Intelligent energy collaborative scheduling method and system based on vehicle-network interaction

Abstract

This invention relates to the field of smart grid dispatching technology, and proposes a smart energy collaborative dispatching method and system based on vehicle-grid interaction. The method includes: acquiring information on the vehicle set to be coordinated and the power grid area; calculating the daily mileage probability of the vehicle set and determining the charging urgency of each vehicle; determining the location of the access node corresponding to the vehicle set in the power grid topology and calculating the spatiotemporal load prediction value of the vehicle set within a preset time period; determining the adjustable margin of each access node in the power grid area, and calculating the power adjustment parameters of the charging facility identifier based on the adjustable margin and the charging urgency; monitoring the net load fluctuation in the power grid area, and when the net load fluctuation exceeds a threshold, resetting the charging power of the charging facility identifier sequentially based on the power adjustment parameters and the charging urgency to obtain the vehicle-grid interactive dispatching result. This invention can improve the accuracy of vehicle-grid interactive smart energy collaborative dispatching.

Description

Technical Field

[0001] This invention relates to a smart energy collaborative scheduling method and system based on vehicle-to-grid interaction, belonging to the field of smart grid scheduling technology. Background Technology

[0002] Vehicle-to-grid (V2G) interaction technology is a key technology for the integration of smart grids and transportation networks. Electric vehicles can effectively smooth grid fluctuations and absorb new energy sources by connecting to the grid for charging and discharging interaction. It is an important research direction in the field of energy internet. With the large-scale application of electric vehicles, the demand for their orderly scheduling is becoming increasingly urgent.

[0003] However, existing vehicle-grid interactive scheduling mainly relies on total quantity control strategies, using uniform power limits or simple time-of-use pricing for management. While this approach can meet the basic peak-valley regulation needs of the power grid, it ignores the differences in charging urgency among different vehicle users and the voltage constraints of nodes at different access locations. This makes it difficult for scheduling strategies to ensure the safety boundaries of the power grid while also taking into account the user charging experience, and thus fails to achieve refined collaborative scheduling. Summary of the Invention

[0004] This invention provides a smart energy collaborative scheduling method and system based on vehicle-to-grid interaction, the main purpose of which is to improve the accuracy of smart energy collaborative scheduling based on vehicle-to-grid interaction.

[0005] To achieve the above objectives, the present invention provides a smart energy collaborative scheduling method based on vehicle-to-grid interaction, comprising: Obtain the set of vehicles to be coordinated and the grid area information, wherein the set of vehicles includes travel logs and charging facility identifiers, and the grid area information includes feeder capacity upper limit and node voltage safety boundary; Based on the travel logs, the daily mileage probability of the vehicle set is calculated, and the charging urgency of each vehicle is determined by combining the current battery state of charge of each vehicle in the vehicle set. Based on the charging facility identifier, the location of the access node corresponding to the vehicle set in the power grid topology is determined. Using the daily mileage probability, the charging urgency, and the access node location, the spatiotemporal load prediction value of the vehicle set within a preset time period is calculated. Combining the spatiotemporal load forecast, the upper limit of the feeder capacity, and the node voltage safety boundary, the adjustable margin of each access node in the power grid area is determined. Based on the adjustable margin and the charging urgency, the power regulation parameters of the charging facility identifier are calculated. Monitor the net load fluctuations within the power grid area. When the net load fluctuations exceed a threshold, based on the power adjustment parameters and the charging urgency, sequentially perform charging power reset processing on the charging facility identifiers to obtain the vehicle-grid interaction scheduling results.

[0006] Optionally, determining the charging urgency of each vehicle by combining the current battery state of charge of each vehicle in the vehicle set includes: State parameters are extracted from the vehicle set to obtain the initial battery state of charge; An urgent demand analysis is performed on the initial battery state of charge to obtain the charging urgency level; Based on the charging urgency level, vehicle scheduling urgency indicators are selected from a pre-built scheduling priority strategy library; Based on the vehicle scheduling urgency index, the charging urgency of each vehicle is determined.

[0007] Optionally, determining the location of the access node corresponding to the vehicle set in the power grid topology based on the charging facility identifier includes: Obtain the electrical connection path information associated with the charging facility identifier from a preset power grid topology database; Calculate the electrical topology distance of each node in the electrical connection path information, and based on the electrical topology distance, filter out the candidate access node set in the electrical connection path information; Obtain the physical geographic coordinates and coverage area corresponding to the charging facility identifier; Construct a spatial mapping relationship model between the candidate access node set, the physical geographic coordinates, and the coverage area; and calculate the spatial matching degree of each node in the candidate access node set relative to the coverage area based on the spatial mapping relationship model. The node with the highest spatial matching degree is selected as the access node location corresponding to the vehicle set in the power grid topology.

[0008] Optionally, calculating the spatial matching degree of each node in the candidate access node set relative to the coverage area based on the spatial mapping relationship model includes: Construct the spatial geometric polygon of the coverage area and extract the geographic coordinates of each node in the candidate access node set; Analyze the relative positional relationship between the geographic coordinates and the spatial geometric polygon; If the relative positional relationship is such that the geographic coordinate point is located inside the spatial geometric polygon, calculate the straight-line distance between the geographic coordinate point and the physical geographic coordinate, and calculate the reciprocal of the straight-line distance to obtain the initial matching score; If the relative positional relationship is such that the geographic coordinate point is located outside the spatial geometric polygon, calculate the vertical distance from the geographic coordinate point to the boundary of the spatial geometric polygon, and calculate the initial matching score based on the vertical distance; The initial matching score is normalized to obtain the spatial matching degree.

[0009] Optionally, the step of calculating the spatiotemporal load prediction value of the vehicle set within a preset time period using the daily mileage probability, the charging urgency, and the access node location includes: The probability density distribution of the daily mileage probability is calculated to obtain the mileage probability distribution function; The mileage probability distribution function is divided into intervals to obtain mileage probability feature clusters; Based on the charging urgency, the power demand spectrum corresponding to the mileage probability feature cluster is statistically analyzed; Based on the power demand spectrum, calculate the load distribution weights corresponding to the mileage probability feature clusters; By combining the load distribution weights and the mileage probability feature clusters, the spatiotemporal load prediction value of the vehicle set is calculated.

[0010] Optionally, calculating the spatiotemporal load prediction value of the vehicle set by integrating the load distribution weights and the mileage probability feature clusters includes: Extract the typical charging power curves corresponding to each interval in the mileage probability feature cluster to obtain the basic load demand vector; The load distribution weights are used to weight and correct the basic load demand vector to generate a weighted load feature matrix. Based on the location of the access node, the physical connection relationship of the vehicle set in the power grid topology is determined, and a node location index set is obtained; Based on the node location index set, the weighted load feature matrix is ​​mapped to each node of the power grid to obtain the node time-series load sequence; Based on the node time-series load sequence and the load distribution weight, the spatiotemporal load prediction value of the vehicle set is calculated.

[0011] Optionally, determining the adjustable margin of each access node within the power grid area by combining the spatiotemporal load forecast, the feeder capacity upper limit, and the node voltage safety boundary includes: The spatiotemporal load forecast and feeder capacity upper limit are processed for supply and demand coordination to obtain a coordinated margin range; Based on the node voltage safety boundary, power flow fitting is performed on the cooperative margin interval to obtain the fitted voltage curve; Calculate the voltage potential difference and power potential difference between each node in the fitted voltage curve; The adjustable margin of the access node is calculated by combining the voltage-to-position difference and the power-to-position difference.

[0012] Optionally, calculating the power adjustment parameters of the charging facility identifier based on the adjustable margin and the charging urgency includes: Collect historical adjustment data of the charging facilities under different scheduling cycles, and calculate the margin sensitivity scale corresponding to the adjustable margin based on the historical adjustment data; Based on the charging urgency, the margin sensitivity scale, and the adjustable margin, the power adjustment parameters of the charging facility identifier are calculated.

[0013] Optionally, calculating the margin sensitivity scale corresponding to the adjustable margin based on the historical adjustment data includes: The historical adjustment data is subjected to multidimensional feature mapping processing to obtain the adjustment feature space matrix; Calculate the mutual information value between each feature dimension in the adjustment feature space matrix and the adjustable margin, select key influencing factors from each feature dimension in the adjustment feature space matrix based on the mutual information value, and fit the margin response surface corresponding to the key influencing factors. Determine the slope of the tangent plane of the margin response surface under the current operating conditions, and perform exponential smoothing on the slope of the tangent plane to obtain the margin sensitive scale.

[0014] To address the aforementioned problems, the present invention also provides a smart energy collaborative scheduling system based on vehicle-to-grid interaction, the system comprising: The information acquisition module is used to acquire the set of vehicles to be coordinated and the grid area information. The set of vehicles includes travel logs and charging facility identifiers, and the grid area information includes feeder capacity upper limit and node voltage safety boundary. The charging urgency determination module is used to calculate the daily mileage probability of the vehicle set based on the travel log, and determine the charging urgency of each vehicle by combining the current battery state of charge of each vehicle in the vehicle set. The load forecasting module is used to determine the location of the access node corresponding to the vehicle set in the power grid topology based on the charging facility identifier, and to calculate the spatiotemporal load forecast value of the vehicle set within a preset time period using the daily mileage probability, the charging urgency and the access node location. The adjustment parameter calculation module is used to combine the spatiotemporal load forecast value, the upper limit of the feeder capacity and the node voltage safety boundary to determine the adjustable margin of each access node in the power grid area, and to calculate the power adjustment parameters of the charging facility identifier based on the adjustable margin and the charging urgency. The vehicle-to-grid interaction module is used to monitor the net load fluctuation within the power grid area. When the net load fluctuation exceeds a threshold, based on the power adjustment parameters and the charging urgency, the module sequentially performs a charging power reset process on the charging facility identifier to obtain the vehicle-to-grid interaction scheduling result.

[0015] Compared to the problems described in the background art, the embodiments of the present invention, by obtaining detailed vehicle travel logs and accurate power grid operation boundary information, can construct a correlation basis between vehicle behavior characteristics and power grid physical constraints. This effectively avoids the risk of scheduling exceeding limits due to information gaps, ensuring the safety and feasibility of subsequent collaborative processes. It also provides a comprehensive understanding of the electricity consumption habits of the vehicle group and the carrying capacity of the power grid area information, facilitating orderly interaction between electric vehicles and the power grid. Secondly, by calculating the daily mileage probability of the vehicle group based on the travel logs, the present invention can predict the future energy consumption required for each vehicle's travel, providing a reliable data foundation for charging scheduling. Finally, by determining the access node location of the vehicle group in the power grid topology based on the charging facility identifier, the present invention can achieve precise mapping between charging physical facilities and power grid logical nodes, clarifying the vehicle charging... The specific injection point of electrical load in the power network provides a basis for subsequent analysis and processing. This invention, by combining the spatiotemporal load forecast, the upper limit of feeder capacity, and the node voltage safety boundary, determines the adjustable margin of each access node within the power grid area. This enables a quantitative assessment of the load-bearing capacity of power grid nodes, identifying nodes with adjustment potential and their remaining capacity in the power grid without exceeding the feeder thermal stability limit and the node voltage stability domain. This provides a safety boundary constraint for formulating scientific power regulation strategies. Finally, by monitoring net load fluctuations within the power grid area and resetting charging power when fluctuations exceed limits, combined with power regulation parameters and charging urgency, this invention achieves peak shaving and valley filling and dynamic balance of the power grid load. This effectively alleviates voltage exceedance problems caused by fluctuations in renewable energy output or sudden load increases, improving the accuracy of vehicle-grid interactive scheduling. Therefore, this invention can improve the accuracy of intelligent energy collaborative scheduling via vehicle-grid interaction. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a smart energy collaborative scheduling method based on vehicle-to-grid interaction, provided in an embodiment of the present invention. Figure 2 A schematic diagram of the daily driving mileage probability distribution of a smart energy collaborative scheduling method based on vehicle-to-grid interaction provided in an embodiment of the present invention; Figure 3 This is a schematic diagram illustrating the determination of charging urgency in a smart energy collaborative scheduling method based on vehicle-to-grid interaction, provided in an embodiment of the present invention. Figure 4 A schematic diagram of a smart energy collaborative scheduling system based on vehicle-to-grid interaction provided in an embodiment of the present invention; Figure 5 A schematic diagram of a computer device for a smart energy collaborative scheduling method based on vehicle-to-grid interaction provided in an embodiment of the present invention; The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0018] This application provides a smart energy collaborative scheduling method based on vehicle-to-grid (V2G) interaction. The executing entity of this smart energy collaborative scheduling method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the smart energy collaborative scheduling method based on V2G interaction can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0019] Reference Figure 1 The diagram shown is a flowchart illustrating a smart energy collaborative scheduling method based on vehicle-to-grid interaction according to an embodiment of the present invention. In this embodiment, the smart energy collaborative scheduling method based on vehicle-to-grid interaction includes: S1. Obtain the set of vehicles to be coordinated and the grid area information. The set of vehicles includes travel logs and charging facility identifiers. The grid area information includes the upper limit of feeder capacity and the node voltage safety boundary.

[0020] By acquiring detailed vehicle travel logs and accurate power grid operation boundary information, this invention can establish a correlation between vehicle behavior characteristics and power grid physical constraints, thereby effectively avoiding scheduling overrun risks caused by missing information, ensuring the safety and feasibility of subsequent collaborative processes, and comprehensively understanding the electricity consumption habits of vehicle groups and the carrying capacity of power grid area information, which helps to achieve orderly interaction between electric vehicles and the power grid.

[0021] It should be explained that the travel log refers to the digital record of a vehicle's driving and parking behavior over a specific period of time, such as departure time, arrival time, mileage, initial state of charge, and final state of charge; the charging facility identifier refers to the coded information used to uniquely identify a charging pile and its associated charging station, including attributes such as geographical coordinates and rated power of the equipment; the feeder capacity limit refers to the maximum apparent power value that a distribution network feeder is allowed to transmit under normal operating conditions, determined by the conductor diameter, insulation class, and ambient temperature; and the node voltage safety boundary refers to the upper and lower limits of voltage amplitude set to ensure the normal operation of power equipment and power supply quality, subject to national standards and the equipment's tolerance capabilities.

[0022] Optionally, the travel logs of the vehicle group can be collected in real time via an onboard remote communication terminal and uploaded to a cloud database. The data should cover the vehicle's driving and parking times throughout the day. The feeder capacity upper limit and node voltage safety boundary in the power grid area information can be read through the distribution network automation system or dispatch master station system. The data source should include the protection settings of the substation outlet circuit breaker, line topology parameters, and load measurement records. During the acquisition process, the timestamps of various data need to be aligned to ensure the consistency between the vehicle behavior time series and the power grid status record time series.

[0023] S2. Based on the travel log, calculate the daily mileage probability of the vehicle set, and determine the charging urgency of each vehicle by combining the current battery state of charge of each vehicle in the vehicle set.

[0024] This invention calculates the daily mileage probability of the vehicle set based on the travel logs, which can predict the future energy consumption of each vehicle, providing a reliable data foundation for charging scheduling. It should be noted that the daily mileage probability is the distribution probability of each vehicle in different daily mileage intervals obtained from historical travel log statistics, used to characterize the expected distribution pattern of each vehicle's future daily mileage. For details, please refer to the following... Figure 2 This is a schematic diagram of the daily mileage probability distribution of the intelligent energy collaborative scheduling method based on vehicle-to-grid interaction provided in an embodiment of the present invention. In the figure, the horizontal axis is the daily mileage of the vehicle, in kilometers; the left vertical axis is the probability distribution of the daily mileage, with a value range of [0,1]; and the right vertical axis is the probability density of the daily mileage, representing the probability intensity of occurrence corresponding to different mileages. The dashed curve represents the cumulative probability distribution curve of daily mileage, while the solid curve represents the probability density curve of daily mileage. The probability density curve shows that the probability density is highest in the lower range of daily mileage (e.g., 0-50 km). As mileage increases, the probability density rapidly decreases, exhibiting a typical travel characteristic of "high frequency for low mileage, low frequency for high mileage." The cumulative probability distribution curve reflects the cumulative probability that daily mileage will not exceed a certain value. For example, when the daily mileage is 100 km, the cumulative distribution probability is close to 0.9, indicating that the daily mileage of most vehicles is concentrated within 100 km. The higher the cumulative distribution probability corresponding to the vehicle's remaining range, the higher the risk of subsequent driving beyond its range capacity, and the higher the urgency of charging. Furthermore, based on the travel logs, the probability of daily mileage for the vehicle set is calculated using probabilistic statistical methods. The daily mileage data in the travel logs is then fitted with a distribution to obtain a continuous probability density function, thereby determining the probability that a vehicle falls within different mileage ranges.

[0025] This invention determines the charging urgency of each vehicle by combining the current battery state of charge of each vehicle in the vehicle set. This effectively distinguishes the urgency of charging needs of different vehicles, thereby prioritizing charging of vehicles with high urgency under limited charging resources, improving charging scheduling efficiency and vehicle availability assurance. It should be noted that the current battery state of charge is the percentage of the vehicle's power battery remaining power relative to its rated total capacity; the charging urgency represents the level of urgency of charging needs assessed by combining the expected future travel power demand of the vehicle with the current power reserve status.

[0026] Specifically, determining the charging urgency of each vehicle by combining the current battery state of charge of each vehicle in the vehicle set includes: State parameters are extracted from the vehicle set to obtain the initial battery state of charge; An urgent demand analysis is performed on the initial battery state of charge to obtain the charging urgency level; Based on the charging urgency level, vehicle scheduling urgency indicators are selected from a pre-built scheduling priority strategy library; Based on the vehicle scheduling urgency index, the charging urgency of each vehicle is determined.

[0027] It should be explained that the initial battery state of charge (SOC) is a multi-dimensional data set encompassing the battery's real-time charge percentage, battery health status, battery temperature, and individual cell voltage difference. The charging urgency level is a classification of urgency based on the initial battery SOC and vehicle task attributes. For example, in a logistics delivery scenario, a vehicle in the middle of a delivery task with an SOC below 20% may be classified as "urgent," while a vehicle with an SOC of 30% in an idle state may be classified as "normal." The scheduling priority strategy library is a database pre-built based on a large amount of vehicle operation data, battery aging models, and charging history records. It stores vehicle scheduling priority determination rules for different charging urgency levels. The vehicle scheduling urgency index is a specific quantitative parameter in the scheduling priority strategy library corresponding to the charging urgency level, such as charging queue priority weight and recommended charging time window.

[0028] Furthermore, the extraction of state parameters from the vehicle set can be achieved through real-time synchronization and fusion of data via the vehicle battery management system (BMS), cloud monitoring platform, and vehicle network communication module; the urgency analysis of the initial battery state of charge can be accomplished using a Long Short-Term Memory (LSTM) network model or fuzzy logic evaluation model in deep learning algorithms. Through deep learning of historical charging behavior data, battery degradation characteristics, and current operating conditions, a nonlinear mapping relationship between battery state parameters and charging urgency can be constructed; the selection of vehicle scheduling urgency indicators from a pre-built scheduling priority strategy library can rely on an intelligent decision recommendation system to quickly and accurately match the optimal scheduling urgency indicator based on the charging urgency level; based on the vehicle scheduling urgency indicators, the charging urgency of each vehicle is determined. For details, please refer to the following... Figure 3 This diagram illustrates the determination of charging urgency in the intelligent energy collaborative scheduling method based on vehicle-to-grid interaction provided in an embodiment of the present invention. The diagram shows that if the selected strategy is designed for vehicle charging scenarios in low-temperature environments, it will focus on the energy consumption attenuation caused by battery preheating, adjust the urgency calculation weights, and prioritize charging vehicles that have completed preheating or are at suitable temperatures. Simultaneously, it optimizes the scheduling path based on the distribution of charging piles to improve charging efficiency. For example, when a new energy logistics fleet is performing delivery tasks in congested urban areas, based on the determined charging urgency, the system automatically marks vehicles with insufficient remaining mileage to complete the remaining orders and prioritizes allocating them to the nearest charging pile with matching power, ensuring maximum overall fleet operating efficiency.

[0029] S3. Based on the charging facility identifier, determine the location of the access node corresponding to the vehicle set in the power grid topology, and use the daily mileage probability, the charging urgency and the access node location to calculate the spatiotemporal load prediction value of the vehicle set within a preset time period.

[0030] This invention determines the access node location of the vehicle set in the power grid topology based on the charging facility identifier, enabling precise mapping between charging physical facilities and power grid logical nodes. It clarifies the specific injection point of the vehicle charging load in the power network, providing a basis for subsequent analysis and processing. It should be explained that the access node location refers to the index number of the distribution transformer node, bus node, or feeder node connected in the power grid topology diagram when the electric vehicle connects to the power grid through the charging pile, reflecting the specific electrical connection location of the charging load in the power grid physical architecture.

[0031] Specifically, determining the location of the access node corresponding to the vehicle set in the power grid topology based on the charging facility identifier includes: Obtain the electrical connection path information associated with the charging facility identifier from a preset power grid topology database; Calculate the electrical topology distance of each node in the electrical connection path information, and based on the electrical topology distance, filter out the candidate access node set in the electrical connection path information; Obtain the physical geographic coordinates and coverage area corresponding to the charging facility identifier; Construct a spatial mapping relationship model between the candidate access node set, the physical geographic coordinates, and the coverage area; and calculate the spatial matching degree of each node in the candidate access node set relative to the coverage area based on the spatial mapping relationship model. The node with the highest spatial matching degree is selected as the access node location corresponding to the vehicle set in the power grid topology.

[0032] It should be explained that the preset power grid topology database is a pre-built repository for storing power grid topology data. The electrical connection path information is topology link data reflecting the electrical connection relationship between charging facilities and upstream substations or distribution transformer nodes, including line impedance, switch status, and connection sequence. The electrical topology distance is a quantitative indicator that measures the electrical tightness of nodes in the power grid topology structure, usually calculated based on impedance values ​​or hop counts. The candidate access node set is a set of potential physical nodes that have direct or indirect connections with charging facilities in the electrical topology. The spatial mapping relationship model is a mathematical model used to project electrical topology nodes onto a geographic spatial coordinate system. The spatial matching degree is a numerical value characterizing the proximity of the spatial location of a candidate node to the physical coordinates of the charging facility.

[0033] Furthermore, the step of retrieving a preset power grid topology database based on the charging facility identifier can be achieved through SQL queries to quickly locate the power supply circuit where the facility is located; the calculation of the electrical topology distance of each node in the electrical connection path information can be achieved using a breadth-first search algorithm to calculate the weighted distance from the charging facility node to the backbone node of the power grid, and nodes with distances exceeding a preset threshold are eliminated to form a candidate access node set; high-precision latitude and longitude coordinates of the charging facility and its power supply radius coverage can be obtained using a WebGIS service interface; the construction of a spatial mapping relationship model can coordinate the electrical nodes in the power grid topology, and determine the spatial matching degree by calculating the Euclidean distance between the candidate node coordinates and the charging facility coordinates; selecting the node with the highest spatial matching degree can effectively avoid positioning errors caused by confusion of nodes with the same name, ensuring that subsequent load forecasting and adjustment commands can be accurately issued to the actual physical access point, and ensuring the accuracy and reliability of power grid control.

[0034] Optionally, calculating the spatial matching degree of each node in the candidate access node set relative to the coverage area based on the spatial mapping relationship model includes: Construct the spatial geometric polygon of the coverage area and extract the geographic coordinates of each node in the candidate access node set; Analyze the relative positional relationship between the geographic coordinates and the spatial geometric polygon; If the relative positional relationship is such that the geographic coordinate point is located inside the spatial geometric polygon, calculate the straight-line distance between the geographic coordinate point and the physical geographic coordinate, and calculate the reciprocal of the straight-line distance to obtain the initial matching score; If the relative positional relationship is such that the geographic coordinate point is located outside the spatial geometric polygon, calculate the vertical distance from the geographic coordinate point to the boundary of the spatial geometric polygon, and calculate the initial matching score based on the vertical distance; The initial matching score is normalized to obtain the spatial matching degree.

[0035] It should be explained that the spatial geometric polygon is determined based on the coverage area and is a geometrically closed region used to define the effective service range boundary of the charging facility in a two-dimensional plane or three-dimensional space; the relative positional relationship is a spatial state description of whether the geographic coordinate point is inside, outside or on the boundary of the spatial geometric polygon; the initial matching score is an intermediate calculated value used to quantify the degree of spatial correlation between the node and the target area, and its value is positively correlated with the suitability of node access.

[0036] Furthermore, the construction of the spatial geometric polygon of the coverage area can utilize coordinate sequence data from a geographic information system, generating closed polygons through vectorized boundary connection operations. The analysis of the relative positional relationship between the geographic coordinate points and the spatial geometric polygon can specifically employ a ray-crossing algorithm, where rays are drawn from the point to be measured in any direction, and the parity of the number of intersections between the rays and the polygon boundary determines whether the point is inside or outside the polygon. The calculation of the initial matching score, for nodes inside the polygon, utilizes the reciprocal form of Euclidean distance to ensure that nodes with closer physical distances receive higher matching scores, reflecting the principle of proximity access. For nodes outside the polygon, an exponential decay function can be introduced to process the vertical distance, quickly reducing the matching weight of nodes far from the service range. The normalization process can employ a maximum-minimum normalization method to unify the matching scores of all candidate nodes to the same order of magnitude, thereby eliminating dimensional differences under different calculation scenarios and ensuring the accuracy and rationality of the finally selected access node location in physical space, providing a reliable node positioning basis for subsequent power adjustment.

[0037] This invention calculates the spatiotemporal load forecast of the vehicle cluster within a preset time period by utilizing the daily mileage probability, the charging urgency, and the location of the access node. It comprehensively considers the power consumption characteristics brought about by vehicle travel patterns, the time distribution characteristics determined by charging urgency, and the spatial constraints of power grid nodes. This enables accurate quantitative prediction of the load change trend of power grid nodes in a specific area within a future time period, thereby effectively assessing the impact of large-scale electric vehicle access on the local distribution network operation. It should be explained that the spatiotemporal load forecast refers to the sum of active power demand generated by the superposition of vehicle charging behavior at each access node location on a preset time series section. It includes the dynamic characteristics of the load magnitude evolving over time and its spatial distribution characteristics in the power grid.

[0038] Specifically, the step of calculating the spatiotemporal load prediction value of the vehicle set within a preset time period using the daily mileage probability, the charging urgency, and the access node location includes: The probability density distribution of the daily mileage probability is calculated to obtain the mileage probability distribution function; The mileage probability distribution function is divided into intervals to obtain mileage probability feature clusters; Based on the charging urgency, the power demand spectrum corresponding to the mileage probability feature cluster is statistically analyzed; Based on the power demand spectrum, calculate the load distribution weights corresponding to the mileage probability feature clusters; By combining the load distribution weights and the mileage probability feature clusters, the spatiotemporal load prediction value of the vehicle set is calculated.

[0039] It should be explained that the mileage probability distribution function is a mathematical model used to describe the statistical regularity of daily vehicle mileage, reflecting the probability density of different mileage occurrences. The mileage probability feature cluster is a set of representative mileage intervals obtained by discretizing continuous mileage distribution data, such as short-distance commuting intervals, medium-distance logistics intervals, and long-distance transportation intervals. The power demand spectrum is the distribution of charging power demand based on the analysis of the vehicle's current remaining battery power and charging urgency, reflecting the distribution characteristics of vehicle charging power under different urgency levels. The load distribution weight is a quantitative indicator used to measure the degree of contribution of vehicles in different mileage intervals to the total load at specific time periods and specific access node locations.

[0040] Furthermore, the probability density distribution of the daily mileage probability can be calculated by statistical analysis of massive historical driving data, using kernel density estimation or maximum likelihood estimation to fit a continuous function that conforms to the actual distribution characteristics; the interval division of the mileage probability distribution function can be achieved by using clustering algorithms or equal frequency partitioning methods to group vehicles with similar mileage characteristics and charging behavior into the same feature cluster; based on the statistical power demand spectrum of the charging urgency, by constructing a mapping matrix between urgency and charging strategy, the power demand characteristics and duration of vehicle grid access under different urgency levels can be analyzed.

[0041] Optionally, calculating the spatiotemporal load prediction value of the vehicle set by integrating the load distribution weights and the mileage probability feature clusters includes: Extract the typical charging power curves corresponding to each interval in the mileage probability feature cluster to obtain the basic load demand vector; The load distribution weights are used to weight and correct the basic load demand vector to generate a weighted load feature matrix. Based on the location of the access node, the physical connection relationship of the vehicle set in the power grid topology is determined, and a node location index set is obtained; Based on the node location index set, the weighted load feature matrix is ​​mapped to each node of the power grid to obtain the node time-series load sequence; Based on the node time-series load sequence and the load distribution weights, the spatiotemporal load prediction value of the vehicle set is calculated using the following formula:

[0042] in, This represents the spatiotemporal load forecast for the vehicle set, where N represents the total number of vehicles in the vehicle set. This represents the load distribution weight corresponding to the mileage probability feature cluster to which the i-th vehicle belongs. Let represent the power value of the base load demand vector corresponding to the i-th vehicle at time τ. This represents the node determination function. If the access node position of the i-th vehicle is n, the function value is 1; otherwise, it is 0.

[0043] It should be explained that the basic load demand vector is a vector data that reflects the change of standard charging power over time within a specific mileage range, obtained by fitting historical vehicle charging behavior data; the weighted load feature matrix is ​​a matrix data that can truly reflect the current dispatch demand characteristics after correcting the basic load by introducing load distribution weights; the node location index set is an index set that records the mapping relationship between vehicles and grid topology nodes, clarifying the specific location of load injection into the grid; and the node time-series load sequence is a data stream of load changes of each grid node over time, used to characterize the dynamic operating state of the local grid.

[0044] Furthermore, by using a lookup table method or a nonlinear fitting model based on battery state of charge and mileage, typical charging power curves corresponding to each interval in the mileage probability feature cluster can be extracted from a pre-set charging characteristic database to obtain the basic load demand vector, ensuring that the power curve matches the actual energy consumption state of the vehicle. A weighted load feature matrix can be generated by constructing a weighting factor matrix and performing a dot product or linear weighting operation with the basic load demand vector, using the load distribution weights to weight and correct the basic load demand vector, thus reflecting the differences in the contribution of different urgency and mileage characteristics to the overall load. Finally, by traversing the node connection relationships in the power grid topology diagram and combining the geographical coordinate information and electrical connection attributes of the access nodes, The physical connection relationships of the vehicle set in the power grid topology are determined, resulting in a set of node location indexes. Using a sparse matrix mapping algorithm or a topology tracing algorithm, the weighted load feature matrix is ​​accurately mapped to each node in the power grid based on the node location index set, forming a node time-series load sequence. This achieves the transformation from abstract vehicle loads to physical nodes in the power grid. The spatiotemporal aggregation operation of the node time-series load sequence is performed. Using discrete-time integration or cumulative summation formulas, the spatiotemporal load prediction value of the vehicle set is calculated. This accurately quantifies the spatiotemporal impact of large-scale electric vehicle charging behavior on the local distribution network, providing solid data support for peak shaving and valley filling and dynamic scheduling of the power grid, and ensuring the safe and stable operation of the power system.

[0045] S4. Combining the spatiotemporal load forecast, the upper limit of the feeder capacity, and the node voltage safety boundary, determine the adjustable margin of each access node in the power grid area, and calculate the power adjustment parameters of the charging facility identifier based on the adjustable margin and the charging urgency.

[0046] This invention, by combining the spatiotemporal load forecast, the upper limit of feeder capacity, and the node voltage safety boundary, determines the adjustable margin of each access node within the power grid area. This enables a quantitative assessment of the load-bearing capacity of power grid nodes, identifying nodes with adjustment potential and their remaining capacity in the power grid without exceeding the feeder thermal stability limit and the node voltage stability domain. This provides a safety boundary constraint for formulating a scientific power regulation strategy. It should be explained that the adjustable margin refers to the power remaining after deducting the necessary voltage safety margin and feeder capacity limit from the future load level derived from the spatiotemporal load forecast based on the current operating state of the power grid node. This remaining power can be used to respond to electric vehicle charging demand or to regulate the load. Its value directly reflects the load absorption potential of the node above the safety operating baseline.

[0047] In detail, determining the adjustable margin of each access node within the power grid area by combining the spatiotemporal load forecast, the upper limit of the feeder capacity, and the node voltage safety boundary includes: The spatiotemporal load forecast and feeder capacity upper limit are processed for supply and demand coordination to obtain a coordinated margin range; Based on the node voltage safety boundary, power flow fitting is performed on the cooperative margin interval to obtain the fitted voltage curve; Calculate the voltage potential difference and power potential difference between each node in the fitted voltage curve; Combining the voltage-to-position difference and the power-to-position difference, the adjustability margin of the access node is calculated using the following formula:

[0048] in, This indicates the adjustable margin of the access node. and Let represent the voltage potential difference and power potential difference at the b-th node in the fitted voltage curve, respectively. This represents the correlation angle between the voltage potential difference and the power potential difference at the b-th node in the fitted voltage curve, where b represents the sequence number of the node in the fitted voltage curve, and r represents the number of nodes in the fitted voltage curve.

[0049] It should be explained that the cooperative margin range refers to the range of difference between the current load and the maximum carrying capacity of the power grid, taking into account feeder capacity limitations. The node voltage safety boundary is the upper and lower limits of allowable fluctuations in node voltage set according to national power quality standards and power grid stable operation procedures. It is used to constrain the power flow calculation results to ensure that the system operates within the safety domain. The fitted voltage curve is a curve that reflects the trend of each node voltage with power change under the constraint of the safety boundary, obtained after power flow fitting processing. The voltage-direction potential difference and the power-direction potential difference are the differences in voltage amplitude and phase between adjacent nodes and the differences in active power flow, respectively, used to characterize the loss and congestion during power transmission.

[0050] Furthermore, the supply-demand coordination processing of the spatiotemporal load forecast and feeder capacity upper limit can preliminarily estimate the static capacity margin of the power grid by comparing the difference between the predicted peak load and the rated capacity of the feeder; based on the node voltage safety boundary, the power flow fitting processing of the coordinated margin interval is performed to obtain the fitted voltage curve, which can be calculated using the PQ decomposition method, and a voltage limit violation penalty function or forced constraint mechanism is introduced during the iteration process to ensure that the generated voltage curve is always within the node voltage safety boundary, eliminating infeasible operating points where voltage exceeds the limit due to excessive load; the voltage direction between each node in the fitted voltage curve is calculated. The voltage and power directional potential differences can be obtained by performing differential operations on the node voltage phasor data extracted from the power flow calculation results. The adjustable margin of the access node is calculated by combining the voltage and power directional potential differences. This comprehensively considers the limitations of voltage stability and power transmission capacity on the node's adjustment space. For example, when the voltage of an access node approaches the lower limit of the safety boundary, even if the power margin is sufficient, the calculated adjustable margin will be significantly reduced, thus indicating to the dispatching system that the node has no adjustment space and voltage support should be prioritized. This effectively prevents the risk of grid collapse caused by voltage exceeding the limit and ensures the safe and stable operation of the grid when accepting electric vehicle charging loads.

[0051] This invention calculates the power adjustment parameters of the charging facility identifier based on the adjustable margin and the charging urgency. Then, while ensuring node voltage safety and line overload, it performs differentiated power allocation to the charging facilities, prioritizing the charging rights of vehicles with high urgency. This maximizes the utilization of the grid's remaining capacity, improves the regional distribution network's capacity to accept electric vehicle charging loads, and enhances its operational economy. It should be noted that the power adjustment parameters are a set of dynamic output power control commands for the charging facility identifier, which includes the maximum power value allowed to be output by the charging pile in the current scheduling cycle, the power change rate, or specific charging current and voltage settings.

[0052] Specifically, calculating the power adjustment parameters of the charging facility identifier based on the adjustable margin and the charging urgency includes: Collect historical adjustment data of the charging facilities under different scheduling cycles, and calculate the margin sensitivity scale corresponding to the adjustable margin based on the historical adjustment data; Combining the charging urgency, the margin sensitivity scale, and the adjustable margin, the power regulation parameters of the charging facility identifier can be calculated using the following formula:

[0053] Where E represents the power adjustment parameter corresponding to the charging facility identifier, D represents the adjustable margin, μ represents the margin sensitivity scale, and λ represents the charging urgency.

[0054] It should be explained that the historical adjustment data is a collection of power output records, node voltage fluctuation records, and load response records covering the past operating cycles of charging facilities. It is used to characterize the mapping relationship between adjustment behavior and grid status. The margin sensitivity scale is an exponential coefficient that reflects the sensitivity of power adjustment parameters to changes in adjustable margin, which is fitted based on the historical adjustment data. It is used to correct the weight of the margin's influence on power under different grid environments.

[0055] Furthermore, the collection of historical adjustment data of the charging facilities under different scheduling cycles can be obtained by reading the charging pile operation log files stored in the distributed database and extracting data sequences containing timestamps, power values ​​and corresponding node voltage states.

[0056] Optionally, calculating the margin sensitivity scale corresponding to the adjustable margin based on the historical adjustment data includes: The historical adjustment data is subjected to multidimensional feature mapping processing to obtain the adjustment feature space matrix; Calculate the mutual information value between each feature dimension in the adjustment feature space matrix and the adjustable margin, select key influencing factors from each feature dimension in the adjustment feature space matrix based on the mutual information value, and fit the margin response surface corresponding to the key influencing factors. Determine the slope of the tangent plane of the margin response surface under the current operating conditions, and perform exponential smoothing on the slope of the tangent plane to obtain the margin sensitive scale.

[0057] It should be explained that the regulation feature space matrix is ​​a high-dimensional data set mapped from multi-dimensional variables such as voltage, current, power, and timestamps in historical regulation data, used to characterize the overall regulation behavior; the mutual information value is a non-linear index that measures the degree of statistical dependence between two random variables, and can accurately capture the non-linear correlation between features and margins; the key influencing factors are the set of variables that have the most significant impact on the adjustable margin, selected from each feature dimension of the regulation feature space matrix; the margin response surface is a geometric surface that describes the mapping relationship between key influencing factors and adjustable margins, intuitively reflecting the dynamic response characteristics of the margin as factors change; the slope of the tangent plane refers to the geometric rate of change of the margin response surface at the current operating point in the multi-dimensional feature space.

[0058] Furthermore, the multidimensional feature mapping processing of historical adjustment data can be performed using principal component analysis or kernel function mapping techniques to transform the high-dimensional sparse original data into a low-dimensional dense feature matrix; the calculation of mutual information values ​​can utilize probability density estimation methods to quantify the contribution of each feature dimension to the adjustable margin and eliminate redundant features; the fitting and generation of the margin response surface can employ multinomial regression or support vector regression algorithms to construct a smooth mathematical surface model, avoiding interference from fluctuations in discrete data points; the determination of the slope of the tangent plane of the margin response surface under the current operating conditions essentially involves solving the partial derivative of the margin with respect to key influencing factors, and this partial derivative value reflects the degree of margin change caused by a unit load change at the current operating point.

[0059] S5. Monitor the net load fluctuation within the power grid area. When the net load fluctuation exceeds the threshold, based on the power adjustment parameters and the charging urgency, sequentially perform charging power reset processing on the charging facility identifier to obtain the vehicle-grid interaction scheduling result.

[0060] This invention monitors net load fluctuations within the power grid area and, when fluctuations exceed limits, combines power regulation parameters and charging urgency to reset the charging power. This enables peak shaving and valley filling and dynamic balancing of the power grid load, effectively alleviating voltage over-limit problems caused by fluctuations in new energy output or sudden load increases, and improving the accuracy of vehicle-grid interactive scheduling.

[0061] Furthermore, the steps for resetting the charging power are as follows: Assuming that the net load fluctuation in the power grid area exceeds a preset fluctuation threshold, indicating that the power grid is under peak load pressure or experiencing difficulties in absorbing loads during off-peak periods, a power reset mechanism is triggered. First, the identifiers of all online charging facilities in the area and their corresponding charging urgency are retrieved. For charging facilities with high charging urgency (i.e., the user's expected departure time is approaching and the battery level has not yet reached the expected target), they are determined to be rigid loads. Their current rated charging power is maintained or only slightly adjusted, and priority is given to allocating power grid capacity resources to ensure that the user's urgent travel needs are not affected. Simultaneously, a charging progress guarantee notification is sent to the user. For charging facilities with low charging urgency (i.e., the user's parking time is long and the current battery level is low), the charging power is reset. Charging facilities whose power supply meets basic travel needs are classified as flexible and adjustable loads. Based on the adjustable margin in the power adjustment parameters, the power reduction or reverse discharge support required is calculated, significantly reducing their charging power or even suspending charging. If necessary, V2G mode is activated to supply power to the grid. At the same time, peak-shaving subsidy forecasts are sent to users in conjunction with time-of-use pricing incentive mechanisms, and their subsequent charging periods are rescheduled to guide them to charge during periods of low grid load. For charging facilities that have undergone power resetting, their charging status data is updated in real time, generating vehicle-grid interaction scheduling results that include power adjustment instructions, expected end time, and compensation amount, and sending them to the grid dispatch center and user terminals. This achieves coordinated optimization of grid load fluctuations and user charging behavior.

[0062] like Figure 4 The diagram shown is a functional block diagram of a smart energy collaborative scheduling system based on vehicle-to-grid interaction according to the present invention.

[0063] The intelligent energy collaborative scheduling system 400 based on vehicle-to-grid interaction described in this invention can be installed in an electronic device. Depending on the functions implemented, the intelligent energy collaborative scheduling system based on vehicle-to-grid interaction includes an information acquisition module 401, a charging urgency determination module 402, a load prediction module 403, a regulation parameter calculation module 404, and a vehicle-to-grid interaction module 405. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.

[0064] In this embodiment of the invention, the functions of each module / unit are as follows: The information acquisition module 401 is used to acquire the set of vehicles to be coordinated and the power grid area information. The set of vehicles includes travel logs and charging facility identifiers. The power grid area information includes the upper limit of feeder capacity and the node voltage safety boundary. The charging urgency determination module 402 is used to calculate the daily mileage probability of the vehicle set based on the travel log, and determine the charging urgency of each vehicle in combination with the current battery charge status of each vehicle in the vehicle set. The load forecasting module 403 is used to determine the location of the access node corresponding to the vehicle set in the power grid topology based on the charging facility identifier, and to calculate the spatiotemporal load forecast value of the vehicle set within a preset time period using the daily driving mileage probability, the charging urgency and the access node location. The adjustment parameter calculation module 404 is used to combine the spatiotemporal load forecast value, the upper limit of the feeder capacity and the node voltage safety boundary to determine the adjustable margin of each access node in the power grid area, and to calculate the power adjustment parameters of the charging facility identifier based on the adjustable margin and the charging urgency. The vehicle-to-grid interaction module 405 is used to monitor the net load fluctuation within the power grid area. When the net load fluctuation exceeds a threshold, based on the power adjustment parameters and the charging urgency, the charging power of the charging facility identifier is reset sequentially to obtain the vehicle-to-grid interaction scheduling result.

[0065] In detail, the modules in the intelligent energy collaborative scheduling system 400 based on vehicle-to-grid interaction described in this embodiment of the invention adopt the same characteristics as described above during use. Figure 1 The method uses the same technical means as the smart energy collaborative scheduling method based on vehicle-to-grid interaction described in the article, and can produce the same technical effect, so it will not be elaborated here.

[0066] In one embodiment, a computer device is provided, which may be a server or a client, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external clients via a network connection. When the computer program is executed by the processor, it implements functions or steps on the server or client side of a smart energy collaborative scheduling method based on vehicle-to-grid interaction.

[0067] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: Obtain the set of vehicles to be coordinated and the grid area information, wherein the set of vehicles includes travel logs and charging facility identifiers, and the grid area information includes feeder capacity upper limit and node voltage safety boundary; Based on the travel logs, the daily mileage probability of the vehicle set is calculated, and the charging urgency of each vehicle is determined by combining the current battery state of charge of each vehicle in the vehicle set. Based on the charging facility identifier, the location of the access node corresponding to the vehicle set in the power grid topology is determined. Using the daily mileage probability, the charging urgency, and the access node location, the spatiotemporal load prediction value of the vehicle set within a preset time period is calculated. Combining the spatiotemporal load forecast, the upper limit of the feeder capacity, and the node voltage safety boundary, the adjustable margin of each access node in the power grid area is determined. Based on the adjustable margin and the charging urgency, the power regulation parameters of the charging facility identifier are calculated. Monitor the net load fluctuations within the power grid area. When the net load fluctuations exceed a threshold, based on the power adjustment parameters and the charging urgency, sequentially perform charging power reset processing on the charging facility identifiers to obtain the vehicle-grid interaction scheduling results.

[0068] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Obtain the set of vehicles to be coordinated and the grid area information, wherein the set of vehicles includes travel logs and charging facility identifiers, and the grid area information includes feeder capacity upper limit and node voltage safety boundary; Based on the travel logs, the daily mileage probability of the vehicle set is calculated, and the charging urgency of each vehicle is determined by combining the current battery state of charge of each vehicle in the vehicle set. Based on the charging facility identifier, the location of the access node corresponding to the vehicle set in the power grid topology is determined. Using the daily mileage probability, the charging urgency, and the access node location, the spatiotemporal load prediction value of the vehicle set within a preset time period is calculated. Combining the spatiotemporal load forecast, the upper limit of the feeder capacity, and the node voltage safety boundary, the adjustable margin of each access node in the power grid area is determined. Based on the adjustable margin and the charging urgency, the power regulation parameters of the charging facility identifier are calculated. Monitor the net load fluctuations within the power grid area. When the net load fluctuations exceed a threshold, based on the power adjustment parameters and the charging urgency, sequentially perform charging power reset processing on the charging facility identifiers to obtain the vehicle-grid interaction scheduling results.

[0069] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0070] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0071] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0072] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0073] Finally, it should be noted that in the above embodiments, each embodiment can be combined with each other or independent. Deleting any one of them will not affect the technical implementation of other embodiments. The above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A smart energy collaborative scheduling method based on vehicle-to-grid interaction, characterized in that, The method includes: Obtain the set of vehicles to be coordinated and the grid area information, wherein the set of vehicles includes travel logs and charging facility identifiers, and the grid area information includes feeder capacity upper limit and node voltage safety boundary; Based on the travel logs, the daily mileage probability of the vehicle set is calculated, and the charging urgency of each vehicle is determined by combining the current battery state of charge of each vehicle in the vehicle set. Based on the charging facility identifier, the location of the access node corresponding to the vehicle set in the power grid topology is determined. Using the daily mileage probability, the charging urgency, and the access node location, the spatiotemporal load prediction value of the vehicle set within a preset time period is calculated. Combining the spatiotemporal load forecast, the upper limit of the feeder capacity, and the node voltage safety boundary, the adjustable margin of each access node in the power grid area is determined. Based on the adjustable margin and the charging urgency, the power regulation parameters of the charging facility identifier are calculated. Monitor the net load fluctuations within the power grid area. When the net load fluctuations exceed a threshold, based on the power adjustment parameters and the charging urgency, sequentially perform charging power reset processing on the charging facility identifiers to obtain the vehicle-grid interaction scheduling results.

2. The intelligent energy collaborative scheduling method based on vehicle-to-grid interaction as described in claim 1, characterized in that, The step of determining the charging urgency of each vehicle by combining the current battery state of charge of each vehicle in the vehicle set includes: State parameters are extracted from the vehicle set to obtain the initial battery state of charge; An urgent demand analysis is performed on the initial battery state of charge to obtain the charging urgency level; Based on the charging urgency level, vehicle scheduling urgency indicators are selected from a pre-built scheduling priority strategy library; Based on the vehicle scheduling urgency index, the charging urgency of each vehicle is determined.

3. The intelligent energy collaborative scheduling method based on vehicle-to-grid interaction as described in claim 1, characterized in that, Determining the location of the access node corresponding to the vehicle set in the power grid topology based on the charging facility identifier includes: Obtain the electrical connection path information associated with the charging facility identifier from a preset power grid topology database; Calculate the electrical topology distance of each node in the electrical connection path information, and based on the electrical topology distance, filter out the candidate access node set in the electrical connection path information; Obtain the physical geographic coordinates and coverage area corresponding to the charging facility identifier; Construct a spatial mapping relationship model between the candidate access node set, the physical geographic coordinates, and the coverage area; and calculate the spatial matching degree of each node in the candidate access node set relative to the coverage area based on the spatial mapping relationship model. The node with the highest spatial matching degree is selected as the access node location corresponding to the vehicle set in the power grid topology.

4. The intelligent energy collaborative scheduling method based on vehicle-to-grid interaction as described in claim 3, characterized in that, The step of calculating the spatial matching degree of each node in the candidate access node set relative to the coverage area based on the spatial mapping relationship model includes: Construct the spatial geometric polygon of the coverage area and extract the geographic coordinates of each node in the candidate access node set; Analyze the relative positional relationship between the geographic coordinates and the spatial geometric polygon; If the relative positional relationship is such that the geographic coordinate point is located inside the spatial geometric polygon, calculate the straight-line distance between the geographic coordinate point and the physical geographic coordinate, and calculate the reciprocal of the straight-line distance to obtain the initial matching score; If the relative positional relationship is such that the geographic coordinate point is located outside the spatial geometric polygon, calculate the vertical distance from the geographic coordinate point to the boundary of the spatial geometric polygon, and calculate the initial matching score based on the vertical distance; The initial matching score is normalized to obtain the spatial matching degree.

5. The intelligent energy collaborative scheduling method based on vehicle-to-grid interaction as described in claim 1, characterized in that, The step of calculating the spatiotemporal load prediction value of the vehicle set within a preset time period using the daily mileage probability, the charging urgency, and the access node location includes: The probability density distribution of the daily mileage probability is calculated to obtain the mileage probability distribution function; The mileage probability distribution function is divided into intervals to obtain mileage probability feature clusters; Based on the charging urgency, the power demand spectrum corresponding to the mileage probability feature cluster is statistically analyzed; Based on the power demand spectrum, calculate the load distribution weights corresponding to the mileage probability feature clusters; By combining the load distribution weights and the mileage probability feature clusters, the spatiotemporal load prediction value of the vehicle set is calculated.

6. The intelligent energy collaborative scheduling method based on vehicle-to-grid interaction as described in claim 5, characterized in that, The calculation of the spatiotemporal load prediction value of the vehicle set by combining the load distribution weights and the mileage probability feature clusters includes: Extract the typical charging power curves corresponding to each interval in the mileage probability feature cluster to obtain the basic load demand vector; The load distribution weights are used to weight and correct the basic load demand vector to generate a weighted load feature matrix. Based on the location of the access node, the physical connection relationship of the vehicle set in the power grid topology is determined, and a node location index set is obtained; Based on the node location index set, the weighted load feature matrix is ​​mapped to each node of the power grid to obtain the node time-series load sequence; Based on the node time-series load sequence and the load distribution weight, the spatiotemporal load prediction value of the vehicle set is calculated.

7. The intelligent energy collaborative scheduling method based on vehicle-to-grid interaction as described in claim 1, characterized in that, The determination of the adjustability margin of each access node within the power grid area, by combining the spatiotemporal load forecast, the upper limit of feeder capacity, and the node voltage safety boundary, includes: The spatiotemporal load forecast and feeder capacity upper limit are processed for supply and demand coordination to obtain a coordinated margin range; Based on the node voltage safety boundary, power flow fitting is performed on the cooperative margin interval to obtain the fitted voltage curve; Calculate the voltage potential difference and power potential difference between each node in the fitted voltage curve; The adjustable margin of the access node is calculated by combining the voltage-to-position difference and the power-to-position difference.

8. The intelligent energy collaborative scheduling method based on vehicle-to-grid interaction as described in claim 1, characterized in that, The calculation of the power adjustment parameters of the charging facility identifier based on the adjustable margin and the charging urgency includes: Collect historical adjustment data of the charging facilities under different scheduling cycles, and calculate the margin sensitivity scale corresponding to the adjustable margin based on the historical adjustment data; Based on the charging urgency, the margin sensitivity scale, and the adjustable margin, the power adjustment parameters of the charging facility identifier are calculated.

9. The intelligent energy collaborative scheduling method based on vehicle-to-grid interaction as described in claim 8, characterized in that, The step of calculating the margin sensitivity scale corresponding to the adjustable margin based on the historical adjustment data includes: The historical adjustment data is subjected to multidimensional feature mapping processing to obtain the adjustment feature space matrix; Calculate the mutual information value between each feature dimension in the adjustment feature space matrix and the adjustable margin, select key influencing factors from each feature dimension in the adjustment feature space matrix based on the mutual information value, and fit the margin response surface corresponding to the key influencing factors. Determine the slope of the tangent plane of the margin response surface under the current operating conditions, and perform exponential smoothing on the slope of the tangent plane to obtain the margin sensitive scale.

10. A smart energy collaborative scheduling system based on vehicle-to-grid interaction, characterized in that, The system includes: The information acquisition module is used to acquire the set of vehicles to be coordinated and the grid area information. The set of vehicles includes travel logs and charging facility identifiers, and the grid area information includes feeder capacity upper limit and node voltage safety boundary. The charging urgency determination module is used to calculate the daily mileage probability of the vehicle set based on the travel log, and determine the charging urgency of each vehicle by combining the current battery state of charge of each vehicle in the vehicle set. The load forecasting module is used to determine the location of the access node corresponding to the vehicle set in the power grid topology based on the charging facility identifier, and to calculate the spatiotemporal load forecast value of the vehicle set within a preset time period using the daily mileage probability, the charging urgency and the access node location. The adjustment parameter calculation module is used to combine the spatiotemporal load forecast value, the upper limit of the feeder capacity and the node voltage safety boundary to determine the adjustable margin of each access node in the power grid area, and to calculate the power adjustment parameters of the charging facility identifier based on the adjustable margin and the charging urgency. The vehicle-to-grid interaction module is used to monitor the net load fluctuation within the power grid area. When the net load fluctuation exceeds a threshold, based on the power adjustment parameters and the charging urgency, the module sequentially performs a charging power reset process on the charging facility identifier to obtain the vehicle-to-grid interaction scheduling result.

Images