An electric vehicle charging decision control method, system, device and medium

Abstract

The application discloses an electric vehicle charging decision control method, system, device and medium, and belongs to the technical field of electric vehicle charging control. The method comprises the following steps: collecting current power distribution network operation state and charging load data; generating a charging price signal according to the current power distribution network operation state and the charging load data; generating a first charging decision in response to the charging price signal and determining a charging load space-time distribution; performing simulation safety checking on the charging load space-time distribution; if there is a safety overrun, generating control information and feeding back a corrected charging decision until the power distribution network safety constraint is met or the iteration number limit is reached; and outputting a target charging decision to a charging facility to perform charging. Therefore, by implementing the application, the matching degree of the charging decision and the power distribution network safety operation requirement can be improved.

Description

Technical Field

[0001] This application relates to the field of electric vehicle charging control technology, and in particular to an electric vehicle charging decision control method, system, device and medium. Background Technology

[0002] With the large-scale application of electric vehicles, charging load exhibits significant spatiotemporal fluctuations and randomness. Charging arrangements not only affect users' travel and charging costs but also alter the load distribution of the power distribution network, potentially causing operational risks such as voltage exceeding limits and line overload. Therefore, reasonable decision-making and control of the electric vehicle charging process are necessary.

[0003] Existing technologies typically generate charging plans based on historical charging records, time-of-use pricing, or preset charging rules, and then perform safety checks on these plans in conjunction with distribution network operating limits. However, methods based on historical charging records primarily reflect existing charging patterns and struggle to accurately depict differences in user choices across different price levels, travel demands, and charging scenarios. Methods based on time-of-use pricing or preset charging rules usually schedule charging according to fixed time periods or strategies, making it difficult to adapt to changes in charging load data and distribution network operating conditions. While safety checks can determine whether a charging plan meets operational boundaries such as voltage and power flow, insufficient consideration of changes in user choices and the impact of charging load on distribution network operating conditions during plan formation may result in a charging plan that does not match the actual safe operating boundaries of the distribution network, leading to insufficient safety in charging decisions. Summary of the Invention

[0004] This application provides a method, system, device, and medium for electric vehicle charging decision control, which can solve the problem that charging plans may still not match the actual safe operation boundary of the power distribution network in the prior art, resulting in insufficient safety of charging decisions.

[0005] Some embodiments of this application provide an electric vehicle charging decision control method, including: Collect current power distribution network operating status and charging load data; A charging price signal is generated based on the current operating status of the power distribution network and the charging load data. In response to the charging price signal, a first charging decision is generated, and the spatiotemporal distribution of charging load is determined based on the first charging decision; Based on the spatiotemporal distribution of the charging load and the preset distribution network safety constraints, a simulation safety verification is performed to obtain the distribution network safety assessment results; If the distribution network safety assessment result is that there is no safety limit violation, then the first charging decision will be used as the target charging decision for the current time step for output control. If the distribution network safety assessment result indicates that there is a safety limit violation, then control information is generated based on the distribution network safety assessment result, and the first charging decision is corrected based on the control information to obtain a second charging decision. The second charging decision is then used as the target charging decision for the current time step for output control.

[0006] Compared to existing technologies, the above embodiments have the following beneficial effects: A charging price signal is generated based on the current distribution network operating status and charging load data, enabling the price signal to reflect changes in current grid operating conditions and charging load data. Upon responding to the price signal, a first charging decision is formed and further converted into a spatiotemporal distribution of the charging load, thus allowing for safety verification of the charging decision from an electrical operation perspective. When the verification result indicates that the distribution network has exceeded safety limits, control information is generated, and a new charging decision is formed based on this information. Through the above processing, charging price, user response, and distribution network safety status can jointly participate in the charging decision at the current time step, reducing the possibility of inconsistency between the charging decision and the distribution network's safety operation boundary. The upper limit on the number of iterations also limits the number of calculations for safety verification and decision correction, preventing the decision-making process from continuously failing to converge and affecting the control timeliness of the current time step.

[0007] Furthermore, at the current time step, a charging price signal is generated based on the current distribution network operating status and the charging load data, including: Acquire historical charging data and electricity price data, and determine price response parameters based on the historical charging data and the electricity price data; Based on the current distribution network operating status, the charging load data, and the price response parameters, predict the charging load and distribution network operating status for multiple simulation time steps in the future; The charging price at each simulation time step is used as the variable to be optimized. For each simulation time step, the charging service revenue item is determined based on the variable to be optimized and the charging load, the electricity purchase cost item is determined based on the charging load, and the safety penalty item is determined based on the over-limit situation in the distribution network operation status. Under the premise of satisfying the preset constraints, with the goal of optimizing the first optimization objective function composed of the charging service revenue item, the electricity purchase cost item, and the safety penalty item, the variable to be optimized is solved, and the solution result of the variable to be optimized corresponding to the first simulation time step is used as the charging price signal.

[0008] Compared to existing technologies, the above embodiments have the following advantages: When generating charging price signals, historical charging data and electricity price data are used to determine price response parameters, providing a data basis for the response relationship of charging load to price changes. Charging load and distribution network operating status are predicted across multiple simulation time steps, and the charging price at each simulation time step is used as a variable to be optimized. This ensures that the currently output price signal not only reflects the current charging load data but also considers subsequent load changes and their impact on the distribution network operating status. Charging service revenue, electricity purchase cost, and safety penalty terms jointly participate in solving the objective function, enabling the simultaneous inclusion of charging service revenue, electricity purchase cost, and safety limit violation risk during price formation. This reduces the distribution network safety limit violation risk that may arise when generating charging prices solely based on revenue or fixed price rules, and improves the executability of the price signal.

[0009] Further, the step of generating a first charging decision in response to the charging price signal includes: Acquire multi-source user data, including user travel behavior data, traffic condition data, and historical charging data; Based on the multi-source user data, candidate charging schemes for each electric vehicle are generated, and the time cost and user preference of each candidate charging scheme are determined. The charging cost of each candidate charging scheme is determined based on the charging price signal. The evaluation results of each candidate charging scheme are determined based on the charging cost, the time cost, and the user preference. The corresponding selection probability is determined based on the evaluation results, and random sampling is performed according to the selection probability to generate the first charging decision for each electric vehicle.

[0010] Compared to existing technologies, the above embodiments have the following advantages: They utilize user travel behavior data, traffic condition data, and historical charging data to generate candidate charging schemes, enabling these schemes to reflect user travel patterns, traffic conditions, and past charging choices. For each candidate charging scheme, time cost and user preference are determined by multi-source user data, while charging cost is determined by charging price signals. This allows price changes and individual user differences to jointly influence the scheme evaluation results. Determining the selection probability based on the evaluation results and performing random sampling avoids treating all electric vehicle users as completely identical deterministic objects. This allows the first charging decision to retain the differences among users in their choices of charging location, charging time, and charging power, improving the fit of the first charging decision to actual user charging behavior.

[0011] Furthermore, the step of performing simulation safety verification based on the spatiotemporal distribution of the charging load and preset distribution network safety constraints to obtain the distribution network safety assessment result includes: Obtain the distribution network topology and equipment parameters, and determine the electrical connection relationship and node admittance parameters between each distribution network node based on the distribution network topology and equipment parameters; The basic load, power output, and initial operating status of each distribution network node are obtained from the current distribution network operating status, and the spatiotemporal distribution of the charging load is superimposed on the basic load of the corresponding node to obtain the first load of each distribution network node; Based on the first load, the power output, the initial operating state, and the node admittance parameters, the active power balance relationship and reactive power balance relationship of each distribution network node are solved to obtain the operating data of each distribution network node. Each of the aforementioned operational data is compared with the preset distribution network safety constraints to obtain the distribution network safety assessment result.

[0012] Compared to existing technologies, the above embodiments have the following advantages: By determining the electrical connection relationships and node admittance parameters between nodes based on the distribution network topology and equipment parameters, the spatiotemporal distribution of charging loads can be allocated to the corresponding nodes according to the actual distribution network structure. By superimposing the charging load with the basic load of each node, and combining the power output and initial operating state to solve for the active power balance and reactive power balance relationships, the operating data required for safety verification of each distribution network node can be obtained. Since the safety assessment results are derived from the calculation of electrical quantities at the node level, rather than solely based on the total charging load, it is possible to pinpoint the safety impact of the charging load on specific nodes or branches, thereby improving the precision and reliability of distribution network safety verification results.

[0013] Furthermore, the distribution network node includes a charging node; if the distribution network safety assessment result indicates a safety limit violation, then control information is generated based on the distribution network safety assessment result, including: Obtain the objects and corresponding limits that exceed the limits from the power distribution network security assessment results; The current power flow calculation results are determined based on the current power distribution network operating status and the spatiotemporal distribution of the charging load, and the sensitivity of the charging power change of each charging node to the over-limit amount of each over-limit object is determined based on the current power flow calculation results. The target charging node to be adjusted is determined from the charging nodes based on the sensitivity, and the adjustable range of each target charging node is determined based on the preset charging power adjustment range and the delay charging time. With the goal of minimizing the total charging load adjustment and the constraint of eliminating safe over-limits for each of the aforementioned over-limit objects, the charging load adjustment amount for each of the target charging nodes is determined within the adjustable range to generate the control information corresponding to each of the target charging nodes.

[0014] Compared to existing technologies, the above embodiments have the following beneficial effects: When safety limits are exceeded, the exceeding objects and quantities are first extracted from the distribution network safety assessment results, and then the sensitivity of the charging power change of each charging node to the exceeding quantity is determined based on the power flow calculation results. Sensitivity reflects the degree of effect of load adjustment of different charging nodes on eliminating safety limits. Based on this, target charging nodes to be adjusted can be screened from the charging nodes, avoiding indiscriminate control of all charging nodes. Furthermore, combined with the adjustable range of the target charging nodes, the charging load adjustment amount of each target charging node is determined with the goal of minimizing the total charging load adjustment amount. This can reduce the impact on normal charging load data while meeting the requirements of safe operation of the distribution network, and make the generated control information have clear adjustment objects and adjustment ranges.

[0015] Further, the step of correcting the first charging decision based on the control information to obtain a second charging decision, and using the second charging decision as the target charging decision for the current time step for output control, includes: Adjust the charging constraints corresponding to the target charging node according to the control information, and generate the first charging constraints for each target charging node. Based on the charging price signal and the first charging constraint, the first charging decision is re-evaluated to obtain the re-evaluation result of the first charging decision. The first charging decision is revised based on the re-evaluation results to obtain the second charging decision.

[0016] Compared to existing technologies, the above embodiments have the following advantages: After the control information is applied to the charging constraints of the corresponding target charging node, the first charging decision is re-evaluated under the original charging price signal and the adjusted constraints. This processing method converts safety control requirements into constraint inputs, enabling the user side to consider both charging prices and grid safety control requirements when revising the charging decision. Compared to directly changing the charging load, this process allows the second charging decision to respond to safety control information without deviating from the user's original charging decision logic, thereby improving the rationality and acceptability of the revised charging decision.

[0017] Furthermore, the output control includes: The charging location, charging start time, and charging power of the corresponding electric vehicle are determined based on the target charging decision. The corresponding charging facility is determined based on the charging location; A charging control command is generated based on the charging start time and the charging power. The charging control command is output to the charging facility to perform a charging operation on the electric vehicle.

[0018] Compared to existing technologies, the above embodiments offer the following advantages: the target charging decision is further parsed into charging location, charging start time, and charging power, and the corresponding charging facility is determined based on the charging location, giving the charging control command a clearly defined recipient. After receiving the control command containing the charging start time and charging power, the charging facility can execute the charging operation on the electric vehicle according to the command. Thus, the target charging decision is no longer merely decision data, but can be converted into a control command that can be executed by a specific charging facility, reducing the possibility of inconsistencies between the decision content and the actual charging operation in terms of objects or parameters, and improving the accuracy and feasibility of charging decision control.

[0019] Another embodiment of this application provides an electric vehicle charging decision control system, which is used to implement the steps of the electric vehicle charging decision control method of this application.

[0020] Another embodiment of this application also provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the steps of the electric vehicle charging decision control method of this application.

[0021] Another embodiment of this application provides a computer-readable storage medium, including: a stored computer program, which, when the computer program is running, controls the device where the computer-readable storage medium is located to perform the steps of the electric vehicle charging decision control method of this application. Attached Figure Description

[0022] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating an electric vehicle charging decision control method provided in some embodiments of this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0026] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0027] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0028] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0029] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0030] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0031] Existing technologies typically generate charging plans based on historical charging records, time-of-use pricing, or preset charging rules, and then perform safety checks on these plans in conjunction with distribution network operating limits. However, methods based on historical charging records primarily reflect existing charging patterns and struggle to accurately depict differences in user choices across different price levels, travel demands, and charging scenarios. Methods based on time-of-use pricing or preset charging rules usually schedule charging according to fixed time periods or strategies, making it difficult to adapt to changes in charging load data and distribution network operating conditions. While safety checks can determine whether a charging plan meets operational boundaries such as voltage and power flow, insufficient consideration of changes in user choices and the impact of charging load on distribution network operating conditions during plan formation may result in a charging plan that does not match the actual safe operating boundaries of the distribution network, leading to insufficient safety in charging decisions.

[0032] Please refer to Figure 1 To address the problem that existing charging plans may still not match the actual safe operation boundary of the power distribution network, resulting in insufficient safety of charging decisions, this application provides an electric vehicle charging decision control method, including the following steps S101 to S107: S101: Collect current power distribution network operating status and charging load data.

[0033] Preferably, in some embodiments of this application, the power distribution network topology and equipment parameters, meteorological data, traffic data, electric vehicle user travel behavior data, historical charging data, and electricity price data are collected in advance, and the collected data are cleaned, normalized, and feature extracted to construct a multi-source heterogeneous database.

[0034] Preferably, in some embodiments of this application, the feature extraction includes: using an autoencoder to perform nonlinear dimensionality reduction and reconstruction on meteorological data, traffic condition data and electric vehicle user travel behavior data to extract hidden features affecting charging load; using a time-series feature extraction method to extract electricity price fluctuation cycle and peak-valley period features from electricity price data; and fusing the extracted features with the distribution network topology and equipment parameters to form a multi-source heterogeneous database under a unified feature space.

[0035] In this embodiment, the current distribution network operating status may include the voltage, branch power flow, base load, power output, and operating status of related equipment at each distribution network node; the charging load data may include information such as the electric vehicle access location, expected charging time, required power, and expected departure time, that is, the charging load of electric vehicles at a certain time interval and at a certain access location.

[0036] Preferably, in some embodiments of this application, in order to perform continuous deduction or simulation verification scenarios, the total simulation duration and the simulation time step can be set, respectively expressed as: ; ; in, The total simulation duration is... This represents the simulation time step. The above value is only one example and can be adjusted in other embodiments based on the charging decision control cycle, load change rate, and computing resources.

[0037] When continuous simulation is required, the current simulation time is recorded as... If the current simulation time satisfies: ; The simulation time is advanced according to the following formula, and the processes of charging price generation, user response, security verification, and charging decision output are repeated at each advanced time step: ; If the current simulation time satisfies: ; Then the continuous deduction is considered complete. This refers to the current simulation moment. The aforementioned time progression process is an optional implementation method and does not affect the control process of generating and outputting the target charging decision for the current time step in this application.

[0038] S102: Generate a charging price signal based on the current distribution network operating status and the charging load data.

[0039] Furthermore, in some embodiments of this application, the step of generating a charging price signal based on the current distribution network operating status and the charging load data at the current time step includes the following steps S1021 to S1024: S1021: Obtain historical charging data and electricity price data, and determine the price response parameters based on the historical charging data and the electricity price data.

[0040] Preferably, in some embodiments of this application, the changes in charging volume, charging start time, and charging location corresponding to different electricity price levels in historical charging data can be statistically analyzed, and price response parameters such as the demand price elasticity coefficient can be determined accordingly to characterize the degree of response of charging load to changes in charging price.

[0041] S1022: Based on the current distribution network operating status, the charging load data, and the price response parameters, predict the charging load and distribution network operating status for multiple simulation time steps in the future.

[0042] Preferably, in some embodiments of this application, the optimization window includes the current time step and several simulation time steps after the current time step. First, the baseline charging load data within the optimization window is determined based on the current charging load data and user travel patterns. Then, the change in charging load data under different candidate charging prices is determined based on the price response parameters to obtain the corresponding predicted charging load, and further, the corresponding distribution network operation status is predicted.

[0043] S1023: The charging price at each simulation time step is used as the variable to be optimized. For each simulation time step, the charging service revenue item is determined based on the variable to be optimized and the charging load, the electricity purchase cost item is determined based on the charging load, and the safety penalty item is determined based on the over-limit situation in the distribution network operation status.

[0044] Preferably, in some embodiments of this application, the charging service revenue item Electricity purchase cost Price response relationship with charging load They are represented as follows: ; ; ; in, For the first The simulated time step shows the electricity price purchased from the main grid. For the first The baseline charging load data at each simulation time step and charging position i. The benchmark charging price, Let be the price elasticity of demand at charging location i; the meanings of the other symbols are the same as described above.

[0045] Preferably, in some embodiments of this application, the security penalty item Represented as: ; in, Let be the voltage at node i. and Let be the lower voltage limit and upper voltage limit of node i, respectively. For the contributing current of branch (i,j), Let (i,j) be the upper limit of the active power flow of branch (i,j). Let (i,j) be the current in branch (i,j). Let (i,j) be the upper limit of the current in branch (i,j). For the collection of distribution network branches, This indicates taking the larger value between 0 and x.

[0046] Preferably, in some embodiments of this application, the preset constraints include a price ceiling constraint, a price change rate constraint, and a power purchase and sale balance constraint, which are respectively expressed as: ; ; ; in, For the first The charging price at each simulation time step and charging position i. and These are the minimum and maximum charging prices, respectively. This represents the maximum permissible difference in price fluctuations between adjacent simulation time steps. For the first The electric vehicle charging load at a given time step and charging location i. To correspond to the base load of the simulation time step, This represents the maximum power received by the distribution network from the main grid. When h=0... The previously published charging price can be used.

[0047] S1024: Under the condition of satisfying the preset constraints, with the goal of optimizing the first optimization objective function composed of the charging service revenue item, the electricity purchase cost item and the safety penalty item, solve the variable to be optimized, and take the solution result of the variable to be optimized corresponding to the first simulation time step as the charging price signal.

[0048] Preferably, in some embodiments of this application, the first optimization objective function is expressed as: ; in, For the current time step, To optimize the number of simulation time steps within the window, For the first The charging service revenue item for each simulated time step. No. The electricity purchase cost item for each simulation time step. The penalty coefficient is... These are safety penalty items determined based on exceeding limits in operating data such as node voltage, branch power flow, or branch current.

[0049] By employing a rolling optimization window that includes the current time step to solve for charging prices in multiple future simulation time steps, and using the solution from the first simulation time step as the charging price signal for the current time step, the current output price not only reflects the current charging load data but also takes into account the impact of subsequent load changes on the distribution network's operating status. Simultaneously, charging service revenue, electricity purchase costs, and safety penalties are incorporated into the same optimization objective. Therefore, the formation of the price signal is no longer limited to fixed time-sharing rules or a single revenue objective, and can proactively suppress charging load growth that might cause voltage exceedances or branch overloads, improving the executability of the charging price signal.

[0050] S103: In response to the charging price signal, generate a first charging decision and determine the spatiotemporal distribution of charging load based on the first charging decision.

[0051] Furthermore, in some embodiments of this application, the step of generating a first charging decision in response to the charging price signal includes the following steps S1031 to S1034: S1031: Obtain multi-source user data, including user travel behavior data, traffic condition data, and historical charging data.

[0052] Preferably, in some embodiments of this application, travel chain features can be extracted from user travel behavior data and traffic condition data. The travel chain features include the start time, end time, start location type, destination type, mileage, and travel time of each trip. A Markov chain is used to construct a spatiotemporal transfer probability matrix of electric vehicles between different regions to describe the travel transfer patterns of users in typical time periods.

[0053] S1032: Generate candidate charging schemes for each electric vehicle based on the multi-source user data, and determine the time cost and user preference of each candidate charging scheme.

[0054] Preferably, in some embodiments of this application, the candidate charging scheme may include whether charging is required, charging location, charging start time, and charging power. The step of generating candidate charging schemes for each electric vehicle based on the multi-source user data includes: determining the current travel stage of the electric vehicle based on the travel chain features extracted in step S1031, and using the spatiotemporal transition probability matrix to determine the candidate charging locations that the electric vehicle may reach after the current time step.

[0055] For each candidate charging location, the travel time of the electric vehicle from its current location to the candidate charging location is estimated by combining the traffic condition data, and a charging time window is determined based on the expected arrival time and expected departure time. At the same time, the user's usual charging power, charging duration and charging period are extracted from the historical charging data to form a candidate charging power set and a candidate charging start time set.

[0056] Within the rechargeable time window, the candidate charging locations, candidate charging start times, and candidate charging powers are combined to generate multiple candidate charging schemes; and no charging is added as a candidate scheme to the candidate charging scheme set. For the combined candidate charging schemes, schemes that do not meet the requirements of travel chain continuity, rechargeable time window, or charging facility availability are eliminated, and candidate charging schemes that meet the constraints are retained.

[0057] For the retained candidate charging solutions, the time cost of each solution is determined based on the detour time to the corresponding charging location, the estimated queuing time, and the estimated charging duration. User preference for each candidate charging solution is determined based on the frequency with which the corresponding user selected the charging location, charging time, and charging power in historical charging data. Therefore, the candidate charging solutions not only reflect the user's travel accessibility but also preserve individual differences in user choices regarding charging location, charging time, and charging power, providing input for subsequent utility value calculations and selection probability sampling.

[0058] S1033: Determine the charging cost of each candidate charging scheme based on the charging price signal.

[0059] Preferably, in some embodiments of this application, for each candidate charging scheme, the charging cost of the candidate charging scheme is calculated based on the charging power of the candidate charging scheme, the expected charging time, and the charging price signal of the corresponding charging location.

[0060] S1034: Determine the evaluation results of each candidate charging scheme based on the charging cost, the time cost, and the user preference; determine the corresponding selection probability based on the evaluation results; and perform random sampling according to the selection probability to generate the first charging decision for each electric vehicle.

[0061] Preferably, in some embodiments of this application, the utility value of the candidate charging scheme is expressed as: ; in, This represents the utility value of user n at the current time step t when selecting charging power p at charging position i. The utility value is used to characterize the evaluation result of the corresponding candidate charging scheme. For charging power Charging time The charging cost is determined by the charging price. For the corresponding time cost, Let be the preference factor for user n for charging location i. , and These are non-negative weighting coefficients. Charging costs and time costs are included in the utility value as negative utilities, while user preferences are included in the utility value as positive utilities.

[0062] Preferably, in some embodiments of this application, the charging cost, time cost, and user preference factor are respectively expressed as: ; ; ; in, The charging price at the current time step t and charging position i. For candidate charging power, For charging time, This is a correction factor for charging efficiency. Let t be the current time step and i be the queuing time at the charging location. The detour time to reach charging location i. The frequency with which user n selects charging location i in historical charging data. A set of optional charging locations; derived from frequency percentage. It can be used as an initial preference factor, and then calibrated by combining it with maximum likelihood estimation.

[0063] Preferably, in some embodiments of this application, the selection probability of candidate charging schemes is expressed as follows: ; in, The probability of user n choosing charging location i and charging power p. Let p' be the set of optional charging power, and let p' be the summation index for iterating through the set of optional charging power. Choose a baseline utility value for user n when not charging. Random sampling based on the selection probability of each candidate charging scheme yields the parameters for whether to charge, charging start time, charging power, and charging location.

[0064] Preferably, in some embodiments of this application, historical charging data can be used and the maximum likelihood estimation method can be employed to... , and User preference factors are calibrated, and an agent-based modeling approach is used to create a corresponding agent for each electric vehicle user. Each agent carries calibrated utility function parameters and generates a travel plan based on travel chain characteristics and spatiotemporal transition probability matrices. The first charging decisions of each electric vehicle are aggregated to form the spatiotemporal distribution of charging load at each charging node at different simulation time steps.

[0065] By using travel behavior data, traffic condition data, and historical charging data to generate candidate charging solutions, and by jointly determining the evaluation results of the solutions based on charging cost, time cost, and user preferences, user charging choices are influenced by price signals while retaining travel patterns and individual differences. Furthermore, selection probabilities are formed based on the evaluation results and random sampling is performed. Therefore, different users can make different choices regarding charging location, time, and power for the same price signal, avoiding treating all users as the same deterministic load and improving the fit between the first charging decision and actual charging behavior.

[0066] S104: Perform simulation safety verification based on the spatiotemporal distribution of the charging load and the preset distribution network safety constraints to obtain the distribution network safety assessment results.

[0067] Furthermore, in some embodiments of this application, the step of performing simulation safety verification based on the spatiotemporal distribution of the charging load and preset distribution network safety constraints to obtain the distribution network safety assessment result includes the following steps S1041 to S1044: S1041: Obtain the distribution network topology and equipment parameters, and determine the electrical connection relationship and node admittance parameters between each distribution network node based on the distribution network topology and equipment parameters.

[0068] Preferably, in some embodiments of this application, a node admittance matrix is ​​established based on the line impedance, ground admittance, and transformer turns ratio, and the node admittance parameters are expressed as follows: ; ; in, Let be the element in the i-th row and j-th column of the nodal admittance matrix. Let i be the set of nodes connected to node i. It is the reciprocal of the branch impedance between node i and node k. Let be the ground admittance of node i in the direction through node k.

[0069] S1042: Obtain the basic load, power output and initial operating status of each distribution network node from the current distribution network operating status, and superimpose the spatiotemporal distribution of the charging load onto the basic load of the corresponding node to obtain the first load of each distribution network node.

[0070] Furthermore, in some embodiments of this application, obtaining the basic load, power output, and initial operating state of each distribution network node from the current distribution network operating state includes: for the current simulation time step to be verified, reading the basic active and reactive loads of each distribution network node, the active and reactive power outputs of each power source node, and the initial operating states such as voltage amplitude and voltage phase angle of each distribution network node from the current distribution network operating state. The initial operating states are used to provide initial values ​​for subsequent power flow equation solving and do not participate in load superposition.

[0071] Further, in some embodiments of this application, a correspondence between charging locations and distribution network nodes is established based on the access point information of charging facilities, and the distribution network node connected to the corresponding charging facility is determined as the charging node. The charging power of each charging location corresponding to the current simulation time step to be verified is extracted from the spatiotemporal distribution of the charging load, and the charging power of each charging location is aggregated to the corresponding charging node according to the correspondence. For cases where the same charging node corresponds to multiple charging locations or multiple electric vehicles, the charging power aggregated to that charging node is summarized to obtain the electric vehicle charging load of that charging node. For distribution network nodes that are not connected to electric vehicle charging loads, their corresponding electric vehicle charging load is zero. The base load of each distribution network node and the aggregated electric vehicle charging load are superimposed according to active and reactive components. The electric vehicle charging load is superimposed as active load to the base active load of the corresponding node. Considering the power factor of the charging facility, the charging reactive load is determined based on the charging active load and the corresponding power factor, and the charging reactive load is superimposed to the base reactive load of the corresponding node. Without considering the reactive power consumption of the charging facility, the charging reactive load is set to zero. The active and reactive loads superimposed on each distribution network node constitute the first load, which serves as the load input for subsequent solutions to the active and reactive power balance relationships of the nodes.

[0072] S1043: Based on the first load, the power output, the initial operating state, and the node admittance parameters, solve for the active power balance relationship and reactive power balance relationship of each distribution network node to obtain the operating data of each distribution network node.

[0073] Preferably, in some embodiments of this application, the power flow equations are established in polar coordinates, and the active power imbalance and reactive power imbalance are expressed as follows: ; ; in, and Let these be the active power output and reactive power output of node i, respectively. and These represent the active and reactive loads in the first load of node i after the charging load is superimposed. Let be the voltage magnitude at node i. The voltage phase angle difference between node i and node j and These are the real and imaginary parts of the nodal admittance matrix elements, respectively. Let be the total number of nodes in the distribution network. After solving the above power balance relationship, we can obtain the operating data such as the voltage amplitude, phase angle, and power flow of each branch at each node.

[0074] Preferably, in some embodiments of this application, the preset distribution network security constraints include node voltage constraints, branch power flow constraints, branch current constraints, transformer capacity constraints, and power output constraints, which are respectively expressed as: ; ; ; ; in, and Let be the lower voltage limit and upper voltage limit of node i, respectively. and These are the upper limits of active power flow and current, respectively, for branch ij. This represents the upper limit of the capacity of transformer branch ij. , , and These are the lower limit of active power output, the upper limit of active power output, the lower limit of reactive power output, and the upper limit of reactive power output of the power supply connected to node i, respectively.

[0075] Preferably, in some embodiments of this application, when it is necessary to consider the dynamic characteristics of generators, loads and related equipment, the implicit trapezoidal integral method can be used to combine the power flow equations with the corresponding dynamic differential equations to form a set of equations describing the dynamic characteristics of the distribution network, and the operating state of the distribution network can be obtained by solving them alternately or simultaneously within the current time step.

[0076] S1044: Compare each of the aforementioned operating data with the preset distribution network safety constraints to obtain the distribution network safety assessment result.

[0077] By superimposing the spatiotemporal distribution of charging load onto the base load of the corresponding distribution network nodes, and solving for the node power balance relationship based on the node admittance parameters determined by the actual topology, the safety verification can reflect the specific access location and electrical propagation path of the charging load in the power grid. Furthermore, operational data such as node voltage, branch power flow, and equipment output are compared with safety constraints. Therefore, the safety assessment results are no longer just a rough judgment of the total charging load, but can pinpoint specific objects exceeding limits and their degree of exceedance, providing a calculation basis for subsequent selective adjustment of the charging load.

[0078] S105: If the distribution network safety assessment result is that there is no safety limit violation, then the first charging decision is taken as the target charging decision for the current time step; if the distribution network safety assessment result is that there is a safety limit violation, then control information is generated based on the distribution network safety assessment result.

[0079] Furthermore, in some embodiments of this application, the distribution network node includes a charging node, which is a distribution network node connected to an electric vehicle charging load; if the distribution network safety assessment result indicates a safety limit violation, then control information is generated based on the distribution network safety assessment result, including the following steps S1051 to S1054: S1051: Obtain the over-limit objects and corresponding over-limit quantities from the power distribution network security assessment results.

[0080] In this embodiment, the object exceeding the limit refers to the node voltage, branch power flow, branch current, transformer capacity, or power output that does not meet the preset distribution network safety constraints; the amount exceeding the limit is the value of the operating data exceeding the corresponding safety constraint boundary.

[0081] S1052: Determine the current power flow calculation result based on the current distribution network operating status and the spatiotemporal distribution of the charging load, and determine the sensitivity of the charging power change of each charging node to the over-limit amount of each over-limit object based on the current power flow calculation result.

[0082] Preferably, in some embodiments of this application, the node voltages, phase angles, and branch power flows obtained in step S104 can be used as the current power flow calculation results. The Jacobian matrix of the power flow equation is used to calculate the influence coefficient of the change in injected power at each charging node on the voltage of the over-limit node, the power flow of the over-limit branch, or the current of the over-limit branch, and the influence coefficient is used as the sensitivity. When the sensitivity is positive and the larger the value, the more significant the effect of reducing the charging power of the corresponding charging node on reducing the corresponding over-limit amount.

[0083] Preferably, in some embodiments of this application, the sensitivity of the charging power change of the charging node to the over-limit amount of the over-limit object is expressed as follows: ; in, The sensitivity of the charging power change at charging node k to the over-limit amount of the over-limit object o. For the over-limit quantity of the over-limit object o, Let be the charging power of charging node k. The sensitivity can be obtained from the Jacobian matrix of the power flow equation, or by applying a small perturbation to the charging node power and comparing the power flow calculation results before and after the perturbation.

[0084] S1053: Determine the target charging node to be adjusted from the charging nodes according to the sensitivity, and determine the adjustable range of each target charging node according to the preset charging power adjustment range and the delay charging time.

[0085] Furthermore, in some embodiments of this application, determining the target charging node to be adjusted from the charging nodes based on the sensitivity includes: for each over-limit object, comparing the magnitude and sign of the sensitivity corresponding to each charging node; when the sensitivity of a charging node is positive, it indicates that reducing the charging power of the charging node can reduce the over-limit amount of the corresponding over-limit object, and the charging node is selected as a candidate control node; when the sensitivity of a charging node is zero or negative, it indicates that reducing the charging power of the charging node cannot reduce the over-limit amount of the corresponding over-limit object, and the charging node is not selected as a candidate control node.

[0086] In the case of multiple over-limit objects, candidate control nodes that have a positive adjustment effect on any over-limit object are merged to obtain a set of candidate control nodes. When the same candidate control node corresponds to multiple over-limit objects, the maximum sensitivity of the candidate control node to each over-limit object is used as its control priority, and the target charging node is determined from the set of candidate control nodes in descending order of control priority.

[0087] Furthermore, in some embodiments of this application, after determining the target charging node, the charging power, the minimum allowable charging power, the remaining charging load data, and the estimated departure time of each target charging node at the current time step are obtained. Based on the charging power and the minimum allowable charging power at the current time step, the range of charging power that the corresponding target charging node can be reduced to at the current time step is determined; based on the estimated departure time and the charging time required to complete the remaining charging load data, the maximum allowable delay time for the corresponding target charging node is determined.

[0088] The allowed reduction in charging power and the maximum allowed delay in charging time are uniformly converted into the charging load adjustment amount for the current time step. With zero as the lower limit and the maximum charging load adjustment amount allowed by the corresponding target charging node as the upper limit, the adjustable range of that target charging node is formed. Therefore, step S1054 can solve for the charging load adjustment amount within the adjustable range of each target charging node, avoiding the generation of control information that exceeds the adjustment capacity of the charging facilities or the user's travel time constraints.

[0089] S1054: With the goal of minimizing the total charging load adjustment, and with the constraint of eliminating safe over-limits for each of the over-limit objects, determine the charging load adjustment amount for each of the target charging nodes within the adjustable range, so as to generate the control information corresponding to each of the target charging nodes.

[0090] Preferably, in some embodiments of this application, a linear programming problem can be constructed, with the objective function being to minimize the sum of the charging load adjustments for each target charging node, and the constraint condition being that the predicted value of each exceeding-limit object, after sensitivity correction, does not exceed the corresponding safety constraint boundary. The charging load adjustment amount for each target charging node is then solved. Each control information includes at least the node identifier and charging load adjustment amount of the corresponding target charging node. The charging load adjustment amount is uniformly used to subsequently generate restrictions on the available charging power and allowed charging time periods for the target charging node.

[0091] Preferably, in some embodiments of this application, the linear programming problem for determining the charging load adjustment amount is expressed as: ; ; ; in, For the target set of charging nodes, For a set of out-of-bounds objects, The charging load adjustment amount for the target charging node k. This represents the maximum allowable charging load adjustment for the target charging node k within its adjustable range. When the control method is delayed charging, the change in charging power at the current time step caused by the delay can be converted into an equivalent charging load adjustment.

[0092] By first extracting the objects and amounts of exceeding limits, and then determining the sensitivity of each charging node based on the power flow calculation results, the control focus is concentrated on the target charging nodes that have a greater impact on safe over-limit operations. Furthermore, the adjustment amount for each target charging node is solved with the goal of minimizing the total charging load adjustment. Therefore, while eliminating safe over-limit operations, the indiscriminate restriction on normal charging load data can be reduced, and the control information has clearly defined adjustment targets and adjustment ranges.

[0093] S106: Based on the control information, correct the first charging decision to obtain a second charging decision, and use the second charging decision as the target charging decision for the current time step for output control; continue to verify the second charging decision until the distribution network safety constraints are met or the upper limit of the number of iterations is reached, and use the final second charging decision as the target charging decision for the current time step.

[0094] Furthermore, in some embodiments of this application, the step of correcting the first charging decision based on the control information to obtain a second charging decision, and using the second charging decision as the target charging decision for the current time step for output control, includes the following steps S1061 to S1063: S1061: Adjust the charging constraints corresponding to the target charging node according to the control information, and generate the first charging constraints for each target charging node.

[0095] In this embodiment, the first charging constraint may include at least one of the following: the maximum charging power allowed for the target charging node at the current time step, the allowed charging period, and the maximum delayable charging time.

[0096] S1062: Based on the charging price signal and the first charging constraint, the first charging decision is re-evaluated to obtain the re-evaluation result of the first charging decision.

[0097] S1063: Based on the re-evaluation results, the first charging decision is corrected to obtain the second charging decision.

[0098] In this embodiment, if the spatiotemporal distribution of the charging load corresponding to the second charging decision still leads to safety overruns, the safety verification, control information generation, and charging decision correction are repeatedly performed based on the latest corrected charging decision. If the verification result meets the distribution network safety constraints, the iteration stops. If the preset iteration limit is reached, the iteration stops and the final second charging decision is used as the target charging decision. At the same time, residual overrun information can be recorded for operation alarms.

[0099] By converting the control information into the first charging constraint condition of the target charging node and re-evaluating the first charging decision under the original charging price signal, the user-side correction process still follows the candidate scheme evaluation and selection logic. At the same time, the second charging decision continues to undergo safety verification and an upper limit is set for the number of iterations. Thus, the correction result can both respond to the grid safety requirements and remain consistent with the user's original charging decision logic, avoiding infinite loops in the decision correction process and improving the rationality of the second charging decision and the timeliness of control.

[0100] S107: Output control of the target charging decision so that the corresponding charging facility performs charging operation according to the target charging decision.

[0101] Furthermore, in some embodiments of this application, the output control includes the following steps S1071 to S1074: S1071: Determine the charging location, charging start time, and charging power of the corresponding electric vehicle based on the target charging decision.

[0102] S1072: Determine the corresponding charging facility based on the charging location.

[0103] S1073: Generate a charging control command based on the charging start time and the charging power.

[0104] S1074: Output the charging control command to the charging facility to perform a charging operation on the electric vehicle.

[0105] Preferably, in some embodiments of this application, the charging facility may be a charging pile, a charging station controller, or a charging station energy management terminal. The charging control command may include a target electric vehicle identifier, a charging facility identifier, a charging start time, a charging power, and a permitted charging duration. Upon receiving the charging control command, the charging facility will charge the target electric vehicle at the corresponding charging start time and according to the corresponding charging power; when the target charging decision is not to charge, the charging facility will remain in standby mode or prohibit the initiation of the corresponding charging process.

[0106] Preferably, in some embodiments of this application, after the charging facility performs a charging operation, it can return execution feedback information such as the actual charging power, the charging start time, and the battery state of charge, which is used to update the power distribution network operation status and the electric vehicle status, thereby ensuring that the recorded charging status is consistent with the actual execution status.

[0107] Because the target charging decision is parsed into charging location, charging start time, and charging power, and the specific charging facility is determined based on the charging location, the control command has a clear execution object and execution parameters. After the charging facility executes the charging according to the command, the decision can be implemented as an actual charging operation. This reduces the execution deviation caused by inconsistencies between the decision data and the on-site charging equipment due to differences in object, time, or power, and improves the feasibility of charging decision control at the current time step.

[0108] In summary, the electric vehicle charging decision control method provided in this application generates a charging price signal based on the current distribution network operating status and charging load data, enabling the price signal to reflect changes in current grid operating conditions and charging load data. Upon responding to the price signal, a first charging decision is formed and further converted into a spatiotemporal distribution of the charging load, thereby enabling safety verification of the charging decision from an electrical operation perspective. When the verification result indicates that the distribution network exceeds safety limits, control information is generated, and a new charging decision is formed based on this information. Through the above processing, charging price, user response, and distribution network safety status can jointly participate in the charging decision at the current time step, reducing the possibility of inconsistency between the charging decision and the distribution network's safety operation boundary. The upper limit on the number of iterations also limits the number of calculations for safety verification and decision correction, preventing the decision-making process from continuously failing to converge and affecting the control timeliness of the current time step.

[0109] It is understood that in some embodiments of this application, the above-described method process can be centrally invoked by the same control platform, or it can be encapsulated as an independent simulation unit and interact with data through a standardized data interface. For example, a data channel between each step can be established based on a High Level Architecture (HLA), a Functional Mock-up Unit (FMU), or a custom Socket communication mechanism, and a unified simulation clock can send time advancement instructions to each execution step according to the simulation time step.

[0110] In other embodiments, the utility function can include factors such as charging facility brand and charging speed, in addition to charging cost, time cost, and user preference. The probability of selecting a charging scheme can be determined using a support vector machine or deep learning model, in addition to multinomial logistic regression. The optimization objective can be composed of charging service revenue, electricity purchase cost, and safety penalties, and can also include load fluctuation suppression or operator revenue objectives based on actual operational needs. These alternative methods do not change the closed-loop interaction between charging price signals, user charging decisions, and distribution network safety verification, and are all optional implementation methods of the embodiments in this application.

[0111] Based on the above-described method embodiments, one embodiment of this application provides an electric vehicle charging decision control system, which is used to implement the electric vehicle charging decision control method of any embodiment of this application.

[0112] It is understood that the above system embodiments correspond to the method embodiments of this application, and can implement the electric vehicle charging decision control method provided by any of the above method embodiments of this application. The above modules can be implemented by the same processor executing the corresponding computer program, or they can be implemented collaboratively by different processors or different servers.

[0113] It should be noted that the system embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0114] Based on the above embodiments of the electric vehicle charging decision control method, another embodiment of this application provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the electric vehicle charging decision control method of any embodiment of this application.

[0115] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete this application. The one or more modules can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0116] The terminal device may be a desktop computer, laptop, handheld computer, cloud server, edge computing device, or charging station control terminal, etc. The terminal device may include, but is not limited to, a processor, memory, and communication interface.

[0117] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0118] Based on the above-described method embodiments, another embodiment of this application provides a 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 execute the electric vehicle charging decision control method described in any of the above-described method embodiments of this application.

[0119] The modules or units integrated into the device or terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, an electrical signal, and a software distribution medium, etc.

Claims

1. A method for decision-making and control of electric vehicle charging, characterized in that, include: Collect current power distribution network operating status and charging load data; A charging price signal is generated based on the current operating status of the power distribution network and the charging load data. In response to the charging price signal, a first charging decision is generated, and the spatiotemporal distribution of charging load is determined based on the first charging decision; Based on the spatiotemporal distribution of the charging load and the preset distribution network safety constraints, a simulation safety verification is performed to obtain the distribution network safety assessment results; If the distribution network safety assessment result is that there is no safety limit violation, then the first charging decision will be used as the target charging decision for the current time step for output control. If the distribution network security assessment result indicates that there is a safety limit violation, then control information is generated based on the distribution network security assessment result; Based on the control information, the first charging decision is corrected to obtain a second charging decision, and the second charging decision is used as the target charging decision for the current time step for output control.

2. The electric vehicle charging decision control method as described in claim 1, characterized in that, At the current time step, a charging price signal is generated based on the current distribution network operating status and the charging load data, including: Acquire historical charging data and electricity price data, and determine price response parameters based on the historical charging data and the electricity price data; Based on the current distribution network operating status, the charging load data, and the price response parameters, predict the charging load and distribution network operating status for multiple simulation time steps in the future; The charging price at each simulation time step is used as the variable to be optimized. For each simulation time step, the charging service revenue item is determined based on the variable to be optimized and the charging load, the electricity purchase cost item is determined based on the charging load, and the safety penalty item is determined based on the over-limit situation in the distribution network operation status. Under the premise of satisfying the preset constraints, with the goal of optimizing the first optimization objective function composed of the charging service revenue item, the electricity purchase cost item, and the safety penalty item, the variable to be optimized is solved, and the solution result of the variable to be optimized corresponding to the first simulation time step is used as the charging price signal.

3. The electric vehicle charging decision control method as described in claim 1, characterized in that, The step of generating a first charging decision in response to the charging price signal includes: Acquire multi-source user data, including user travel behavior data, traffic condition data, and historical charging data; Based on the multi-source user data, candidate charging schemes for each electric vehicle are generated, and the time cost and user preference of each candidate charging scheme are determined. The charging cost of each candidate charging scheme is determined based on the charging price signal. The evaluation results of each candidate charging scheme are determined based on the charging cost, the time cost, and the user preference. The corresponding selection probability is determined based on the evaluation results, and random sampling is performed according to the selection probability to generate the first charging decision for each electric vehicle.

4. The electric vehicle charging decision control method as described in claim 3, characterized in that, The simulation safety verification based on the spatiotemporal distribution of the charging load and preset distribution network safety constraints yields the distribution network safety assessment results, including: Obtain the distribution network topology and equipment parameters, and determine the electrical connection relationship and node admittance parameters between each distribution network node based on the distribution network topology and equipment parameters; The basic load, power output, and initial operating status of each distribution network node are obtained from the current distribution network operating status, and the spatiotemporal distribution of the charging load is superimposed on the basic load of the corresponding node to obtain the first load of each distribution network node; Based on the first load, the power output, the initial operating state, and the node admittance parameters, the active power balance relationship and reactive power balance relationship of each distribution network node are solved to obtain the operating data of each distribution network node. Each of the aforementioned operational data is compared with the preset distribution network safety constraints to obtain the distribution network safety assessment result.

5. The electric vehicle charging decision control method as described in claim 4, characterized in that, The power distribution network nodes include charging nodes; If the distribution network security assessment result indicates that a safety limit has been exceeded, then control information is generated based on the distribution network security assessment result, including: Obtain the objects and corresponding limits that exceed the limits from the power distribution network security assessment results; The current power flow calculation results are determined based on the current power distribution network operating status and the spatiotemporal distribution of the charging load, and the sensitivity of the charging power change of each charging node to the over-limit amount of each over-limit object is determined based on the current power flow calculation results. The target charging node to be adjusted is determined from the charging nodes based on the sensitivity, and the adjustable range of each target charging node is determined based on the preset charging power adjustment range and the delay charging time. With the goal of minimizing the total charging load adjustment and the constraint of eliminating safe over-limits for each of the aforementioned over-limit objects, the charging load adjustment amount for each of the target charging nodes is determined within the adjustable range to generate the control information corresponding to each of the target charging nodes.

6. The electric vehicle charging decision control method as described in claim 5, characterized in that, The step of correcting the first charging decision based on the control information to obtain a second charging decision, and using the second charging decision as the target charging decision for the current time step for output control, includes: Adjust the charging constraints corresponding to the target charging node according to the control information, and generate the first charging constraints for each target charging node. Based on the charging price signal and the first charging constraint, the first charging decision is re-evaluated to obtain the re-evaluation result of the first charging decision. The first charging decision is revised based on the re-evaluation results to obtain the second charging decision.

7. The electric vehicle charging decision control method as described in claim 1, characterized in that, The output control includes: The charging location, charging start time, and charging power of the corresponding electric vehicle are determined based on the target charging decision. The corresponding charging facility is determined based on the charging location; A charging control command is generated based on the charging start time and the charging power. The charging control command is output to the charging facility to perform a charging operation on the electric vehicle.

8. An electric vehicle charging decision control system, characterized in that, The electric vehicle charging decision control system is used to implement the electric vehicle charging decision control method as described in any one of claims 1 to 7.

9. A terminal device, characterized in that, The device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements an electric vehicle charging decision control method as described in any one of claims 1 to 7.

10. 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 where the computer-readable storage medium is located to perform an electric vehicle charging decision control method as described in any one of claims 1 to 7.

Images