Charging pile-based charging control method and system, medium, product and terminal

Abstract

The invention provides a charging pile-based charging control method, a charging pile-based charging control system, a medium, a product and a terminal, a reward function capable of fusing a multi-dimensional optimization target is constructed, each weight in the reward function is adjusted in real time based on multi-dimensional state space real-time data, and the method does not depend on a fixed rule any more, so that the efficiency of the reward function is improved. The real-time power distribution scheme and the charging circuit on-off time sequence real-time scheme can be optimized on the basis of the latest environment feedback, the dynamic response speed is high, global optimal scheduling is continuously approached, and the real-time power distribution scheme and the charging circuit on-off time sequence real-time scheme can be dynamically balanced and decided according to the current comprehensive scene type identified in real time. Therefore, the overall operation efficiency is improved and the local optimum problem of the traditional technology is avoided while the stable adaptation of a power grid is ensured, the battery attenuation is delayed, and the emergency demand of a user and the equipment safety are fully met.

Description

Technical Field

[0001] This application relates to the field of charging pile technology, and in particular to a charging control method, system, medium, product and terminal based on a charging pile. Background Technology

[0002] With the rapid development of the new energy vehicle industry, charging infrastructure, especially high-power charging piles, has become a key link in ensuring the sustainable development of the industry. Charging pile technology achieves intelligent dynamic power distribution by centralizing and pooling charging modules, making it widely used in scenarios with urgent needs for high-power, fast-paced charging, such as highway service areas, public transport hubs, and urban core charging stations.

[0003] In existing technologies, charging control of charging piles mostly adopts fixed-rule scheduling or simple PID algorithms, which can only achieve single-objective optimization (such as prioritizing charging speed) and fail to build a multi-dimensional collaborative scheduling system involving the power grid, users, equipment, and batteries. First, multi-objective balancing capability is lacking: traditional charging pile control methods only focus on single charging efficiency or battery protection objectives, failing to incorporate multi-dimensional factors such as grid load, equipment health status, and differentiated user needs into a unified scheduling system, easily leading to local optima rather than global optima. Second, dynamic response lag: relying on fixed rules or simple PID algorithms, it cannot handle dynamic scenarios such as sudden increases in grid load, sudden equipment failures, and changes in user demand in real time. The system's response time far exceeds millisecond requirements, and this lag can lead to resource coordination conflicts. Summary of the Invention

[0004] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a charging control method, system, medium, product and terminal based on a charging pile, to solve the technical problems of lack of multi-objective balancing capability and dynamic response lag in the existing charging control strategies.

[0005] To achieve the above and other related objectives, a first aspect of this application provides a charging control method based on a charging pile, applied to a charging control system based on a charging pile. The charging control system is electrically connected to a charging pile, and the charging pile is electrically connected to the rechargeable batteries of multiple vehicles to be charged. The charging control method based on the charging pile includes: collecting real-time data in a multi-dimensional state space; the real-time data in the multi-dimensional state space includes one or a combination of real-time data of the power grid, real-time operating data of each module in the charging pile, multiple user demand data, and real-time state data of each rechargeable battery; identifying the current comprehensive scenario type based on the real-time data in the multi-dimensional state space, and dynamically updating a preset reward function accordingly; generating a real-time power allocation scheme for the charging pile and a real-time on / off timing scheme for the charging circuit based on the dynamically updated reward function and the current comprehensive scenario type; controlling the charging pile to charge each of the rechargeable batteries according to the real-time power allocation scheme and the real-time on / off timing scheme for the charging circuit; and cyclically executing the above steps of data acquisition, comprehensive scenario type identification, dynamic update of reward function, scheme generation, and charging operation at preset time intervals until each of the rechargeable batteries meets a preset charging termination condition.

[0006] In some embodiments of the first aspect of this application, the reward function is calculated in the following manner:

[0007] ;

[0008] in, Represents the reward function; Indicates the rate at which user needs are met; This indicates the charging cost optimization rate; Indicates the battery degradation suppression rate; Indicates the equipment failure risk rate; Indicates grid adaptability; Indicates the first weighting coefficient; This represents the second weighting coefficient; Indicates the third weighting coefficient; This represents the fourth weighting coefficient; t represents the fifth weighting coefficient; t represents the current time.

[0009] In some embodiments of the first aspect of this application, the method of generating a real-time power allocation scheme for the charging pile and a real-time on / off timing scheme for the charging circuit based on the dynamically updated reward function and the current comprehensive scenario type includes: calculating the real-time optimal charging power of each of the charging batteries based on the dynamically updated reward function; and generating a real-time power allocation scheme for the charging pile and a real-time on / off timing scheme for the charging circuit based on the real-time optimal charging power of each of the charging batteries and the current comprehensive scenario type.

[0010] In some embodiments of the first aspect of this application, the method for calculating the real-time optimal charging power of each of the rechargeable batteries according to the dynamically updated reward function includes: calculating the real-time charge deviation of each of the rechargeable batteries according to the user demand data; calculating the real-time charge error change rate of each of the rechargeable batteries according to the real-time charge deviation of each of the rechargeable batteries; calculating the real-time base charging power of each of the rechargeable batteries according to the real-time charge error change rate of each of the rechargeable batteries; and calculating the real-time optimal charging power of each of the rechargeable batteries according to the real-time base charging power of each of the rechargeable batteries and the dynamically updated reward function.

[0011] In some embodiments of the first aspect of this application, the real-time base charging power of each of the rechargeable batteries is calculated in the following ways:

[0012] ;

[0013] in, This indicates the real-time base charging power of the rechargeable battery. Indicates the proportionality coefficient; This indicates the real-time charge deviation of the rechargeable battery. Indicates the integral coefficient; Represents the differential coefficient; This represents the real-time charge error rate of the rechargeable battery; t represents the current time.

[0014] In some embodiments of the first aspect of this application, the method for calculating the real-time optimal charging power of each of the rechargeable batteries includes:

[0015] ;

[0016] in, This indicates the real-time optimal charging power of the rechargeable battery. This indicates the real-time base charging power of the rechargeable battery. This represents the dynamically updated reward function; t represents the current time.

[0017] To achieve the above and other related objectives, a second aspect of this application provides a charging control system based on a charging pile, wherein the charging control system is electrically connected to the charging pile, and the charging pile is electrically connected to the charging batteries of multiple vehicles to be charged; wherein the charging control system includes: a data acquisition module for acquiring real-time data in a multi-dimensional state space; the real-time data in the multi-dimensional state space includes one or a combination of real-time power grid data, real-time operating data of each module in the charging pile, multiple user demand data, and real-time state data of each charging battery; and a data processing module for identifying, based on the real-time data in the multi-dimensional state space, the current... The system identifies the current scenario type and dynamically updates the preset reward function accordingly. An intelligent agent module generates a real-time power allocation scheme for the charging pile and a real-time on / off timing scheme for the charging circuit based on the dynamically updated reward function and the current scenario type. It then controls the charging pile to charge each of the rechargeable batteries according to the real-time power allocation scheme and the real-time on / off timing scheme. The system repeatedly executes the above steps—data acquisition, scenario type identification, dynamic update of the reward function, scheme generation, and charging operation—at preset time intervals until each rechargeable battery meets the preset charging termination condition.

[0018] To achieve the above and other related objectives, a third aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the charging control method based on a charging pile as described above.

[0019] To achieve the above and other related objectives, a fourth aspect of this application provides a computer program product comprising computer program code that, when executed on a computer, causes the computer to implement the charging control method based on a charging pile as described above.

[0020] To achieve the above and other related objectives, a fifth aspect of this application provides an electronic terminal, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the charging control method based on a charging pile as described above.

[0021] As described above, the charging control method, system, medium, product, and terminal based on the charging pile of this application have the following beneficial effects:

[0022] (1) Improved global optimization effect: A reward function that can integrate multi-dimensional optimization objectives was constructed, and the weights in the reward function were adjusted in real time based on real-time data of multi-dimensional state space. Instead of relying on fixed rules, it can intelligently and dynamically weigh and decide according to the current comprehensive scenario type identified in real time. This allows the generated real-time power allocation scheme and the real-time charging circuit on / off timing scheme to be optimized based on the latest environmental feedback. This ensures stable grid adaptation, delays battery degradation, fully meets users' urgent needs, and ensures equipment safety, while improving overall operating efficiency and avoiding the local optima problem of traditional technologies.

[0023] (2) Fast dynamic response speed: According to the preset time interval, the real-time data of the multi-dimensional state space is updated, and the steps of comprehensive scenario type identification, dynamic update of reward function, scheme generation, charging operation are repeatedly executed. Through the cyclic iteration mechanism, the control strategy can be optimized online based on the latest environmental feedback. The dynamic response speed is fast and it continuously approaches the global optimal scheduling. Compared with traditional rule scheduling, it can quickly respond to dynamic scenarios such as sudden increase in grid load and sudden equipment failure, and reduce system downtime. Attached Figure Description

[0024] Figure 1 The diagram shows an applicable scenario for a charging control method based on a charging pile according to an embodiment of this application.

[0025] Figure 2 The diagram shown is a flowchart illustrating a charging control method based on a charging pile in one embodiment of this application.

[0026] Figure 3 The diagram shown is a flowchart illustrating the calculation of the real-time optimal charging power in one embodiment of this application.

[0027] Figure 4 The diagram shown is a schematic block diagram of a charging control system based on a charging pile according to one embodiment of this application.

[0028] Figure 5 The diagram shown is a structural schematic of an electronic terminal according to an embodiment of this application. Detailed Implementation

[0029] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0030] Before providing a further detailed description of the present invention, the nouns and terms used in the embodiments of the present invention are explained, and the nouns and terms used in the embodiments of the present invention are subject to the following interpretations:

[0031] <1> PID algorithm: Proportional-Integral-Derivative control algorithm. It continuously measures the deviation between the actual value of the controlled object and the desired target value, and performs three different mathematical operations on this deviation to generate a control signal. This allows the deviation to be eliminated quickly, smoothly and accurately, so that the system can be stabilized at the target state.

[0032] To facilitate understanding of the embodiments of this application, firstly, in conjunction with Figure 1 Detailed explanation. Figure 1 This illustration shows an applicable scenario for the charging control method based on a charging pile in this embodiment of the invention. In this embodiment, the charging control method based on a charging pile is applied to a charging control system based on a charging pile. The charging control system is electrically connected to the charging pile, and the charging pile is electrically connected to the rechargeable batteries of multiple vehicles to be charged. The charging control system includes a data acquisition module, a data processing module, and an intelligent agent module. The charging control system controls the charging pile to charge the rechargeable batteries of the multiple vehicles to be charged. The charging pile includes a device health monitoring module, multiple bidirectional charging and discharging modules, a relay matrix, a relay matrix control module, multiple charging circuits (not shown), and multiple charging terminals (not shown). The device health monitoring module monitors the operating status of each device. The input terminals of each bidirectional charging and discharging module are connected to the power grid to convert AC power to DC power, and their output terminals are connected in parallel to a common DC bus. The input terminals of the relay matrix are connected to the common DC bus, and their output terminals are connected to each charging terminal through corresponding charging circuits. The relay matrix control module drives the corresponding relays in the relay matrix to operate, guiding the electrical energy from the common DC bus to the corresponding charging terminal via the charging circuit, thereby charging the rechargeable batteries connected to that charging terminal.

[0033] In this embodiment, as Figure 2 The diagram illustrates a flowchart of a charging control method based on a charging pile, as shown in an embodiment of the present invention. The charging control method based on a charging pile mainly includes the following steps:

[0034] S201: Collect real-time data of multi-dimensional state space.

[0035] In this embodiment, the multi-dimensional state space real-time data includes one or a combination of real-time power grid data, real-time operation data of each module in the charging pile, multiple user demand data, and real-time state data of each charging battery, thereby obtaining multi-dimensional data such as power grid dimension parameters, equipment dimension parameters, user dimension parameters, and battery dimension parameters, which are then classified and incorporated into the state space of the reinforcement learning agent module to achieve real-time global state perception.

[0036] In this embodiment, real-time grid data includes, but is not limited to: grid load factor data, voltage monitoring data, and peak / valley electricity price period data. User demand data includes, but is not limited to: battery state of charge (SOC) data, user departure time data, and departure urgency score. Real-time operating data of each module in the charging pile includes, but is not limited to: temperature data of each bidirectional charge / discharge module, temperature distribution image of each bidirectional charge / discharge module, cumulative usage time of each bidirectional charge / discharge module, and relay contact current value. Real-time status data of the charging battery includes, but is not limited to: current state of charge data, battery health (SOH) data, battery degradation rate data, and battery type data.

[0037] In this embodiment, the data acquisition module in the charging control system obtains real-time grid data through the grid interface, obtains real-time operating data of each module in the charging pile through the equipment health monitoring module, obtains user demand data through the communication interface of the vehicle to be charged or the human-machine interface (such as a screen or a matching mobile application) of the charging pile, and obtains real-time status data of the charging battery through the communication interface of the battery management system (BMS) of the vehicle to be charged.

[0038] In this embodiment, for grid-level parameters, the monitoring range of grid load rate data is 0-100%, the range of voltage monitoring data is 220V±10%, and the peak-valley electricity price period data is preset according to local grid policies (e.g., peak hours 9:00-21:00, valley hours 23:00-7:00 the next day, and the rest are normal hours).

[0039] In this embodiment, for user-level parameters, the user sets the battery's final charge state data, ranging from 0-100%. The user's departure time data is input by the user. The departure urgency score characterizes the user's need to complete charging under time constraints, using an integer scale of 1 to 5. Here, 1 point represents "no time constraint, flexible scheduling," 2 points represent "mildly urgent, with a relatively relaxed time window," 3 points represent "moderately urgent, needs to be completed within the expected time," 4 points represent "highly urgent, time is tight," and 5 points represent "extremely urgent, requires increased charging power to meet travel needs." The departure urgency score can be automatically calculated based on the user's departure time data and the battery's current charge state data. For example, if the current charge state data is <20% and the departure time is <30 minutes, the score is ≥4 points. Alternatively, the departure urgency score can be directly selected or input by the user through the human-computer interaction interface.

[0040] In this embodiment, for device-level parameters, the temperature data monitoring range of the bidirectional charging and discharging module is 0-100℃, the cumulative usage time of the bidirectional charging and discharging module has no upper limit (real-time cumulative), and the monitoring range of the relay contact current value is set according to the rated specifications of the relay.

[0041] In this embodiment, for battery-related parameters, the monitoring range for the current state of charge (SOH) data of the rechargeable battery is 0-100%, the monitoring range for the SOH data is 0-100%, and the monitoring period for the degradation rate data is each charge-discharge cycle. It should be noted that the battery's SOH data is the percentage of its current remaining charge to its nominal total capacity.

[0042] S202: Based on the real-time data of the multi-dimensional state space, identify the current comprehensive scenario type, and dynamically update the preset reward function accordingly.

[0043] In this embodiment, the data processing module normalizes the real-time data in the multi-dimensional state space to eliminate dimensional differences and form a unified scale input. These processed multi-dimensional parameters are then integrated into a structured state vector, which serves as the normalized state space input for the reinforcement learning agent module. This enables global, real-time perception of the entire charging pile operating environment, providing a foundation for subsequent scene recognition and intelligent decision-making.

[0044] In this embodiment, the method of identifying the current comprehensive scene type based on the real-time data of the multi-dimensional state space, and dynamically updating the preset reward function accordingly, includes:

[0045] (1) Based on the real-time data of the power grid, determine the load scenario of the power grid, whether it is a peak load scenario, a flat load scenario or a low load scenario.

[0046] In this embodiment, the load scenario of the power grid is determined based on grid load factor data and peak-valley electricity price time period data. Specifically, a peak-valley time period division model is constructed, such as peak hours 9:00-21:00, valley hours 23:00-7:00 the next day, and the rest as normal hours. When the grid load factor data is higher than a preset peak threshold (e.g., 85%) and is in the peak hours, it is determined to be a peak load scenario; when the grid load factor data is lower than a valley threshold (e.g., 30%) and is in the valley hours, it is determined to be a valley load scenario; the rest are determined to be normal load scenarios. If the voltage monitoring data fluctuates continuously by more than ±3%, a grid anomaly flag is triggered. This flag will affect the subsequent comprehensive scenario identification and adjustment of the grid adaptability weight in the reward function.

[0047] (2) Based on the real-time status data of the charging battery and the pre-built list of connected batteries, determine the access scenario of the charging pile, whether it is a new battery access scenario or a no new battery access scenario.

[0048] In this embodiment, the type data of each rechargeable battery is obtained through the communication interface of the battery management system (BMS) of the vehicle to be charged, and compared with the list of connected batteries. If the type data of a rechargeable battery does not appear in the list, it is determined to be a new battery access scenario, and the new type data is added to the list. If the type data of all obtained rechargeable batteries already exists in the list, it is determined to be a no-new-battery access scenario.

[0049] In this embodiment, for newly connected rechargeable batteries, if their type (e.g., lithium iron phosphate / ternary lithium hybrid) or characteristic parameters exceed the coverage of existing types, the data processing module obtains a sample data package for the new rechargeable battery through the communication interface of the battery management system (BMS) of the vehicle to be charged or manually imported by maintenance personnel. This sample data package includes: voltage-current-time curves for three charge-discharge cycles, the rated voltage of the rechargeable battery, and the maximum allowable charging current at different temperatures. The data processing module calls its built-in general battery characteristic model for the charging pile field, which has been pre-trained based on massive historical data. This pre-trained model has learned general patterns such as charge-discharge dynamics, degradation trends, and thermal characteristics of various types of batteries. For new rechargeable batteries, a few-shot learning technique is used, employing only the aforementioned small number of input sample data packages to update the model parameters, adapting the model to the characteristics of the new battery. This eliminates the need for retraining or manual reconstruction of control rules, achieving rapid knowledge transfer and model personalization for new scenarios.

[0050] In this embodiment, after updating the model parameters through transfer learning, the charging control system controls the charging pile to perform several charge-discharge tests using the newly added charging battery. This verifies whether the charge-discharge power and SOC control accuracy meet the standards (error ≤ 2%). Once verified, the system formally incorporates the real-time state data of the new charging battery into the state space of the reinforcement learning agent module. The agent module can then autonomously schedule power and manage charging based on a unified reward function and dynamically updated comprehensive scenario types.

[0051] It is worth noting that existing systems lack the ability to autonomously adapt to new battery types and new grid policies, resulting in high costs and low efficiency in scenario adaptation. Adaptation to new battery types (such as niche battery specifications) and new grid policies (such as time-of-use pricing adjustments) requires manual reconstruction of control rules and relies on professional technicians, leading to high operation and maintenance costs. This application leverages large-model, small-sample transfer learning, using only a small amount of sample data to update model parameters, enabling the model to adapt to the characteristics of new batteries without retraining or manual reconstruction of control rules. This improves efficiency, achieves rapid knowledge transfer and model personalization for new scenarios, and reduces operation and maintenance costs.

[0052] (3) Based on the real-time operating data of each module in the charging pile, determine the operating scenario of the charging pile, whether it is in a normal operating scenario or a fault scenario.

[0053] In this embodiment, the device health monitoring module collects temperature data, temperature distribution images, cumulative usage time, and relay contact current values ​​for each bidirectional charge / discharge module to determine the operating scenario of the charging pile. The device health monitoring module collects temperature data at key points on each bidirectional charge / discharge module using temperature sensors installed on them, and simultaneously acquires real-time temperature distribution images of each module using a thermal imaging camera. The AI ​​visual detection unit in the data processing module combines the temperature data and performs pixel-level analysis of the temperature distribution images of each bidirectional charge / discharge module based on preset temperature thresholds to identify latent faults such as localized overheating and abnormal temperature gradients. If a bidirectional charge / discharge module exhibits localized hot spots with a temperature >70°C, it is determined to be a latent fault in the module.

[0054] In this embodiment, the device health monitoring module collects the relay contact current value through a current sensor. The fault diagnosis unit in the data processing module calculates the relay contact resistance value based on the relay contact current value, and predicts problems such as contact oxidation and poor contact based on the relay contact resistance value and a preset resistance threshold. For example, if the relay contact resistance value is >50mΩ, it is determined to be contact oxidation.

[0055] In this embodiment, a normal operating scenario is defined as when the real-time operating data of each module are within the preset threshold range and the AI ​​vision detection unit and fault diagnosis unit do not detect any abnormalities. A fault scenario is defined as when the real-time operating data of any module exceeds the preset threshold or the AI ​​vision detection unit and fault diagnosis unit issue an early warning. In a fault scenario, the charging control system automatically triggers preset adjustment strategies (such as disabling the faulty module and switching to a backup relay channel), forming a self-healing closed loop of "prediction-adjustment-early warning" to prevent the fault from escalating.

[0056] It is worth noting that existing charge and discharge control systems can only identify pre-set explicit faults (such as module overheating alarms) and cannot detect implicit faults such as relay contact oxidation and module hidden losses. Furthermore, manual troubleshooting and repair are required after a fault occurs, resulting in long charging interruption times and affecting system reliability. In contrast, this application uses an AI vision detection unit and a fault diagnosis unit to identify faults such as relay contact oxidation and module hidden losses, and establishes a self-healing closed loop of "prediction-adjustment-early warning" to prevent fault escalation and improve system reliability.

[0057] (4) Identify the current comprehensive scenario type based on the judgment results of the load scenario of the power grid, the access scenario of the charging pile, and the operation scenario of the charging pile.

[0058] In this embodiment, based on the judgment results of the load scenario of the power grid, the access scenario of the charging pile, and the operation scenario of the charging pile, the current comprehensive scenario type is identified, such as "Peak Grid Operation - New Battery Access - Normal Operation", "Peak Grid Operation - No New Access - Fault", and "Off-Peak Grid Operation - New Battery Access - Normal Operation". This current comprehensive scenario type reflects the real-time status of the power grid, users, equipment, and batteries in four dimensions, providing a basis for the dynamic update of the subsequent reward function.

[0059] (5) Update the preset reward function dynamically according to the current comprehensive scenario type.

[0060] In this embodiment, the reward function is calculated as follows:

[0061] Formula (1)

[0062] in, Represents the reward function; Indicates the rate at which user needs are met; This indicates the charging cost optimization rate; Indicates the battery degradation suppression rate; Indicates the equipment failure risk rate; Indicates grid adaptability; Indicates the first weighting coefficient; represents the second weight coefficient; represents the third weight coefficient; represents the fourth weight coefficient; represents the fifth weight coefficient; t represents the current moment.

[0063] In this embodiment, according to the current comprehensive scenario type and based on the real-time data in the multi-dimensional state space, each weight in the preset reward function is dynamically updated. The reward function is composed of the weighted sum of five sub-items. For the user demand fulfillment rate , according to the leaving urgency score value, it is judged whether the user is an urgent user or an ordinary user. The user demand fulfillment rate =Urgent user's full charge rate × 0.6 + Ordinary user's full charge rate × 0.4. According to the peak-valley electricity price period data, the charging cost optimization rate is calculated, which is the reciprocal of the ratio of the actual electricity cost to the benchmark electricity cost. According to the attenuation rate data of the charging battery, the battery attenuation suppression rate is calculated, which is the reciprocal of the ratio of the actual attenuation rate to the rated attenuation rate.

[0064] In this embodiment, according to the temperature data of the bidirectional charging and discharging module and the relay contact current value, fault judgment is performed, and the fault warning value is calculated. According to the fault warning value, the equipment fault risk rate is calculated, =1 - fault warning value. According to the current temperature data and the preset temperature threshold, the temperature healthiness H1 is calculated. Exemplarily, when the current temperature data is 50°C and the preset temperature threshold is 70°C, the temperature healthiness H1 = 1 - 50 / 70 = 0.29. According to the relay contact current values in different time periods, the average current value (I avg ) and the standard deviation (α) within the preset time are calculated. According to the average current value and the standard deviation, the current fluctuation coefficient (K1) is calculated. The current fluctuation coefficient K1 = α / I avg . Two thresholds are set, namely the fluctuation upper threshold (L) and the fluctuation lower threshold (M). When K1 ≤ L (such as 0.02), it is determined that the current is extremely stable, and the current stability healthiness H2 is 1.0; when K1 ≥ M (such as 0.1), it is determined that the current is extremely unstable, and the current stability healthiness H2 is 0; when L < K1 < M, the current stability healthiness H2 = 1 - (K1 - L) / (M - L). By performing weighted calculation on the temperature healthiness and the current stability healthiness, the fault warning value F W is obtained. F W =β1×H1 + β2×H2, where β1 represents the sixth weight coefficient and β2 represents the seventh weight coefficient.

[0065] In this embodiment, the percentage of time the grid load exceeds the standard is determined based on the grid load rate data in order to calculate the grid adaptability. , =1 - Percentage of time the power grid load exceeds the standard.

[0066] In this embodiment, The initial weights are set as follows: =0.2、 =0.15、 =0.25、 =0.2、 =0.2. For example, when the voltage monitoring data fluctuates continuously by more than ±3%, the fifth weighting coefficient will be... Increase to 0.3, and simultaneously adjust the second weighting coefficient. Reduced to 0.05. When there are urgent users (leaving urgency score ≥ 4 points), the first weighting coefficient will be reduced. Increase to 0.3, and simultaneously adjust the third weighting coefficient. The value was reduced to 0.15. Furthermore, for specific integrated scenarios (such as "peak grid activity - new battery integration - normal operation"), the weight allocation strategy was fine-tuned through transfer learning to make the reward function more aligned with the optimization objectives of the current scenario. The updated reward function will serve as the real-time optimization objective for the reinforcement learning agent module, guiding it to generate a charging pile optimization control strategy adapted to the integrated scenario.

[0067] S203: Based on the dynamically updated reward function and the current comprehensive scenario type, generate a real-time power allocation scheme for the charging pile and a real-time on / off timing scheme for the charging circuit. The methods include:

[0068] (1) The real-time optimal charging power of each of the rechargeable batteries is calculated based on the dynamically updated reward function.

[0069] (2) Based on the real-time optimal charging power of each of the charging batteries and the current comprehensive scenario type, generate a real-time power allocation scheme for the charging pile and a real-time on / off timing scheme for the charging circuit.

[0070] In this embodiment, as Figure 3 The diagram shown illustrates the process of calculating the real-time optimal charging power in an embodiment of the present invention. The method for calculating the real-time optimal charging power of each charging battery based on the dynamically updated reward function includes:

[0071] S2031: Calculate the real-time charge deviation of each of the user demand data.

[0072] In this embodiment, the method for calculating the real-time charge deviation of each of the rechargeable batteries includes:

[0073] Formula (II)

[0074] in, This indicates the real-time charge deviation of the rechargeable battery. This indicates the final state of charge (SOC) data of the rechargeable battery. This represents the charge state data of the rechargeable battery at the current moment; t represents the current moment.

[0075] In this embodiment, the terminal charge state data of the rechargeable battery indicates how much power the user ultimately wants to "charge" to, whether to charge to 80% and leave, or to charge to 100%. The difference between the current battery power and the user's target can be obtained through formula (II).

[0076] S2032: Calculate the real-time charge error change rate of each of the rechargeable batteries based on the real-time charge deviation of each of the rechargeable batteries.

[0077] In this embodiment, the method for calculating the real-time charge error change rate of each of the rechargeable batteries includes:

[0078] Formula (3)

[0079] in, This indicates the real-time charge error rate of the rechargeable battery. This indicates the real-time charge deviation of the rechargeable battery. This indicates the historical charge deviation of the rechargeable battery (at the previous moment). t represents the preset time interval; t represents the current time.

[0080] S2033: Calculate the real-time basic charging power of each of the rechargeable batteries based on the real-time charge error change rate of each of the rechargeable batteries.

[0081] In this embodiment, the method for calculating the real-time base charging power of each of the rechargeable batteries includes:

[0082] Formula (IV)

[0083] in, This indicates the real-time base charging power of the rechargeable battery. Indicates the proportionality coefficient; This indicates the real-time charge deviation of the rechargeable battery. Indicates the integral coefficient; Represents the differential coefficient; This represents the real-time charge error rate of the rechargeable battery; t represents the current time.

[0084] S2034: Calculate the real-time optimal charging power of each of the rechargeable batteries based on their real-time base charging power and the dynamically updated reward function.

[0085] In this embodiment, the method for calculating the real-time optimal charging power of each of the rechargeable batteries includes:

[0086] Formula (5)

[0087] in, This indicates the real-time optimal charging power of the rechargeable battery. This indicates the real-time base charging power of the rechargeable battery. This represents the dynamically updated reward function; t represents the current time.

[0088] In this embodiment, based on the real-time optimal charging power of each of the rechargeable batteries and the current comprehensive scenario type jointly determined by the grid dimension, device dimension, user dimension, and battery dimension, an executable control scheme for the charging pile is generated. This control scheme includes two parts: (1) a real-time power allocation scheme for the charging pile, that is, under the total power capacity and scenario constraints of the charging pile, adjusting the number of bidirectional charging and discharging modules activated and controlling the bidirectional charging and discharging modules to adjust their output power (i.e., which bidirectional charging and discharging modules work and how much power they output) to perform real-time power coordination and allocation. (2) a real-time scheme for the on / off timing of the charging circuit, that is, based on the power allocation results and the charging process of each rechargeable battery, dynamically planning the switching time, sequence, and duration of each relay in the relay matrix connecting each charging circuit to achieve accurate power allocation and dynamic scheduling, while reducing switching losses and suppressing current surges.

[0089] S204: Based on the real-time power allocation scheme of the charging pile and the real-time on / off timing scheme of the charging circuit, control the charging pile to charge each of the rechargeable batteries respectively.

[0090] In this embodiment, based on the real-time power allocation scheme of the charging pile and the real-time on / off timing scheme of the charging circuit, a power command is sent to the bidirectional charging and discharging module, and an on / off timing control command is sent to the relay matrix control module. This allows the bidirectional charging and discharging module to adjust its output power according to the power command, and the relay matrix control module to control the contacts of the corresponding relays to close or open according to the on / off timing control command, so that the electrical energy output by the charging pile is orderly delivered to the corresponding charging circuit or removed from the charging circuit that has completed charging.

[0091] S205: The above steps of data acquisition, comprehensive scene type identification, dynamic update of reward function, scheme generation, and charging operation are executed repeatedly at preset time intervals until each of the rechargeable batteries meets the preset charging termination conditions.

[0092] In this embodiment, the intelligent agent module updates the real-time data of the multi-dimensional state space at preset time intervals (e.g., every 10 milliseconds) using the TD (Time Differential) learning algorithm. Then, based on the updated real-time data, it performs comprehensive scene type identification again and dynamically updates the weights in the reward function to adapt them to the optimization objective of the current scene. Next, based on the dynamically updated reward function, it calculates the optimal real-time charging power for each battery in the next round, generating a new real-time power allocation scheme for the charging pile and a real-time on / off timing scheme for the charging circuit. The charging pile then controls each battery to perform charging operations. This process is repeated cyclically, allowing the control strategy to be optimized online based on the latest environmental feedback, resulting in a fast dynamic response and continuous approximation of the globally optimal scheduling until all batteries meet the preset charging termination conditions. The preset charging termination conditions are that the battery charge reaches the termination charge state or the user-set departure time.

[0093] It is worth noting that the charging control method based on the charging pile in this application has the following advantages:

[0094] (1) Improved global optimization effect: A reward function that can integrate multi-dimensional optimization objectives was constructed, and the weights in the reward function were adjusted in real time based on real-time data of multi-dimensional state space. Instead of relying on fixed rules, it can intelligently and dynamically weigh and decide according to the current comprehensive scenario type identified in real time. This allows the generated real-time power allocation scheme and the real-time charging circuit on / off timing scheme to be optimized based on the latest environmental feedback. This ensures stable grid adaptation, delays battery degradation, fully meets users' urgent needs, and ensures equipment safety, while improving overall operating efficiency and avoiding the local optima problem of traditional technologies.

[0095] (2) Fast dynamic response speed: According to the preset time interval, the real-time data of the multi-dimensional state space is updated, and the steps of comprehensive scenario type identification, dynamic update of reward function, scheme generation, charging operation are repeatedly executed. Through the cyclic iteration mechanism, the control strategy can be optimized online based on the latest environmental feedback. The dynamic response speed is fast and it continuously approaches the global optimal scheduling. Compared with traditional rule scheduling, it can quickly respond to dynamic scenarios such as sudden increase in grid load and sudden equipment failure, and reduce system downtime.

[0096] In the embodiments of this application, terms such as "first" and "second" are used to distinguish identical or similar items with essentially the same function and effect. For example, the first weight coefficient and the second weight coefficient are only used to distinguish different weight coefficients and do not limit their order. Those skilled in the art will understand that terms such as "first" and "second" do not limit the quantity or execution order, and that terms such as "first" and "second" do not necessarily imply that they are different.

[0097] It should be noted that, in the embodiments of this application, the words "exemplary" or "for example" indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0098] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0099] Figure 4 This is a schematic block diagram of a charging control system based on a charging pile provided in an embodiment of this application. The charging control system is electrically connected to the charging pile, and the charging pile is electrically connected to the rechargeable batteries of multiple vehicles to be charged. Figure 4 As shown, the charging control system 400 includes:

[0100] The data acquisition module 401 is used to acquire real-time data of multi-dimensional state space; the real-time data of multi-dimensional state space includes one or a combination of real-time power grid data, real-time operation data of each module in the charging pile, multiple user demand data, and real-time state data of each charging battery.

[0101] The data processing module 402 is used to identify the current comprehensive scenario type based on the real-time data of the multi-dimensional state space, so as to dynamically update the preset reward function accordingly.

[0102] The intelligent agent module 403 is used to generate a real-time power allocation scheme for the charging pile and a real-time on / off timing scheme for the charging circuit based on the dynamically updated reward function and the current comprehensive scenario type; and to control the charging pile to charge each of the charging batteries according to the real-time power allocation scheme and the real-time on / off timing scheme for the charging circuit; and to repeatedly execute the above steps of data acquisition, comprehensive scenario type identification, dynamic update of reward function, scheme generation, and charging operation at preset time intervals until each of the charging batteries meets the preset charging termination condition.

[0103] It should be understood that the specific process of each module performing the above-mentioned steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0104] It should also be understood that the module division in the embodiments of this application is illustrative and only represents a logical functional division; in actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0105] Figure 5 This is a schematic block diagram of an electronic terminal provided in an embodiment of this application. The electronic terminal includes a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the charging control method based on a charging pile as described above. Figure 5 As shown, the electronic terminal 500 includes at least one processor 501, a memory 502, at least one network interface 503, and a user interface 505. The various components in the device are coupled together via a bus system 504. It is understood that the bus system 504 is used to implement communication between these components. In addition to a data bus, the bus system 504 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 5 The general will label all buses as bus systems.

[0106] The user interface 505 may include a monitor, keyboard, mouse, trackball, clicker, button, touchpad, or touch screen.

[0107] It is understood that memory 502 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM) or programmable read-only memory (PROM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable categories of memory.

[0108] In this embodiment of the invention, the memory 502 is used to store various types of data to support the operation of the electronic terminal 500. Examples of this data include: any executable program for operation on the electronic terminal 500, such as the operating system 5021 and application programs 5022; the operating system 5021 contains various system programs, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and handling hardware-based tasks. The application program 5022 may contain various applications, such as a media player, browser, etc., for implementing various application services. The charging control method based on the charging pile provided in this embodiment of the invention can be included in the application program 5022.

[0109] The methods disclosed in the above embodiments of the present invention can be applied to processor 501, or implemented by processor 501. Processor 501 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 501 or by instructions in the form of software. The processor 501 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 501 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. General-purpose processor 501 may be a microprocessor or any conventional processor, etc. The steps of the accessory optimization method provided in the embodiments of the present invention can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, which is located in memory. The processor reads the information in the memory and combines it with its hardware to complete the steps of the aforementioned method.

[0110] In an exemplary embodiment, the electronic terminal 500 may be used by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs) to execute the aforementioned method.

[0111] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the charging control method based on a charging pile as described above.

[0112] According to the method provided in the embodiments of this application, this application also provides a computer program product, which includes computer program code. When the computer program code is run on a computer, the computer implements the charging control method based on the charging pile as described above.

[0113] As used in this specification, the terms "component," "module," "system," etc., are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0114] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0115] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0116] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0117] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0118] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0119] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs, DVDs), or semiconductor media (e.g., solid-state disks, SSDs, etc.).

[0120] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0121] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0122] In summary, this application provides a charging control method, system, medium, product, and terminal based on a charging pile. It constructs a reward function that integrates multi-dimensional optimization objectives and adjusts the weights in the reward function in real time based on real-time data from the multi-dimensional state space. Instead of relying on fixed rules, it intelligently and dynamically weighs and makes decisions based on the currently identified comprehensive scenario type. This allows the generated real-time power allocation scheme and charging circuit on / off timing scheme to be optimized based on the latest environmental feedback, resulting in fast dynamic response and continuously approaching the globally optimal scheduling. This ensures stable grid adaptation, slows battery degradation, fully meets users' urgent needs, and guarantees equipment safety, while simultaneously improving overall operating efficiency and avoiding the local optima problem of traditional technologies. Therefore, this application effectively overcomes the various shortcomings of existing technologies and has high industrial application value.

[0123] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A charging control method based on a charging pile, applied to a charging control system based on a charging pile, the charging control system being electrically connected to a charging pile, the charging pile being electrically connected to charging batteries of a plurality of vehicles to be charged; characterized in that, The charging control method based on the charging pile comprises: Collecting multi-dimensional state space real-time data; the multi-dimensional state space real-time data comprises one or a combination of multiple ways of grid real-time data, real-time operation data of each module in the charging pile, multiple user demand data and real-time state data of each charging battery; According to the multi-dimensional state space real-time data, the current comprehensive scene type is identified, and the preset reward function is dynamically updated accordingly; According to the dynamically updated reward function and the current comprehensive scene type, a real-time power distribution scheme of the charging pile and a real-time scheme of the charging circuit on-off time sequence are generated; According to the real-time power distribution scheme of the charging pile and the real-time scheme of the charging circuit on-off time sequence, the charging operation of each charging battery is controlled by the charging pile; According to the preset time interval, the above data collection, comprehensive scene type identification, reward function dynamic updating, scheme generation, charging operation and other steps are cyclically executed until each charging battery meets the preset charging termination condition.

2. The charge control method based on a charge stack according to claim 1, characterized by, The calculation method of the reward function comprises: ； wherein, represents a reward function; represents a user demand achievement rate; represents a charging cost optimization rate; represents a battery degradation suppression rate; represents a device failure risk rate; represents a grid adaptation degree; represents a first weight coefficient; represents a second weight coefficient; represents a third weight coefficient; represents a fourth weight coefficient; represents a fifth weight coefficient; t represents a current time.

3. The charge control method based on a charge stack according to claim 1, characterized by, According to the dynamically updated reward function and the current comprehensive scene type, a real-time power distribution scheme of the charging pile and a real-time scheme of the charging circuit on-off time sequence are generated; According to the dynamically updated reward function, the real-time optimal charging power of each charging battery is calculated; According to the real-time optimal charging power of each charging battery and based on the current comprehensive scene type, a real-time power distribution scheme of the charging pile and a real-time scheme of the charging circuit on-off time sequence are generated.

4. The charge control method based on a charge stack according to claim 3, characterized by, According to the dynamically updated reward function, the real-time optimal charging power of each charging battery is calculated; According to each user demand data, the real-time charge deviation of each charging battery is calculated; According to the real-time charge deviation of each charging battery, the real-time charge error change rate of each charging battery is calculated; According to the real-time charge error change rate of each charging battery, the real-time basic charging power of each charging battery is calculated; According to the real-time basic charging power of each charging battery and the dynamically updated reward function, the real-time optimal charging power of each charging battery is calculated.

5. The charge control method based on a charge stack according to claim 4, characterized by, The method for calculating the real-time basic charging power of each charging battery comprises: ； wherein, represents a real-time base charging power of the charging battery; represents a proportional coefficient; represents a real-time charge deviation of the charging battery; represents an integral coefficient; represents a differential coefficient; represents a real-time charge error change rate of the charging battery; and t represents a current time.

6. The charge control method based on a charge stack according to claim 4, characterized by, The method for calculating the real-time optimal charging power of each charging battery comprises: ； wherein, represents the real-time optimal charging power of the rechargeable battery; represents the real-time basic charging power of the rechargeable battery; represents the dynamically updated reward function; t represents the current time.

7. A charge control system based on a charge stack, characterized by The charging control system is electrically connected to the charging pile, and the charging pile is electrically connected to the charging batteries of multiple vehicles to be charged; wherein the charging control system comprises: A data collection module is configured to collect multi-dimensional state space real-time data; the multi-dimensional state space real-time data comprises one or a combination of multiple ways of grid real-time data, real-time operation data of each module in the charging pile, multiple user demand data and real-time state data of each charging battery; A data processing module is configured to identify the current comprehensive scene type according to the multi-dimensional state space real-time data, and dynamically update the preset reward function accordingly; The intelligent agent module is configured to generate a real-time power distribution scheme of the charging stack and a real-time scheme of on-off timing of the charging circuit according to the dynamically updated reward function and the current comprehensive scene type, and control the charging stack to perform charging operations on each of the charging batteries according to the real-time power distribution scheme of the charging stack and the real-time scheme of on-off timing of the charging circuit. The above steps of data collection, comprehensive scene type identification, reward function dynamic updating, scheme generation, charging operation, etc. are cyclically executed at a preset time interval until each of the charging batteries meets a preset charging termination condition.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, implements the charging control method based on the charging stack according to any one of claims 1 to 6.

9. A computer program product, characterised in that, The computer program product includes computer program code, and when the computer program code is executed on a computer, the computer program code causes the computer to implement the charging control method based on the charging stack according to any one of claims 1 to 6.

10. An electronic terminal comprising a memory, a processor and a computer program stored on the memory, characterized in that, The processor executes the computer program to implement the charging control method based on the charging stack according to any one of claims 1 to 6.

Images