Intelligent operation decision method, device and equipment of charging station and medium

Abstract

The embodiment of the application discloses a charging station intelligent operation decision method, device, equipment and medium. The method comprises the following steps: obtaining operation data of the charging station based on a pre-constructed digital twin model of the charging station, and simulating a plurality of preset operation strategies according to the operation data to obtain respective simulation results corresponding to each preset operation strategy; obtaining user behavior data and multi-source auxiliary data, and performing demand prediction based on the operation data, the user behavior data and the multi-source auxiliary data to obtain a predicted demand result; and performing multi-objective game decision by using the simulation result and the predicted demand result to obtain a target operation decision. Therefore, the operation strategy is optimized by using the multi-objective game mode, so that the target operation decision can meet the requirements of more targets and has stronger comprehensive optimization capability.

Description

Technical Field

[0001] This application relates to the field of charging station management technology, and in particular to a method, device, equipment and medium for intelligent operation decision-making of charging stations. Background Technology

[0002] With the continuous development of new energy electric vehicles, the related technologies of electric vehicle charging stations are also constantly improving. At present, the operation of charging stations usually focuses on monitoring, basic scheduling and simple strategy formulation in order to meet the needs of charging users as much as possible.

[0003] However, current operations management focuses primarily on demand scheduling in terms of "space and time," mainly addressing the questions of "where to charge" and "when to charge," and is unable to conduct more comprehensive operations management and decision-making. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, and medium for intelligent operation decision-making of charging stations, enabling more comprehensive operation management and decision-making.

[0005] Firstly, embodiments of this application provide a smart operation decision-making method for charging stations. Based on a pre-built digital twin model of a charging station, the operation data of the charging station is obtained, and various preset operation strategies are simulated according to the operation data to obtain the simulation results corresponding to each preset operation strategy. Acquire user behavior data and multi-source auxiliary data, and perform demand forecasting based on operational data, user behavior data, and multi-source auxiliary data to obtain the predicted demand results; Multi-objective game decision-making is conducted using simulation results and predicted demand results to obtain target operational decisions.

[0006] Secondly, embodiments of this application provide a smart operation decision-making device for charging stations. The simulation module is used to acquire the operating data of the charging station based on the pre-built digital twin model of the charging station, and to simulate various preset operation strategies based on the operating data to obtain the simulation results corresponding to each preset operation strategy. The prediction module is used to acquire user behavior data and multi-source auxiliary data, and to perform demand prediction based on the runtime data, user behavior data and multi-source auxiliary data to obtain the predicted demand results; The game optimization module is used to make multi-objective game decisions using simulation results and predicted demand results, and to obtain the target operation decision.

[0007] Thirdly, embodiments of this application also provide an electronic device, including: one or more processors and a storage device; Storage devices are used to store one or more programs; When one or more programs are executed by one or more processors, the one or more processors implement the smart operation decision-making method for charging stations as provided in any embodiment of this application.

[0008] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, characterized in that, when the program is executed by a processor, it implements the intelligent operation decision-making method for charging stations as provided in any embodiment of this application.

[0009] The technical solution of this application embodiment is based on a pre-constructed digital twin model of the charging station, acquiring the charging station's operational data, and simulating various preset operational strategies based on the operational data to obtain simulation results corresponding to each preset operational strategy; acquiring user behavior data and multi-source auxiliary data, and performing demand prediction based on the operational data, user behavior data, and multi-source auxiliary data to obtain predicted demand results; and using the simulation results and predicted demand results to perform multi-objective game decision-making to obtain the target operational decision. Based on this, the operational strategy is optimized using a multi-objective game approach, enabling the obtained target operational decision to meet the requirements of more objectives and achieving stronger comprehensive optimization capabilities. Attached Figure Description

[0010] Figure 1 A flowchart illustrating the intelligent operation decision-making method for charging stations provided in Embodiment 1 of this application; Figure 2 This is a schematic diagram of the structure of a smart operation decision-making device for charging stations provided in Embodiment 2 of this application; Figure 3 This is a schematic diagram of the structure of a collaborative computing device provided in Embodiment 3 of this application. Detailed Implementation

[0011] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present application, not the entire structure.

[0012] Example 1 Figure 1 This is a flowchart illustrating the intelligent operation decision-making method for charging stations provided in Embodiment 1 of this application. It should be noted that this method can run on a system computing device equipped with the necessary hardware, such as... Figure 1 As shown, the method includes: Step 101: Based on the pre-built digital twin model of the charging station, obtain the operating data of the charging station, and simulate various preset operating strategies according to the operating data to obtain the simulation results corresponding to each preset operating strategy.

[0013] When building a digital twin model of a charging station, static and dynamic data are collected to support operational monitoring in order to ensure the accuracy of virtual-real linkage monitoring.

[0014] For static data collection, core geometric parameters and installation locations of charging piles and power distribution equipment can be obtained through laser scanning and drawing verification. Equipment specification parameters (charging pile power, transformer capacity, etc.) can be collected, and electrical topology and pipeline paths can be sorted out to ensure that the model and physical equipment correspond accurately.

[0015] For dynamic data collection, sensors can be deployed on key equipment to collect real-time operating parameters such as charging current, voltage, equipment load rate, temperature rise, and station environmental data; historical operation, fault, and energy consumption data of the charging station management system can be extracted, and data can be labeled to provide support for monitoring and analysis.

[0016] Then, based on static data, 3D modeling software is used to recreate the spatial layout and appearance features of core entities such as charging piles and power distribution equipment at a 1:1 scale, building a virtual geometric model. Point cloud data is compared and calibrated to correct dimensional and positional deviations, ensuring the geometric accuracy of the model and meeting the visualization requirements of operational monitoring.

[0017] After the model is built, geometric calibration is performed. The point cloud data obtained by laser scanning is compared with the virtual model to correct issues such as dimensional deviations and positional offsets, ensuring that the geometric errors between the model and the physical entity are controlled within the allowable range. For concealed facilities such as cables and pipelines, the model accurately represents their direction, burial depth, and connection relationships by combining laying drawings and detection data, avoiding the impact of missing modeling of concealed parts on the implementation of subsequent functions.

[0018] Next, physical attributes are assigned to the virtual model by inputting collected equipment specifications, electrical characteristics, thermodynamic parameters, etc., so that the virtual equipment has the same operating rules as the physical equipment. For example, charging power range, voltage regulation logic, and fault triggering conditions are set for the charging pile model, and capacity limits and loss calculation formulas are set for the transformer model, so that the virtual model can simulate the operating state of the physical equipment.

[0019] Finally, a data transmission link was established to enable data exchange between the physical entity and the virtual model. Real-time data collected by sensors and operational data output from the device controller were transmitted to the data platform via an IoT gateway. After data cleaning, filtering, and format conversion, the data was synchronized to the corresponding entity module in the virtual model, establishing a real-time transmission channel between the physical device, data platform, and virtual model. Simultaneously, a data feedback mechanism was set up so that changes in the virtual model's state could be reflected back to the monitoring interface of the physical device, achieving bidirectional linkage between virtual and physical data. This completed the construction of the digital twin model of the charging station.

[0020] Based on the aforementioned digital twin model of charging stations, operational data of charging stations can be obtained more conveniently. This operational data includes, but is not limited to, equipment operating parameters, energy consumption and load data, fault and anomaly data, charging process and user-related data, and environmental auxiliary data.

[0021] The equipment operating parameters can include charging pile operating data, such as charging current, charging voltage, charging power, start / stop status, charging duration, charged amount, interface connection status, and voltage adjustment range. They can also include power distribution equipment operating data, such as transformer load rate, temperature rise, insulation status, and loss values; and distribution cabinet circuit current / voltage, switch status, and circuit load distribution.

[0022] Energy consumption and load data can include real-time energy consumption data, such as total energy consumption of the entire station, energy consumption of a single device, and energy consumption statistics for each time period; it can also include load data, such as peak / off-peak charging load, number of devices charging simultaneously, and load fluctuation trends.

[0023] Fault and abnormal data can include fault records, such as fault equipment number, fault type (short circuit, overload, interface fault, etc.), fault occurrence time, fault duration, and handling results; it can also include abnormal parameters, such as abnormal data such as equipment overheating, excessive voltage / current fluctuations, and decreased insulation performance.

[0024] Data associated with the charging process and users can include charging process data, such as scheduled charging records, reasons for charging interruption, and charging completion rate; it can also include user-related data, such as vehicle parking time, charging time preferences, and single-charge amount per vehicle.

[0025] Environmental auxiliary data may include real-time temperature and humidity, wind speed (which affects equipment heat dissipation and operational stability), etc.

[0026] Based on the digital twin model constructed above, the operation data of the charging station can be obtained more quickly and conveniently. Specifically, the port data of the charging station can be obtained from each data port in the pre-constructed digital twin model of the charging station; based on the mapping relationship between data ports and data types, the port data can be sorted into the operation data of the charging station.

[0027] In digital twin models, data ports and data types are usually mapped. For example, data port 1 may contain the operating status data of charging station equipment 1, while data port 2 may contain the charging power data of charging station equipment 1.

[0028] It should be noted that data type refers to content or identifiers that can represent the meaning of data. This mapping relationship can be stored in the digital twin model for easy retrieval.

[0029] In addition, in this step, when simulating the operation strategy based on the running data, for any preset operation strategy, the preset operation strategy is simulated based on the running data to obtain the simulation result of the preset operation strategy.

[0030] This simulation process can be performed in the strategy sandbox module, which can be integrated into the digital twin model. The strategy sandbox stores a variety of preset operation strategies, such as different energy storage charging and discharging strategies, dynamic electricity pricing strategies, and user guidance strategies.

[0031] By using the "what-if" simulation method, the various operational strategies are simulated and extrapolated based on the aforementioned operational data, and the impact of each operational strategy on multiple objectives such as operational revenue, equipment loss, and grid pressure is predicted. This impact is reflected in the simulation results.

[0032] Step 102: Obtain user behavior data and multi-source auxiliary data, and perform demand forecasting based on the operational data, user behavior data and multi-source auxiliary data to obtain the predicted demand results.

[0033] To improve the final operational strategy and better align with users' potential charging needs, this step can involve demand forecasting. The forecasted demand results may include, but are not limited to, charging demand, electricity price fluctuation trends, and user reach rates.

[0034] Specifically, runtime data, user behavior data, and multi-source auxiliary data can be input into a pre-trained spatiotemporal convolutional network model for demand prediction; and the predicted demand results output by the spatiotemporal convolutional network model can be obtained.

[0035] Among them, the spatiotemporal convolutional network model is a machine learning model that integrates spatiotemporal features. The spatiotemporal convolutional network model is trained by using pre-acquired training data and validation data. That is, the model parameters in the spatiotemporal convolutional network model are trained and adjusted using training data, and the trained and adjusted model is validated using validation data. The model parameters are further adjusted using the validation results.

[0036] It should be noted that the architecture of this spatiotemporal convolutional network model may include an input layer, a data normalization layer, a spatial convolutional layer, a temporal convolutional layer, a spatiotemporal fusion layer, and a fully connected output layer.

[0037] The spatiotemporal fusion layer is the core module of this model. It can perform spatiotemporal fusion, residual connection, batch normalization, and other functions. For details, please refer to the relevant technologies. It will not be elaborated here.

[0038] This spatiotemporal convolutional network model can be used to predict demand, obtaining predicted demand information such as user charging demand, electricity price fluctuation trends, and user reach rates.

[0039] Step 103: Use simulation results and predicted demand results to make multi-objective game decisions and obtain target operation decisions.

[0040] In this step, each participant in the charging operation can be identified as a different intelligent agent; the simulation results and predicted demand results are input into a pre-built multi-objective game decision engine, and the intelligent agents are used as players to perform multi-objective game optimization to obtain target operation decisions that meet the optimization conditions.

[0041] The multi-objective game decision engine includes an input module and a decision module. The input module receives the simulation results and predicted demand results, while the decision module uses a game algorithm based on multi-agent reinforcement learning (MARL). The participants in the charging operation can include, but are not limited to, charging stations, energy storage systems, and user groups. Each agent has at least one optimization objective that is biased towards its own interests.

[0042] For example, charging stations have economic benefit targets and grid-friendliness targets, energy storage systems have equipment lifespan targets, and user groups have user experience targets.

[0043] Among them, the economic benefit objective is to maximize peak-valley electricity price arbitrage profits and charging service revenue; the grid friendliness objective is to smooth grid load and improve the capacity for renewable energy absorption; the equipment lifespan objective is to optimize energy storage charging and discharging strategies and reduce battery degradation; and the user experience objective is to shorten user waiting time through dynamic pricing and guidance.

[0044] Since the demand results have been predicted and the simulation results have been generated in the aforementioned process, the key parameters of the objectives of each intelligent agent can be calculated based on the demand results and simulation results under different operational strategies.

[0045] For example, key parameters for economic benefit objectives include maximizing peak-valley electricity price arbitrage profits and charging service revenue; key parameters for grid-friendly objectives include grid load during operation according to different operating strategies; key parameters for equipment lifespan objectives may include battery degradation; and key parameters for user experience objectives are the average waiting time for users.

[0046] In multi-objective games, each agent can set a game weight to reflect the importance of different agents in the game. In a specific example, if the user experience is of greater importance at the current stage, then its game weight can be set to the highest.

[0047] For each agent, the key parameters of the objectives are evaluated for conflict (correlation analysis can be used to determine this). The conflict between objectives is determined. For example, the correlation coefficient between the charging station's "revenue" and "user waiting time" is -0.7, which indicates a strong conflict.

[0048] Finally, based on the aforementioned game weights and conflicts, and through strategy interaction and objective trade-offs, we seek the Pareto optimal equilibrium solution. For details, please refer to the relevant process of obtaining the Pareto optimal equilibrium solution, which will not be elaborated here.

[0049] In this step, the final output of the target operational decision is a comprehensive and optimal dynamic electricity price table, energy storage system charging and discharging plan, and user-oriented guidance suggestions.

[0050] In addition, this embodiment can also use target operation decisions to operate charging stations and obtain real-time data on the actual effects of the target operation decisions; the engine on which the simulation and prediction processes rely can be dynamically updated using the actual effect data.

[0051] Specifically, real-time data on the actual effects of strategy execution (such as actual revenue, user feedback, and device status) can be collected. This data is then compared with the predictions from the digital twin sandbox, and the prediction model and decision-making strategies are dynamically updated through online learning technology, forming a closed loop and enabling continuous self-optimization of the system.

[0052] To facilitate operations personnel's understanding of the entire process, an integrated dashboard can be set up to centrally display the simulation results of the strategy sandbox, the suggestions of the decision engine, the real-time execution status, and the achievement of multiple objectives. Intelligent alarms can also be configured to promptly notify administrators of abnormal situations such as equipment failures and policy deviations from expectations.

[0053] In this embodiment, based on a pre-built digital twin model of the charging station, operational data of the charging station is acquired, and various preset operational strategies are simulated according to the operational data to obtain simulation results corresponding to each preset operational strategy. User behavior data and multi-source auxiliary data are acquired, and demand prediction is performed based on the operational data, user behavior data, and multi-source auxiliary data to obtain predicted demand results. Multi-objective game decision-making is performed using the simulation results and predicted demand results to obtain the target operational decision. Based on this, the operational strategy is optimized using a multi-objective game approach, so that the obtained target operational decision can meet the requirements of more objectives and has a stronger comprehensive optimization capability.

[0054] Example 2 Figure 2 This is a schematic diagram of a smart charging station operation decision-making device provided in Embodiment 2 of this application. The smart charging station operation decision-making device provided in this embodiment can execute the smart charging station operation decision-making method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of the execution method. This device can be implemented in software and / or hardware, and is applied to a collaborative computing device. The collaborative computing device is equipped with memory, a hardware filter, and a vector processor. The vector processor stores force calculation microcode, such as... Figure 2As shown, the intelligent operation decision-making device for charging stations specifically includes: a simulation module 201, a prediction module 202, and a game optimization module 203.

[0055] The simulation module is used to acquire the operating data of the charging station based on the pre-built digital twin model of the charging station, and to simulate various preset operating strategies based on the operating data to obtain the simulation results corresponding to each preset operating strategy. The prediction module is used to acquire user behavior data and multi-source auxiliary data, and to perform demand prediction based on the runtime data, user behavior data and multi-source auxiliary data to obtain the predicted demand results; The game optimization module is used to make multi-objective game decisions using simulation results and predicted demand results, and to obtain the target operation decision.

[0056] Furthermore, the simulation module is specifically used for: Obtain port data of the charging station from each data port in the pre-built digital twin model of the charging station; Based on the mapping relationship between data ports and data types, the port data is organized into the operating data of the charging station.

[0057] Furthermore, the simulation module is specifically used for: For any preset operation strategy, the preset operation strategy is simulated based on the operating data to obtain the simulation results of the preset operation strategy.

[0058] Furthermore, the prediction module is specifically used for: Operational data, user behavior data, and multi-source auxiliary data are input into a pre-trained spatiotemporal convolutional network model for demand prediction. Obtain the prediction results output by the spatiotemporal convolutional network model.

[0059] Furthermore, the forecast results include charging demand, electricity price fluctuation trends, and user reach.

[0060] Furthermore, the game optimization module is specifically used for: Each participant in the charging operation is identified as a different intelligent agent; The simulation results and predicted demand results are input into a pre-built multi-objective game decision engine. The intelligent agent is used as the player to perform multi-objective game optimization and obtain the target operation decision that meets the optimization conditions.

[0061] Furthermore, the device is also used for: The operation of charging stations is carried out using target-oriented operational decisions, and the actual effect data after the implementation of target-oriented operational decisions is obtained in real time. The engine used in the simulation and prediction processes is dynamically updated using actual performance data.

[0062] Example 3 Figure 3 This is a schematic diagram of the structure of a collaborative computing device provided in Embodiment 3 of this application, as shown below. Figure 3 As shown, the collaborative computing device includes a processor 310, a memory 320, an input device 330, and an output device 340; the number of processors 310 in the collaborative computing device can be one or more. Figure 3 Taking a processor 310 as an example; the processor 310, memory 320, input device 330, and output device 340 in the collaborative computing device can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0063] The memory 320, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the cross-application task invocation method in this embodiment of the invention. The processor 310 executes various functional applications and data processing of the collaborative computing device by running the software programs, instructions, and modules stored in the memory 320, thereby realizing the aforementioned intelligent operation decision-making method for charging stations. Based on a pre-built digital twin model of a charging station, the operation data of the charging station is obtained, and various preset operation strategies are simulated according to the operation data to obtain the simulation results corresponding to each preset operation strategy. Acquire user behavior data and multi-source auxiliary data, and perform demand forecasting based on operational data, user behavior data, and multi-source auxiliary data to obtain the predicted demand results; Multi-objective game decision-making is conducted using simulation results and predicted demand results to obtain target operational decisions.

[0064] Furthermore, based on a pre-built digital twin model of the charging station, operational data of the charging station is obtained, including: Obtain port data of the charging station from each data port in the pre-built digital twin model of the charging station; Based on the mapping relationship between data ports and data types, the port data is organized into the operating data of the charging station.

[0065] Furthermore, simulations were performed on various preset operational strategies based on operational data to obtain simulation results for each preset operational strategy, including: For any preset operation strategy, the preset operation strategy is simulated based on the operating data to obtain the simulation results of the preset operation strategy.

[0066] Furthermore, demand forecasting is performed based on operational data, user behavior data, and multi-source auxiliary data to obtain forecasted demand results, including: Operational data, user behavior data, and multi-source auxiliary data are input into a pre-trained spatiotemporal convolutional network model for demand prediction. Obtain the prediction results output by the spatiotemporal convolutional network model.

[0067] Furthermore, the forecast results include charging demand, electricity price fluctuation trends, and user reach.

[0068] Furthermore, multi-objective game decision-making is conducted using simulation results and predicted demand results to obtain target operational decisions, including: Each participant in the charging operation is identified as a different intelligent agent; The simulation results and predicted demand results are input into a pre-built multi-objective game decision engine. The intelligent agent is used as the player to perform multi-objective game optimization and obtain the target operation decision that meets the optimization conditions.

[0069] Furthermore, the methods also include: The operation of charging stations is carried out using target-oriented operational decisions, and the actual effect data after the implementation of target-oriented operational decisions is obtained in real time. The engine used in the simulation and prediction processes is dynamically updated using actual performance data.

[0070] The memory 320 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on terminal usage. Furthermore, the memory 320 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory, or other non-volatile solid-state storage device. In some instances, the memory 320 may further include memory remotely located relative to the processor 310, which can be connected to a collaborative computing device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0071] Example 4 Embodiment 4 of this application also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform a smart operation decision-making method for charging stations, the method comprising: Based on a pre-built digital twin model of a charging station, the operation data of the charging station is obtained, and various preset operation strategies are simulated according to the operation data to obtain the simulation results corresponding to each preset operation strategy. Acquire user behavior data and multi-source auxiliary data, and perform demand forecasting based on operational data, user behavior data, and multi-source auxiliary data to obtain the predicted demand results; Multi-objective game decision-making is conducted using simulation results and predicted demand results to obtain target operational decisions.

[0072] Furthermore, based on a pre-built digital twin model of the charging station, operational data of the charging station is obtained, including: Obtain port data of the charging station from each data port in the pre-built digital twin model of the charging station; Based on the mapping relationship between data ports and data types, the port data is organized into the operating data of the charging station.

[0073] Furthermore, simulations were performed on various preset operational strategies based on operational data to obtain simulation results for each preset operational strategy, including: For any preset operation strategy, the preset operation strategy is simulated based on the operating data to obtain the simulation results of the preset operation strategy.

[0074] Furthermore, demand forecasting is performed based on operational data, user behavior data, and multi-source auxiliary data to obtain forecasted demand results, including: Operational data, user behavior data, and multi-source auxiliary data are input into a pre-trained spatiotemporal convolutional network model for demand prediction. Obtain the prediction results output by the spatiotemporal convolutional network model.

[0075] Furthermore, the forecast results include charging demand, electricity price fluctuation trends, and user reach.

[0076] Furthermore, multi-objective game decision-making is conducted using simulation results and predicted demand results to obtain target operational decisions, including: Each participant in the charging operation is identified as a different intelligent agent; The simulation results and predicted demand results are input into a pre-built multi-objective game decision engine. The intelligent agent is used as the player to perform multi-objective game optimization and obtain the target operation decision that meets the optimization conditions.

[0077] Furthermore, the methods also include: The operation of charging stations is carried out using target-oriented operational decisions, and the actual effect data after the implementation of target-oriented operational decisions is obtained in real time. The engine used in the simulation and prediction processes is dynamically updated using actual performance data.

[0078] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the above-described method operations, but can also execute related operations in the smart operation decision-making method for charging stations provided in any embodiment of this application.

[0079] Based on the above description of the implementation methods, those skilled in the art can clearly understand that this application can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0080] It is worth noting that in the embodiments of the above-mentioned device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of this application.

[0081] Note that the above description is merely a preferred embodiment and the technical principles employed in this application. Those skilled in the art will understand that this application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments. Many other equivalent embodiments may be included without departing from the concept of this application, and the scope of this application is determined by the scope of the appended claims.

Claims

1. A smart operation decision-making method for charging stations, characterized in that, include: Based on a pre-built digital twin model of a charging station, the operation data of the charging station is obtained, and various preset operation strategies are simulated according to the operation data to obtain the simulation results corresponding to each preset operation strategy. Acquire user behavior data and multi-source auxiliary data, and perform demand prediction based on the operational data, user behavior data and multi-source auxiliary data to obtain the predicted demand results; The simulation results and the predicted demand results are used to make multi-objective game decisions to obtain the target operation decision.

2. The method according to claim 1, characterized in that, The acquisition of operational data of the charging station based on a pre-built digital twin model of the charging station includes: The port data of the charging station is obtained from each data port in the pre-built digital twin model of the charging station; Based on the mapping relationship between data ports and data types, the port data is organized into the operating data of the charging station.

3. The method according to claim 1, characterized in that, The step of simulating multiple preset operation strategies based on the operational data to obtain simulation results corresponding to each preset operation strategy includes: For any preset operation strategy, the preset operation strategy is simulated based on the operation data to obtain the simulation results of the preset operation strategy.

4. The method according to claim 1, characterized in that, The process of predicting demand based on the operational data, user behavior data, and multi-source auxiliary data to obtain predicted demand results includes: The operational data, user behavior data, and multi-source auxiliary data are input into a pre-trained spatiotemporal convolutional network model for demand prediction. Obtain the prediction results output by the spatiotemporal convolutional network model.

5. The method according to claim 4, characterized in that, The predicted demand results include charging demand, electricity price fluctuation trends, and user reach.

6. The method according to claim 1, characterized in that, The step of using the simulation results and the predicted demand results to perform multi-objective game decision-making to obtain the target operational decision includes: Each participant in the charging operation is identified as a different intelligent agent; The simulation results and the predicted demand results are input into a pre-built multi-objective game decision engine. The intelligent agent is used as the player to perform multi-objective game optimization, and the target operation decision that meets the optimization conditions is obtained.

7. The method according to claim 1, characterized in that, The method further includes: The charging station is operated using the target operational decision, and the actual effect data after the execution of the target operational decision is obtained in real time; The engine used in the simulation and prediction processes is dynamically updated using the actual performance data.

8. A smart operation decision-making device for charging stations, characterized in that, The device includes: The simulation module is used to acquire the operation data of the charging station based on a pre-built digital twin model of the charging station, and to simulate multiple preset operation strategies based on the operation data to obtain the simulation results corresponding to each preset operation strategy. The prediction module is used to acquire user behavior data and multi-source auxiliary data, and perform demand prediction based on the operation data, user behavior data and multi-source auxiliary data to obtain the predicted demand results; The game optimization module is used to make multi-objective game decisions using the simulation results and the predicted demand results to obtain the target operation decision.

9. An electronic device, characterized in that, include: One or more processors and storage devices; The storage device is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the smart operation decision-making method for charging stations as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the intelligent operation decision-making method for charging stations as described in any one of claims 1-7.

Images