Multi-vehicle fast charging station intelligent regulation and control system and method

Abstract

The invention relates to the technical field of intelligent regulation and control of multi-vehicle fast charging stations, in particular to an intelligent regulation and control system and method for multi-vehicle fast charging stations, and the system comprises a main control unit, a distributed data collection module, a dynamic power distribution module, a priority division module and a collaborative optimization module. According to the system, through construction of a charging demand model, real-time data acquisition and processing, dynamic power adjustment, priority division based on the game theory and edge calculation collaborative optimization, the resource utilization efficiency and the charging response performance are remarkably improved. Meanwhile, deep reinforcement learning is introduced to optimize overall performance, homomorphic encryption is adopted to protect privacy, and elastic expansion is supported. According to the invention, power grid fluctuation and load change can be effectively coped, charging waiting time is reduced, and regulation and control precision and system adaptability are improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of electric vehicle charging, specifically a multi-vehicle fast charging station intelligent control system and method. BACKGROUND

[0002] In today's rapidly developing new energy field, the popularity of electric vehicles has driven the research and application of multi-vehicle fast charging station intelligent control technology. Although certain progress has been made in charging station resource allocation and dynamic power control, there are still limitations in intelligent control capability in the scenario of multiple vehicles charging simultaneously, and the efficient and accurate demand under complex working conditions has not been fully met.

[0003] Through retrieval, the prior art discloses a fast charging station resource aggregation and interactive control method based on an energy router, which collects fast charging station parameter data through the energy router, and constructs a resource aggregation model using machine learning to optimize the resource utilization evaluation index, thereby determining the resource utilization degree. However, this technical solution focuses on the aggregation and optimization of internal resources of a single station, and does not adequately consider dynamic control problems when multiple vehicles are simultaneously connected, especially under high load conditions. There are certain limitations in intelligent power distribution and priority control among multiple vehicles, which may affect the charging efficiency or prolong the waiting time of some vehicles. In addition, this solution has weak adaptability in scenarios with high real-time requirements, and the ability to respond to power grid fluctuations or load changes needs to be improved.

[0004] Another prior art discloses an aggregation control system supporting safe access and rapid control of a large number of charging piles, which uploads charging pile operation data through an edge computing terminal, and generates control instructions using a pre-trained control information recognition model to realize safe access and rapid control of the charging piles. However, this technical solution mainly targets the control of a single charging pile and lacks the ability to cooperatively optimize the overall resources of a multi-vehicle fast charging station. In particular, when multiple vehicles are charging simultaneously, it fails to effectively solve the problems of charging priority division and dynamic power distribution among vehicles. In addition, this solution does not adequately consider the interaction and cooperative control between charging piles, which may lead to a decrease in overall system efficiency, and there is room for improvement in response speed and control accuracy when dealing with sudden load fluctuations.

[0005] The above problems indicate that the existing fast charging station control technology still has room for improvement in terms of intelligent control capability, dynamic power distribution, priority management, and real-time response performance in the scenario of multiple vehicles charging simultaneously. Therefore, the present application aims to provide a multi-vehicle fast charging station intelligent control system and method, which realizes dynamic priority division and power distribution for multiple vehicle charging through intelligent algorithms, optimizes the resource utilization efficiency of the fast charging station, and improves the real-time response capability and overall control accuracy of the charging process, thereby meeting the demand for efficient and intelligent control of modern fast charging stations. SUMMARY

[0006] The present application is based on the above problems, proposes a multi-vehicle fast charging station intelligent regulation system and method, which can significantly improve the resource utilization efficiency in the multi-vehicle simultaneous charging scene, optimize the dynamic power distribution and priority management ability, and enhance the adaptability of the system to complex working conditions. The present application realizes accurate matching and real-time response of multi-vehicle charging demand through intelligent algorithm, reduces charging waiting time, improves overall regulation accuracy, and effectively responds to power grid fluctuations and load changes.

[0007] Therefore, one aspect of the present application proposes a multi-vehicle fast charging station intelligent regulation system, which comprises a main control unit, a distributed data acquisition module, a dynamic power distribution module, a priority division module and a collaborative optimization module.

[0008] The main control unit is configured to: Construct a unified charging demand description model to standardize and virtualize the multi-vehicle charging request; Design a distributed data acquisition module to acquire real-time charging pile operating state, vehicle battery parameters and power grid load information, and generate unified data stream through data cleaning and standardization processing; Develop a dynamic power distribution module to integrate adaptive power regulation algorithm, dynamically adjust the output power of each charging pile according to the vehicle charging demand and real-time load of power grid; Establish a priority division module to adopt priority allocation algorithm based on game theory, combine vehicle remaining power, expected residence time and user preference, etc. to calculate the charging priority of each vehicle; Construct a collaborative optimization module to realize interaction and collaborative control between charging piles through edge computing technology, ensure load balancing and efficient use of resources in multi-vehicle charging process; Introduce global performance optimization model to continuously optimize the overall performance of the system by using deep reinforcement learning technology, improve resource utilization and charging efficiency; Integrate privacy protection mechanism to encrypt vehicle charging data by using homomorphic encryption technology to ensure the security of data in transmission and processing process; Design elastic expansion mechanism to support dynamic adjustment of system size and seamless access of new charging pile equipment.

[0009] Another aspect of the present application provides a multi-vehicle fast charging station intelligent regulation method, comprising the following steps: Construct a unified charging demand description model to standardize and virtualize the multi-vehicle charging request; Design a distributed data acquisition module to acquire real-time charging pile operating state, vehicle battery parameters and power grid load information, and generate unified data stream through data cleaning and standardization processing; Develop a dynamic power allocation module and integrate an adaptive power adjustment algorithm to dynamically adjust the output power of each charging pile according to the vehicle charging demand and the real-time load of the power grid. A priority allocation module is established, and a priority allocation algorithm based on game theory is adopted to calculate the charging priority of each vehicle by combining factors such as the vehicle's remaining battery power, expected dwell time, and user preferences. A collaborative optimization module is constructed to realize the interaction and collaborative control between charging piles through edge computing technology, ensuring load balancing and efficient resource utilization during the charging process of multiple vehicles; A global performance optimization model is introduced, and deep reinforcement learning technology is used to continuously optimize the overall system performance, improve resource utilization and charging efficiency; An integrated privacy protection mechanism is used, employing homomorphic encryption technology to encrypt vehicle charging data, ensuring data security during transmission and processing. The system is designed with a flexible expansion mechanism to support dynamic adjustment of system size and seamless integration of new charging pile devices.

[0010] Specifically, the dynamic power distribution module uses the following formula for power adjustment: in, Indicates the first Each charging station at any time 'output power' This represents the maximum output power of a single charging station. Indicates the time of the power grid Total available power This represents the total number of vehicles currently charging. The weight coefficient for the i-th vehicle is calculated by the priority partitioning module.

[0011] The priority allocation module is based on a game theory model and uses the following formula to calculate the priority weight of each vehicle: in, Indicates the first The vehicle's current remaining battery power. This refers to the maximum capacity of the vehicle's battery. Indicates the first The estimated dwell time of the vehicle. The maximum permitted stay time, Indicates user preference score, , and These are the weighting coefficients, satisfying... .

[0012] The global performance optimization model employs a deep reinforcement learning framework and defines a state space. Including grid load, vehicle charging demand, and charging pile operating status, action space This includes power allocation strategies and priority adjustment strategies, and reward functions. Defined as: in, Indicates the total power capacity of the system. This indicates the average charging wait time. Indicates the magnitude of power grid load fluctuation. , and These are the weighting coefficients.

[0013] The collaborative optimization module enables interaction between charging piles through edge computing technology and employs a consensus algorithm to ensure that the power allocation strategy of each charging pile is updated synchronously. The specific formula is as follows: in, Indicates the first The charging pile is at the first Power allocation value at the next iteration Indicates the relationship with the first A collection of charging stations that are directly connected to each other. Let be the weighting coefficient, satisfying .

[0014] The privacy protection mechanism employs homomorphic encryption technology to encrypt vehicle charging data, ensuring that the data is not leaked during transmission and processing. The specific encryption process is as follows: in, Represents the original data. For public key, This is the encrypted data.

[0015] The elastic scaling mechanism enables seamless access to new charging pile devices through a dynamic registration protocol. The specific process includes device authentication, resource configuration negotiation, and data synchronization initialization.

[0016] In summary, the present invention addresses the shortcomings of existing multi-vehicle fast charging stations in terms of intelligent control capabilities, dynamic power allocation, priority management, and real-time response performance through the aforementioned technical means, significantly improving the overall performance and resource utilization efficiency of the system. Attached Figure Description

[0017] Figure 1This is a schematic diagram of the overall architecture of the intelligent control system for multi-vehicle fast charging stations provided in an embodiment of the present invention, showing the connection relationship between the main control unit, the distributed data acquisition module, the dynamic power allocation module, the priority division module, and the collaborative optimization module.

[0018] Figure 2 The flowchart of the dynamic power allocation module details the implementation process of the power regulation algorithm based on grid load and vehicle charging demand.

[0019] Figure 3 The calculation logic diagram for the priority division module illustrates the priority weight calculation method based on the game theory model and its influencing factors.

[0020] Figure 4 This diagram illustrates the interaction mechanism of the collaborative optimization module, describing the process by which charging piles synchronize and update power allocation strategies through edge computing technology.

[0021] Figure 5 The flowchart illustrates the data encryption process for privacy protection mechanisms, showcasing the application steps of homomorphic encryption technology in vehicle charging data transmission and processing.

[0022] The attached figures are labeled as follows: 1. Main control unit; 2. Distributed data acquisition module; 3. Dynamic power allocation module; 4. Priority partitioning module; 5. Collaborative optimization module; 6. Power grid load information; 7. Vehicle charging demand; 8. Power regulation algorithm; 9. Priority weight calculation; 10. Edge computing interaction; 11. Homomorphic encryption process. Detailed Implementation

[0023] This invention provides an intelligent control system and method for multi-vehicle fast charging stations, the specific implementation of which is described in conjunction with the appendix. Figure 1 To be continued Figure 5 Please provide a detailed explanation. For example... Figure 1 As shown, the system includes a main control unit 1, a distributed data acquisition module 2, a dynamic power allocation module 3, a priority division module 4, and a collaborative optimization module 5. These modules are interconnected and work together through a communication network to achieve intelligent control of the charging process of multiple vehicles.

[0024] The main control unit 1, as the control core of the system, is responsible for overall scheduling and management. Main control unit 1 first constructs a unified charging demand description model, standardizing and virtualizing charging requests from different vehicles. This process integrates information such as battery parameters, user preferences, and expected dwell time for each vehicle to form a global view of charging demand. The distributed data acquisition module 2 collects real-time data on the charging pile's operating status, vehicle battery parameters, and grid load information 6, and generates a unified data stream through data cleaning and standardization. This data stream is transmitted to main control unit 1, providing decision-making support. The distributed data acquisition module 2 is directly connected to the charging pile via a sensor network, and simultaneously utilizes a communication interface to acquire grid load information 6 and vehicle charging demands 7, ensuring the comprehensiveness and real-time nature of data acquisition.

[0025] The dynamic power distribution module 3 integrates an adaptive power adjustment algorithm 8, which dynamically adjusts the output power of each charging pile based on the vehicle's charging needs 7 and the real-time load of the power grid. For example... Figure 2 As shown, the workflow of the dynamic power allocation module 3 includes the following steps: First, it obtains the current grid load information 6 and vehicle charging demand 7 from the distributed data acquisition module 2; second, based on the formula... Calculate the output power of each charging station. Among them, Indicates the first One charging station Output power at any moment This represents the maximum output power of a single charging station. Indicates that the power grid is Total available power at any given time. This represents the total number of vehicles currently charging. For the first Vehicle weighting coefficient. The calculations, derived from priority allocation module 4, ensure that power allocation can balance vehicle priority and grid load.

[0026] Priority allocation module 4 employs a game theory-based priority allocation algorithm 9, combining factors such as remaining vehicle battery power, estimated dwell time, and user preferences to calculate the charging priority of each vehicle. For example... Figure 3 As shown, the priority weight calculation formula is: ,in Indicates the first The vehicle's current remaining battery power. This refers to the maximum capacity of the vehicle's battery. Indicates the first The estimated dwell time of the vehicle. The maximum permitted stay time, Indicates user preference score, , and They are weight coefficients and satisfy the following conditions: Priority allocation module 4 calculates the priority weight of each vehicle using the above formula and transmits the result to dynamic power allocation module 3 to guide the formulation of power allocation strategy.

[0027] The collaborative optimization module 5 utilizes edge computing technology to achieve interaction and collaborative control between charging piles, ensuring load balancing and efficient resource utilization during multi-vehicle charging. For example... Figure 4 As shown, the collaborative optimization module 5 uses a consensus algorithm to ensure that the power allocation strategy of each charging pile is updated synchronously. The specific formula is as follows: ,in Indicates the first The charging pile is at the first Power allocation value at the next iteration Indicates the relationship with the first A collection of charging stations that are directly connected to each other. The weighting coefficients are and satisfy the following conditions: The collaborative optimization module 5 uses the above algorithm to synchronize the power allocation strategy updates among charging piles, thereby avoiding load imbalance caused by local power fluctuations.

[0028] The global performance optimization model employs a deep reinforcement learning framework and defines a state space. Including grid load, vehicle charging demand, and charging pile operating status, action space This includes power allocation strategies and priority adjustment strategies, and reward functions. Defined as: in, Indicates the total power capacity of the system. This indicates the average charging wait time. Indicates the magnitude of power grid load fluctuation. , and These are the weighting coefficients. The global performance optimization model continuously learns and optimizes to improve the overall system performance, ensuring maximum resource utilization and charging efficiency.

[0029] The privacy protection mechanism uses homomorphic encryption technology to encrypt vehicle charging data, ensuring data security during transmission and processing. For example... Figure 5 As shown, the homomorphic encryption process 11 includes the following steps: First, the original data... The encryption algorithm is input; secondly, the public key is used. The original data is encrypted using the following encryption formula: ,in The encrypted data is then transmitted to main control unit 1 for processing. Homomorphic encryption technology enables computation on encrypted data without decryption, thus ensuring data security and privacy.

[0030] The elastic expansion mechanism enables seamless integration of new charging pile devices through a dynamic registration protocol. The specific process includes device authentication, resource configuration negotiation, and data synchronization initialization. When a new charging pile device connects to the system, its legitimacy is first confirmed through authentication. Secondly, the main control unit 1 negotiates a resource configuration plan with the new charging pile device to ensure its normal operation. Finally, the main control unit 1 synchronizes the relevant data of the new charging pile device to the distributed data acquisition module 2 and the dynamic power allocation module 3, thereby achieving seamless device integration and collaborative operation.

[0031] The main control unit 1, distributed data acquisition module 2, dynamic power allocation module 3, priority division module 4, and collaborative optimization module 5 communicate with each other via a network to achieve data interaction and collaborative control. The main control unit 1 receives real-time data from the distributed data acquisition module 2 and transmits the processing results to the dynamic power allocation module 3 and the priority division module 4. The dynamic power allocation module 3 adjusts the output power of each charging pile according to the priority weight calculation results provided by the priority division module 4 and transmits the power allocation strategy to the collaborative optimization module 5. The collaborative optimization module 5 uses edge computing technology to synchronously update the power allocation strategy among the charging piles, thereby ensuring load balancing and efficient resource utilization during multi-vehicle charging.

[0032] In a practical application scenario, suppose a fast charging station simultaneously hosts 10 electric vehicles. Distributed data acquisition module 2 collects real-time information on each vehicle's battery parameters, estimated dwell time, and user preferences, transmitting this information to main control unit 1. Main control unit 1 standardizes this information according to a charging demand description model and passes the results to priority allocation module 4. Priority allocation module 4 calculates the priority weight of each vehicle based on a game theory model and passes the results to dynamic power allocation module 3. Dynamic power allocation module 3 calculates the output power of each charging pile based on the priority weight and grid load information 6, and passes the power allocation strategy to collaborative optimization module 5. Collaborative optimization module 5 uses a consensus algorithm to synchronize and update the power allocation strategy among charging piles, ensuring load balancing and efficient resource utilization during multi-vehicle charging. Throughout the process, a privacy protection mechanism encrypts vehicle charging data using homomorphic encryption technology, ensuring data security during transmission and processing. An elastic scaling mechanism enables seamless integration of new charging pile devices through a dynamic registration protocol, supporting dynamic adjustments to the system scale.

[0033] The above embodiments describe in detail the specific implementation process of the present invention, covering the functional implementation of each module, data interaction process, and operating principles in practical application scenarios. Through the above technical means, the present invention solves the shortcomings of existing multi-vehicle fast charging stations in terms of intelligent control capabilities, dynamic power allocation, priority management, and real-time response performance, significantly improving the overall performance and resource utilization efficiency of the system.

[0034] To enable those skilled in the art to fully understand and implement this invention, the specific implementation principle of this invention is further explained below in conjunction with a specific application scenario.

[0035] In a real-world scenario at a fast-charging station, assuming 10 electric vehicles need to charge simultaneously, the distributed data acquisition module 2 first connects directly to the charging pile via a sensor network and uses a communication interface to acquire grid load information 6 and vehicle charging demands 7. At this point, the distributed data acquisition module 2 collects real-time information on each vehicle's battery parameters, estimated dwell time, and user preferences, and transmits this data to the main control unit 1. The main control unit 1 standardizes this information based on a pre-built charging demand description model, forming a global view of charging demand. This process integrates key parameters such as the remaining battery power of each vehicle, the user-set charging priority, and the estimated dwell time, ensuring that subsequent control strategies accurately match actual demand.

[0036] Subsequently, the main control unit 1 transmits the standardized data to the priority allocation module 4. The priority allocation module 4, based on a game theory model and considering factors such as remaining vehicle battery power, estimated dwell time, and user preferences, calculates the priority weight for each vehicle. Specifically, the formula for calculating the priority weight is as follows: .in, Indicates the first The vehicle's current remaining battery power. This refers to the maximum capacity of the vehicle's battery. Indicates the first The estimated dwell time of the vehicle. The maximum permitted stay time, Indicates user preference score, , and These are the weighting coefficients, satisfying... Using this formula, the priority allocation module 4 can comprehensively consider the urgency of the vehicle, user needs, and the overall system load to generate reasonable priority weights, and then transmit the results to the dynamic power allocation module 3.

[0037] After receiving the priority weights, the dynamic power allocation module 3, combined with the grid load information 6 and vehicle charging demand 7, dynamically adjusts the output power of each charging pile using an adaptive power adjustment algorithm 8. Specifically, the dynamic power allocation module 3 is based on the formula... Calculate the output power of each charging station. Among them, Indicates the first One charging station Output power at any moment This represents the maximum output power of a single charging station. Indicates that the power grid is Total available power at any given time. This represents the total number of vehicles currently charging. For the first The weighting coefficient of each vehicle. Through this formula, the dynamic power allocation module 3 can reasonably allocate the output power of each charging pile under the condition of grid load fluctuation, ensuring that high-priority vehicles receive sufficient charging resources, while avoiding grid overload.

[0038] The collaborative optimization module 5 utilizes edge computing technology to achieve interaction and collaborative control between charging piles, ensuring load balancing and efficient resource utilization during multi-vehicle charging. Specifically, the collaborative optimization module 5 employs a consensus algorithm to ensure that the power allocation strategies of each charging pile are updated synchronously. The formula for the consensus algorithm is as follows: in, Indicates the first The charging pile is at the first Power allocation value at the next iteration Indicates the relationship with the first A collection of charging stations that are directly connected to each other. Let be the weighting coefficient, satisfying Through this algorithm, the collaborative optimization module 5 can quickly respond to local power fluctuations, ensuring that the power distribution strategy among each charging pile remains consistent, thereby avoiding system performance degradation caused by local load imbalance.

[0039] Throughout the process, the privacy protection mechanism uses homomorphic encryption technology to encrypt vehicle charging data, ensuring data security during transmission and processing. Specifically, the raw data... Input into the encryption algorithm, using the public key The original data is encrypted using the following encryption formula: ,in The data is encrypted. The encrypted data is transmitted to the main control unit 1 for processing. Homomorphic encryption technology can perform operations on the encrypted data without decryption, thereby ensuring data security and privacy.

[0040] Furthermore, the elastic expansion mechanism enables seamless access to new charging pile devices through a dynamic registration protocol. When a new charging pile device accesses the system, its legitimacy is first verified through identity authentication; secondly, the main control unit 1 negotiates a resource configuration plan with the new charging pile device to ensure its normal operation; finally, the main control unit 1 synchronizes the relevant data of the new charging pile device to the distributed data acquisition module 2 and the dynamic power allocation module 3, thereby achieving seamless access and collaborative operation of the device.

[0041] In summary, this invention achieves intelligent control of multi-vehicle fast charging stations through the aforementioned technical means. In actual operation, the distributed data acquisition module 2 ensures the comprehensiveness and real-time nature of data acquisition; the priority allocation module 4 generates reasonable priority weights through a game theory model; the dynamic power allocation module 3 achieves precise power allocation based on an adaptive power adjustment algorithm; the collaborative optimization module 5 ensures load balancing among charging piles through a consensus algorithm; the privacy protection mechanism safeguards data security through homomorphic encryption technology; and the elastic expansion mechanism supports dynamic adjustment and expansion of the system. Through the coordinated operation of these steps, this invention significantly improves the resource utilization efficiency and overall control accuracy of multi-vehicle fast charging stations under complex operating conditions, effectively addressing the challenges posed by grid fluctuations and load changes.

Claims

1. A multi-vehicle fast charging station intelligent control system, characterized in that, include: The main control unit (1), the distributed data acquisition module (2), the dynamic power allocation module (3), the priority division module (4), and the collaborative optimization module (5) are all included. The main control unit (1) is configured as follows: Build a unified charging demand description model to standardize and virtualize the charging requests of multiple vehicles; Design a distributed data acquisition module (2) to collect charging pile operating status, vehicle battery parameters and grid load information in real time, and generate a unified data stream through data cleaning and standardization; Develop a dynamic power allocation module (3) and integrate an adaptive power adjustment algorithm to dynamically adjust the output power of each charging pile according to the vehicle charging demand and the real-time load of the power grid. Establish a priority division module (4), adopt a priority allocation algorithm based on game theory, and calculate the charging priority of each vehicle by combining the vehicle's remaining battery power, expected dwell time and user preference factors; Construct a collaborative optimization module (5) to realize the interaction and collaborative control between charging piles through edge computing technology, so as to ensure load balance and efficient resource utilization during the charging process of multiple vehicles; A global performance optimization model is introduced, and deep reinforcement learning techniques are used to continuously optimize the overall system performance. An integrated privacy protection mechanism is used, employing homomorphic encryption technology to encrypt vehicle charging data; The system is designed with a flexible expansion mechanism to support dynamic adjustment of system size and seamless integration of new charging pile devices.

2. A method for intelligent control of multi-vehicle fast charging stations, characterized in that, Includes the following steps: Build a unified charging demand description model to standardize and virtualize the charging requests of multiple vehicles; Design a distributed data acquisition module (2) to collect charging pile operating status, vehicle battery parameters and grid load information in real time, and generate a unified data stream through data cleaning and standardization; Develop a dynamic power allocation module (3) and integrate an adaptive power adjustment algorithm to dynamically adjust the output power of each charging pile according to the vehicle charging demand and the real-time load of the power grid. Establish a priority division module (4), adopt a priority allocation algorithm based on game theory, and calculate the charging priority of each vehicle by combining the vehicle's remaining battery power, expected dwell time and user preference factors; Construct a collaborative optimization module (5) to realize the interaction and collaborative control between charging piles through edge computing technology, so as to ensure load balance and efficient resource utilization during the charging process of multiple vehicles; A global performance optimization model is introduced, and deep reinforcement learning techniques are used to continuously optimize the overall system performance. An integrated privacy protection mechanism is used, employing homomorphic encryption technology to encrypt vehicle charging data; The system is designed with a flexible expansion mechanism to support dynamic adjustment of system size and seamless integration of new charging pile devices.

3. The intelligent control method for multi-vehicle fast charging stations according to claim 2, characterized in that, The dynamic power distribution module (3) uses the following formula to adjust the power: in, Indicates the first Each charging station at any time 'output power' This represents the maximum output power of a single charging station. Indicates the time of the power grid Total available power This represents the total number of vehicles currently charging. Let be the weighting coefficient for the i-th vehicle.

4. The intelligent control method for multi-vehicle fast charging stations according to claim 3, characterized in that, The priority division module (4) calculates the priority weight of each vehicle using the following formula: in, Indicates the first The vehicle's current remaining battery power. This refers to the maximum capacity of the vehicle's battery. Indicates the first The estimated dwell time of the vehicle. The maximum permitted stay time, Indicates user preference score, , and These are the weighting coefficients, satisfying... .

5. The intelligent control method for multi-vehicle fast charging stations according to claim 2, characterized in that, The collaborative optimization module (5) uses a consensus algorithm to ensure that the power allocation strategy of each charging pile is updated synchronously. The specific formula is as follows: in, Indicates the first The charging pile is at the first Power allocation value at the next iteration Indicates the relationship with the first A collection of charging stations that are directly connected to each other. For the weighting coefficients, satisfying .

6. The intelligent control method for multi-vehicle fast charging stations according to claim 2, characterized in that, The global performance optimization model defines a state space. Including grid load, vehicle charging demand, and charging pile operating status, action space This includes power allocation strategies and priority adjustment strategies, and reward functions. Defined as: in, Indicates the total power capacity of the system. This indicates the average charging wait time. Indicates the magnitude of power grid load fluctuation. , and These are the weighting coefficients.

7. The intelligent control method for multi-vehicle fast charging stations according to claim 2, characterized in that, The privacy protection mechanism uses homomorphic encryption technology to encrypt vehicle charging data. The specific encryption formula is as follows: in, Represents the original data. For public key, This is the encrypted data.

8. The intelligent control method for multi-vehicle fast charging stations according to claim 2, characterized in that, The elastic expansion mechanism enables seamless access to new charging pile devices through a dynamic registration protocol. The specific process includes device authentication, resource configuration negotiation, and data synchronization initialization.

9. The intelligent control method for multi-vehicle fast charging stations according to claim 2, characterized in that, The distributed data acquisition module (2) is directly connected to the charging pile through the sensor network, and at the same time uses the communication interface to obtain grid load information and vehicle charging demand, so as to ensure the comprehensiveness and real-time nature of data acquisition.

10. The intelligent control method for multi-vehicle fast charging stations according to claim 2, characterized in that, The main control unit (1) receives real-time data from the distributed data acquisition module (2) and transmits the processing results to the dynamic power allocation module (3) and the priority division module (4). The dynamic power allocation module (3) adjusts the output power of each charging pile according to the priority weight calculation results provided by the priority division module (4) and transmits the power allocation strategy to the collaborative optimization module (5).

Images