A battery-swap vehicle charging strategy management system based on power grid optimization

Abstract

The present invention discloses a battery-swap car charging strategy management system based on power grid optimization, which relates to the technical field of battery-swap car charging strategy management, including a power grid monitoring module, a user demand collection module, a central control system and a charging site control module, wherein: the power grid monitoring module: is used to collect power grid monitoring data in real time, wherein the power grid monitoring data includes but is not limited to power grid load, electricity price information and power grid operation status, and transmits the power grid monitoring data to the central control system. The battery-swap car charging strategy management system based on power grid optimization distributes the charging demand evenly to the off-peak period of the power grid by reasonably scheduling the charging load, reduces the pressure of the power grid during the peak load period, improves the overall operation efficiency and safety of the power grid, and recommends users to charge during the period with lower electricity prices through economic optimization strategies, thereby reducing the charging cost and improving the economic benefits of users.

Description

Technical Field

[0001] The present invention relates to the technical field of battery-swap vehicle charging strategy management, and specifically to a battery-swap vehicle charging strategy management system based on power grid optimization. Background Art

[0002] With the development of new energy vehicles, electric vehicles have gradually become an effective way to solve the energy crisis and environmental pollution. However, with the increase in the number of electric vehicles, the contradiction between charging demand and grid load has become increasingly prominent. Traditional charging modes often fail to fully consider the load conditions of the grid, resulting in excessive pressure on the grid during peak hours, which may cause local grid overload, unstable power supply and other problems. At the same time, the charging experience of electric vehicle users is also affected, especially when the charging demand is concentrated, it is easy to have charging queues, affecting the user experience. Summary of the invention

[0003] In order to solve the above problems, a battery swap vehicle charging strategy management system based on power grid optimization has emerged. The system monitors the operation status of the power grid in real time, combines the charging needs of users, intelligently schedules charging time and power, reasonably distributes power grid load, balances power grid pressure, and optimizes the charging process of electric vehicles. The system can not only improve the operation efficiency of the power grid, but also improve the charging experience of users.

[0004] The present invention is implemented through the following technical solutions: A battery swap vehicle charging strategy management system based on power grid optimization, including a power grid monitoring module, a user demand collection module, a central control system and a charging site control module, wherein:

[0005] Grid monitoring module: used to collect grid monitoring data in real time, including but not limited to grid load, electricity price information and grid operation status, and transmit the grid monitoring data to the central control system;

[0006] User demand collection module: used to collect users' charging demand information and upload the charging demand information to the central control system;

[0007] Central control system: Based on the grid monitoring data and charging demand information, it generates charging scheduling strategies using optimization algorithms and sends the charging scheduling strategies to each charging station through the communication network;

[0008] Charging site control module: used to receive the charging scheduling strategy issued by the central control system, and control the charging piles in the charging site according to the charging scheduling strategy, adjust the charging power and charging time of the charging piles, and ensure a smooth and orderly charging process.

[0009] Preferably, the power grid monitoring module includes a data preprocessing unit, a load forecasting unit and an anomaly detection unit:

[0010] The data preprocessing unit is used to clean, remove noise and convert the format of the collected power grid monitoring data to improve the accuracy and effectiveness of the data;

[0011] The load forecasting unit uses the power grid load forecasting model to forecast the power grid load in the future based on the historical charging data and the currently collected power grid monitoring data, generates the future charging load, and guides the central control system to formulate a charging scheduling strategy; the charging scheduling strategy includes early warning information and scheduling suggestions for the power grid load;

[0012] The anomaly detection unit analyzes the grid monitoring data in real time, identifies abnormal conditions during grid operation, such as voltage fluctuations, overloads, and equipment failures, and promptly sends alarms to the central control system to ensure the stability and security of the grid.

[0013] Preferably, the user demand collection module includes a mobile application interface, an intelligent demand prediction unit and a preference setting unit:

[0014] The mobile application interface is used to communicate with the user's mobile device or vehicle information system, the user inputs his charging demand through the mobile device or the vehicle information system, and the charging demand of the user is generated into charging demand information via the mobile device;

[0015] The intelligent demand prediction unit uses data mining technology to predict users' future charging needs based on their historical charging data and behavior patterns, including the expected charging time period and charging volume requirements, to assist the central control system in generating an optimized charging scheduling strategy;

[0016] The preference setting unit is used for users to customize charging preferences, including but not limited to priority charging during low electricity price periods, priority fast charging, and priority green energy. The central control system optimizes the charging scheduling strategy based on these charging preferences to improve the user's charging experience.

[0017] Preferably, the central control system includes a data processing module, an optimization algorithm module and a strategy generation module:

[0018] The data processing module is used to receive and integrate the grid monitoring data and charging demand information from the grid monitoring module and the user demand collection module, and conduct comprehensive analysis to extract valuable information;

[0019] The optimization algorithm module integrates a variety of optimization algorithms, including but not limited to genetic algorithm, particle swarm optimization algorithm, linear programming algorithm and dynamic programming algorithm. The optimization algorithm module is used to generate optimized calculation results based on the optimization algorithm according to different power grid loads and user needs;

[0020] The strategy generation module generates a basic charging strategy based on the calculation results of the optimization algorithm module, and sends the basic charging strategy to each charging station through the communication network to ensure the dynamic balance of the grid load and the effective satisfaction of user needs;

[0021] Among them, genetic algorithm and particle swarm optimization algorithm are mainly used for global optimization to avoid local optimal solutions;

[0022] Among them, linear programming and dynamic programming algorithms are used for precise control to optimize the allocation of charging time and charging power under constraints, ensuring a balance between grid stability and user demand satisfaction.

[0023] Preferably, the central control system includes a user demand response model, which is used to adjust the charging scheduling strategy according to the dynamic changes of the power grid monitoring data and the charging demand information; wherein the user demand response model is constructed as follows:

[0024] Collect charging demand information related to user charging behavior, including but not limited to: user personal information, historical charging data, required charging amount, vehicle power status, vehicle information, environmental and time factors, and user preferences; and pre-process the charging demand information:

[0025] Data cleaning: remove missing values, outliers and noise data in charging demand information to improve the accuracy of user demand response model;

[0026] Data standardization: Convert charging demand information of different scales to the same scale and generate raw data to ensure equal treatment of each feature during the training process of the user demand response model;

[0027] Feature extraction: Extract features from raw data that are useful for predicting user demand response models. For example, infer users’ future charging needs through historical charging data and behavior patterns: that is, the expected charging time period and charging amount required.

[0028] According to different application scenarios and requirements, select the corresponding prediction model to build a user demand response model.

[0029] The user demand response model also collects the user's charging demand information and grid monitoring data in real time, and uses the response mechanism to dynamically adjust the charging power of the charging pile; the response mechanism includes:

[0030] Price incentives: When the grid load is high, the central control system guides users to charge during low-load periods by raising electricity prices; when the grid load is low, it lowers electricity prices to attract users to charge.

[0031] Power regulation: The central control system monitors the grid load in real time. When the grid load is too high, it automatically reduces the charging power of some vehicles or delays the charging time to ensure the overall stability of the grid. When the grid load is low, it automatically increases the charging power of some vehicles or shortens the charging time.

[0032] Preferably, the central control system includes a power grid load forecasting model and a charging scheduling optimization model:

[0033] The grid load forecasting model is based on time series analysis and uses the future charging load generated by the load forecasting unit to forecast. The forecasting formula includes an autoregressive moving average model, and the forecast results are used to formulate a preliminary dispatch plan.

[0034] The charging scheduling optimization model is based on linear programming to formulate a reasonable charging scheduling strategy: the optimization objectives include reducing the peak load of the power grid and the charging cost of users. The charging scheduling optimization model takes the balance of the power grid load and the satisfaction of user needs as the objective function, generates an intermediate scheduling plan, and then uses a genetic algorithm based on the operations of selection, crossover and mutation to continuously evolve to obtain the global optimal solution, that is, the optimized charging scheduling strategy. Among them, the charging scheduling optimization model is used to meet the charging needs of users while minimizing the peak load of the power grid and the cost of user charging, thereby realizing charging scheduling optimization.

[0035] Preferably, the central control system further includes a feedback learning unit for collecting and analyzing user feedback and charging station operation data, and continuously optimizing the charging scheduling strategy through a machine learning algorithm:

[0036] The feedback learning unit optimizes the parameter settings and optimization algorithms in the central control system by analyzing historical charging data, user feedback, and charging site operation data, thereby improving the adaptability of the central control system in different scenarios, generating new feedback data, and transmitting the feedback data to the central control system. After receiving the new feedback data, the central control system automatically adjusts the charging scheduling strategy and generates a charging feedback strategy. Under the operation mechanism of this feedback learning unit, the central control system can transmit the charging feedback strategy to the charging piles of each charging site through the communication network, further optimizing and adjusting the charging power and charging time of the charging piles; gradually improving the accuracy of the charging feedback strategy and user satisfaction, ensuring that the central control system is always in the best operating state and has the ability to self-improve.

[0037] Preferably, the central control system further includes a real-time dynamic scheduling unit, a distributed processing unit and a multi-objective optimization unit:

[0038] The real-time dynamic dispatching unit supports dynamic adjustment of charging dispatching strategies based on real-time updated grid monitoring data and charging demand information, and generates corresponding dynamic charging dispatching strategies to adapt to dynamic changes in grid load and user demand;

[0039] The distributed processing unit realizes distributed processing and scheduling optimization of data through cloud computing, and improves the response speed and fault tolerance of the central control system;

[0040] The multi-objective optimization unit is used to comprehensively consider the grid load balance, user charging costs, and carbon emissions, and generate the optimal multiple charging scheduling strategy that meets multiple requirements.

[0041] Preferably, the charging station control module includes a charging power adjustment unit, an adaptive control unit and a charging process monitoring unit:

[0042] The charging power adjustment unit dynamically adjusts the charging power output of the charging pile according to the charging scheduling strategy issued by the central control system, ensuring that the charging power output is reduced when the grid load is high, and the charging power output is increased when the grid load is low;

[0043] The adaptive control unit is used to autonomously adjust the charging power and charging time according to the actual grid load, user demand and charging scheduling strategy to cope with instantaneous changes;

[0044] The charging process monitoring unit monitors the voltage parameters, current parameters and power parameters during the charging process in real time, detects and handles abnormal conditions during the charging process, and ensures the safety and stability of the charging process.

[0045] The present invention provides a battery-swap vehicle charging strategy management system based on power grid optimization, which has the following beneficial effects:

[0046] Improve grid operation efficiency: By rationally dispatching charging loads, the charging demand is evenly distributed during the off-peak hours of the grid, reducing the pressure during peak hours and improving the overall operation efficiency and safety of the grid.

[0047] Reduce user charging costs: Through economic optimization strategies, users are advised to charge during periods of lower electricity prices, thereby reducing charging costs and improving users' economic benefits.

[0048] Optimized user charging experience: Based on the user's charging needs and preferences, the system provides personalized charging solutions to ensure that users can complete charging within a reasonable time while avoiding the problem of waiting in line for charging.

[0049] Ensure grid stability: When the grid load is too high, the system can intelligently adjust the charging power or delay some charging tasks to ensure the overall stability of the grid and power supply security.

[0050] Promoting the use of renewable energy: The system can be combined with renewable energy generation, giving priority to the use of low-carbon energy for charging, promoting the use of green energy and reducing carbon emissions.

[0051] Through intelligent scheduling and load management, the coordinated optimization of the power grid and electric vehicle charging demand is achieved, which has broad application prospects and significant social and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0053] Figure 1 It is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0054] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0055] Examples, such as Figure 1 As shown, the present invention provides a technical solution: a battery swap vehicle charging strategy management system based on power grid optimization, including a power grid monitoring module, a user demand collection module, a central control system and a charging site control module, wherein:

[0056] Grid monitoring module: used to collect grid monitoring data in real time, including but not limited to grid load, electricity price information and grid operation status, and transmit the grid monitoring data to the central control system;

[0057] User demand collection module: used to collect users' charging demand information and upload the charging demand information to the central control system;

[0058] Central control system: Based on the grid monitoring data and charging demand information, it generates charging scheduling strategies using optimization algorithms and sends the charging scheduling strategies to each charging station through the communication network;

[0059] Charging site control module: used to receive the charging scheduling strategy issued by the central control system, and control the charging piles in the charging site according to the charging scheduling strategy, adjust the charging power and charging time of the charging piles, and ensure a smooth and orderly charging process.

[0060] The power grid monitoring module includes a data preprocessing unit, a load forecasting unit, and an anomaly detection unit:

[0061] The data preprocessing unit is used to clean, remove noise and convert the format of the collected power grid monitoring data to improve the accuracy and effectiveness of the data;

[0062] The load forecasting unit uses the power grid load forecasting model to forecast the power grid load in the future based on the historical charging data and the currently collected power grid monitoring data, generates the future charging load, and guides the central control system to formulate a charging scheduling strategy; the charging scheduling strategy includes early warning information and scheduling suggestions for the power grid load;

[0063] The anomaly detection unit analyzes the grid monitoring data in real time, identifies abnormal conditions during grid operation, such as voltage fluctuations, overloads, and equipment failures, and promptly sends alarms to the central control system to ensure the stability and security of the grid.

[0064] The user demand collection module includes a mobile application interface, an intelligent demand prediction unit, and a preference setting unit:

[0065] The mobile application interface is used to communicate with the user's mobile device or vehicle information system, the user inputs his charging demand through the mobile device or the vehicle information system, and the charging demand of the user is generated into charging demand information via the mobile device;

[0066] The intelligent demand prediction unit uses data mining technology to predict users' future charging needs based on their historical charging data and behavior patterns, including the expected charging time period and charging volume requirements, to assist the central control system in generating an optimized charging scheduling strategy;

[0067] The preference setting unit is used for users to customize charging preferences, including but not limited to priority charging during low electricity price periods, priority fast charging, and priority green energy. The central control system optimizes the charging scheduling strategy based on these charging preferences to improve the user's charging experience.

[0068] The central control system includes an optimization algorithm module and a strategy generation module:

[0069] The optimization algorithm module integrates a variety of optimization algorithms, including but not limited to genetic algorithm, particle swarm optimization algorithm, linear programming algorithm and dynamic programming algorithm. The optimization algorithm module is used to generate optimized calculation results based on the optimization algorithm according to different power grid loads and user needs;

[0070] The strategy generation module generates a basic charging strategy based on the calculation results of the optimization algorithm module, and sends the basic charging strategy to each charging station through the communication network to ensure the dynamic balance of the grid load and the effective satisfaction of user needs;

[0071] Among them, genetic algorithm and particle swarm optimization algorithm are mainly used for global optimization to avoid local optimal solutions;

[0072] Among them, linear programming and dynamic programming algorithms are used for precise control to optimize the allocation of charging time and charging power under constraints, ensuring a balance between grid stability and user demand satisfaction.

[0073] The central control system includes a user demand response model, which is used to adjust the charging scheduling strategy according to the dynamic changes of power grid monitoring data and charging demand information; the user demand response model is constructed as follows:

[0074] Collect charging demand information related to user charging behavior, including but not limited to: user personal information, historical charging data, required charging amount, vehicle power status, vehicle information, environmental and time factors, and user preferences; and pre-process the charging demand information:

[0075] Data cleaning: remove missing values, outliers and noise data in charging demand information to improve the accuracy of user demand response model;

[0076] Data standardization: Convert charging demand information of different scales to the same scale and generate raw data to ensure equal treatment of each feature during the training process of the user demand response model;

[0077] Feature extraction: Extract features from raw data that are useful for predicting user demand response models. For example, infer users’ future charging needs through historical charging data and behavior patterns: that is, the expected charging time period and charging amount required.

[0078] According to different application scenarios and requirements, select the corresponding prediction model to build a user demand response model:

[0079] Time series models are used to predict users’ future charging behavior, especially their charging time and frequency.

[0080] Autoregressive moving average model: used for linear time series forecasting to capture seasonal and trend changes in users’ charging behavior;

[0081] Long short-term memory artificial neural network model, a neural network model for processing long-term series dependencies: used to capture complex patterns in users' charging behavior;

[0082] Regression model is used to predict the user's charging amount and the intensity of charging demand:

[0083] Linear regression model: used in scenarios with linear relationships to predict continuous variables such as charging capacity;

[0084] Polynomial regression model: used for scenarios with nonlinear relationships and complex user behavior patterns: capturing charging needs;

[0085] The classification model is used to classify users’ charging needs and classify users into high-frequency charging users and low-frequency charging users:

[0086] Logistic regression model: used to predict whether the user will charge during a certain period of time;

[0087] Decision tree model: used to generate rules to classify users’ charging needs;

[0088] Select the corresponding prediction model to generate the model to be formed, and train the model to be formed with the collected historical charging data: use the training data set to train the model to be formed so that it can learn the user's charging behavior; use the validation data set to evaluate the performance of the model to be formed and adjust the model parameters to improve the prediction accuracy; use the test data set to conduct a final test on the model to be formed to ensure the generalization ability of the model;

[0089] Optimize the model to be formed: adjust the hyperparameters of the model to be formed through grid search to further improve the performance of the user demand response model; improve the accuracy and robustness of the prediction by integrating the above multiple prediction models; combine the future charging demand generated by the intelligent demand prediction unit to continuously optimize the model to be formed so that it can adapt to changes in user behavior and generate a user demand response model;

[0090] Finally, the trained user demand response model is deployed in the central control system to predict the user's charging demand in real time, and the prediction results are input into the central control system to generate an adjusted charging demand strategy;

[0091] The user demand response model also collects the user's charging demand information and grid monitoring data in real time, and uses the response mechanism to dynamically adjust the charging power of the charging pile; the response mechanism includes:

[0092] Price incentives: When the grid load is high, the central control system guides users to charge during low-load periods by raising electricity prices; when the grid load is low, it lowers electricity prices to attract users to charge.

[0093] Power regulation: The central control system monitors the grid load in real time. When the grid load is too high, it automatically reduces the charging power of some vehicles or delays the charging time to ensure the overall stability of the grid. When the grid load is low, it automatically increases the charging power of some vehicles or shortens the charging time.

[0094] That is, during peak grid load periods, the central control system guides users to adjust their charging times by increasing electricity prices or reducing the charging power of some vehicles;

[0095] During the low-load period of the power grid, the central control system attracts users to charge by lowering electricity prices or increasing charging power, thereby maximizing the utilization efficiency of power grid resources.

[0096] By constructing a user demand response model, based on historical data and real-time data, the system can accurately predict when users need to charge and how much electricity they need to charge, so as to better match grid resources with user needs. The system can accurately predict user charging needs; according to user demand forecasts, charging resources are prepared for users in advance to reduce user waiting time and optimize the charging experience; by predicting user charging needs, the system can better schedule charging loads, balance grid pressure, avoid overloads, and optimize grid load management; the construction of user demand models is a key part of the battery-swap vehicle charging strategy management system based on grid optimization. It provides reliable data support and prediction capabilities for optimizing charging strategies, thereby improving user charging satisfaction while ensuring grid stability.

[0097] The central control system includes a power grid load forecasting model and a charging scheduling optimization model:

[0098] The grid load forecasting model is based on time series analysis and uses the future charging load generated by the load forecasting unit to forecast. The forecasting formula includes an autoregressive moving average model, and the forecast results are used to formulate a preliminary dispatch plan.

[0099] The charging scheduling optimization model is based on linear programming to develop a reasonable charging scheduling strategy: the optimization objectives include reducing the peak load of the power grid and the charging cost of users. The charging scheduling optimization model takes the balance of the power grid load and the satisfaction of user needs as the objective function, generates an intermediate scheduling plan, and then uses a genetic algorithm based on the operations of selection, crossover and mutation to continuously evolve to obtain the global optimal solution, that is, the optimized charging scheduling strategy.

[0100] Genetic algorithm steps:

[0101] 1. Initialization: Generate an initial population, where each individual in the population represents a possible charging scheduling strategy.

[0102] 2. Fitness evaluation: Calculate the fitness value of each individual. The fitness function can be set to optimize the value of the objective function.

[0103] 3. Selection: Select excellent individuals for reproduction based on their fitness values ​​and eliminate individuals with lower fitness.

[0104] 4. Crossover and mutation: Perform crossover and mutation operations on the selected individuals to generate new offspring individuals.

[0105] 5. Update the population: Replace parent individuals with offspring individuals to form a new population.

[0106] 6. Iteration: Repeat steps 2 to 5 until the maximum number of iterations is reached or the convergence condition is met, thus obtaining the global optimal solution.

[0107] Through iterative optimization of genetic algorithms, a charging scheduling strategy that meets user needs and optimizes grid load can be ultimately generated.

[0108] The central control system also includes a feedback learning unit, which is used to collect and analyze user feedback and charging station operation data, and continuously optimize the charging scheduling strategy through machine learning algorithms:

[0109] The feedback learning unit optimizes the parameter settings and optimization algorithms in the central control system by analyzing historical charging data, user feedback, and charging site operation data, improves the adaptability of the central control system in different scenarios, generates new feedback data, and transmits the feedback data to the central control system. After receiving the new feedback data, the central control system automatically adjusts the charging scheduling strategy and generates a charging feedback strategy. Under the mechanism of this feedback learning unit operation, the central control system can transmit the charging feedback strategy to the charging piles of each charging site through the communication network to further optimize and adjust the charging power and charging time of the charging piles; gradually improve the accuracy of the charging feedback strategy and user satisfaction, ensure that the central control system is always in the best operating state, and has the ability to self-improve;

[0110] Among them, historical charging data includes:

[0111] Total grid load data: It is the total power consumption data of the entire grid in different time periods, including daily, weekly, monthly and annual load data. It can reflect the overall load trend and periodic fluctuations of the grid.

[0112] Peak and valley load data: refers to the maximum and minimum load values ​​of the power grid in different time periods (such as the morning peak, evening peak and night valley in a day). It can help identify the peak load period and valley load period of the power grid, thereby optimizing the charging strategy.

[0113] Time-of-day load data: It is the load change data of the power grid at different time intervals (such as every minute, every minute or every hour). It is very useful for analyzing load fluctuations in a short period of time and helps to refine the load forecasting model.

[0114] Regional load data: It is the charging load data of different regions in the power grid, usually including the load conditions in urban areas, industrial areas and rural areas. The power demand and load characteristics of different regions may vary significantly, and regional load data can provide more detailed load forecasts.

[0115] Seasonal load data: It is the load variation data in different seasons (such as winter and summer). Seasonal load reflects the change of grid load under different climate conditions, such as the load peak caused by heating demand in winter or cooling demand in summer.

[0116] Special event load data: It is the grid load data during special events (such as holidays, large-scale events or natural disasters). It can help predict the abnormal fluctuations in grid load that may occur when similar events occur.

[0117] Electricity price and load relationship data: It is the load data at different electricity price levels, which is used to analyze the relationship between electricity price and grid load. It is very important for load management strategies based on price signals.

[0118] User behavior data: refers to the electricity consumption behavior data of users in different periods of time, such as the daily electricity consumption patterns of household users and the production electricity consumption patterns of industrial users. It can reflect the electricity consumption habits and preferences of users and help predict future grid loads.

[0119] These historical charging data can be analyzed through time series models or machine learning algorithms to provide a reliable basis for grid load forecasting and charging strategy formulation, thereby achieving effective management and optimization of grid load.

[0120] The central control system further includes a real-time dynamic scheduling unit, a distributed processing unit and a multi-objective optimization unit:

[0121] The real-time dynamic dispatching unit supports dynamic adjustment of charging dispatching strategies based on real-time updated grid monitoring data and charging demand information, and generates corresponding dynamic charging dispatching strategies to adapt to dynamic changes in grid load and user demand;

[0122] The distributed processing unit realizes distributed processing and scheduling optimization of data through cloud computing, and improves the response speed and fault tolerance of the central control system;

[0123] The multi-objective optimization unit is used to comprehensively consider the grid load balance, user charging costs, and carbon emissions, and generate the optimal multiple charging scheduling strategy that meets multiple requirements.

[0124] The charging station control module includes a charging power adjustment unit, an adaptive control unit and a charging process monitoring unit:

[0125] The charging power adjustment unit dynamically adjusts the charging power output of the charging pile according to the charging scheduling strategy issued by the central control system, ensuring that the charging power output is reduced when the grid load is high, and the charging power output is increased when the grid load is low;

[0126] The adaptive control unit is used to autonomously adjust the charging power and charging time according to the actual grid load, user demand and charging scheduling strategy to cope with instantaneous changes;

[0127] The charging process monitoring unit monitors the voltage parameters, current parameters and power parameters during the charging process in real time, detects and handles abnormal conditions during the charging process, and ensures the safety and stability of the charging process.

[0128] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. A battery swap vehicle charging strategy management system based on power grid optimization, characterized in that: It includes power grid monitoring module, user demand collection module, central control system and charging station control module, among which: Grid monitoring module: used to collect grid monitoring data in real time and transmit the grid monitoring data to the central control system; User demand collection module: used to collect users' charging demand information and upload the charging demand information to the central control system; Central control system: Based on the grid monitoring data and charging demand information, it generates charging scheduling strategies using optimization algorithms and sends the charging scheduling strategies to each charging station through the communication network; Charging site control module: used to receive the charging scheduling strategy issued by the central control system, and control the charging piles in the charging site according to the charging scheduling strategy, and adjust the charging power and charging time of the charging piles; The power grid monitoring module includes a data preprocessing unit, a load prediction unit and an anomaly detection unit: The data preprocessing unit is used to clean, denoise and convert the format of the collected power grid monitoring data; The load forecasting unit uses the grid load forecasting model to forecast the grid load in the future based on the historical charging data and the currently collected grid monitoring data, generates the future charging load, and guides the central control system to formulate a charging scheduling strategy; The anomaly detection unit analyzes the power grid monitoring data in real time, identifies abnormal conditions during the operation of the power grid, and promptly issues an alarm to the central control system; The user demand collection module includes a mobile application interface, an intelligent demand prediction unit and a preference setting unit: The mobile application interface is used to communicate with the user's mobile device, the user inputs his charging demand through the mobile device, and the charging demand of the user is generated into charging demand information via the mobile device; The intelligent demand prediction unit uses data mining technology to predict the user's future charging needs based on the user's historical charging data and behavior patterns, including the expected charging time period and charging amount required; The preference setting unit is used for users to customize charging preferences, and the central control system optimizes the charging scheduling strategy according to the charging preferences; The central control system includes an optimization algorithm module and a strategy generation module: The optimization algorithm module integrates a variety of optimization algorithms, including genetic algorithm, particle swarm optimization algorithm, linear programming algorithm and dynamic programming algorithm. The optimization algorithm module is used to generate optimized calculation results based on the optimization algorithm according to different power grid loads and user needs; The strategy generation module generates a basic charging strategy based on the calculation results of the optimization algorithm module, and sends the basic charging strategy to each charging station through the communication network; The central control system includes a user demand response model, which is used to adjust the charging scheduling strategy according to the dynamic changes of power grid monitoring data and charging demand information; wherein, the user demand response model is constructed as follows: Collect charging demand information related to user charging behavior and pre-process the charging demand information: Data cleaning: remove missing values, outliers and noise data in charging demand information; Data standardization: convert charging demand information of different scales into the same scale and generate raw data; Feature extraction: extracting features from raw data that are helpful for predicting user demand response models; According to different application scenarios and requirements, select the corresponding prediction model to build a user demand response model: Time series model, used to predict users’ future charging behavior; Autoregressive moving average model: used for linear time series forecasting to capture seasonal and trend changes in users’ charging behavior; Long short-term memory artificial neural network model, a neural network model for processing long-term series dependencies: used to capture complex patterns in users' charging behavior; Regression model is used to predict the user's charging amount and the intensity of charging demand: Linear regression model: used to predict continuous variables such as charging capacity; Polynomial regression model: used to capture complex user behavior patterns: charging needs; Classification model, used to classify users' charging needs: Logistic regression model: used to predict whether the user will charge during a certain period of time; Decision tree model: used to generate rules to classify users’ charging needs; Select the corresponding prediction model to be used in combination to generate the model to be formed, and train the model to be formed with the collected historical charging data: use the training data set to train the model to be formed; use the validation data set to evaluate the performance of the model to be formed; use the test data set to conduct the final test on the model to be formed; Optimize the model to be formed: adjust the hyperparameters of the model to be formed through grid search; integrate the above multiple prediction models; combine the future charging demand generated by the intelligent demand prediction unit, continuously optimize the model to be formed, and generate a user demand response model; Finally, the trained user demand response model is deployed in the central control system to predict the user's charging demand in real time, and the prediction results are input into the central control system to generate an adjusted charging demand strategy; The user demand response model also collects the user's charging demand information and grid monitoring data in real time, and uses the response mechanism to dynamically adjust the charging power of the charging pile; the response mechanism includes: Price incentives: When the grid load is high, the central control system guides users to charge during low-load periods by raising electricity prices; when the grid load is low, it lowers electricity prices to attract users to charge. Power regulation: The central control system monitors the grid load in real time. When the grid load is too high, it automatically reduces the charging power of some vehicles. When the grid load is low, it automatically increases the charging power of some vehicles.

2. According to the power grid optimization-based battery swap vehicle charging strategy management system of claim 1, it is characterized by: The central control system includes a power grid load prediction model and a charging scheduling optimization model: The grid load forecasting model is based on time series analysis and uses the future charging load generated by the load forecasting unit to forecast. The forecasting formula includes an autoregressive moving average model, and the forecast results are used to formulate a preliminary dispatch plan. The charging scheduling optimization model is based on linear programming to formulate a reasonable charging scheduling strategy: the charging scheduling optimization model takes the grid load and user demand as the objective function, generates an intermediate scheduling plan, and then uses a genetic algorithm based on the charging demand strategy, charging basic strategy, preliminary scheduling plan and intermediate scheduling plan to obtain the global optimal solution, that is, the optimized charging scheduling strategy.

3. According to claim 2, a battery-swap vehicle charging strategy management system based on power grid optimization is characterized in that: The central control system also includes a feedback learning unit for collecting and analyzing user feedback and charging station operation data: The feedback learning unit optimizes the parameter settings and optimization algorithms in the central control system by analyzing historical charging data, user feedback, and charging site operation data, generates new feedback data, and transmits the feedback data to the central control system. After receiving the new feedback data, the central control system automatically adjusts the charging scheduling strategy and generates a charging feedback strategy.

4. According to claim 3, a battery-swap vehicle charging strategy management system based on power grid optimization is characterized in that: The central control system further includes a real-time dynamic scheduling unit, a distributed processing unit and a multi-objective optimization unit: The real-time dynamic scheduling unit supports dynamic adjustment of charging scheduling strategies based on real-time updated grid monitoring data and charging demand information, and generates corresponding dynamic charging scheduling strategies; The distributed processing unit realizes distributed processing and scheduling optimization of data through cloud computing, and improves the response speed and fault tolerance of the central control system; The multi-objective optimization unit is used to comprehensively consider the grid load balance, user charging costs, and carbon emissions, and generate the optimal multiple charging scheduling strategy that meets multiple requirements.

5. According to claim 4, a battery-swap vehicle charging strategy management system based on power grid optimization is characterized in that: The charging station control module includes a charging power adjustment unit, an adaptive control unit and a charging process monitoring unit: The charging power adjustment unit dynamically adjusts the charging power output of the charging pile according to the charging scheduling strategy issued by the central control system, ensuring that the charging power output is reduced when the grid load is high, and the charging power output is increased when the grid load is low; The adaptive control unit is used to autonomously adjust the charging power and charging time according to the actual grid load, user demand and charging scheduling strategy; The charging process monitoring unit monitors the voltage parameters, current parameters and power parameters during the charging process in real time, and detects and handles abnormal conditions during the charging process.

Images