Energy supplement management method and system

Abstract

The embodiment of the invention relates to the technical field of new energy automobiles, and discloses an energy supplement management method and system, and the method comprises the steps: obtaining multi-modal data, the multi-modal data comprises battery state data acquired by a vehicle, vehicle environment data, charging environment data acquired by charging equipment, power grid data acquired by a power grid platform and user demand data uploaded by a user terminal; performing data preprocessing on the multi-modal data to obtain target multi-modal data; analyzing an energy complementing strategy based on a preset strategy decision model and the target multi-modal data to obtain an optimal energy complementing strategy; and sending the optimal energy complementing strategy to the vehicle and the charging equipment to enable the vehicle and the charging equipment to execute adaptive energy complementing management, so that the problem of poor energy complementing efficiency caused by the fact that a traditional energy complementing mode cannot adapt to variable energy supply and demand relationships can be avoided; through fusion of multi-modal data and combination of a preset strategy decision model, deep analysis is carried out on an energy complementation strategy, and accurate and efficient energy complementation management is realized.

Description

Technical Field

[0001] This invention relates to the field of new energy vehicle technology, specifically to a method and system for energy replenishment management. Background Technology

[0002] Traditional energy replenishment management technologies reveal numerous shortcomings when faced with complex real-world scenarios. In terms of data utilization, they struggle to fully mine and utilize the vast amounts of data collected in real time. Regarding decision-making accuracy, fixed algorithms are ill-suited to the complex and ever-changing energy supply and demand dynamics, resulting in poor energy replenishment efficiency. Summary of the Invention

[0003] In view of the above problems, embodiments of the present invention provide an energy replenishment management method and system to solve the problem that traditional energy replenishment methods cannot adapt to the changing energy supply and demand relationship, resulting in poor energy replenishment efficiency.

[0004] According to one aspect of the present invention, a charging management system includes a cloud server, a vehicle interacting with the cloud server, charging equipment, a power grid platform, and a user terminal. The charging management method is applied to the cloud server, and the method includes: Acquire multimodal data, wherein the multimodal data includes battery status data collected by the vehicle, vehicle environment data, charging environment data collected by the charging equipment, power grid data collected by the power grid platform, and user demand data uploaded by the user terminal; The multimodal data is preprocessed to obtain the target multimodal data; The energy replenishment strategy is analyzed based on the preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy; The optimal energy replenishment strategy is sent to the vehicle and the charging equipment to enable the vehicle and the charging equipment to perform adaptive energy replenishment management.

[0005] According to another aspect of the present invention, a charging management method is provided, the charging management method being applied to a vehicle interacting with a cloud server, the method comprising: The collected battery status data and vehicle environment data are uploaded to the cloud server. Receive the optimal energy replenishment strategy generated by the cloud server based on the battery status data and the vehicle environment data; Adaptive energy replenishment management is performed based on the optimal energy replenishment strategy.

[0006] According to another aspect of the present invention, a power replenishment management system is provided, the system including a cloud server, a vehicle interacting with the cloud server, charging equipment, a power grid platform, and a user terminal; The cloud server is used to acquire multimodal data, which includes battery status data collected by the vehicle, vehicle environment data, charging environment data collected by the charging equipment, power grid data collected by the power grid platform, and user demand data uploaded by the user terminal. The cloud server is also used to preprocess the multimodal data to obtain target multimodal data; The cloud server is also used to analyze the energy replenishment strategy based on the preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy. The cloud server is also used to send the optimal energy replenishment strategy to the vehicle and the charging equipment, so that the vehicle and the charging equipment can perform adaptive energy replenishment management.

[0007] This invention acquires multimodal data, including battery status data collected by the vehicle, vehicle environment data, charging environment data collected by the charging equipment, power grid data collected by the power grid platform, and user demand data uploaded by the user terminal. The multimodal data is preprocessed to obtain target multimodal data. Based on a preset strategy decision model and the target multimodal data, the energy replenishment strategy is analyzed to obtain the optimal energy replenishment strategy. The optimal energy replenishment strategy is sent to the vehicle and the charging equipment to enable adaptive energy replenishment management. This avoids the problem of poor energy replenishment efficiency caused by traditional energy replenishment methods failing to adapt to changing energy supply and demand relationships. By fusing multimodal data and combining it with a preset strategy decision model for in-depth analysis of the energy replenishment strategy, precise and efficient energy replenishment management is achieved.

[0008] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0009] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart illustrating a first embodiment of the energy replenishment management method provided by the present invention is shown; Figure 2 This invention illustrates a schematic diagram of the overall architecture of the energy replenishment management system according to a first embodiment of the energy replenishment management method provided by the present invention. Figure 3 This diagram illustrates the data processing of a first embodiment of the energy replenishment management method provided by the present invention. Figure 4This diagram illustrates the adaptive decision-making process of a first embodiment of the energy replenishment management method provided by the present invention. Figure 5 This invention illustrates a schematic diagram of the strategy decision-making process of a first embodiment of the energy replenishment management method provided by the present invention. Figure 6 A flowchart illustrating a second embodiment of the energy replenishment management method provided by the present invention is shown; Figure 7 A flowchart illustrating a third embodiment of the energy replenishment management method provided by the present invention is shown; Figure 8 A flowchart illustrating a fourth embodiment of the energy replenishment management method provided by the present invention is shown; Figure 9 A schematic diagram of an embodiment of the energy replenishment management system provided by the present invention is shown. Detailed Implementation

[0010] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0011] Figure 1 A flowchart of a first embodiment of the energy replenishment management method of the present invention is shown, the method being executed by an energy replenishment management system. The energy replenishment management system includes a cloud server, vehicles interacting with the cloud server, charging equipment, a power grid platform, and user terminals, such as... Figure 1 As shown, the method includes the following steps: Step 10: Acquire multimodal data.

[0012] The multimodal data includes battery status data collected by the vehicle, vehicle environment data, charging environment data collected by the charging equipment, power grid data collected by the power grid platform, and user demand data uploaded by the user terminal.

[0013] In one implementation, the battery status data collected by the vehicle can be obtained in real time through high-precision battery management system sensors, which collect parameters such as battery voltage, current, temperature, and state of charge (SOC). Vehicle environmental data can be collected using environmental sensors, which collect parameters such as ambient temperature, humidity, and light intensity. Charging environment parameters collected by the charging equipment can be collected using environmental sensors, which collect parameters such as temperature and humidity of the environment in which the charging equipment is located. The charging equipment can be a charging pile or other portable charging device. Grid data collected by the grid platform can be real-time electricity prices, load information, etc., obtained from smart meters or grid interfaces. User demand data uploaded by the user terminal can be personalized demand data such as user travel plans and electricity usage habits collected through the user interface or smart terminal.

[0014] For further illustration of the overall architecture diagram of the energy replenishment management system in this application, please refer to... Figure 2 The diagram shows the overall architecture of the energy replenishment management system, illustrating its main components and their interrelationships. The entire system primarily consists of a multimodal data acquisition module (DataCollection), a data processing and analysis module (DataProcessing), an adaptive decision-making module (DecisionModule), an energy replenishment execution and control module (ExecutionModule), and a communication module (ConmmunicationModule). The ExecutionModule includes a monitoring and feedback unit, a charging pile controller, and an energy distribution controller. The DataCollection module includes battery sensors, environmental sensors, a smart meter, and a user interface. The DataProcessing module includes a data preprocessing unit and a data analysis algorithm library. The DecisionModule includes a machine learning model and a decision engine. The CommunicationModule includes wired and wireless communication interfaces. The multimodal data acquisition module is responsible for collecting various types of data. Battery sensors collect data such as battery voltage, current, and temperature; environmental sensors collect data such as ambient temperature and humidity; smart meters obtain real-time electricity prices and load information from the power grid; and the user interface collects user demand data. This data is transmitted to the data processing and analysis module via the communication module. In this module, the data preprocessing unit cleans, denoises, aligns the time, and standardizes the format of the raw data. The data analysis algorithm library then uses various data analysis algorithms to perform in-depth analysis on the preprocessed data. The analysis results are sent to the adaptive decision-making module. The machine learning model in this module is trained using historical data to learn the relationships between different data sets. The decision engine then generates the optimal energy replenishment strategy based on the output of the machine learning model and real-time data. The energy replenishment execution and control module, according to the energy replenishment strategy, controls the output power and charging time of the charging pile through the charging pile controller and achieves reasonable energy allocation through the energy distribution controller. The monitoring and feedback unit monitors the status of the energy replenishment equipment and energy storage equipment in real time and transmits feedback data back to the data processing and analysis module for real-time system adjustments. The communication module is responsible for data transmission between the modules, ensuring timely information exchange.

[0015] In one possible implementation, the sensor can be based on novel materials, such as graphene. Graphene possesses excellent electrical and mechanical properties, and graphene-based voltage and current sensors can theoretically achieve higher sensitivity and a wider operating temperature range. In electric vehicle battery monitoring, graphene voltage sensors can more accurately capture minute changes in battery voltage and maintain stable operation even in high or low temperature environments, which is of great significance for improving the accuracy and reliability of battery management.

[0016] For example, to acquire battery status data, multiple sensors are used to comprehensively acquire different types of data. Sensors in the Battery Management System (BMS) are responsible for collecting key data such as battery voltage, current, temperature, and state of charge (SOC). A high-precision voltage sensor can monitor the battery's terminal voltage in real time, with a measurement accuracy of ±0.01V, accurately reflecting the battery's charging and discharging state. The current sensor, employing the Hall effect principle, can accurately measure the current during battery charging and discharging, with a measurement error controlled within ±1%. To acquire vehicle environmental data, the system is equipped with temperature and humidity sensors and a light sensor. The temperature and humidity sensor can sense ambient temperature and humidity in real time. Its temperature measurement range is typically -40℃ to 125℃ with an accuracy of ±0.5℃, and its humidity measurement range is 0%-100%RH with an accuracy of ±3%RH. This data is crucial for evaluating the vehicle battery's performance under different environments. The light sensor is used to detect light intensity, providing data support for scenarios such as solar charging. Its measurement range is from 0 lx to 100,000 lx, adapting to different lighting environments. To obtain grid data, real-time electricity prices and load information can be collected through smart meters on the grid platform. Smart meters interact with the grid data center via communication modules, accurately acquiring hourly or even shorter time intervals of electricity price data, as well as real-time grid load conditions. This provides a basis for the system to consider cost and grid stability when allocating energy. User demand data can also be collected through user interfaces or smart terminals. The above figures are for illustrative purposes only and are not intended to impose specific limitations.

[0017] Step 20: Perform data preprocessing on the multimodal data to obtain target multimodal data.

[0018] For further explanation of the data preprocessing process, please refer to Figure 3 The data processing diagram shown includes data preprocessing operations such as time alignment, format unification, and data cleaning. By performing time alignment, format unification, and data cleaning on all modal data, target multimodal data is generated from the obtained multimodal data of various types.

[0019] In one possible implementation, current systems use general-purpose high-performance computing chips to process large amounts of multimodal data. This invention can select ASIC chips to process multimodal data. The ASIC chip can be designed according to the specific algorithms and data processing requirements of the power management system, thereby significantly improving data processing speed while reducing power consumption. For neural network model computation, the ASIC chip can achieve rapid processing of key operations such as matrix operations through optimized hardware architecture. Compared to general-purpose chips, it can complete data analysis and decision-making in a shorter time, improving the system's real-time response capability.

[0020] Furthermore, step 20 also includes: aligning the multimodal data according to a timestamp calibration method to obtain aligned multimodal data; unifying the format of the aligned multimodal data to obtain multimodal data in a target format; filtering out outliers in the multimodal data in the target format based on a preset anomaly threshold to obtain initial multimodal data; and removing noise from the initial multimodal data based on a preset filtering algorithm to obtain target multimodal data.

[0021] This involves the deep fusion and analysis of collected multimodal data by introducing artificial intelligence and machine learning algorithms. Data preprocessing techniques are used to perform time alignment, format standardization, and data cleaning preprocessing on the collected raw multimodal data to improve data quality.

[0022] In one possible implementation, the acquired multimodal data has different formats, frequencies, and timestamps, thus requiring preprocessing. The first step is time alignment preprocessing. For data collected from different sensors, timestamp calibration can be used to unify the data to the same time scale. Specifically, for battery data and environmental data, time alignment is performed in seconds to ensure that data from the same moment can be correlated. The second step is format unification preprocessing. This involves converting data in different formats into a standard format that the system can process, obtaining multimodal data in the target format, such as converting physical quantities like voltage and current into floating-point format.

[0023] The preset anomaly threshold is a pre-set reasonable threshold for temperature; values ​​exceeding this threshold are considered abnormal. Outliers in the target format multimodal data are filtered out using this preset threshold to obtain initial multimodal data. Then, noise is removed from the initial multimodal data using a preset filtering algorithm to obtain the target multimodal data. The preset filtering algorithm can be a moving average filtering algorithm or other filtering algorithms; the specific algorithm can be set according to the data type.

[0024] In one implementation, data cleaning is also an important preprocessing step. By setting appropriate thresholds and filtering algorithms, noise and outliers in the data are removed. For battery temperature data, if there are outliers with sudden and large fluctuations, a moving average filtering algorithm can be used to ensure the accuracy and reliability of the data.

[0025] Step 30: Analyze the energy replenishment strategy based on the preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy.

[0026] By fusing multimodal data, a more comprehensive and accurate understanding of energy replenishment needs and environmental changes can be achieved, avoiding the limitations of single data sources. This improves the scientific rigor and accuracy of decision-making. Real-time analysis and dynamic decision-making using a pre-set strategy decision-making model enable the system to respond quickly to changes, significantly enhancing the efficiency and flexibility of energy replenishment management. This intelligent adaptive energy replenishment strategy helps reduce energy loss, extend the lifespan of energy equipment, and improve the user experience, providing a more efficient and intelligent solution for the development of energy applications. The pre-set strategy decision-making model is a pre-configured model used to predict energy replenishment needs from pre-processed multimodal data. Based on the processed multimodal data, this model uses advanced algorithms and models to determine energy replenishment needs and identify the optimal energy replenishment strategy. For further explanation of the adaptive decision-making process of this solution, please refer to [link / reference]. Figure 4 The diagram illustrates an adaptive decision-making process where a cloud server receives multimodal data, preprocesses it, and then inputs the processed data into a pre-defined strategy decision-making model for computation. The model analyzes and predicts the data using internal algorithms and parameters, ultimately outputting a power replenishment strategy, such as charging power and charging time. Besides neural networks, the pre-defined strategy decision-making model can also include other machine learning algorithms such as decision trees and Bayesian networks. Decision tree algorithms construct a tree-structured decision model by selecting and partitioning data features, providing a clear visual representation of the decision-making process and results. Bayesian networks, based on Bayes' theorem, utilize probabilistic reasoning to handle uncertainty, enabling more accurate assessment of power replenishment needs and risks in complex energy systems and changing environments. Through pre-defined strategy decision-making models, such as neural networks, decision trees, and Bayesian networks, the processed data is modeled and analyzed to uncover potential relationships and patterns within the data. Taking electric vehicle charging as an example, based on the battery's real-time status data, ambient temperature, and the user-set departure time, the system predicts the battery's charging time and final SOC under different charging power levels. Taking into account the grid load and real-time electricity price, the system formulates the optimal charging strategy, including when to start charging and what charging power to use.

[0027] In one possible implementation, to further illustrate the pre-defined strategy decision-making model processing procedure in this solution, refer to... Figure 5 The schematic diagram of the strategy decision-making process illustrates how this invention provides a data foundation for subsequent analysis and decision-making by inputting preprocessed multimodal data into the input layer. The pre-defined strategy decision-making model includes various machine learning models such as neural networks, decision trees, and Bayesian networks. These models perform calculations and analyses based on the input data, uncovering potential information and patterns within the data. Different models are suitable for different types of data and problems. Neural networks excel at handling complex nonlinear relationships, decision trees can intuitively display the decision-making process and results, and Bayesian networks have advantages in handling uncertainty problems. The model's calculation results are fed into the decision engine layer. The strategy generator generates multiple possible energy replenishment strategies based on the model results. The strategy evaluator then evaluates these strategies, considering factors such as energy utilization efficiency, cost, and user needs, to select the optimal energy replenishment strategy. The evaluation results are fed back to the strategy generator for optimization and adjustment. Finally, the optimal energy replenishment strategy is output through the output layer.

[0028] In one possible implementation, besides currently used machine learning algorithms such as neural networks and decision trees, other algorithms can be employed to achieve adaptive multimodal energy replenishment management. For example, reinforcement learning, through the interaction between an agent and its environment, continuously tries different behavioral strategies and optimizes these strategies based on reward signals from the environment, aiming to maximize cumulative rewards. In adaptive multimodal energy replenishment management, the agent can be the decision-making module for the energy replenishment strategy, while the environment is a combination of factors such as energy equipment, user needs, and the external environment. By continuously adjusting energy replenishment strategies, such as charging power and energy allocation ratios, the agent gradually learns the optimal energy replenishment strategy based on reward signals such as energy utilization efficiency and user satisfaction. Compared to traditional machine learning algorithms, reinforcement learning algorithms do not require a large amount of prior data for training and can learn and adjust in real time in dynamically changing environments, exhibiting stronger adaptability and flexibility. Algorithms based on fuzzy logic can also be used. Fuzzy logic can handle imprecise and fuzzy information, mapping the input multimodal data to the corresponding energy replenishment strategy output by defining fuzzy sets and fuzzy rules. In electric vehicle charging scenarios, fuzzy sets can be defined for data such as battery status and ambient temperature, such as "low battery power" and "high ambient temperature," and corresponding fuzzy rules can be formulated, such as "if the battery power is low and the ambient temperature is high, then reduce the charging power." Fuzzy logic-based algorithms do not require precise mathematical models, better handling uncertainties and fuzziness in practical applications. They also have relatively low computational complexity, offering unique advantages in scenarios with high real-time requirements and where the data exhibits a degree of fuzziness.

[0029] Step 40: Send the optimal energy replenishment strategy to the vehicle and the charging equipment so that the vehicle and the charging equipment can perform adaptive energy replenishment management.

[0030] Specifically, by generating target control commands based on the optimal energy replenishment strategy and sending them to the vehicle and charging equipment, the vehicle and charging equipment can perform adaptive energy replenishment management according to the optimal energy replenishment strategy.

[0031] In one possible implementation, the system possesses the capability for real-time dynamic adjustment of the energy replenishment strategy. When changes in energy demand or the external environment are detected, such as a sudden change in the route of an electric vehicle during operation, or fluctuations in grid load, the system can respond quickly and re-optimize the energy replenishment strategy. Through intelligent interaction with charging equipment, such as adjusting the output power of the charging equipment and controlling the charging and discharging status of the energy storage equipment, real-time optimization of the energy replenishment process is achieved, ensuring efficient energy utilization and stable system operation. In one possible implementation, step 40 further includes: when the optimal energy replenishment strategy is fast charging, determining the maximum safe charging power based on the maximum output voltage and maximum output current of the charging device and the charging parameters of the vehicle; determining the output voltage and current of the charging device based on the maximum safe charging power; generating a control command based on the output voltage and current of the charging device, and sending the control command to the vehicle and the charging device to enable the vehicle and the charging device to perform adaptive energy replenishment management.

[0032] During the energy replenishment execution and control phase, the system sends control commands to the charging equipment according to the optimal energy replenishment strategy, thereby controlling the output power and charging time of the charging equipment. When the optimal energy replenishment strategy is fast charging, in order to ensure the safety and stability of the energy replenishment process, the maximum safe charging power needs to be determined based on the maximum output voltage and maximum output current of the charging equipment and the charging parameters of the vehicle. Based on the maximum safe charging power, the optimal output voltage and current of the charging equipment are determined, and control commands are generated based on the optimal output voltage and current. The control commands are then sent to the vehicle and the charging equipment to enable the vehicle and the charging equipment to perform adaptive energy replenishment management.

[0033] In one implementation, by collecting and analyzing multimodal data in real time, the cloud server can accurately predict energy demand and dynamically adjust the energy replenishment strategy, thereby significantly improving energy replenishment efficiency. In electric vehicle fast charging scenarios, traditional systems often result in long charging times because they cannot adjust charging power in real time according to battery status and environmental changes. This invention, however, can intelligently adjust charging power based on real-time battery temperature, SOC, and other data, reducing charging time by approximately 20%-30% compared to traditional systems. For example, for an electric vehicle with a range of 500 kilometers, fast charging to 80% using a traditional charging management system takes about 40 minutes, while the system of this invention can reduce charging time to 25-30 minutes, significantly improving user convenience.

[0034] As can be seen from the above, the energy replenishment management method provided in this embodiment of the invention acquires multimodal data, which includes battery status data collected by the vehicle, vehicle environment data, charging environment data collected by the charging equipment, power grid data collected by the power grid platform, and user demand data uploaded by the user terminal; preprocesses the multimodal data to obtain target multimodal data; analyzes the energy replenishment strategy based on the preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy; and sends the optimal energy replenishment strategy to the vehicle and the charging equipment so that the vehicle and the charging equipment can perform adaptive energy replenishment management. This can avoid the problem that traditional energy replenishment methods cannot adapt to the changing energy supply and demand relationship, resulting in poor energy replenishment efficiency. By fusing multimodal data and combining the preset strategy decision model to perform in-depth analysis of the energy replenishment strategy, accurate and efficient energy replenishment management is achieved.

[0035] Figure 6 A flowchart of another embodiment of the energy replenishment management method of the present invention is shown, which is performed by an energy replenishment management device. Figure 6 As shown, the following steps are included after step 30: Step 50: If the battery temperature in the battery state parameters is greater than a preset safety threshold, then reduce the output power of the charging device in the optimal energy replenishment strategy to obtain the adjusted energy replenishment strategy.

[0036] To ensure the safety and stability of the charging process, the system monitors the status of the charging equipment and the vehicle battery in real time, thereby reducing battery heat generation and ensuring battery safety.

[0037] In one possible implementation, sensors collect real-time data on battery voltage, current, temperature, and the operating status of the charging equipment. If any abnormality is detected, such as excessively high battery temperature or excessive charging current, the system will immediately take regulatory measures.

[0038] For example, when the battery temperature in the battery status parameters is detected to be greater than a preset safety threshold, the output power of the charging device in the optimal energy replenishment strategy is reduced, thereby updating and adjusting the optimal energy replenishment strategy.

[0039] Step 60: Send the adjusted power replenishment strategy to the charging device so that the charging device reduces its output power according to the adjusted power replenishment strategy.

[0040] Specifically, the adjusted energy replenishment strategy generates new control commands and sends them to the charging device, so that the charging device reduces its output power according to the adjusted energy replenishment strategy.

[0041] In one possible implementation, when the battery temperature is detected to exceed a preset safety threshold, the system will reduce the output power of the charging device to reduce battery heat generation and ensure battery safety. As can be seen from the above, the energy replenishment management method provided in this embodiment of the invention acquires multimodal data, which includes battery status data collected by the vehicle, vehicle environment data, charging environment data collected by the charging equipment, power grid data collected by the power grid platform, and user demand data uploaded by the user terminal; performs data preprocessing on the multimodal data to obtain target multimodal data; analyzes the energy replenishment strategy based on a preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy; sends the optimal energy replenishment strategy to the vehicle and the charging equipment so that the vehicle and the charging equipment perform adaptive energy replenishment management; if the battery temperature in the battery status parameters is greater than a preset safety threshold, the output power of the charging equipment in the optimal energy replenishment strategy is reduced to obtain an adjusted energy replenishment strategy; sends the adjusted energy replenishment strategy to the charging equipment so that the charging equipment reduces its output power according to the adjusted energy replenishment strategy, which can avoid the problem of vehicle battery overheating. By monitoring the status of the charging equipment and the vehicle battery in real time and taking timely control measures in abnormal situations, battery heating is reduced and battery safety is ensured.

[0042] Figure 7 A flowchart of another embodiment of the energy replenishment management method of the present invention is shown, which is executed by the energy replenishment management system. Figure 7 As shown, step 30 includes the following steps: Step 301: Plan the driving route based on the user demand data in the target multimodal data to obtain route planning information.

[0043] Specifically, the travel route is planned based on the user's travel plan input in the user demand data of the target multimodal data to obtain route planning information.

[0044] Furthermore, step 301 also includes: determining the departure time and destination information based on the user demand data in the target multimodal data; and planning the driving route based on the departure time and destination information to obtain route planning information.

[0045] To meet personalized user needs, this invention also provides route planning based on user travel plans, thereby customizing charging strategies based on route planning information and saving users time. This invention can plan driving routes based on user-input travel plans using a pre-set spatiotemporal network model, obtaining route planning information. The spatiotemporal network model can combine a physical network with a time dimension to construct a three-dimensional "spatiotemporal network." Nodes in the network represent "being at a specific location at a specific time" (e.g., "located at charging station A at 3 PM"), and arcs represent actions (driving, charging, waiting). This model can uniformly model actions such as driving, charging, and waiting, as well as constraints such as time windows and time-varying electricity prices. The shortest path algorithm running on this network directly obtains the optimal spatiotemporal trajectory including charging arrangements. It is very suitable for handling electric vehicle route planning problems with complex time constraints and resource allocation.

[0046] In one possible implementation, users can set their travel plans on a mobile app, including departure time, destination, and other information. The system will then plan the route based on this information and generate route planning information.

[0047] Step 302: Based on the route planning information, predict the energy demand to obtain the energy demand prediction results.

[0048] Among them, energy demand is predicted by using route planning information to obtain energy demand prediction results, which can be the electricity consumption required for travel.

[0049] Step 303: Determine the target multimodal data based on the energy demand forecast results.

[0050] Among them, the energy demand forecast results are combined with data collected by other sensors to generate target multimodal data.

[0051] Step 304: Analyze the energy replenishment strategy based on the preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy.

[0052] In one implementation, the optimal energy replenishment strategy is obtained by performing customized analysis on target multimodal data containing energy demand forecasts using a preset strategy decision model.

[0053] Furthermore, step 30 also includes: extracting grid load and real-time electricity price from the grid data; predicting the charging parameters and target battery capacity corresponding to the charging device based on the battery status data, vehicle environment data, grid load, real-time electricity price, and user-set departure time in the user demand data, and obtaining prediction results; and analyzing the energy replenishment strategy based on the preset strategy decision model and the prediction results to obtain the optimal energy replenishment strategy.

[0054] The battery status data can include real-time battery status data such as voltage, current, temperature, and state of charge (SOC). Charging parameters include charging power and charging time. Vehicle environmental data includes ambient temperature and humidity. By acquiring real-time battery status data, vehicle ambient temperature, user-set departure time, and comprehensively considering grid load and real-time electricity price, the system predicts the battery charging time at different charging powers and the final target battery SOC. Based on the prediction results and a preset strategy decision model, the system analyzes the energy replenishment strategy to obtain the optimal energy replenishment strategy.

[0055] In one implementation, by collecting and analyzing multimodal data in real time, a cloud server can accurately predict energy demand and dynamically adjust the energy replenishment strategy, thereby significantly improving energy replenishment efficiency. Taking electric vehicle charging as an example, a neural network model predicts the charging time of the battery at different charging powers and the final target battery state of charge (SOC) based on real-time battery status data, ambient temperature, user-set departure time, and a comprehensive consideration of grid load and real-time electricity price. The optimal charging strategy is then formulated, including when to start charging and what charging power to use. Regarding the optimization and adjustment of the energy replenishment strategy, the system has the ability to dynamically adjust in real time. When changes in energy demand or the external environment are detected, such as a sudden change in the electric vehicle's route or fluctuations in grid load, the system can respond quickly and re-optimize the energy replenishment strategy. Through intelligent interaction with energy devices, such as adjusting the output power of the charging pile and controlling the charging and discharging status of energy storage devices, real-time optimization of the energy replenishment process is achieved, ensuring efficient energy utilization and stable system operation.

[0056] For example, based on battery status and ambient temperature, the available charging power range is determined (considering battery thermal safety and charging efficiency). An available charging time window is calculated based on the user-set departure time. Within this window, considering real-time electricity prices and grid load, the optimal charging power curve is selected to minimize total cost while meeting the target State of Charge (SOC). A battery charging model is constructed based on a neural network model. This model predicts the target battery SOC, charging time, and charging power of the charging equipment based on real-time battery status data, ambient temperature, humidity, and the user-set departure time, while also considering grid load and real-time electricity prices. The model then analyzes the charging strategy based on the prediction results and a pre-defined strategy decision model to obtain the optimal charging strategy.

[0057] As can be seen from the above, the energy replenishment management method provided in this embodiment of the invention acquires multimodal data, which includes battery status data collected by the vehicle, vehicle environment data, charging environment data collected by the charging equipment, power grid data collected by the power grid platform, and user demand data uploaded by the user terminal; performs data preprocessing on the multimodal data to obtain target multimodal data; plans the driving route based on the user demand data in the target multimodal data to obtain route planning information; predicts energy demand based on the route planning information to obtain energy demand prediction results; determines the target multimodal data based on the energy demand prediction results; analyzes the energy replenishment strategy based on a preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy; and sends the optimal energy replenishment strategy to the vehicle and the charging equipment so that the vehicle and the charging equipment can perform adaptive energy replenishment management. This allows for personalized customization of the energy replenishment strategy according to user needs, meeting the user's energy replenishment needs in different scenarios.

[0058] Figure 8 A flowchart of another embodiment of the energy replenishment management method of the present invention is shown, which is performed by a vehicle in the energy replenishment management system that interacts with a cloud server. The method includes: Step 01: Upload the collected battery status data and vehicle environment data to the cloud server.

[0059] The vehicle utilizes a variety of pre-configured sensors to comprehensively acquire different types of data. Sensors within the Battery Management System (BMS) collect key data such as battery voltage, current, temperature, and state of charge (SOC). High-precision voltage sensors monitor the battery's terminal voltage in real time, achieving a measurement accuracy of ±0.01V, accurately reflecting the battery's charging and discharging states. Current sensors, employing the Hall effect principle, accurately measure the current during battery charging and discharging, with a measurement error controlled within ±1%. To acquire environmental data, the vehicle is equipped with temperature and humidity sensors and a light sensor. The temperature and humidity sensors sense ambient temperature and humidity in real time, with a temperature measurement range typically from -40℃ to 125℃ and an accuracy of ±0.5℃, and a humidity measurement range of 0%-100%RH and an accuracy of ±3%RH. This data is crucial for evaluating the vehicle's battery performance under different environments. The light sensor detects light intensity, providing data support for scenarios such as solar charging, and its measurement range extends from 0 lx to 100,000 lx, adapting to various lighting conditions. The collected battery status data and vehicle environment data are uploaded to the cloud server.

[0060] Step 02: Receive the optimal recharging strategy generated by the cloud server based on the battery status data and the vehicle environment data.

[0061] In one possible implementation, the system receives the optimal recharging strategy based on battery status data and vehicle environment data from a cloud server.

[0062] Step 03: Execute adaptive energy replenishment management according to the optimal energy replenishment strategy.

[0063] In one possible implementation, the collected battery status data and vehicle environment data are uploaded to a cloud server in real time, so that the cloud server can adjust and distribute the charging strategy in real time, and perform charging management based on the received optimal charging strategy.

[0064] Figure 9 A schematic diagram of an embodiment of the energy replenishment management system of the present invention is shown. Figure 9 As shown, the system 100 includes: a cloud server 110, a vehicle 120 that interacts with the cloud server, a charging device 130, a power grid platform 140, and a user terminal 150.

[0065] The cloud server 110 is used to acquire multimodal data; The multimodal data includes battery status data collected by the vehicle 120, vehicle environment data, charging environment data collected by the charging equipment 130, power grid data collected by the power grid platform 140, and user demand data uploaded by the user terminal 150. In one implementation, the battery status data collected by vehicle 120 can be obtained in real time through high-precision battery management system sensors, which can collect parameters such as battery voltage, current, temperature, and state of charge (SOC). Vehicle environmental data can be collected using environmental sensors, which can collect parameters such as ambient temperature, humidity, and light intensity. Charging environment parameters collected by charging equipment 130 can be collected using environmental sensors, which can collect parameters such as temperature and humidity of the environment in which the charging equipment is located. Power grid data collected by power grid platform 140 can be real-time electricity price, load, and other information obtained from smart meters or power grid interfaces. User demand data uploaded by user terminal 150 can be personalized demand data such as user travel plans and electricity usage habits collected through the user interface or smart terminal.

[0066] In one possible implementation, the sensor can be based on novel materials, such as graphene. Graphene possesses excellent electrical and mechanical properties, and graphene-based voltage and current sensors can theoretically achieve higher sensitivity and a wider operating temperature range. In electric vehicle battery monitoring, graphene voltage sensors can more accurately capture minute changes in battery voltage and maintain stable operation even in high or low temperature environments, which is of great significance for improving the accuracy and reliability of battery management.

[0067] For example, to acquire battery status data, multiple sensors are used to comprehensively acquire different types of data. Sensors in the Battery Management System (BMS) are responsible for collecting key data such as battery voltage, current, temperature, and state of charge (SOC). A high-precision voltage sensor can monitor the battery's terminal voltage in real time, with a measurement accuracy of ±0.01V, accurately reflecting the battery's charging and discharging state. The current sensor, employing the Hall effect principle, can accurately measure the current during battery charging and discharging, with a measurement error controlled within ±1%. To acquire vehicle environmental data, the system is equipped with temperature and humidity sensors and a light sensor. The temperature and humidity sensor can sense ambient temperature and humidity in real time. Its temperature measurement range is typically -40℃ to 125℃ with an accuracy of ±0.5℃, and its humidity measurement range is 0%-100%RH with an accuracy of ±3%RH. This data is crucial for evaluating the vehicle battery's performance under different environments. The light sensor is used to detect light intensity, providing data support for scenarios such as solar charging. Its measurement range is from 0 lx to 100,000 lx, adapting to different lighting environments. To obtain grid data, real-time electricity prices and load information can be collected through smart meters on the grid platform 140. These smart meters interact with the grid data center via communication modules, accurately acquiring hourly or even shorter time intervals of electricity price data, as well as real-time grid load conditions. This provides a basis for the system to consider cost and grid stability when allocating energy. User demand data can also be collected through user interfaces or smart terminals. The above figures are for illustrative purposes only and are not intended to impose specific limitations.

[0068] The cloud server 110 is also used to perform data preprocessing on the multimodal data to obtain target multimodal data; For further explanation of the data preprocessing process, please refer to Figure 3 The data processing diagram shown includes data preprocessing operations such as time alignment, format unification, and data cleaning. By performing time alignment, format unification, and data cleaning preprocessing operations on multimodal data, target multimodal data is generated from the obtained multimodal data of various types.

[0069] In one possible implementation, current systems use general-purpose high-performance computing chips to process large amounts of multimodal data. This invention can select ASIC chips to process multimodal data. The ASIC chip can be designed according to the specific algorithms and data processing requirements of the power management system, thereby significantly improving data processing speed while reducing power consumption. For neural network model computation, the ASIC chip can achieve rapid processing of key operations such as matrix operations through optimized hardware architecture. Compared to general-purpose chips, it can complete data analysis and decision-making in a shorter time, improving the system's real-time response capability.

[0070] The cloud server 110 is also used to analyze the energy replenishment strategy based on the preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy. By fusing multimodal data, a more comprehensive and accurate understanding of energy replenishment needs and environmental changes can be achieved, avoiding the limitations of single data sources. This improves the scientific rigor and accuracy of decision-making. Real-time analysis and dynamic decision-making using a pre-set strategy decision-making model enable the cloud server 110 to respond quickly to changes, significantly enhancing the efficiency and flexibility of energy replenishment management. This intelligent adaptive energy replenishment strategy helps reduce energy loss, extend the lifespan of energy equipment, and improve the user experience, providing a more efficient and intelligent solution for the development of energy applications. The pre-set strategy decision-making model is a pre-configured model used to predict energy replenishment needs from pre-processed multimodal data. Based on the processed multimodal data, this model uses advanced algorithms and models to determine energy replenishment needs and identify the optimal energy replenishment strategy. For further explanation of the adaptive decision-making process of this solution, please refer to [link / reference]. Figure 4 The diagram illustrates the adaptive decision-making process. Cloud server 110 receives multimodal data, preprocesses it, and then inputs the processed data into a pre-defined strategy decision-making model for calculation. The model analyzes and predicts the data using internal algorithms and parameters, ultimately outputting a power replenishment strategy, such as charging power and charging time. Besides neural networks, the pre-defined strategy decision-making model can also include other machine learning algorithms such as decision trees and Bayesian networks. Decision tree algorithms construct a tree-structured decision model by selecting and partitioning data features, providing a clear visual representation of the decision-making process and results. Bayesian networks, based on Bayes' theorem, utilize probabilistic reasoning to handle uncertainty, enabling more accurate assessment of power replenishment needs and risks in complex energy systems and changing environments. Through pre-defined strategy decision-making models, such as neural networks, decision trees, and Bayesian networks, the processed data is modeled and analyzed to uncover potential relationships and patterns between data points. Taking electric vehicle charging as an example, based on the battery's real-time status data, ambient temperature, and the user-set departure time, the system predicts the battery's charging time and final SOC under different charging power levels. Taking into account the grid load and real-time electricity price, the system formulates the optimal charging strategy, including when to start charging and what charging power to use.

[0071] In one possible implementation, to further illustrate the pre-defined strategy decision-making model processing procedure in this solution, refer to... Figure 5The schematic diagram of the strategy decision-making process illustrates how this invention provides a data foundation for subsequent analysis and decision-making by inputting preprocessed multimodal data into the input layer. The pre-defined strategy decision-making model includes various machine learning models such as neural networks, decision trees, and Bayesian networks. These models perform calculations and analyses based on the input data, uncovering potential information and patterns within the data. Different models are suitable for different types of data and problems. Neural networks excel at handling complex nonlinear relationships, decision trees can intuitively display the decision-making process and results, and Bayesian networks have advantages in handling uncertainty problems. The model's calculation results are fed into the decision engine layer. The strategy generator generates multiple possible energy replenishment strategies based on the model results. The strategy evaluator then evaluates these strategies, considering factors such as energy utilization efficiency, cost, and user needs, to select the optimal energy replenishment strategy. The evaluation results are fed back to the strategy generator for optimization and adjustment. Finally, the optimal energy replenishment strategy is output through the output layer.

[0072] In one possible implementation, besides currently used machine learning algorithms such as neural networks and decision trees, other algorithms can be employed to achieve adaptive multimodal energy replenishment management. For example, reinforcement learning, through the interaction between an agent and its environment, continuously tries different behavioral strategies and optimizes these strategies based on reward signals from the environment, aiming to maximize cumulative rewards. In adaptive multimodal energy replenishment management, the agent can be the decision-making module for the energy replenishment strategy, while the environment is a combination of factors such as energy equipment, user needs, and the external environment. By continuously adjusting energy replenishment strategies, such as charging power and energy allocation ratios, the agent gradually learns the optimal energy replenishment strategy based on reward signals such as energy utilization efficiency and user satisfaction. Compared to traditional machine learning algorithms, reinforcement learning algorithms do not require a large amount of prior data for training and can learn and adjust in real time in dynamically changing environments, exhibiting stronger adaptability and flexibility. Algorithms based on fuzzy logic can also be used. Fuzzy logic can handle imprecise and fuzzy information, mapping the input multimodal data to the corresponding energy replenishment strategy output by defining fuzzy sets and fuzzy rules. In electric vehicle charging scenarios, fuzzy sets can be defined for data such as battery status and ambient temperature, such as "low battery power" and "high ambient temperature," and corresponding fuzzy rules can be formulated, such as "if the battery power is low and the ambient temperature is high, then reduce the charging power." Fuzzy logic-based algorithms do not require precise mathematical models, better handling uncertainties and fuzziness in practical applications. They also have relatively low computational complexity, offering unique advantages in scenarios with high real-time requirements and where the data exhibits a degree of fuzziness.

[0073] The cloud server 110 is also used to send the optimal energy replenishment strategy to the vehicle 120 and the charging device 130, so that the vehicle 120 and the charging device 130 can perform adaptive energy replenishment management.

[0074] The cloud server 110 generates target control commands based on the optimal energy replenishment strategy and sends them to the vehicle 120 and the charging equipment 130, so that the vehicle 120 and the charging equipment 130 can perform adaptive energy replenishment management according to the optimal energy replenishment strategy.

[0075] In one possible implementation, the system has the capability to dynamically adjust the energy replenishment strategy in real time. When the cloud server 110 detects changes in energy demand or the external environment, such as a sudden change in the electric vehicle's route or fluctuations in the grid load, the cloud server 110 can respond quickly and re-optimize the energy replenishment strategy. Through intelligent interaction with charging equipment, such as adjusting the output power of the charging equipment and controlling the charging and discharging status of the energy storage equipment, real-time optimization of the energy replenishment process is achieved, ensuring efficient energy utilization and stable system operation.

[0076] In one possible implementation, the system further includes a photovoltaic power generation device and an energy storage device; the photovoltaic power generation device is used to prioritize charging the energy storage device when the output power of the photovoltaic power generation is greater than the load demand power and the grid load collected by the grid platform is lower than a preset threshold; the energy storage device is used to prioritize supplying power to the load when the output power of the photovoltaic power generation is less than the load demand power or the grid load collected by the grid platform is higher than the preset threshold.

[0077] In this invention, the photovoltaic power generation equipment can be a solar power generation device, the energy storage device can be an energy storage battery, and the preset threshold can be a minimum supply threshold set in advance based on the grid load. In an energy distribution scenario, when the output power of the photovoltaic power generation exceeds the load demand and the grid load collected by the grid platform is lower than the preset threshold, the photovoltaic power generation equipment will preferentially store solar energy in the energy storage battery. When the output power of the photovoltaic power generation is less than the load demand or the grid load collected by the grid platform is higher than the preset threshold, the energy storage device will discharge to provide energy to the load. In one implementation, by optimizing energy allocation strategies, energy losses during transmission and conversion are reduced. In distributed energy systems, traditional systems struggle to flexibly coordinate the complementarity and cooperation between various energy sources based on real-time energy output and demand, leading to significant energy waste. The system of this invention can monitor the output of renewable energy sources such as solar and wind power in real time, as well as grid load and real-time electricity prices, prioritizing energy allocation to the most needed equipment and storing energy when prices are low, thereby effectively reducing energy costs. Compared to traditional systems, energy consumption can be reduced by 15%-20%. Therefore, the system of this invention possesses strong fault tolerance and adaptability. When an anomaly is detected in energy equipment, it can quickly switch to backup energy or adjust the energy replenishment strategy to ensure the continuous and stable operation of the system. Under extreme weather conditions, such as a sudden drop in photovoltaic power generation due to heavy rain, the system of this invention can promptly detect and quickly adjust energy allocation, prioritizing the energy supply to critical equipment and maintaining normal system operation. In contrast, traditional systems may fail to respond in time, causing some equipment to stop working.

[0078] In one possible implementation, the controller in the vehicle is used to obtain the current vehicle battery temperature when it receives the optimal charging strategy issued by the cloud server 110; the controller in the vehicle is also used to perform preheating control on the vehicle battery when the current vehicle battery temperature is lower than the preset optimal charging temperature.

[0079] In order to improve charging efficiency, when the vehicle 120 receives the optimal charging strategy from the cloud server 110, it obtains the current vehicle battery temperature through the controller. When the current vehicle battery temperature is lower than the preset optimal charging temperature, it performs preheating control on the vehicle battery until the vehicle battery temperature reaches the optimal charging temperature and then stops preheating.

[0080] As can be seen from the above, in the energy replenishment management system provided by the embodiments of the present invention, the cloud server 110 acquires multimodal data, including battery status data collected by the vehicle 120, vehicle environment data, charging environment data collected by the charging equipment 130, power grid data collected by the power grid platform 140, and user demand data uploaded by the user terminal 150; the cloud server 110 performs data preprocessing on the multimodal data to obtain target multimodal data; the cloud server 110 analyzes the energy replenishment strategy based on the preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy; the cloud server 110 sends the optimal energy replenishment strategy to the vehicle 120 and the charging equipment 130 so that the vehicle 120 and the charging equipment 130 perform adaptive energy replenishment management, which can avoid the problem that traditional energy replenishment methods cannot adapt to the changing energy supply and demand relationship, resulting in poor energy replenishment efficiency. By integrating multimodal data and combining the preset strategy decision model to perform in-depth analysis of the energy replenishment strategy, accurate and efficient energy replenishment management is achieved.

[0081] The energy replenishment management system provided in this embodiment can execute the methods provided in the above-described method embodiments. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0082] Furthermore, all information to be extracted in this application was obtained with the user's permission or consent; that is, when this application is applied to a specific product or technology, user permission is required to obtain and process the relevant data, and the processing of the relevant data must comply with the relevant laws, regulations and regulatory standards of the relevant countries and regions.

[0083] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Furthermore, the embodiments of this invention are not directed to any particular programming language.

[0084] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. Similarly, for the sake of brevity and to aid in understanding one or more aspects of the invention, in the description of exemplary embodiments of the invention above, various features of the embodiments are sometimes grouped together in a single embodiment, figure, or description thereof. The claims, which follow the detailed description, are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0085] Those skilled in the art will understand that the modules in the device of the embodiment can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiment can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components, except that at least some of such features and / or processes or units are mutually exclusive.

[0086] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A method for managing energy replenishment, the energy replenishment management system comprising a cloud server, vehicles interacting with the cloud server, charging equipment, a power grid platform, and user terminals, wherein the energy replenishment management method is applied to the cloud server, characterized in that, The method includes: Acquire multimodal data, wherein the multimodal data includes battery status data collected by the vehicle, vehicle environment data, charging environment data collected by the charging equipment, power grid data collected by the power grid platform, and user demand data uploaded by the user terminal; The multimodal data is preprocessed to obtain the target multimodal data; The energy replenishment strategy is analyzed based on the preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy; The optimal energy replenishment strategy is sent to the vehicle and the charging equipment to enable the vehicle and the charging equipment to perform adaptive energy replenishment management.

2. The method as described in claim 1, characterized in that, Sending the optimal charging strategy to the vehicle and the charging equipment to enable the vehicle and the charging equipment to perform adaptive charging management includes: When the optimal energy replenishment strategy is fast charging, the maximum safe charging power is determined based on the maximum output voltage and maximum output current of the charging equipment and the charging parameters of the vehicle. The output voltage and current of the charging device are determined based on the maximum safe charging power. Based on the output voltage and current of the charging device, a control command is generated and sent to the vehicle and the charging device to enable the vehicle and the charging device to perform adaptive energy replenishment management.

3. The method as described in claim 2, characterized in that, After sending the optimal charging strategy to the vehicle and the charging equipment to enable the vehicle and the charging equipment to perform adaptive charging management, the method further includes: If the battery temperature in the battery state parameters is greater than a preset safety threshold, then the output power of the charging device in the optimal energy replenishment strategy is reduced to obtain an adjusted energy replenishment strategy. The adjusted energy replenishment strategy is sent to the charging device so that the charging device reduces its output power according to the adjusted energy replenishment strategy.

4. The method as described in claim 1, characterized in that, The step of analyzing the energy replenishment strategy based on the preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy includes: Extract grid load and real-time electricity price from the grid data; Based on the battery status data, vehicle environment data, power grid load, real-time electricity price, and the user-set departure time in the user demand data, the charging parameters corresponding to the charging equipment and the target battery capacity are predicted to obtain the prediction result. The energy replenishment strategy is analyzed based on the preset strategy decision model and the prediction results to obtain the optimal energy replenishment strategy.

5. The method as described in claim 1, characterized in that, The step of analyzing the energy replenishment strategy based on the preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy includes: Based on the user demand data in the target multimodal data, the driving route is planned to obtain route planning information; Based on the route planning information, energy demand is predicted to obtain energy demand prediction results; Target multimodal data are determined based on energy demand forecast results; The energy replenishment strategy is analyzed based on the preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy.

6. The method as described in claim 5, characterized in that, The step of planning a driving route based on user demand data in the target multimodal data to obtain route planning information includes: Determine the departure time and destination information based on the user demand data in the target multimodal data; Based on the departure time and destination information, a driving route is planned to obtain route planning information.

7. A power replenishment management method, wherein the power replenishment management method is applied to a vehicle interacting with a cloud server, characterized in that, The method includes: The collected battery status data and vehicle environment data are uploaded to the cloud server. Receive the optimal energy replenishment strategy generated by the cloud server based on the battery status data and the vehicle environment data; Adaptive energy replenishment management is performed based on the optimal energy replenishment strategy.

8. A power replenishment management system, characterized in that, The system includes a cloud server, vehicles that interact with the cloud server, charging equipment, a power grid platform, and user terminals. The cloud server is used to acquire multimodal data, which includes battery status data collected by the vehicle, vehicle environment data, charging environment data collected by the charging equipment, power grid data collected by the power grid platform, and user demand data uploaded by the user terminal. The cloud server is also used to preprocess the multimodal data to obtain target multimodal data; The cloud server is also used to analyze the energy replenishment strategy based on the preset strategy decision model and the target multimodal data to obtain the optimal energy replenishment strategy. The cloud server is also used to send the optimal energy replenishment strategy to the vehicle and the charging equipment, so that the vehicle and the charging equipment can perform adaptive energy replenishment management.

9. The energy replenishment management system as described in claim 8, characterized in that, The system also includes photovoltaic power generation equipment and energy storage equipment; The photovoltaic power generation equipment is used to prioritize charging the energy storage device when the output power of the photovoltaic power generation is greater than the load demand power and the grid load collected by the grid platform is lower than a preset threshold. The energy storage device is used to prioritize supplying power to the load when the output power of the photovoltaic power generation is less than the power demand of the load or when the grid load collected by the grid platform is higher than the preset threshold.

10. The energy replenishment management system as described in claim 8, characterized in that, The controller in the vehicle is used to obtain the current vehicle battery temperature when it receives the optimal energy replenishment strategy from the cloud server. The controller in the vehicle is also used to preheat the vehicle battery when the current vehicle battery temperature is lower than the preset optimal charging temperature.

Images