Electric power allocation method and device based on electrical load of electric vehicle, and electronic equipment

Abstract

The invention discloses an electric power allocation method and device based on an electric vehicle electrical load and electronic equipment, and relates to the technical field of electric vehicle charging management and electric power system scheduling or other related fields, the method comprises the following steps: collecting travel behavior data of N electric vehicle users, and obtaining road network topology data, N being a specified numerical value; simulating road network driving conditions of the N electric vehicles in the target time period based on the travel behavior data and the road network topology data to obtain simulated travel information; determining charging demand information of each electric vehicle based on the simulated travel information; and summarizing the charging demand information of all the electric vehicles to obtain the spatial and temporal distribution demand of the electrical load, and generating an electric power allocation strategy based on the spatial and temporal distribution demand of the electrical load. The technical problem that the time-space allocation of electric power and electric energy is difficult to match the power demand of a user due to low accuracy of charging load analysis of the electric vehicle in the related technology is solved.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle charging management and power system dispatching technology, and more specifically, to a power dispatching method, apparatus, and electronic equipment based on the electric load of electric vehicles. Background Technology

[0002] With the rapid development of electrified transportation, electric vehicles (EVs) have become an important part of global green mobility, profoundly impacting the operation and planning of energy systems, especially power distribution networks. Against this backdrop, accurately predicting the spatiotemporal distribution of EV charging loads has become crucial for optimizing charging infrastructure layout and improving power system operating efficiency.

[0003] However, existing forecasting methods often overlook the complexity of traffic conditions and user charging habits, leading to significant discrepancies between forecasts and actual demand. This discrepancy, especially during peak hours and in key areas, can result in over- or under-investment in charging infrastructure, affecting the timely distribution of electricity and making it difficult to accurately match users' dynamically changing charging needs. For example, models based on fixed charging periods and methods, while reflecting the basic characteristics of charging load to some extent, fail to consider the specific behavioral patterns of different EV users and the impact of external factors such as traffic congestion on charging time.

[0004] More specifically, the low accuracy of electric vehicle charging load analysis in related technologies makes it difficult to match the timing and distribution of electrical energy with user demand. The root of this problem lies in neglecting changes in EV user behavior and the traffic environment: EV user behavior is highly variable and influenced by a variety of complex factors, while existing prediction methods (such as simple statistical analysis or predictions based on historical data) often fail to capture these subtle but crucial dynamic changes, thus making it difficult to provide accurate charging load forecasts. This problem is particularly prominent in the current context of rapid growth in EV ownership and constantly evolving user behavior patterns.

[0005] There is currently no effective solution to the above problems. Summary of the Invention

[0006] This invention provides a power dispatching method, apparatus, and electronic device based on the electric load of electric vehicles, to at least solve the technical problem in the related art where the timing and distribution of power is difficult to match the user's power demand due to the low accuracy of electric vehicle charging load analysis.

[0007] According to one aspect of the present invention, a power dispatching method based on the electric load of electric vehicles is provided, comprising: collecting travel behavior data of N electric vehicle users and obtaining road network topology data, wherein the travel behavior data includes travel start and end times, parking duration, and statistical distribution of charging decision data, and the road network topology data is used to characterize the node connection relationship and road segment length information of the road network, and N is a specified value; simulating the road network driving situation of N electric vehicles in a target time period based on the travel behavior data and the road network topology data to obtain simulated travel information; determining the charging demand information of each electric vehicle based on the simulated travel information, wherein the charging demand information includes: charging time point, charging location, and charging power demand; summarizing the charging demand information of all electric vehicles to obtain the spatiotemporal distribution demand of the power load, and generating a power dispatching strategy based on the spatiotemporal distribution demand of the power load, wherein the power dispatching strategy is used to guide the power dispatching and charging facility dispatching in each region and time period.

[0008] Further, the step of collecting travel behavior data from N electric vehicle users includes: obtaining historical travel records for the N electric vehicle users, wherein the historical travel records include: departure time, arrival time, parking duration, parking location, current trip power consumption, remaining power upon arrival, next trip power consumption, and charging behavior data for each trip; establishing a trip start and end time dataset based on the departure time and arrival time; establishing a parking duration distribution dataset based on the location type of the parking location and the corresponding parking duration; generating a charging decision dataset based on the current trip power consumption, remaining power upon arrival, next trip power consumption, and charging behavior data; and integrating the trip start and end time dataset, the parking duration distribution dataset, and the charging decision dataset to obtain the travel behavior data.

[0009] Further, the steps for obtaining road network topology data include: extracting basic road segment information from the road traffic management system, wherein the basic road segment information includes the location of road segment intersections and the road segment connection relationships; establishing a road segment length database by surveying the actual length of each road segment; constructing a road network model based on the road segment intersection locations, the road segment connection relationships, and the road segment length database, using the road segment intersections as topology nodes and the road segments as connecting lines; and outputting the road network model as the road network topology data.

[0010] Further, the step of simulating the road network driving conditions of N electric vehicles within a target time period based on the travel behavior data and the road network topology data to obtain simulated travel information includes: for each electric vehicle, determining the simulated travel time point of each simulated trip based on the statistical distribution of the travel start and end times in the travel behavior data; determining the simulated driving segment of each simulated trip based on the start and end points of the simulated trip and the road network topology data; for each simulated trip, calculating the estimated travel time and estimated power consumption of the simulated trip based on the simulated travel time point and the simulated driving segment; and generating the simulated travel information based on the estimated travel time and estimated power consumption of each simulated trip of the N electric vehicles.

[0011] Further, the step of determining the charging demand information of each electric vehicle based on the simulated travel information includes: determining the remaining battery power of the electric vehicle when it arrives at the simulated destination based on each simulated trip of each electric vehicle, according to the estimated time and estimated power consumption of the simulated trip; determining the charging strategy of the electric vehicle at the parking point corresponding to the simulated destination based on the remaining battery power, the simulated parking time, and the statistical distribution of the charging decision data in the travel behavior data, wherein the charging strategy includes: whether to charge, charging mode, and charging time; and calculating the charging power demand by combining the charging facility power parameters and availability information of the parking point with the charging strategy to obtain the charging demand information including the charging time point, charging location, and charging power demand.

[0012] Further, the step of summarizing the charging demand information of all the electric vehicles to obtain the spatiotemporal distribution demand of the electricity load includes: classifying and statistically analyzing the charging demand information according to pre-divided time intervals and geographical regions; calculating the total charging power demand for each time interval and each geographical region based on the classified charging demand information; generating matrix data reflecting the spatiotemporal distribution demand of the electricity load based on the total charging power demand for each time interval and each geographical region; and drawing an electricity load heat map reflecting the spatiotemporal distribution demand of the electricity load based on the matrix data.

[0013] Furthermore, the step of generating a power dispatching strategy based on the spatiotemporal distribution demand of the electricity load includes: analyzing the peak load period and the corresponding peak load region based on the spatiotemporal distribution demand; generating the power dispatching strategy based on the peak load period and the peak load region, combined with each dispatching node of the distribution network, wherein the power dispatching strategy includes: a first dispatching period and a first regional dispatching scheme for electricity, and a second dispatching period and a second regional dispatching scheme for charging facilities.

[0014] According to another aspect of the present invention, a power dispatching device based on the electric load of electric vehicles is also provided, comprising: a data acquisition unit, configured to acquire travel behavior data of N electric vehicle users and obtain road network topology data, wherein the travel behavior data includes travel start and end times, parking duration, and statistical distribution of charging decision data, and the road network topology data is used to characterize the node connection relationship and road segment length information of the road network, and N is a specified value; a simulation unit, configured to simulate the road network driving situation of N electric vehicles within a target time period based on the travel behavior data and the road network topology data, and obtain simulated travel information; a determination unit, configured to determine the charging demand information of each electric vehicle based on the simulated travel information, wherein the charging demand information includes: charging time point, charging location, and charging power demand; and a generation unit, configured to summarize the charging demand information of all electric vehicles to obtain the spatiotemporal distribution demand of the power load, and generate a power dispatching strategy based on the spatiotemporal distribution demand of the power load, wherein the power dispatching strategy is used to guide the power dispatching and charging facility dispatching in various regions and time periods.

[0015] Further, the collection unit includes: an acquisition module, used to acquire historical travel records of N electric vehicle users, wherein the historical travel records include: departure time, arrival time, parking duration, parking location, current trip power consumption, remaining power upon arrival, next trip power consumption, and charging behavior data for each trip; a first establishment module, used to establish a trip start and end time dataset based on the departure time and arrival time; a second establishment module, used to establish a parking duration distribution dataset based on the location type of the parking location and the corresponding parking duration; a first generation module, used to generate a charging decision dataset based on the current trip power consumption, remaining power upon arrival, next trip power consumption, and charging behavior data; and an integration module, used to integrate the trip start and end time dataset, the parking duration distribution dataset, and the charging decision dataset to obtain the travel behavior data.

[0016] Furthermore, the acquisition unit also includes: an extraction module for extracting basic road segment information from the road traffic management system, wherein the basic road segment information includes the location of road segment intersections and the road segment connection relationships; a third establishment module for establishing a road segment length database by surveying the actual length of each road segment; a construction module for constructing a road network model based on the location of the road segment intersections as topology nodes and the road segments as connecting lines, and the road segment length database; and an output module for outputting the road network model as the road network topology data.

[0017] Further, the simulation unit includes: a first determining module, used to determine the simulated travel time point of each simulated trip for each electric vehicle based on the statistical distribution of the travel start and end times in the travel behavior data; a second determining module, used to determine the simulated driving segment of each simulated trip based on the start and end points of the simulated trip and the road network topology data; a first calculating module, used to calculate the estimated time consumption and estimated power consumption of the simulated trip for each simulated trip based on the simulated travel time point and the simulated driving segment; and a second generating module, used to generate the simulated travel information based on the estimated time consumption and estimated power consumption of the simulated trip corresponding to each simulated trip of N electric vehicles.

[0018] Further, the determining unit includes: a third determining module, used to determine the remaining battery power of the electric vehicle when it arrives at the simulated destination based on each simulated trip of the electric vehicle, according to the estimated time and estimated power consumption of the simulated trip; a judging module, used to judge the charging strategy of the electric vehicle at the parking point corresponding to the simulated destination based on the remaining battery power, the simulated parking time, and the statistical distribution of the charging decision data in the travel behavior data, wherein the charging strategy includes: whether to charge, charging mode, and charging time; and a second calculation module, used to calculate the charging power demand by combining the charging facility power parameters and availability information of the parking point with the charging strategy, to obtain the charging demand information including the charging time point, charging location, and charging power demand.

[0019] Furthermore, the generation unit includes: a classification module, used to classify and statistically analyze the charging demand information according to pre-divided time intervals and geographical regions; a third calculation module, used to calculate the total charging power demand for each time interval and each geographical region based on the classified charging demand information; a third generation module, used to generate matrix data reflecting the spatiotemporal distribution demand of the electricity load based on the total charging power demand for each time interval and each geographical region; and a drawing module, used to draw a heat map of the electricity load reflecting the spatiotemporal distribution demand of the electricity load based on the matrix data.

[0020] Furthermore, the generation unit also includes: an analysis module, used to analyze the load peak period and the load peak region corresponding to the load peak period based on the spatiotemporal distribution demand analysis; and a fourth generation module, used to generate the power dispatch strategy based on the load peak period and the load peak region, combined with each dispatch node of the distribution network, wherein the power dispatch strategy includes: a first dispatch period and a first regional dispatch scheme for power, and a second dispatch period and a second regional dispatch scheme for charging facilities.

[0021] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the power dispatching method based on the electric load of electric vehicles as described above.

[0022] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the power dispatching method based on the electric load of electric vehicles as described in any one of the preceding embodiments.

[0023] According to another aspect of the present invention, a computer program product is also provided, including computer instructions, wherein when the computer instructions are executed by a processor, they implement the steps of the power dispatching method based on the electric load of electric vehicles as described in any one of the above embodiments.

[0024] This invention proposes a power dispatching method based on the electrical load of electric vehicles. First, travel behavior data of N electric vehicle users is collected, along with road network topology data. The travel behavior data includes travel start and end times, parking duration, and the statistical distribution of charging decision data. The road network topology data characterizes the node connections and road segment lengths of the road network. N is a specified value. Then, based on the travel behavior data and road network topology data, the road network driving conditions of the N electric vehicles within a target time period are simulated to obtain simulated travel information. Next, based on the simulated travel information, the charging demand information for each electric vehicle is determined. This charging demand information includes charging time, charging location, and charging power demand. Finally, the charging demand information of all electric vehicles is summarized to obtain the spatiotemporal distribution demand of the electrical load. Based on this spatiotemporal distribution demand, a power dispatching strategy is generated. This power dispatching strategy guides the power scheduling and charging facility scheduling in different regions and time periods.

[0025] This invention employs a combination of big data analysis and intelligent simulation. By comprehensively collecting and analyzing travel behavior data and road network topology data from multiple electric vehicle users, it aims to accurately depict the dynamic charging needs of the electric vehicle population. Specifically, the system first collects and processes diverse behavioral data, including travel start and end times, parking duration, and charging decisions. This data, combined with key information such as road network node connections and road segment lengths, constructs a highly realistic road network driving scenario model. Subsequently, simulation algorithms are used to reproduce the driving trajectories and behavioral patterns of multiple electric vehicle users within a specific target time period, generating accurate simulated travel information. Based on this, the personalized charging needs of each electric vehicle are further refined, including charging time, charging location, and charging power requirements. Finally, by summarizing and analyzing all electric vehicle charging needs information, a detailed spatiotemporal distribution map of electricity load is depicted. Based on this, a power allocation strategy is generated. This strategy guides the scheduling of electricity and charging facilities in different regions and at different times, ensuring a high degree of matching between electricity supply and electric vehicle charging needs. This solves the technical problem in related technologies where the low accuracy of electric vehicle charging load analysis leads to difficulties in matching the spatiotemporal allocation of electricity with user electricity demand. Attached Figure Description

[0026] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0027] Figure 1 This is a flowchart of an optional power dispatching method based on the electrical load of electric vehicles according to an embodiment of the present invention;

[0028] Figure 2 This is a schematic diagram of an optional road network topology based on graph theory according to an embodiment of the present invention;

[0029] Figure 3 This is an optional flowchart for predicting the spatiotemporal distribution of electric vehicle charging load based on the OD matrix and considering user charging behavior, according to an embodiment of the present invention.

[0030] Figure 4 This is a schematic diagram of an optional power dispatching device based on the electrical load of an electric vehicle according to an embodiment of the present invention;

[0031] Figure 5 This is a structural block diagram of an electronic device for performing a power dispatching method based on the electrical load of an electric vehicle, according to an embodiment of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] To facilitate understanding of the present invention by those skilled in the art, some terms or nouns involved in the various embodiments of the present invention are explained below:

[0035] EV stands for Electric Vehicle, a type of automobile that uses an onboard power source to drive its wheels via an electric motor. Compared to traditional gasoline-powered vehicles, electric vehicles have significant advantages in terms of environmental protection and energy efficiency.

[0036] The Origin-Destination Matrix (OD Matrix) describes the travel volume from each origin to the destination in a transportation network. In this invention, it is used to analyze the travel probability of electric vehicles from each origin to the destination and forms the basis for establishing a travel probability model.

[0037] The Monte Carlo method is a numerical computation method based on random sampling. It is often used to solve complex problems in probabilistic models by generating a large number of random samples to simulate various possible scenarios, thereby estimating the solution to the problem.

[0038] The Floyd Algorithm is an algorithm for finding the shortest path between all pairs of vertices, particularly suitable for shortest path problems in directed and weighted graphs. In this invention, it is used to simulate the driving path of an electric vehicle in a road network.

[0039] The Speed-Flow Model is a mathematical model used to describe the relationship between road speed and vehicle flow, and can be used to simulate vehicle speed under traffic congestion. The Speed-Flow Model in this invention considers factors such as road speed limits, traffic flow, and road capacity to more accurately simulate the speed of electric vehicles.

[0040] The following embodiments of the present invention can be applied to various systems / applications / equipment that require electric vehicle charging load prediction and power resource optimization scheduling, enabling a method for predicting the spatiotemporal distribution of charging load based on traffic conditions and user charging behavior. This invention uses big data analytics and intelligent simulation technology to perform refined modeling of electric vehicle travel behavior and charging demand, and then analyzes the driving and charging characteristics of electric vehicles in the road network based on the OD matrix and speed-flow model, which can better guide decisions on power allocation and charging facility construction.

[0041] In its specific implementation, this invention first collects and analyzes the statistical distribution of electric vehicle users' travel start and end times, parking durations, and charging decision data. Combined with information on road network node connections and road segment lengths, a detailed travel behavior database is formed. Subsequently, a path optimization model based on OD matrix analysis and the Floyd algorithm is used to simulate the travel path and required time for each electric vehicle within a target time period. Next, the Monte Carlo method is used to simulate electric vehicle charging behavior, including charging time, location, and power demand, resulting in a personalized charging plan for each electric vehicle. Finally, by integrating the charging demand information of all electric vehicles, a power allocation strategy is generated to ensure the efficient allocation of power resources in time and space, meeting the diverse charging needs of users.

[0042] This invention, by combining travel behavior habits, traffic condition analysis, and charging behavior simulation, not only overcomes the problem of low accuracy in charging load prediction in existing technologies and provides more accurate load prediction data for the power system, but also greatly improves the intelligence level of power dispatching and the rationality of charging infrastructure layout.

[0043] The present invention will now be described in detail with reference to various embodiments.

[0044] Example 1

[0045] According to an embodiment of the present invention, a power dispatching method based on the electrical load of an electric vehicle is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0046] The implementing entity of this invention can be a smart grid management system, which combines big data analysis and intelligent simulation technology for predicting electric vehicle charging loads. In particular, it addresses the problem in related technologies where the low accuracy of electric vehicle charging load analysis leads to difficulties in matching the timing and distribution of electricity with user demand. This is achieved by establishing a charging demand prediction model based on electric vehicle user travel behavior and traffic conditions. Specifically, this involves collecting and analyzing travel behavior data and constructing simulation steps of road network driving and charging behavior to achieve the goal of accurately allocating power resources and optimizing the layout of charging facilities.

[0047] The embodiments of the present invention will now be described in detail with reference to the specific implementation steps.

[0048] Figure 1 This is a flowchart of an optional power dispatching method based on the electrical load of electric vehicles according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0049] Step S101: Collect travel behavior data from N electric vehicle users and obtain road network topology data. The travel behavior data includes the statistical distribution of travel start and end times, parking duration, and charging decision data. The road network topology data is used to characterize the node connection relationship and road segment length information of the road network. N is a specified value.

[0050] Specifically, the travel behavior data of electric vehicle users is the foundation for predicting the spatiotemporal distribution of charging load. Among these, the start and end times of trips record the time of each electric vehicle user's first trip and the time of their last trip each day, reflecting their daily life and work patterns. For example, most users may begin their first trip in the morning commute and end their last trip in the evening or at night, forming typical morning and evening peak charging demand.

[0051] Parking duration refers to the length of time an electric vehicle remains at its destination. This parameter helps understand whether the user charges at that location and the duration of charging chosen. Parking duration can vary depending on the nature of the destination, such as short-term parking in a commercial area versus long-term parking in a residential area.

[0052] Charging decision data includes users' decisions on whether to charge (fast or slow) after a single trip, as well as emergency charging behavior when the SOC (State of Charge) is lower than a preset threshold during driving. These decisions are influenced by a combination of factors, including the electric vehicle's current SOC, user habits, charging infrastructure availability, and cost-effectiveness.

[0053] Another point to note is that road network topology data provides the skeleton information of the transportation network. Node connectivity describes how road segments are interconnected, i.e., which nodes have direct path connections. This helps in constructing a complete road network model and clarifying the potential travel paths of electric vehicles. Road segment length information records the actual length of each road segment in the network. This directly impacts the calculation of travel time, energy consumption, and the selection of charging locations, making it indispensable data for analyzing charging behavior and predicting charging load.

[0054] Alternatively, travel behavior data can also cover factors such as the frequency of user trips, typical travel distances, preferred routes, and usage habits of charging facilities. For example, some users may prefer to charge at specific charging stations, while others prefer to find the nearest charging point to save time.

[0055] Alternatively, road network topology data can also include road types (such as highways, urban arterial roads, alleyways, etc.) and road conditions (such as pavement quality, speed limits, etc.) to more accurately simulate the actual driving conditions of electric vehicles. In addition, real-time traffic flow data and congestion information can also be included as part of the road network data to dynamically adjust driving routes and predict real-time changes in charging load.

[0056] The aforementioned data collection can be achieved through various means, such as through the intelligent connected systems of electric vehicles, usage records of public charging facilities, travel planning data from mobile applications, and historical statistical data from traffic management departments.

[0057] Optionally, the step of collecting travel behavior data from N electric vehicle users includes: obtaining historical travel records for N electric vehicle users, wherein the historical travel records include: departure time, arrival time, parking duration, parking location, current trip power consumption, remaining power upon arrival, next trip power consumption, and charging behavior data for each trip; establishing a trip start and end time dataset based on the departure and arrival times; establishing a parking duration distribution dataset based on the parking location type and the corresponding parking duration; generating a charging decision dataset based on the current trip power consumption, remaining power upon arrival, next trip power consumption, and charging behavior data; and integrating the trip start and end time dataset, the parking duration distribution dataset, and the charging decision dataset to obtain travel behavior data.

[0058] It should be noted that departure and arrival times describe the time periods of a user's trip, revealing the regularity of travel patterns, such as morning and evening rush hours and weekend leisure trips; parking duration and parking spots record the user's stay time at each location and the nature of the location (e.g., commercial area, residential area), helping to understand the likelihood and location of charging behavior; current trip power consumption and remaining power upon arrival reflect the energy consumption of electric vehicles in different trips; next trip power consumption refers to predicting the user's power demand for the next trip, used to determine whether charging is necessary at the current location to avoid low SOC; charging behavior data includes charging frequency, charging type (fast charging or slow charging), and charging location selection, reflecting user charging habits and helping to analyze the utilization efficiency of charging facilities.

[0059] In a specific implementation scenario, taking electric private cars as an example, their start and end times are mostly determined by factors such as work hours and travel habits. Data fitting is performed on the start and end times of electric private cars:

[0060] The probability density function for the first travel time of the day is:

[0061] Where t is a time variable, representing the specific travel time, and α and β represent the expected value and standard deviation of the probability density function of the travel time, respectively.

[0062] The probability density function for the last moment of the day is:

[0063] Where t is a time variable, representing the end time of the total journey in a day, and μ and σ represent the expected value and standard deviation of the probability density function of the travel time, respectively.

[0064] In another specific implementation scenario, electric vehicles need to consume electricity while driving, while also taking into account the lifespan of the EV battery and the user's travel needs.

[0065] During each trip, when the SOC is less than 0.2, the EV will be quickly charged at the nearest charging station, and will continue driving once the charge meets the requirements of the destination.

[0066] After each trip, EV users will decide on their charging behavior based on the current State of Charge (SOC), including fast charging, slow charging, or not charging. Furthermore, the parking time and charging time incurred each time the EV reaches its destination are also important factors influencing EV users' decision-making.

[0067] First, we analyze the impact of EV's State of Charge (SOC) on user charging decisions. Considering the lifespan of the EV battery, if the SOC < 0.2 after the EV arrives at its destination, it must be charged there; if the SOC ≥ 0.2, it is necessary to determine whether the SOC at the end of the next trip will be less than 0.2. If it is less than 0.2, charging will be chosen at that location; otherwise, charging will not be performed.

[0068] Therefore, decision-making behavior after an EV trip can be categorized into the following three types:

[0069] Then, the impact of parking duration and charging duration on EV users' charging decision-making behavior is analyzed. The charging duration for EVs varies depending on the charging behavior: Among them, Q e P represents EV battery capacity, in kWh; s The charging power (kW) indicates the slow charging power; P f This indicates the charging power of fast charging, expressed in kW.

[0070] Considering actual travel conditions, EV users will incur a certain parking time (t) when completing a trip. park The duration of parking time limits the charging time of EVs, which in turn affects users' charging decisions.

[0071] Right now,

[0072] EV single parking time t park The probability density function is:

[0073] Where, μ P and σ P Let $\mathbf$ and $\mathbf$ represent the expected value and standard deviation of the probability density function, respectively.

[0074] Next, by analyzing the departure and arrival times in users' historical travel records, a time distribution model, such as a Gaussian distribution or other probability distribution model, is established to identify peak and off-peak charging periods, providing a time-dimensional reference for charging load prediction. Based on the type of parking location and the corresponding parking duration, differences in parking duration in different locations (such as office parking lots, shopping malls, etc.) can be identified. The parking duration distribution dataset, combined with the speed-flow model, not only helps predict charging demand but also optimizes the layout of charging facilities to ensure that they provide services at appropriate times and locations.

[0075] Based on the above information (especially SOC status and expected power consumption for the next trip), a charging decision dataset can be created, recording in detail the conditions under which users choose to charge, the type of charging chosen (fast or slow charging), and the charging location selected. By mining patterns in the dataset using machine learning algorithms, user charging preferences under specific SOC states and parking durations can be predicted, thereby optimizing the charging load prediction model.

[0076] Finally, these three datasets are merged to form travel behavior data, which comprehensively describes the behavioral habits of electric vehicle users, including when they travel, where they park, and how they charge. This data is the core input for predicting the spatiotemporal distribution of charging load.

[0077] To provide an accurate road network foundation for charging load forecasting, the steps for acquiring road network topology data optionally include: extracting basic road segment information from the road traffic management system, whereby the basic road segment information includes the locations of road segment intersections and the connection relationships between road segments; establishing a road segment length database by surveying the actual lengths of each road segment; constructing a road network model based on the road segment intersection locations, connection relationships, and the road segment length database, using road segment intersections as topology nodes and road segments as connecting lines; and outputting the road network model as road network topology data. Obtaining accurate road network topology data is the foundation for building an effective forecasting model.

[0078] It should be noted that the road traffic management system contains a large amount of traffic operation data and road network information, including the location of road intersections and the connections between road segments. The actual length of a road segment is a crucial factor affecting the driving time, energy consumption, and selection of charging points for electric vehicles. A road segment length database can be established through on-site surveying, satellite image analysis, or the use of high-precision map data, thereby ensuring the accuracy of the speed-flow model and improving the accuracy of charging load prediction.

[0079] A detailed road network model can be constructed based on a database of intersection locations, road segment connections, and road segment lengths. Each intersection in the model is considered a topological node, and road segments serve as edges connecting these nodes, forming a graph structure. This model not only reflects the physical structure of the road network but also provides a framework for subsequent route selection and travel time calculations. After constructing the road network model, it is output in a standardized road network topology data format, which can be directly used by prediction models as a basis for simulating electric vehicle travel paths and predicting charging load distribution.

[0080] In one specific implementation, Figure 2 This is a schematic diagram of an optional road network topology based on graph theory according to an embodiment of the present invention. Figure 2For example, the road network graph can be represented by G(V, E), where E represents the set of road segments in the road network, V represents the set of endpoints of the road segments, and the length of each road segment and the node connection relationship in G are described by matrix D. Assuming all road segments are two-way streets, then:

[0081] The method for assigning values ​​to each element in D is as follows:

[0082] The corresponding D matrix is: Among them, l ij Indicates the length of the road segment between two nodes, and inf indicates that the two nodes are not directly connected.

[0083] Furthermore, the OD matrix generates the origin i and destination j of the electric vehicle. Generally, there are multiple paths that can reach j from i. Assume that the EV user chooses the shortest path, and the set of shortest paths between i and j is R = {i,…,e,f,…,j}, along with the total travel distance l. ij It can be obtained using the Floyd shortest path algorithm.

[0084] The actual driving speed of electric vehicles is often affected by road speed limits, traffic flow, and road capacity. Therefore, to simulate EV driving speed, a speed-flow model is introduced:

[0085] Among them, v ij (t) represents the speed of EV on road segment (i,j) at time t; v ijmax This represents the speed limit for the EV to travel on road segment (i,j); q ij (t) represents the traffic flow of road segment (i,j) at time t; C ij λ represents the traffic capacity of road segment (i,j) corresponding to the road grade; λ is a nonlinear function of traffic flow / traffic capacity of the road segment; a, b, n represent the correlation coefficients of road grades.

[0086] Based on the speed-flow model, the travel speed V of the h-th direct segment in the shortest travel path set R can be calculated. h The travel time ΔT for this road segment can be calculated using the following formula: (t). h : Where L h It is the distance of the h-th directly connected segment, following d ij The assignment rules.

[0087] The total travel time for a single trip is: Where C represents the number of shortest paths.

[0088] Step S102: Based on travel behavior data and road network topology data, simulate the road network driving conditions of N electric vehicles within the target time period to obtain simulated travel information.

[0089] Specifically, the simulated travel information is obtained by comprehensively applying statistical methods, road network analysis algorithms, and Monte Carlo simulation techniques. Among these, the trip start and end time simulation refers to simulating the first trip time and the last trip end time of each electric vehicle within the target time period based on the probability distribution of the trip start and end times of electric vehicle users. This fully considers the dynamic nature of user travel and provides a time basis for subsequent trip planning.

[0090] Route selection and travel time calculation refer to using OD matrix analysis, combined with road network topology data, to determine the travel path and probability of each electric vehicle from its origin to its destination. The Floyd-Warshall algorithm is used to determine the shortest path, while the speed-flow model models the electric vehicle's speed based on real-time traffic conditions and speed limits, thus accurately calculating travel time for different routes. Data-driven route selection and time prediction can reflect the impact of real-world driving conditions such as traffic congestion and speed limits on electric vehicle charging demand.

[0091] Parking and charging behavior simulation refers to simulating travel information while considering the parking duration and charging decisions of electric vehicles after arriving at their destination. Based on the current SOC state of the electric vehicle and the user's charging preferences, it simulates the choices of fast charging, slow charging, or no charging, as well as the corresponding charging duration. It also considers the availability of charging facilities to ensure that the simulation of charging behavior is both consistent with user habits and meets the possibilities of actual operation.

[0092] By comprehensively applying the above steps, detailed simulated travel information of multiple electric vehicles within the target time period will be obtained, including but not limited to: the specific trip of each vehicle (including departure node, destination node, departure time and end time); the driving path (the shortest or actual selected path determined based on the OD matrix and Floyd algorithm); the driving time (the driving time of each segment of the path calculated based on the speed-flow model); the parking locations and times (the possible parking locations and durations of the electric vehicle during the trip); and the charging behavior (charging decisions at each parking point, including whether to charge, the charging type (fast charging or slow charging), and the charging duration).

[0093] The simulated travel information provided above offers a detailed data foundation for predicting the spatiotemporal distribution of charging load. Further analysis can predict charging demand in different regions and at different times within a target time period, as well as the load pressure on the power grid, thereby supporting the rational planning of charging infrastructure and the efficient allocation of power resources. Through continuous iteration and optimization of the simulation process, the spatiotemporal changes in charging demand can be predicted more accurately.

[0094] In a specific implementation scenario, the traffic volume of each road segment of the EV is obtained, and the OD matrix A for each time period is derived by using the OD matrix calculation method. The OD matrix A consists of 24 sub-matrices. Where T takes values ​​of 0, 1, 2, ..., 23, and m represents the number of road nodes. Let represent the traffic volume between the starting and ending points of the road during the time period (T, T+1). Then, the probability that an EV starts at node i and ends at node j within the time period (T, T+1) can be represented by dividing the traffic volume from node i to node j during that time period by the total EV traffic volume from node i to all other nodes, i.e.:

[0095] Where, p ij These are elements in the travel probability matrix, representing the probability that an EV travels from node i to node j; a ij This represents the number of EVs that travel from node i to node j within the time period (T, T+1).

[0096] Figure 3 This is an optional flowchart of the spatiotemporal distribution prediction of electric vehicle charging load based on the OD matrix, considering user charging behavior, according to an embodiment of the present invention. Figure 3 As shown, to address the uncertainty of EV user travel behavior, a Monte Carlo method is employed based on a probability distribution model of travel behavior to generate random numbers that satisfy its probability distribution, thereby simulating the travel behavior of individual EV users. Simultaneously, the charging behavior of EV users during driving and at the end of a single trip is considered to determine data such as charging time periods, charging durations, and charging power in the load prediction model. These data are then sequentially calculated and superimposed onto the EV load within a specific area, thus achieving charging load prediction.

[0097] Furthermore, based on travel behavior data and road network topology data, the steps for simulating the road network driving conditions of N electric vehicles within a target time period to obtain simulated travel information include: for each electric vehicle, determining the simulated travel time point for each simulated trip based on the statistical distribution of travel start and end times in the travel behavior data; determining the simulated driving segment for each simulated trip based on the start and end points of the simulated trip and the road network topology data; for each simulated trip, calculating the estimated travel time and estimated power consumption of the simulated trip based on the simulated travel time point and simulated driving segment; and generating simulated travel information based on the estimated travel time and estimated power consumption of each simulated trip for the N electric vehicles.

[0098] It should be noted that the simulation is based on the statistical distribution of the start and end times of electric vehicle users' trips. Specifically, it involves analyzing historical data to determine the probability density functions for the first trip and the end of the last trip each day. For each simulated trip, Monte Carlo simulation technology is used to randomly generate the travel time points based on these probability distribution functions, ensuring that the simulation results reflect the real-world travel habits of users.

[0099] The start and end points of the simulated journey are generated using OD matrix analysis, while the specific driving path is selected using the Floyd algorithm. This algorithm can find the shortest path from the start point to the end point, and considering the segment lengths, intersection locations, and connectivity relationships in the road network topology data, it can determine the set of road segments that need to be traversed in each simulated journey.

[0100] For each simulated trip, the driving speed and time are accurately calculated based on the speed-flow model, combined with the simulated travel time and real-time traffic conditions of the route. The estimated power consumption is calculated based on the energy consumption characteristics of electric vehicles, the total mileage of the route, and the driving speed, ensuring that the simulation results reflect the driving time and power consumption under real road conditions.

[0101] The estimated time, power consumption, and route information for each simulated trip are aggregated to form detailed simulated travel information. This includes not only the trip details of each electric vehicle, but also the traffic conditions and charging demand distribution of the entire road network within the target time period.

[0102] Step S103: Determine the charging demand information for each electric vehicle based on the simulated travel information, wherein the charging demand information includes: charging time, charging location, and charging power demand.

[0103] Specifically, considering that electric vehicle users' charging decisions are influenced not only by their State of Charge (SOC) but also by external factors such as parking duration and charging facility availability, a near-ground fast charging behavior can be automatically triggered during the simulation by setting a threshold (e.g., SOC < 0.2). Simultaneously, for charging decisions after the trip, the predicted SOC before the next trip is used as a basis for judgment. If the predicted SOC is below the threshold, charging will occur at the current time and location. This process, through Monte Carlo simulation, can obtain the charging decisions of each electric vehicle at different locations and times, thereby determining the charging time.

[0104] Furthermore, charging locations are determined based on the actual driving routes and parking locations of electric vehicles. During the journey, if a low state of charge (SOC) alert is triggered, the vehicle can be guided to the nearest charging station for fast charging. At the end of the trip, electric vehicle users may choose to slow charge at their destination or at home, depending on the length of parking and the convenience of charging facilities. Analyzing road network structure and electric vehicle travel behavior can predict locations with high charging demand.

[0105] Furthermore, charging power demand is directly related to the charging type (fast charging or slow charging). During simulation, power thresholds for fast and slow charging can be set (representing the charging power of fast charging in kW; and the charging power of slow charging in kW), and the charging power is determined based on the charging decision. Fast charging typically has higher power (e.g., 60kW to 150kW), which can replenish a large amount of power in a shorter time, suitable for handling emergency charging needs or quickly replenishing range; while slow charging has lower power (e.g., 3kW to 11kW), takes longer to charge, but is less expensive, suitable for charging at night or during off-peak hours. By calculating the actual power demand for each charge and matching it to the charging type, the power demand for each charging event can be obtained.

[0106] In this embodiment of the invention, in addition to the charging decision triggered by SOC status mentioned above, some long-established user habits also need to be taken into consideration. For example, some users tend to charge at specific locations or prefer to use specific types of charging facilities (such as public fast charging stations or home slow charging stations). These habits are influenced by factors such as charging cost, convenience, reliability of charging facilities, and user time arrangements. Through long-term data collection and analysis, user charging behavior can be predicted more accurately.

[0107] Determining charging demand information also takes into account the layout and capacity of charging facilities. In densely populated areas or commercial centers, charging facilities are likely to be more abundant and provide higher charging power; while in residential areas or remote areas, charging facilities may be sparser and primarily offer slow charging. Furthermore, the real-time status of charging facilities (such as occupancy and remaining charging power) also influences electric vehicle users' choices. Therefore, during the simulation, information on charging facilities can be updated in real time to ensure the rationality of charging decisions.

[0108] Furthermore, the charging demand information for electric vehicles is dynamic and influenced by various real-time factors, such as weather changes (low winter temperatures may reduce battery efficiency and increase charging demand) and holidays (which may lead to changes in travel patterns, thus affecting charging demand). Therefore, the process of determining charging demand information can also have a certain degree of flexibility, allowing for dynamic adjustments based on actual conditions to improve the accuracy of predictions.

[0109] To further refine the conversion process from simulated travel information to electric vehicle charging demand information and ensure more accurate charging demand forecasts, optionally, the step of determining the charging demand information for each electric vehicle based on simulated travel information includes: determining the remaining battery power of the electric vehicle when it arrives at the simulated destination based on each simulated trip of each electric vehicle, according to the estimated trip duration and estimated power consumption; determining the charging strategy of the electric vehicle at the parking point corresponding to the simulated trip destination based on the remaining battery power, simulated parking duration, and the statistical distribution of charging decision data in the travel behavior data, wherein the charging strategy includes: whether to charge, charging mode, and charging duration; and calculating the charging power demand by combining the charging facility power parameters and availability information of the parking point with the charging strategy to obtain charging demand information including charging time, charging location, and charging power demand.

[0110] It should be noted that the estimated travel time and power consumption of a simulated electric vehicle trip can be used to calculate the vehicle's state of charge (SOC) upon arrival at its destination. Considering the vehicle's initial SOC, the power consumption during the simulated trip, and potential charging behavior, the vehicle's state of charge under specific driving conditions can be accurately reflected.

[0111] By analyzing the statistical distribution of remaining battery power, simulated parking duration, and user charging decision data, and comprehensively considering SOC threshold, parking time length, user preferences, and charging facility availability, the charging strategy for electric vehicles at each parking location is determined. For example, if the SOC is expected to drop too low before the next trip, fast charging is recommended; while for long-term parking, slow charging is recommended.

[0112] Once the charging strategy is determined, the actual charging power demand can be calculated by combining the power parameters and availability information of the charging facilities at the parking location. This involves matching the charging mode (fast charging or slow charging) with the maximum output power of the charging facilities and estimating the required charging power based on the SOC status and charging duration. This calculation yields complete information about the charging event, including the charging time, location, and power demand.

[0113] Step S104: Summarize the charging demand information of all electric vehicles to obtain the spatiotemporal distribution demand of electricity load, and generate a power dispatching strategy based on the spatiotemporal distribution demand of electricity load. The power dispatching strategy is used to guide the power dispatching and charging facility dispatching in each region and time period.

[0114] Specifically, constructing a spatiotemporal distribution of demand can create an overview of the charging load demand of the entire region at different time periods. For each moment and each charging station, the expected total charging power demand can be calculated, thereby depicting the charging load curve of the entire region.

[0115] Due to the uncertainty of user charging behavior, the charging demand of electric vehicles has significant randomness and volatility. Therefore, when constructing the spatiotemporal distribution of demand, statistical methods (such as probability density functions) can be used to estimate the average charging demand and demand range in different time periods and regions.

[0116] Furthermore, different regions have varying geographical features, population densities, economic activities, and charging infrastructure layouts, resulting in significant differences in charging demand. For example, densely populated commercial areas may experience higher charging demand during the day, while residential areas may see greater demand at night. Therefore, the spatiotemporal distribution of electricity load demand should be subdivided into multiple sub-regions, and demand analysis should be conducted for each sub-region to reflect regional differences.

[0117] The power dispatch strategy generated based on the above factors involves the dynamic scheduling of the power system, such as adjusting power plant output, controlling the load balance of power transmission lines, and mobilizing energy storage facilities to participate in dispatch. It also involves optimizing the scheduling of charging facilities, such as activating charging facilities in advance in areas where peak charging demand is predicted to ensure sufficient power; appropriately slowing down or shutting down some charging stations during off-peak hours to reduce energy waste; and may also include load balancing among charging facilities to prevent overcrowding at certain sites and ensure a uniform distribution of charging services.

[0118] Alternatively, the power dispatch strategy can also include a flexible response mechanism to quickly address unforeseen changes in charging demand. For example, when a sudden event (such as a large gathering or festival) causes a sudden increase in charging demand in a certain area, the power transmission plan and the operating status of charging facilities can be adjusted in a timely manner.

[0119] To accurately pinpoint the spatiotemporal distribution of charging load demand and provide data support for the formulation of power dispatching strategies, the following steps are taken to aggregate the charging demand information of all electric vehicles and obtain the spatiotemporal distribution demand of electricity load: Classifying and statistically analyzing the charging demand information according to pre-divided time intervals and geographical regions; calculating the total charging power demand for each time interval and each geographical region based on the classified charging demand information; generating matrix data reflecting the spatiotemporal distribution demand of electricity load based on the total charging power demand for each time interval and each geographical region; and drawing a heat map of electricity load reflecting the spatiotemporal distribution demand of electricity load based on the matrix data.

[0120] In one optional embodiment, the target time period is first divided into multiple consecutive time intervals of equal length, for example, in units of 1 hour; at the same time, the geographical area is subdivided into multiple sub-regions based on road network topology data, and each sub-region can correspond to one or more charging stations; then, the simulated charging demand information is classified and statistically analyzed, that is, the charging time and charging location of each charging demand are classified into the corresponding time interval and geographical area.

[0121] For each time interval and each geographical region, the total charging power demand of all electric vehicles in that region is summed. This calculation process takes into account the charging strategy (fast charging or slow charging) and the power parameters of the charging facilities, generating the total charging load for each region at each time point.

[0122] Next, the total charging power demand for each time interval and geographical region is organized into a matrix. Rows in the matrix correspond to time intervals, and columns correspond to geographical regions. Each element represents the charging power demand for a specific time interval and geographical region, visually reflecting the spatiotemporal distribution characteristics of the charging load. Based on the matrix data, data visualization tools can be used to create heat maps of electricity load, clearly showing the changes in charging load in different regions at different times. The intensity of the color represents the load level, providing power dispatchers with intuitive decision-making support.

[0123] To ensure the effective dispatch of power resources and the rational layout of charging facilities, optionally, the step of generating a power dispatch strategy based on the spatiotemporal distribution demand of power load includes: analyzing the peak load period and the corresponding peak load region based on the spatiotemporal distribution demand; generating a power dispatch strategy based on the peak load period and the peak load region, combined with the dispatch nodes of the distribution network, wherein the power dispatch strategy includes: a first dispatch period and a first regional dispatch scheme for power, and a second dispatch period and a second regional dispatch scheme for charging facilities.

[0124] In one alternative embodiment, data on the spatiotemporal distribution of electric vehicle charging loads is used to identify the time periods (i.e., peak load periods) and spatial regions (i.e., peak load areas) where load demand reaches its peak through statistical analysis techniques. This analysis is performed by comparing charging load demand at different times and in different regions to determine which time periods and regions may require special power allocation and charging facility scheduling.

[0125] Based on the analysis of peak load periods and peak regions, the generation of power dispatching strategies consists of two parts:

[0126] For identified peak load periods and areas, priority should be given to ensuring sufficient power supply. Dispatch strategies may include increasing power generation, adjusting grid transmission paths to optimize power distribution, and using energy storage systems to store and release electricity to ensure a stable power supply.

[0127] Simultaneously, considering the scheduling of charging facilities, during peak load periods and areas, it is also possible to increase the number and duration of charging facility operations to enhance charging power and meet the demand for fast charging. It is also possible to optimize the layout of charging facilities to ensure the supply of charging services in load hotspot areas. During off-peak periods and areas, the operating status of charging facilities can be adjusted, such as reducing the number of operations or adjusting the charging mode, to reduce unnecessary operating costs.

[0128] Through steps S101 to S104 above, travel behavior data of N electric vehicle users can be collected first, and road network topology data can be obtained. The travel behavior data includes the travel start and end times, parking duration, and statistical distribution of charging decision data. The road network topology data is used to characterize the node connection relationship and road segment length information of the road network. N is a specified value. Then, based on the travel behavior data and road network topology data, the road network driving situation of N electric vehicles in the target time period is simulated to obtain simulated travel information. Then, based on the simulated travel information, the charging demand information of each electric vehicle is determined. The charging demand information includes: charging time point, charging location, and charging power demand. Finally, the charging demand information of all electric vehicles is summarized to obtain the spatiotemporal distribution demand of electricity load. Based on the spatiotemporal distribution demand of electricity load, a power dispatching strategy is generated. The power dispatching strategy is used to guide the power dispatching and charging facility dispatching in each region and time period.

[0129] In this embodiment of the invention, a combination of big data analysis and intelligent simulation is employed. By comprehensively collecting and analyzing travel behavior data and road network topology data from multiple electric vehicle users, the aim is to accurately depict the dynamic charging needs of the electric vehicle population. Specifically, the system first collects and processes diverse behavioral data, including travel start and end times, parking duration, and charging decisions. This data, combined with key information such as road network node connections and road segment lengths, constructs a highly realistic road network driving scenario model. Subsequently, simulation algorithms are used to reproduce the driving trajectories and behavioral patterns of multiple electric vehicle users within a specific target time period, generating accurate simulated travel information. Based on this, the personalized charging needs of each electric vehicle are further refined, including charging time, charging location, and charging power requirements. Finally, by summarizing and analyzing all electric vehicle charging needs information, a detailed spatiotemporal distribution map of electricity load is depicted, generating a power allocation strategy. This strategy guides the scheduling of electricity and charging facilities in different regions and time periods, ensuring a high degree of matching between electricity supply and electric vehicle charging needs. This solves the technical problem in related technologies where the low accuracy of electric vehicle charging load analysis leads to difficulties in matching the spatiotemporal allocation of electricity with user electricity demand.

[0130] The invention will now be described in conjunction with another alternative embodiment.

[0131] Example 2

[0132] The power dispatching device based on the electric load of electric vehicles provided in this embodiment includes multiple implementation units, each of which corresponds to a specific implementation step in Embodiment 1 above.

[0133] Figure 4 This is a schematic diagram of an optional power dispatching device based on the electrical load of an electric vehicle according to an embodiment of the present invention, such as... Figure 4 As shown, the device may include: a data acquisition unit 401, a simulation unit 402, a determination unit 403, and a generation unit 404.

[0134] The acquisition unit 401 is used to collect travel behavior data from N electric vehicle users and obtain road network topology data. The travel behavior data includes the statistical distribution of travel start and end times, parking duration, and charging decision data. The road network topology data is used to characterize the node connection relationship and road segment length information of the road network. N is a specified value.

[0135] Simulation unit 402 is used to simulate the road network driving conditions of N electric vehicles within a target time period based on travel behavior data and road network topology data, and obtain simulated travel information.

[0136] The determining unit 403 is used to determine the charging demand information of each electric vehicle based on simulated travel information, wherein the charging demand information includes: charging time point, charging location and charging power demand.

[0137] The generation unit 404 is used to summarize the charging demand information of all electric vehicles, obtain the spatiotemporal distribution demand of the power load, and generate a power dispatching strategy based on the spatiotemporal distribution demand of the power load. The power dispatching strategy is used to guide the power dispatching and charging facility dispatching in each region and time period.

[0138] The aforementioned power dispatching device based on electric vehicle power load can first collect travel behavior data of N electric vehicle users through the acquisition unit 401 and obtain road network topology data. The travel behavior data includes the travel start and end times, parking duration, and statistical distribution of charging decision data. The road network topology data is used to characterize the node connection relationship and road segment length information of the road network. N is a specified value. Then, the simulation unit 402 simulates the road network driving situation of N electric vehicles in a target time period based on the travel behavior data and road network topology data to obtain simulated travel information. Then, the determination unit 403 determines the charging demand information of each electric vehicle based on the simulated travel information. The charging demand information includes: charging time point, charging location, and charging power demand. Finally, the generation unit 404 summarizes the charging demand information of all electric vehicles to obtain the spatiotemporal distribution demand of power load and generates a power dispatching strategy based on the spatiotemporal distribution demand of power load. The power dispatching strategy is used to guide the power dispatching and charging facility dispatching in various regions and time periods.

[0139] In this embodiment of the invention, a combination of big data analysis and intelligent simulation is employed. By comprehensively collecting and analyzing travel behavior data and road network topology data from multiple electric vehicle users, the aim is to accurately depict the dynamic charging needs of the electric vehicle population. Specifically, the system first collects and processes diverse behavioral data, including travel start and end times, parking duration, and charging decisions. This data, combined with key information such as road network node connections and road segment lengths, constructs a highly realistic road network driving scenario model. Subsequently, simulation algorithms are used to reproduce the driving trajectories and behavioral patterns of multiple electric vehicle users within a specific target time period, generating accurate simulated travel information. Based on this, the personalized charging needs of each electric vehicle are further refined, including charging time, charging location, and charging power requirements. Finally, by summarizing and analyzing all electric vehicle charging needs information, a detailed spatiotemporal distribution map of electricity load is drawn, generating a power allocation strategy. This strategy guides the scheduling of electricity and charging facilities in different regions and time periods, ensuring a high degree of matching between electricity supply and electric vehicle charging needs. This solves the technical problem in related technologies where the low accuracy of electric vehicle charging load analysis leads to difficulties in matching the spatiotemporal allocation of electricity with user electricity demand.

[0140] Furthermore, the data collection unit includes: an acquisition module for acquiring historical travel records of N electric vehicle users, wherein the historical travel records include: departure time, arrival time, parking duration, parking location, current trip power consumption, remaining power upon arrival, next trip power consumption, and charging behavior data for each trip; a first establishment module for establishing a trip start and end time dataset based on the departure and arrival times; a second establishment module for establishing a parking duration distribution dataset based on the parking location type and the corresponding parking duration; a first generation module for generating a charging decision dataset based on the current trip power consumption, remaining power upon arrival, next trip power consumption, and charging behavior data; and an integration module for integrating the trip start and end time dataset, parking duration distribution dataset, and charging decision dataset to obtain travel behavior data.

[0141] Furthermore, the data acquisition unit also includes: an extraction module for extracting basic road segment information from the road traffic management system, wherein the basic road segment information includes the location of road segment intersections and the road segment connection relationships; a third establishment module for establishing a road segment length database by surveying the actual length of each road segment; a construction module for constructing a road network model based on the location of road segment intersections, the road segment connection relationships, and the road segment length database, using road segment intersections as topology nodes and road segments as connecting lines; and an output module for outputting the road network model as road network topology data.

[0142] Furthermore, the simulation unit includes: a first determining module, used to determine the simulated travel time point for each simulated trip based on the statistical distribution of travel start and end times in the travel behavior data for each electric vehicle; a second determining module, used to determine the simulated driving segment for each simulated trip based on the start and end points of the simulated trip and road network topology data; a first calculating module, used to calculate the estimated travel time and estimated power consumption for each simulated trip based on the simulated travel time point and simulated driving segment; and a second generating module, used to generate simulated travel information based on the estimated travel time and estimated power consumption for each simulated trip of N electric vehicles.

[0143] Furthermore, the determining unit includes: a third determining module, used to determine the remaining battery power of the electric vehicle when it arrives at the simulated destination based on the estimated time and estimated power consumption of the simulated trip for each simulated trip of each electric vehicle; a judging module, used to judge the charging strategy of the electric vehicle at the parking point corresponding to the simulated destination based on the remaining battery power, the simulated parking time, and the statistical distribution of charging decision data in the travel behavior data, wherein the charging strategy includes: whether to charge, the charging mode, and the charging time; and a second calculation module, used to calculate the charging power demand by combining the power parameters and availability information of the charging facilities at the parking point with the charging strategy, to obtain charging demand information including the charging time point, the charging location, and the charging power demand.

[0144] Furthermore, the generation unit includes: a classification module, used to classify and statistically analyze charging demand information according to pre-divided time intervals and geographical regions; a third calculation module, used to calculate the total charging power demand for each time interval and each geographical region based on the classified charging demand information; a third generation module, used to generate matrix data reflecting the spatiotemporal distribution of electricity load demand based on the total charging power demand for each time interval and each geographical region; and a drawing module, used to draw a heat map of electricity load reflecting the spatiotemporal distribution of electricity load demand based on the matrix data.

[0145] Furthermore, the generation unit also includes: an analysis module, used to analyze the load peak period and the load peak area corresponding to the load peak period based on the spatiotemporal distribution demand; and a fourth generation module, used to generate a power dispatch strategy based on the load peak period and the load peak area, combined with the dispatch nodes of the distribution network, wherein the power dispatch strategy includes: a first dispatch period and a first area dispatch scheme for power, and a second dispatch period and a second area dispatch scheme for charging facilities.

[0146] The aforementioned power dispatching device based on the electric load of electric vehicles may also include a processor and a memory. The aforementioned acquisition unit 401, simulation unit 402, determination unit 403, generation unit 404, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0147] The aforementioned processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and by adjusting kernel parameters, the charging demand information for each electric vehicle is determined based on simulated travel information. This includes charging time, charging location, and charging power demand. The charging demand information of all electric vehicles is aggregated to obtain the spatiotemporal distribution of electricity load demand. Based on this spatiotemporal distribution demand, a power dispatching strategy is generated to guide power scheduling and charging facility scheduling in different regions and time periods.

[0148] The aforementioned memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0149] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program with the following method steps: collecting travel behavior data of N electric vehicle users and obtaining road network topology data, wherein the travel behavior data includes travel start and end times, parking duration, and statistical distribution of charging decision data, and the road network topology data is used to characterize the node connection relationship and road segment length information of the road network, and N is a specified value; based on the travel behavior data and road network topology data, simulating the road network driving situation of N electric vehicles in a target time period to obtain simulated travel information; determining the charging demand information of each electric vehicle based on the simulated travel information, wherein the charging demand information includes: charging time point, charging location, and charging power demand; summarizing the charging demand information of all electric vehicles to obtain the spatiotemporal distribution demand of electricity load, and generating a power dispatching strategy based on the spatiotemporal distribution demand of electricity load, wherein the power dispatching strategy is used to guide the power dispatching and charging facility dispatching in various regions and time periods.

[0150] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute any one of the power dispatching methods based on the electric vehicle electrical load in Embodiment 1 above.

[0151] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the power dispatching method based on the electric vehicle electrical load of any one of the above embodiments.

[0152] Figure 5 This is a structural block diagram of an electronic device for executing a power dispatching method based on the electrical load of an electric vehicle, according to an embodiment of the present invention. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 Only one of the components is shown: processor 502, memory 504, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module, and display.

[0153] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the power dispatching method and device based on the electric vehicle's electrical load in this embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned power dispatching method based on the electric vehicle's electrical load. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0154] Those skilled in the art will understand that Figure 5 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 5 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 5 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 5 The different configurations shown.

[0155] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0156] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0157] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0158] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0159] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0160] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0161] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0162] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A power dispatching method based on the electrical load of electric vehicles, characterized in that, include: Collect travel behavior data from N electric vehicle users and obtain road network topology data. The travel behavior data includes the statistical distribution of travel start and end times, parking duration, and charging decision data. The road network topology data is used to characterize the node connection relationship and road segment length information of the road network. N is a specified value. Based on the travel behavior data and the road network topology data, simulate the road network driving situation of N electric vehicles in a target time period to obtain simulated travel information; Based on the simulated travel information, the charging demand information for each of the electric vehicles is determined, wherein the charging demand information includes: charging time, charging location, and charging power requirement; The charging demand information of all electric vehicles is aggregated to obtain the spatiotemporal distribution demand of the electricity load, and a power dispatching strategy is generated based on the spatiotemporal distribution demand of the electricity load. The power dispatching strategy is used to guide the power dispatching and charging facility dispatching in each region and time period.

2. The power dispatching method based on the electric vehicle power load according to claim 1, characterized in that, The steps for collecting travel behavior data from N electric vehicle users include: Obtain the historical travel records of N electric vehicle users, wherein the historical travel records include: departure time, arrival time, parking duration, parking location, current trip power consumption, remaining power upon arrival, next trip power consumption, and charging behavior data for each trip; Establish a travel start and end time dataset based on the departure time and the arrival time; Based on the location type of the parking spot and the corresponding parking duration, a parking duration distribution dataset is established. A charging decision dataset is generated based on the current trip power consumption, the remaining power upon arrival, the next trip power consumption, and the charging behavior data; The travel behavior data is obtained by integrating the travel start and end time dataset, the parking duration distribution dataset, and the charging decision dataset.

3. The power dispatching method based on the electrical load of electric vehicles according to claim 1, characterized in that, The steps to obtain road network topology data include: Basic road segment information is extracted from the road traffic management system, including the location of road segment intersections and the road segment connection relationships. A road segment length database was established by surveying the actual length of each road segment; Using the intersections of the road segments as topology nodes and the road segments as connecting lines, a road network model is constructed based on the location of the intersections of the road segments, the connection relationships of the road segments, and the length of the road segments. The road network model is output as the road network topology data.

4. The power dispatching method based on the electrical load of electric vehicles according to claim 1, characterized in that, Based on the travel behavior data and the road network topology data, the steps for simulating the road network driving conditions of N electric vehicles within a target time period to obtain simulated travel information include: For each electric vehicle, the simulated travel time point for each simulated trip is determined based on the statistical distribution of the travel start and end times in the travel behavior data; The simulated driving segment for each simulated trip is determined based on the start and end points of the simulated trip and the road network topology data; For each simulated trip, the estimated time and estimated power consumption of the simulated trip are calculated based on the simulated travel time and the simulated route. The simulated travel information is generated based on the estimated time and estimated power consumption of each simulated trip for each of the N electric vehicles.

5. The power dispatching method based on the electrical load of electric vehicles according to claim 4, characterized in that, The step of determining the charging demand information for each of the electric vehicles based on the simulated travel information includes: Based on each simulated trip of each electric vehicle, the remaining battery power of the electric vehicle when it arrives at the simulated trip destination is determined according to the estimated time and estimated power consumption of the simulated trip. Based on the remaining battery power, simulated parking time, and the statistical distribution of the charging decision data in the travel behavior data, the charging strategy of the electric vehicle at the parking point corresponding to the simulated trip destination is determined, wherein the charging strategy includes: whether to charge, charging mode, and charging time. By combining the power parameters and availability information of the charging facilities at the parking spots with the charging strategy, the charging power demand is calculated to obtain the charging demand information, which includes the charging time, charging location, and charging power requirement.

6. The power dispatching method based on the electrical load of electric vehicles according to claim 1, characterized in that, The step of summarizing the charging demand information of all the electric vehicles to obtain the spatiotemporal distribution demand of the electricity load includes: The charging demand information is classified and statistically analyzed according to pre-defined time intervals and geographical regions; Based on the classified charging demand information, the total charging power demand for each time interval and each geographical region is calculated respectively. Based on the total charging power demand of each time interval and each geographical region, a matrix of data reflecting the spatiotemporal distribution of the electricity load is generated. A heat map of electricity load, reflecting the spatiotemporal distribution of electricity demand, is drawn based on the matrix data.

7. The power dispatching method based on the electrical load of electric vehicles according to claim 1, characterized in that, The steps for generating a power dispatching strategy based on the spatiotemporal distribution of the electricity load include: Based on the spatiotemporal distribution of demand, analyze the peak load periods and the corresponding peak load regions; Based on the peak load period and the peak load region, the power dispatch strategy is generated by combining the dispatch nodes of the distribution network. The power dispatch strategy includes: a first dispatch period and a first regional dispatch scheme for power, and a second dispatch period and a second regional dispatch scheme for charging facilities.

8. A power dispatching device based on the electrical load of electric vehicles, characterized in that, include: The data acquisition unit is used to collect travel behavior data from N electric vehicle users and obtain road network topology data. The travel behavior data includes the statistical distribution of travel start and end times, parking duration, and charging decision data. The road network topology data is used to characterize the node connection relationship and road segment length information of the road network. N is a specified value. The simulation unit is used to simulate the road network driving conditions of N electric vehicles within a target time period based on the travel behavior data and the road network topology data, and obtain simulated travel information. The determining unit is used to determine the charging demand information of each of the electric vehicles based on the simulated travel information, wherein the charging demand information includes: charging time point, charging location and charging power demand; The generation unit is used to summarize the charging demand information of all the electric vehicles, obtain the spatiotemporal distribution demand of the power load, and generate a power dispatching strategy based on the spatiotemporal distribution demand of the power load. The power dispatching strategy is used to guide the power dispatching and charging facility dispatching in each region and time period.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the power dispatching method based on the electric load of an electric vehicle as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the power dispatching method based on the electric load of an electric vehicle as described in any one of claims 1 to 7.

Images