the objective, optimization calculation is performed to calculate how much the load of each simulated charging station should be to minimize the impact on the system voltage when the total simulated charging station load remains unchanged. That is, the load of each simulated charging station is allocated.

[0104] In the above embodiments, by acquiring the initial second power consumption resource information of each of the multiple simulated charging stations, the charging load information before load allocation when no load allocation was performed in the previous time step, and the charging load information after load allocation was performed in the previous time step, the second power consumption resource information matching the charging load of the multiple simulated charging stations in the same time step can be accurately detected for each simulated charging station.

[0105] In an exemplary embodiment, acquiring the driving resource consumption information and time resource consumption information of a simulated vehicle traveling to multiple simulated charging stations includes: for each simulated charging station, when the simulated vehicle is traveling towards the simulated charging station on a target road, detecting the charging distance information between the simulated vehicle and the simulated charging station based on the vehicle's position information; acquiring the unit driving resource consumption information, unit time resource consumption information, and road speed information of the simulated vehicle; detecting the driving resource consumption information of the simulated vehicle traveling to the simulated charging station based on the unit driving resource consumption information and the charging distance information; and detecting the time resource consumption information of the simulated vehicle traveling to the simulated charging station based on the unit time resource consumption information, the charging distance information, and the road speed information.

[0106] Specifically, when selecting a target simulated charging station from multiple simulated charging stations, it is also necessary to consider the resource consumption information of the simulated vehicle traveling to and from each station. When the simulated vehicle is traveling towards the simulated charging station on the target road, for each station, the charging distance information between the simulated vehicle and the station is first detected based on the vehicle's location information. Then, the resource consumption information per unit of travel, the resource consumption information per unit of time, and the road speed information of the target road are obtained. At this point, the resource consumption information of the simulated vehicle traveling to the station can be detected by multiplying the resource consumption information per unit of travel and the charging distance information. Furthermore, the resource consumption information of the simulated vehicle traveling to the station can be detected by combining the resource consumption information per unit of time, the charging distance information, and the road speed information.

[0107] Furthermore, when the simulated vehicle and the simulated charging station are not on the same node—that is, when the current location of the simulated vehicle is not at the location of the simulated charging station—the charging distance information is obtained from the road length information of the current road or a combination of the road length information of multiple roads. In other words, when a simulated vehicle travels to a simulated charging station, the charging distance information is obtained from the combination of the relevant roads between the simulated vehicle and the simulated charging station. The resource consumption information for traveling to the simulated charging station is detected by multiplying the unit travel resource consumption information of each road by the road length information of each road. Simultaneously, the travel time information of each road can be obtained based on the charging distance information and road speed information of each road, and the resource consumption information for traveling to the simulated charging station is detected by combining the travel time information and the unit time resource consumption information of each road.

[0108] Information on driving resource consumption Time consumption resource information Their respective expressions are as follows: , In the formula, This represents the resource consumption per unit distance traveled on road ij when heading to the simulated charging station m; that is, the cost of travel per unit distance. This represents the resource consumption information per unit time on road ij when heading to the simulated charging station m, i.e., the cost per unit time. G is the set of all roads.

[0109] In the above embodiments, the resource consumption information of the simulated vehicle traveling to the simulated charging station is accurately detected by using the resource consumption information per unit of travel and the road length information corresponding to each road; the resource consumption information of the simulated vehicle traveling to the simulated charging station is accurately detected by using the resource consumption information per unit of time, the road length information, and the road speed information corresponding to each road.

[0110] In an exemplary embodiment, the method for predicting the charging load of a simulated vehicle further includes: after the simulated vehicle travels to the target simulated charging station for charging, obtaining the charging capacity information of the simulated vehicle and the charging power information corresponding to the charging pile used by the simulated vehicle when charging at the target simulated charging station; and updating the state of charge information of the simulated vehicle at the previous time step based on the charging capacity information and the charging power information.

[0111] Specifically, during the process of the simulated vehicle traveling to the target simulated charging station, the vehicle's state of charge (SOC) and location information are updated in real time. When the simulated vehicle arrives at the target simulated charging station to prepare for charging, it first selects a charging pile within the station. Different types of charging piles have different charging power information. Therefore, by combining the simulated vehicle's charging capacity information and the charging power information of the charging pile used, the simulated vehicle can be charged at a fixed charging power to obtain the amount of electricity charged by the simulated vehicle (n) at the simulated charging station (m) per unit time. Based on the amount of electricity charged by the simulated vehicle (n) at the simulated charging station (m) per unit time, the vehicle's SOC information at the previous time step is updated in real time. Simultaneously, the load status of the simulated charging station can also be updated.

[0112] Furthermore, the process of updating the state of charge information of the simulated vehicle during charging is as follows: , ,in, This indicates the time interval between each time step during the charging process. For charging capacity information, For charging power information, This represents the amount of electricity that the simulated vehicle n charges at the simulated charging station m per unit time. This represents the state of charge information updated at time step t. This represents the state of charge information at time step t-1.

[0113] In one embodiment, this application studies vehicles that travel continuously, such as electric taxis, which are generally charged using fast charging. Therefore, the selected charging station also needs to meet this requirement. However, after the simulated vehicle returns to its residence, since the stay at home is relatively long, the charging behavior after returning home will be slow charging.

[0114] In the above embodiments, by acquiring charging capacity information and charging power information, the amount of electricity charged by the simulated vehicle can be accurately analyzed, and the state of charge information of the simulated vehicle at the previous time step can be accurately updated.

[0115] In an exemplary embodiment, to more accurately simulate a pre-defined traffic network, generally, more than one simulated vehicle is traveling in the pre-defined traffic network. Therefore, each simulated charging station needs to consider the charging status of all simulated vehicles. Taking resource consumption information as cost information as an example, a specific example of the load prediction for each simulated charging station is as follows: The simulated traffic network has 24 nodes, of which 9 are the nodes where the simulated charging stations are located. The topology of the simulated traffic network is as follows: Figure 4As shown; the simulated power distribution network includes 33 nodes, of which 9 nodes are where the simulated charging stations are located, serving as the coupling points between the simulated transportation network and the simulated power distribution network. The topology of the simulated transportation network is as follows. Figure 5 As shown in the figure. The simulated traffic network is divided into three areas: residential, work, and commercial, and roads are classified into four levels, with different average travel speeds at each level. The simulated power distribution network voltage is 12.66 kV, and the reference power is 1 MVA. The total simulation duration is T = 24 hours, and the voltage reference value for the simulated power distribution network is set to 1.0 pu. The membership functions for state of charge information and charging distance information are shown below. Figure 6 and Figure 7 As shown; the time-of-use electricity price of the power grid is as follows Figure 8 As shown, Figure 8 Pricing method 1 in the simulation is based on basic load information, while pricing method 2 is based on a combination of basic load information and historical charging load information; the simulated charging station service electricity price is as follows: Figure 9 As shown, a method based on simulated traffic network and real-time vehicle status is used for load forecasting. Following the steps described above, the daily load forecast for each simulated charging station can be obtained. To verify the effectiveness of this method, three forecasting methods are compared:

[0116] Method 1: For example Figure 10 As shown, without considering the effect of electricity prices, the load forecast results for disordered user charging show that user charging behavior is highly random, generally charging when the state of charge level is low or when the user is close to the simulated charging station. This method has many load peaks and the user's cost is also high, resulting in poor economic efficiency; Method 2: Figure 11 As shown, considering the load forecasting results guided by the grid time-of-use pricing based on both basic load information and historical charging load information, and without considering service pricing, users will concentrate their charging behavior when prices are lower; Method 3: As Figure 12 As shown, considering the grid time-of-use pricing based on both basic load information and historical charging load information, as well as the load forecasting results guided by the simulated service price of charging stations, the charging load distribution is more uniform, the peak value is lower than the previous two methods, and the impact on the distribution network is smaller. Not only are the forecast results more accurate, but they are also beneficial to the safe and stable operation of the distribution network.

[0117] The computer hardware environment for performing the optimized calculations can be an Intel(R) Core(TM) CPU i5-13500HX with a clock speed of 2.5GHz and 16GB of memory; the software environment is a Windows 11 operating system, which is not limited here.

[0118] Furthermore, taking electric vehicles as an example, the technical problem to be solved by this application is to propose a method for predicting the charging load of simulated vehicles by combining traffic network information, the status of the electric vehicle itself, and the real-time status of the charging station, and considering the information interaction among the three parties. By dynamically setting electricity prices to guide the charging behavior of electric vehicles, the charging load of simulated vehicles can be accurately predicted, thereby improving the accuracy and practicality of the daily load prediction of each charging station.

[0119] To achieve the above objectives, such as Figure 13 As shown, the technical solution adopted in this application is:

[0120] 1) Randomly sample relevant parameters of electric vehicles using the Monte Carlo method, assuming these parameters satisfy a certain probability distribution and range, including the vehicle's capacity, initial state of charge, residential location (i.e., trip start point), trip start and end times, expected state of charge, and charging power; 2) Construct a traffic network, forming an adjacency matrix of roads. This matrix provides the connection relationships and distances between road nodes, while also marking the locations of charging stations. Divide each node into residential, work, and commercial zones. Users start from a residential zone and return to their residential zone, forming a complete daily travel chain; 3) Complete the preparations for steps 1) and 2). Then, the trip simulation for each vehicle begins. First, the destination of a segment of the trip for each vehicle is extracted, and the shortest path to the destination is planned according to Dijstra's shortest path algorithm; 4) The driving route is planned using the shortest path algorithm in step 3), and the state of charge of each electric vehicle is updated according to the time segment, including the state of charge and location information of each vehicle, and the load of each charging station is updated according to the charging status of each vehicle in the current time segment; 5) After updating the state of charge and location information of the vehicles in step 4), a decision is made on whether to charge based on the state of charge, location, grid electricity price and charging station service electricity price information of the vehicles. If not charging, the vehicle continues driving until it reaches its destination, updating the vehicle and charging station status during the journey. Upon arrival, a decision is made regarding ending the day's trip. If ending the trip, the final destination is set as the accommodation, and a return route is planned. The vehicle's real-time status is also updated. If not ending the trip, the current destination is used as the starting point for the next segment, and the destination is extracted using the Monte Carlo method (step 3). This process is repeated until the day's trip ends or a charging decision is made. If charging is decided, the current road travel is completed first, then the cost of reaching different charging stations is considered, including the time-of-use electricity price provided by the power grid, the service price of each charging station, and the driving and time costs associated with each station. A suitable charging station is selected with the goal of minimizing the user's total cost. The route to that station is planned, and the changes in the vehicle's state of charge and location information during the journey are updated. Updating the vehicle's real-time status refers to updating its state of charge and location information. 6) After completing step 5) and selecting a suitable charging station, plan the route to the charging station using the method in step 3) and update the real-time status of the vehicle en route using the method in step 4). When arriving at the charging station to charge, first select the type of charging pile. Generally, fast charging is used, but if the vehicle is to be charged after arriving home, since the stay at home is relatively long, slow charging is selected for charging after arriving home. During charging, charge at a fixed charging power and update the changes in the vehicle's state of charge, while also updating the load status of the charging station. A judgment is made during charging, and charging is stopped when the expected state of charge is reached.7) After charging is complete, it will be determined whether to continue the next leg of the journey. If so, the destination will be randomly selected again using the method in step 3), and the above process will be repeated until the last leg of the journey is completed. If the journey is to be ended, the destination of the last leg of the journey for the day will be determined as the residence, completing the final status update process and forming a complete travel chain. 8) After returning to the residence, the current charge status will be assessed, taking into account the user's psychological state, to determine whether to continue charging. If charging is to be continued, since the user will stay at the residence for a relatively long time, slow charging will be used; otherwise, the journey will end.

[0121] Based on the above steps, this method comprehensively considers traffic network information, the randomness of vehicle parameters, and the randomness of the driving process, and accurately describes the vehicle's driving process. At the same time, it combines the real-time status of the vehicle itself, the real-time status of the power distribution system and the charging station to predict and guide the electric vehicle charging load, thereby improving the accuracy of electric vehicle charging. In addition, the method for guiding electric vehicle charging in this application also has the effect of peak shaving and valley filling of the power distribution network load, effectively alleviating the voltage drop phenomenon caused by the disorderly charging of large-scale electric vehicles, and laying the foundation for subsequent research on orderly charging strategies.

[0122] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time step, but can be executed at different time steps. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0123] Based on the same inventive concept, this application also provides a charging load prediction device for a simulated vehicle to implement the charging load prediction method for the simulated vehicle described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the charging load prediction device for simulated vehicles provided below can be found in the limitations of the charging load prediction method for simulated vehicles described above, and will not be repeated here.

[0124] In one exemplary embodiment, such as Figure 14As shown, a charging load prediction device for a simulated vehicle is provided, comprising: an information detection module 100, a charging judgment module 200, a resource consumption acquisition module 300, a resource consumption analysis module 400, and a charging module 500. The information detection module 100 is used to detect the state of charge (SBC) and vehicle location information of the simulated vehicle while it is traveling in a preset simulated traffic network. The charging judgment module 200 is used to determine whether the simulated vehicle needs charging based on the SBC and vehicle location information. The resource consumption acquisition module 300 is used to, when the simulated vehicle needs charging, acquire the power supply information from the simulated power distribution network connected to multiple simulated charging stations within the preset simulated traffic network at different time steps. The system includes: first, power consumption resource information; second, power consumption resource information matching the charging load of multiple simulated charging stations within the same time step; and third, driving and time consumption resource information of the simulated vehicle traveling to multiple simulated charging stations for charging. A resource consumption analysis module 400 is used to weight the first, second, driving, and time consumption resource information to obtain the target power consumption resource information for each simulated charging station. A charging module 500 is used to select the target simulated charging station with the lowest target power consumption resource information from among multiple simulated charging stations, and obtain the predicted charging load information of the simulated vehicle after controlling the simulated vehicle to travel to the target simulated charging station for charging.

[0125] In one embodiment, the information detection module 100 is used to acquire the road type of the target road and detect the road speed matching the road type when the simulated vehicle is traveling on any target road in the preset simulated traffic network; based on the road speed, detect the unit state of charge consumption information and travel distance information of the simulated vehicle traveling on the target road; based on the unit state of charge consumption information, update the historical state of charge information of the simulated vehicle in the previous time step to obtain the state of charge information of the simulated vehicle in the current time step; based on the travel distance information, update the historical vehicle position information of the simulated vehicle in the previous time step to obtain the vehicle position information of the simulated vehicle in the current time step.

[0126] In one embodiment, the charging determination module 200 is further configured to: when the state of charge information is within a preset state of charge information range, perform membership function processing on the state of charge information to obtain a first charging probability corresponding to the state of charge information, wherein the preset state of charge information range indicates whether the simulated vehicle needs charging; when the state of charge information is less than the preset state of charge information range, the simulated vehicle needs charging; when the state of charge information is greater than the preset state of charge information range, the simulated vehicle does not need charging; when the first charging probability is a first preset value, detect the charging distance information between the simulated vehicle and multiple simulated charging stations based on the vehicle location information; when there is charging distance information within the preset charging distance information range and no charging distance information is less than the preset charging distance information range, perform membership function processing on the charging distance information to obtain a second charging probability corresponding to the charging distance information, wherein the preset charging distance information range indicates whether the simulated vehicle needs charging; when there is charging distance information less than the preset charging distance information range, the simulated vehicle needs charging; when all charging distance information is greater than the preset charging distance information range, the simulated vehicle does not need charging; when the second charging probability is a second preset value, determine that the simulated vehicle needs charging.

[0127] In one embodiment, the resource consumption acquisition module 300 is further configured to acquire, for each simulated charging station, historical charging load information, basic load information of the simulated distribution network to which the simulated charging station is connected, and initial power consumption resource information of the connected simulated distribution network supplying power to the simulated charging station at each time step; and detect the first power consumption resource information of the simulated distribution network supplying power to the simulated charging station at different time steps based on the historical charging load information, basic load information and initial power consumption resource information.

[0128] In one embodiment, the resource consumption acquisition module 300 is further configured to acquire the initial second power consumption resource information of each of the multiple simulated charging stations, the pre-allocation charging load information when no load allocation was performed in the previous time step, and the post-allocation charging load information after load allocation was performed in the previous time step; and detect the second power consumption resource information that matches the charging load of each of the multiple simulated charging stations in the current time step based on the multiple initial second power consumption resource information, the multiple pre-allocation charging load information and the multiple post-allocation charging load information.

[0129] In one embodiment, the resource consumption acquisition module 300 is further configured to, for each simulated charging station, when the simulated vehicle is traveling towards the simulated charging station on the target road, detect the charging distance information between the simulated vehicle and the simulated charging station based on the vehicle's location information; acquire the unit travel resource consumption information, unit time resource consumption information, and road speed information of the simulated vehicle; detect the travel resource consumption information of the simulated vehicle traveling to the simulated charging station for charging based on the unit travel resource consumption information and the charging distance information; and detect the time resource consumption information of the simulated vehicle traveling to the simulated charging station for charging based on the unit time resource consumption information, the charging distance information, and the road speed information.

[0130] In one embodiment, the simulated vehicle charging device further includes a state of charge information update module. The state of charge information update module is used to obtain the charging capacity information of the simulated vehicle and the charging power information corresponding to the charging pile used by the simulated vehicle when charging at the target simulated charging station after the simulated vehicle has driven to the target simulated charging station for charging; and to update the state of charge information of the simulated vehicle in the previous time step according to the charging capacity information and the charging power information.

[0131] Each module in the aforementioned simulated vehicle charging device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0132] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 15As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for predicting the charging load of a simulated vehicle. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0133] Those skilled in the art will understand that Figure 15 The structure shown is a block diagram of a partial structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0134] In one embodiment, a computer device is also provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments. In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps in the above-described method embodiments. In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0135] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0136] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0137] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for predicting the charging load of a simulated vehicle, characterized in that, The method includes: During the process of the simulated vehicle driving in a preset simulated traffic network, the state of charge information and vehicle position information of the simulated vehicle are detected. Based on the state of charge information and the vehicle location information, it is determined whether the simulated vehicle needs to be charged; When the simulated vehicle needs to be charged, the system acquires the first power consumption resource information of the simulated power distribution network connected to the multiple simulated charging stations in the preset simulated traffic network at different time steps, the second power consumption resource information of the charging load matching the multiple simulated charging stations at the same time step, and the driving resource information and time resource information of the simulated vehicle going to the multiple simulated charging stations for charging. The first power consumption resource information, the second power consumption resource information, the driving consumption resource information, and the time consumption resource information are weighted and processed to obtain the target consumption resource information of each simulated charging station. The target simulated charging station with the lowest resource consumption information is selected from the plurality of simulated charging stations, and after the simulated vehicle is controlled to drive to the target simulated charging station for charging, the predicted charging load information of the simulated vehicle is obtained.

2. The method according to claim 1, characterized in that, The detection of the state of charge information and vehicle position information of the simulated vehicle includes: When the simulated vehicle travels on any target road in the preset simulated traffic network, the road type of the target road is obtained, and the road speed matching the road type is detected. Based on the road travel speed, detect the unit state of charge consumption information and travel distance information of the simulated vehicle traveling on the target road; Based on the unit state of charge consumption information, the historical state of charge information of the simulated vehicle at the previous time step is updated to obtain the state of charge information of the simulated vehicle at the current time step. Based on the travel distance information, the historical vehicle position information of the simulated vehicle in the previous time step is updated to obtain the vehicle position information of the simulated vehicle in the current time step.

3. The method according to claim 2, characterized in that, The step of determining whether the simulated vehicle needs charging based on the state of charge information and the vehicle location information includes: When the state of charge information is within a preset state of charge information range, the state of charge information is processed by a membership function to obtain the first charging probability corresponding to the state of charge information. The preset state of charge information range indicates that it is uncertain whether the simulated vehicle needs to be charged. When the state of charge information is less than the preset state of charge information range, the simulated vehicle needs to be charged. When the state of charge information is greater than the preset state of charge information range, the simulated vehicle does not need to be charged. When the first charging probability is a first preset value, the charging distance information between the simulated vehicle and the multiple simulated charging stations is detected based on the vehicle location information. When the charging distance information is within a preset charging distance information range and there is no charging distance information less than the preset charging distance information range, the charging distance information is processed by a membership function to obtain the second charging probability corresponding to the charging distance information. The preset charging distance information range represents whether the simulated vehicle needs to be charged. When there is a charging distance information less than the preset charging distance information range, the simulated vehicle needs to be charged. When all the charging distance information is greater than the preset charging distance information range, the simulated vehicle does not need to be charged. When the second charging probability is the second preset value, it is determined that the simulated vehicle needs to be charged.

4. The method according to claim 1, characterized in that, The step of obtaining the first power consumption resource information of the simulated power distribution network connected to multiple simulated charging stations in the preset simulated traffic network at different time steps includes: For each of the simulated charging stations, historical charging load information, basic load information of the simulated distribution network to which the simulated charging station is connected, and initial power consumption resource information of the simulated distribution network to which the station is connected at each time step are obtained. Based on the historical charging load information, the basic load information, and the initial power consumption resource information, the first power consumption resource information of the simulated distribution network supplying power to the simulated charging station at different time steps is detected.

5. The method according to claim 1, characterized in that, Obtain second power consumption resource information that matches the charging load of each of the multiple simulated charging stations within the same time step, including: The initial second power consumption resource information of each of the multiple simulated charging stations, the charging load information before allocation when no load allocation was performed in the previous time step, and the charging load information after allocation after load allocation was performed in the previous time step are obtained. Based on multiple initial second power consumption resource information, multiple pre-allocation charging load information, and multiple post-allocation charging load information, detect the second power consumption resource information that matches the charging load of each of the multiple simulated charging stations within the current time step.

6. The method according to claim 1, characterized in that, Obtain information on the driving resource consumption and time resource consumption of the simulated vehicle as it travels to multiple simulated charging stations for charging, including: For each of the simulated charging stations, when the simulated vehicle is traveling towards the simulated charging station on the target road, the charging distance information between the simulated vehicle and the simulated charging station is detected based on the vehicle's position information; Obtain the resource consumption information per unit of travel, the resource consumption information per unit of time of the simulated vehicle, and the road speed information of the target road; Based on the unit driving resource consumption information and the charging distance information, the driving resource consumption information of the simulated vehicle traveling to the simulated charging station for charging is detected; Based on the resource consumption information per unit time, the charging distance information, and the road speed information, the time and resource consumption information of the simulated vehicle traveling to the simulated charging station for charging is detected.

7. The method according to claim 1, characterized in that, The method further includes: After the simulated vehicle travels to the target simulated charging station for charging, the charging capacity information of the simulated vehicle and the charging power information of the charging pile used by the simulated vehicle when charging at the target simulated charging station are obtained. Based on the charging capacity information and the charging power information, the state of charge information of the simulated vehicle at the previous time step is updated.

8. A charging load prediction device for a simulated vehicle, characterized in that, The device includes: The information detection module is used to detect the charge state information and vehicle position information of the simulated vehicle while it is driving in a preset simulated traffic network. The charging determination module is used to determine whether the simulated vehicle needs to be charged based on the state of charge information and the vehicle location information. The resource consumption acquisition module is used to acquire, when the simulated vehicle needs to be charged, the first power consumption resource information of the simulated power distribution network connected to the multiple simulated charging stations in the preset simulated traffic network at different time steps, the second power consumption resource information matching the charging load of the multiple simulated charging stations at the same time step, and the driving resource consumption information and time resource consumption information of the simulated vehicle going to the multiple simulated charging stations for charging. The resource consumption analysis module is used to perform weighted processing on the first power consumption resource information, the second power consumption resource information, the driving resource information and the time consumption resource information to obtain the target resource consumption information of each of the simulated charging stations. The charging module is used to select the target simulation charging station with the lowest target resource consumption information from the plurality of simulation charging stations, and to obtain the predicted charging load information of the simulation vehicle after the simulation vehicle drives to the target simulation charging station for charging.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images