Large-scale charging load power coordination control method, system, device and medium

Abstract

The present application relates to the technical field of load power control, and discloses a large-scale charging load power coordination control method, system, device and medium, the method comprising: collecting power grid real-time operation data and load operation parameters, grouping the charging equipment according to the power grid real-time operation data and the load operation parameters to obtain a charging load cluster; analyzing the load power set value of the charging load cluster according to the power grid real-time power balance demand information of the power grid real-time operation data and the load operation parameters; analyzing the load power of the charging load cluster based on the load power set value to obtain a power adjustment value; predicting the load power of the charging load cluster according to the power adjustment value to generate a load power prediction curve; and adjusting the load power of the charging equipment according to the load operation priority and the load power prediction curve by the power grid dispatching center. The present application can improve the accuracy and efficiency of large-scale charging load power coordination control.

Description

Technical Field

[0001] This invention relates to the field of load power control technology, and in particular to a method, system, device and medium for coordinated control of large-scale charging load power. Background Technology

[0002] With the booming development of the electric vehicle industry and the widespread deployment of large-scale charging facilities, the proportion of charging load in the power grid is gradually increasing. While facilitating travel, this also brings challenges to power grid operation and management. One key challenge is the randomness and uncertainty of charging behavior; different users have significantly different charging needs at different times, leading to uneven distribution of charging load in time and space. For example, during off-peak electricity consumption periods in residential areas at night, a large number of electric vehicles charging simultaneously can cause a sharp increase in the local power grid load, seriously threatening residents' charging safety.

[0003] Currently, most methods for controlling charging load are relatively simple and crude. Some methods only make unified scheduling based on the overall load of the power grid without fully considering the individual differences and operating characteristics of different charging devices. This one-size-fits-all control approach may cause some charging devices to fail to meet basic charging needs, prolong charging time, and cause energy waste.

[0004] Meanwhile, when faced with changes in the real-time power balance demand of the power grid, traditional methods cannot quickly and flexibly adjust the load power of charging equipment dynamically. When the power grid experiences power deficit or surplus, the charging power of the charging equipment cannot be increased or decreased in a timely manner according to the actual situation. It is difficult to achieve real-time interactive coordination and control between the charging load and the power grid, and the potential of the charging load as an adjustable load resource cannot be fully utilized, which is not conducive to the optimized operation of the power grid and the efficient use of energy.

[0005] Therefore, improving the accuracy and efficiency of power coordination control for large-scale charging load interactions has become an urgent problem to be solved. Summary of the Invention

[0006] This invention provides a method, system, device, and medium for large-scale charging load power coordination control, the main purpose of which is to solve the problems of insufficient accuracy and low efficiency of large-scale charging load interactive power coordination control.

[0007] In a first aspect, to achieve the above objectives, the present invention provides a method for coordinated control of large-scale charging load power, comprising: Collect real-time power grid operation data from the power grid dispatch center and load operation parameters of multiple charging devices. Based on the real-time power grid operation data and the load operation parameters, group the multiple charging devices into equipment clusters to obtain multiple charging load clusters. Extract the real-time power balance demand information of the power grid from the real-time operation data of the power grid, and analyze the load power setpoint of the charging load cluster based on the real-time power balance demand information of the power grid and the load operation parameters; Based on the load power setpoint, load power analysis is performed on multiple charging load clusters to obtain the power adjustment value of the charging load clusters; Based on the power adjustment value, the total load power of the charging load cluster is predicted, and a load power prediction curve is generated. The operating priority of the charging equipment is extracted from the load operating parameters, and the power grid dispatch center adjusts the load power of the charging equipment according to the operating priority and the load power prediction curve.

[0008] Secondly, the present invention also provides a large-scale charging load power coordination control system, comprising: The device cluster grouping module is used to collect real-time power grid operation data from the power grid dispatch center and load operation parameters of multiple charging devices, and to group the multiple charging devices into multiple charging load clusters based on the real-time power grid operation data and the load operation parameters. The load power setting module is used to extract the real-time power balance demand information of the power grid from the real-time operation data of the power grid, and analyze the load power setting value of the charging load cluster based on the real-time power balance demand information of the power grid and the load operation parameters. The load power analysis module is used to perform load power analysis on multiple charging load clusters based on the load power setpoint, and obtain the power adjustment value of the charging load cluster; The load power prediction module is used to predict the total load power of the charging load cluster based on the power adjustment value and generate a load power prediction curve. The load power adjustment module is used to extract the operating priority of the charging equipment from the load operating parameters, and use the power grid dispatch center to adjust the load power of the charging equipment according to the operating priority and the load power prediction curve.

[0009] Thirdly, the present invention also provides an electronic device, the electronic device comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the large-scale charging load power coordination control method described above.

[0010] Fourthly, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the above-described method for coordinated control of large-scale charging load power.

[0011] In this embodiment of the invention, by processing massive heterogeneous data from the power grid and charging stations in real time and using streaming computing and clustering algorithms for dynamic grouping, dispersed charging devices are aggregated into a coordinateably controllable load cluster. This not only significantly improves the utilization efficiency of computing resources and achieves load balancing and optimized control, but also, by analyzing the power grid power balance demand and integrating the real-time operating parameters of the charging load clusters, the optimal load power setpoint for each cluster can be dynamically calculated using optimization algorithms. This enables refined and automated regulation of distributed charging resources, significantly improving the intelligent decision-making level and computational control efficiency of the energy internet. By using the load power setpoint as the adjustment target and efficiently decomposing it into specific power adjustment commands for each charging device through distributed computing or constraint solving algorithms, this process solves the "last mile" problem in the collaborative control of large-scale heterogeneous devices. This not only ensures the agility and accuracy of the cluster's overall response to power grid demands, but also avoids local overload through optimized allocation algorithms, significantly improving computational decision-making efficiency and robustness.

[0012] Based on predetermined power regulation values, time series forecasting or digital twin models are used to simulate and deduce the future total power change trajectory of the charging load cluster, thereby generating a load power prediction curve. This improves the accuracy and efficiency of load power coordination control for large-scale charging equipment. By introducing the key dimension of operation priority, the macroscopic load prediction curve is transformed into equipment-level control commands with business differentiation. Under the premise of meeting the total power constraints of the power grid, the load adjustment amount can be intelligently allocated according to the preset priority strategy, which not only improves the accuracy of load interaction power coordination control for large-scale charging equipment, but also improves the efficiency of load power coordination control. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a flowchart illustrating a method for coordinated control of large-scale charging load power according to an embodiment of the present invention. Figure 2This is a functional block diagram of a large-scale charging load power coordination control system provided in an embodiment of the present invention.

[0015] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0016] To enable those skilled in the art to better understand the technical solutions of this disclosure, and to fully understand and implement the process of how this disclosure applies technical means to solve technical problems and achieve corresponding technical effects, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, not all embodiments. The embodiments of this disclosure and the various features within them can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort should fall within the protection scope of this disclosure.

[0017] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0018] This application provides a method for coordinated control of large-scale charging load power. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the system provided in this application: a server, a terminal, etc. In other words, the method for coordinated control of large-scale charging load power can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0019] Reference Figure 1 The diagram shown is a flowchart illustrating a large-scale charging load power coordination control method according to an embodiment of the present invention. In this embodiment, the large-scale charging load power coordination control method includes: S1. Collect real-time power grid operation data from the power grid dispatch center and load operation parameters of multiple charging devices. Based on the real-time power grid operation data and the load operation parameters, group the multiple charging devices into equipment clusters to obtain multiple charging load clusters.

[0020] In this embodiment of the invention, the power grid dispatch center refers to a system responsible for guiding and coordinating the operation of the power grid, and for real-time monitoring, dispatching and managing the power grid to ensure its safe, stable and economical operation. The real-time operation data of the power grid refers to various data information reflecting the actual operating status of the power grid at the current moment, including but not limited to parameters such as voltage, current, frequency and power. These data can reflect the power grid's power supply capacity, load conditions and other operating characteristics in real time. The load operation parameters refer to relevant parameters describing the load conditions undertaken by the charging equipment during operation, such as charging power, charging current, charging time, and charged amount. These parameters reflect the working status and power demand of the charging equipment.

[0021] In this embodiment of the invention, the step of grouping multiple charging devices into multiple charging load clusters based on the real-time operation data of the power grid and the load operation parameters includes: The real-time power grid operation data and the load operation parameters are respectively subjected to data standardization and cleaning processing to obtain corresponding standard power grid operation data and standard load operation parameters; Extract the grid load characteristics from the standard grid operation data, and extract the charging load characteristics from the standard load operation parameters; Analyze the load characteristic similarity between the power grid load characteristics and the charging load characteristics, and determine the equipment similarity between each of the charging devices based on the load characteristic similarity; Based on the device similarity, multiple charging devices are clustered into groups to obtain multiple charging load clusters.

[0022] In this embodiment of the invention, the data standardization and cleaning process includes data standardization and data cleaning. Data standardization refers to scaling the data proportionally using a normalization method to make it fall into a small, specific interval, such as mapping the data to the [0, 1] interval. This can eliminate the influence of different dimensions between different data, allowing data of different magnitudes to be compared and analyzed on the same scale. Data cleaning refers to checking whether there are missing values ​​in the data. For missing values, various processing methods can be used, such as directly deleting records containing missing values ​​(when the proportion of missing values ​​is small and has little impact on the overall analysis), or filling them with the mean, median, mode, etc. (suitable for numerical data). More complex interpolation methods can also be used according to the distribution and correlation of the data. Secondly, it checks whether there are outliers in the data. Outliers may be caused by data acquisition errors, equipment failures, etc. For outliers, reasonable thresholds can be set for identification, and then corrections or deletions can be made according to the actual situation.

[0023] For real-time power grid operation data and load operation parameters, such as voltage, current, and power, the process begins by checking for missing data at each point. If voltage data is missing at a certain time point, and the missing percentage is small, all relevant data records for that time point can be deleted directly. If there are many missing data points, the average voltage value of adjacent time points can be used to fill the gap. Next, the process checks for voltage anomalies. For example, a reasonable voltage range is set, and data outside this range is considered an anomaly. The causes of anomalies can be analyzed, and if the anomaly is due to a data acquisition error, it can be corrected or deleted. Then, the cleaned voltage, current, and other data are normalized and mapped to the [0, 1] interval to obtain standard power grid operation data and standard load operation parameters.

[0024] In detail, for standard power grid operation data, it is first treated as time series data. In the time domain, the mean, variance, maximum, minimum and other characteristics of data such as voltage, current and power are calculated for each time period. For example, the average voltage is calculated for each hour of the day. These mean values ​​can reflect the average level change of voltage throughout the day. In the frequency domain, Fourier transform is performed on the voltage, current and other data to obtain the spectrum. The dominant frequency and spectral energy are analyzed. The dominant frequency can reflect the fluctuations that may exist in the power grid. Then, a filtering method is used to select features. Based on the correlation score between the features and the power grid load, the features with higher correlation are selected as the power grid load features.

[0025] For standard load operating parameters, time-domain feature extraction is performed first to calculate the mean, variance, peak value, and other features of parameters such as charging power and charging time. For example, the peak power of each charging device during each charge is calculated to reflect the maximum power demand during the charging process. In the frequency domain, if the charging load data shows periodic changes (such as some devices charging intensively during a specific time period), Fourier transform analysis of frequency domain features can also be performed. Then, the wrapping method is used for feature selection, and the feature subset is input into a simple classification or regression model. The optimal charging load features are selected based on the model performance.

[0026] Furthermore, for grid load characteristics and charging load characteristics, such as the grid's average voltage and power variance, and the charging power and charging duration variance of charging equipment, Euclidean distance is first selected as the similarity calculation method. The Euclidean distance between the grid load characteristic vector and the charging load characteristic vector are calculated respectively. For example, the Euclidean distance between the average charging power of a certain charging equipment and the average grid power, and the Euclidean distance between the charging duration variance and the grid power variance are calculated.

[0027] Then, a weighted average method is used to aggregate similarity scores. The weight of each feature is determined based on experience or data analysis. For example, the charging power feature is considered to have a greater impact on equipment similarity, so it is given a higher weight, while the charging duration feature has a relatively lower weight. The similarity scores of each feature are then weighted and averaged to obtain the comprehensive load feature similarity between the grid load feature and the charging load feature.

[0028] Finally, the similarity between charging devices is determined based on load characteristic similarity. If the load characteristics similarity between two charging devices and the power grid are both high, then the similarity between the two charging devices is considered to be high. Conversely, if the load characteristics similarity between the charging devices and the power grid differs greatly, then the similarity between the devices is low.

[0029] In detail, the K-means clustering algorithm is chosen for clustering charging devices. First, the number of clusters K needs to be determined. This can be done using methods such as the elbow rule or the silhouette coefficient. The elbow rule involves plotting the sum of squared errors (SSE) curves within clusters for different K values ​​and finding the K value corresponding to the inflection point of the curve as the optimal number of clusters. The silhouette coefficient is calculated by taking the average silhouette coefficient for different K values ​​and selecting the K value with the largest average silhouette coefficient. After determining the K value, K charging devices are randomly selected as initial cluster centers. Then, the similarity between each charging device and each cluster center is calculated (which can be measured by previously calculated Euclidean distance, etc.). Each charging device is assigned to the cluster with the highest similarity. Next, the center of each cluster (i.e., the feature mean of all charging devices in the cluster) is recalculated, and the charging devices are reassigned to the new cluster centers. This process is repeated until the cluster centers no longer change or the preset number of iterations is reached.

[0030] Finally, the silhouette coefficient is used to evaluate the clustering results. The silhouette coefficient of each charging device is calculated, and then the average silhouette coefficient of all charging devices is calculated. If the average silhouette coefficient is close to 1, it indicates that the clustering effect is good and the resulting multiple charging load clusters have high cohesion and low coupling. If the average silhouette coefficient is low, it is necessary to readjust the clustering algorithm parameters or select other clustering algorithms for optimization.

[0031] In this embodiment of the invention, by processing massive heterogeneous data from the power grid and charging stations in real time and using streaming computing and clustering algorithms for dynamic grouping, the dispersed charging devices are aggregated into a load cluster that can be coordinated and controlled. This not only significantly improves the utilization efficiency of computing resources and achieves load balancing and optimized control, but also enables the charging load cluster to participate in power grid interaction as a flexible resource, providing key technical support for building an efficient and stable energy internet computing platform.

[0032] S2. Extract the real-time power balance demand information of the power grid from the real-time operation data of the power grid, and analyze the load power setpoint of the charging load cluster based on the real-time power balance demand information of the power grid and the load operation parameters.

[0033] In this embodiment of the invention, the real-time power balance demand information of the power grid is extracted from the real-time operation data of the power grid and is used to describe the specific requirements of the power grid for power balance at the current moment. When the power generation is greater than the power consumption, the power grid has a power surplus, and it may be necessary to adjust the output of the power generation equipment or increase the charging power of the energy storage equipment. When the power generation is less than the power consumption, the power grid has a power shortage, and measures need to be taken to increase the power generation or reduce some non-critical loads to provide a basis for subsequent load regulation.

[0034] The load power setpoint is a target power value determined for the charging load cluster based on the real-time power balance demand information of the power grid and the load operation parameters. This setpoint aims to ensure that the power consumption of the charging load cluster can both meet the charging needs of users and match the real-time power balance demand of the power grid.

[0035] In this embodiment of the invention, the extraction of real-time power balance demand information of the power grid employs data mining correlation analysis methods to analyze the correlation between different operating parameters, such as the relationship between voltage fluctuations and power changes, and to identify key factors affecting power balance. Then, using pattern recognition technology, data patterns during normal operation and power imbalance are learned and classified to construct a power balance state model. Real-time data is input into this model, and by comparison, the current power state of the power grid is determined. If a power deviation occurs, trend analysis technology is used to predict the development trend of power imbalance based on historical power change trends and real-time data trends, thereby accurately extracting the real-time power balance demand information of the power grid.

[0036] In this embodiment of the invention, the step of analyzing the load power setpoint of the charging load cluster based on the real-time power balance demand information of the power grid and the load operation parameters includes: Extract the load power operating parameters from the load operating parameters; The initial power setting value of the charging load cluster is determined based on the real-time power balance demand information of the power grid and the load power operation parameters. An environmental analysis was performed on the charging load cluster to obtain multiple environmental impact parameters; The target setting model is obtained by weighting and optimizing the preset cluster load power setting model based on multiple environmental impact parameters. The load power is reset based on the initial power setting value and the target setting model to obtain the load power setting value of the charging load cluster.

[0037] In this embodiment of the invention, data directly related to the charging load power is accurately selected from a massive amount of load operating parameters according to pre-set feature rules. These feature rules may be based on the physical meaning of the parameters, historical correlation, etc., such as identifying parameters such as the real-time power value of the charging equipment and the historical power fluctuation amplitude, to ensure that the extracted load power operating parameters can accurately reflect the actual power status of the charging equipment.

[0038] On the one hand, by analyzing the real-time power balance demand information of the power grid, if the power grid has excess power, it means that the charging load needs to be reduced to maintain balance, and in this case, a lower initial power value is preferred; if the power is insufficient, the initial power setting value should be appropriately increased to meet the power grid demand. On the other hand, based on the extracted load power operating parameters, factors such as the current maximum allowable power of the charging equipment and the historical stable operating power range are considered. Combining these two factors, an initial, relatively reasonable initial power setting value for the charging load cluster is determined through empirical judgment or simple rule logic.

[0039] Furthermore, by rationally deploying various sensors around the charging load cluster, such as temperature sensors, humidity sensors, and light intensity sensors, these sensors monitor environmental data in real time and transmit the collected data to the data processing system. Through the organization and analysis of this raw data, multiple environmental impact parameters are obtained. For example, temperature parameters can reflect the heat dissipation environment of the equipment, humidity parameters may affect the insulation performance of the equipment, and light intensity parameters may also have an indirect impact on the operation of the equipment in certain specific charging scenarios.

[0040] Specifically, the weight optimization algorithm in machine learning is used as the basis for a preset cluster load power setting model, which includes multiple parameters and weights that affect the power setting. Multiple environmental impact parameters are used as input features, and the actual effects of power setting under different environmental conditions in historical data (such as equipment operation stability and impact on the power grid) are used as feedback information. The algorithm continuously adjusts the weights of each parameter in the model so that the model can more accurately reflect the impact of environmental factors on the power setting of the charging load cluster, and finally obtains the optimized target setting model.

[0041] In detail, model calculation and parameter fusion techniques are used to input the determined initial power setpoint into the target setting model. Based on the previously optimized weights, the model comprehensively considers environmental impact parameters and the initial setpoint, and adjusts and corrects the initial power setpoint through internal calculation logic and rules. For example, if the ambient temperature is high, the model may appropriately reduce the power setpoint to ensure the safe operation of the equipment; if the light intensity is suitable, the impact on the power setpoint may be small. Finally, through model calculation and parameter fusion, a charging load cluster load power setpoint that meets the grid balance requirements, conforms to the equipment's operating capacity, and adapts to environmental conditions is obtained.

[0042] In this embodiment of the invention, by analyzing the power balance demand of the power grid and integrating the real-time operating parameters of the charging load clusters, the optimal load power setting value of each cluster can be dynamically calculated using optimization algorithms. This enables refined and automated control of distributed charging resources, significantly improving the intelligent decision-making level and computational control efficiency of the energy internet.

[0043] S3. Based on the load power setting value, perform load power analysis on multiple charging load clusters to obtain the power adjustment value of the charging load cluster.

[0044] In this embodiment of the invention, the load power analysis refers to the process of evaluating and judging the current power usage of each charging load cluster based on the load power setpoint and using specific analysis methods and logic. Through analysis, the difference between the actual power and the setpoint of each charging load cluster can be understood, identifying which clusters have excessively high power and which have excessively low power, as well as the degree of such difference and its possible impact, providing a basis for subsequently determining the power adjustment value.

[0045] In this embodiment of the invention, the step of performing load power analysis on multiple charging load clusters based on the load power setpoint to obtain the power adjustment value of the charging load cluster includes: Calculate the total load power of all the charging load clusters, and calculate the load power deviation of each charging load cluster based on the total load power and the load power setpoint. The power adjustment direction and power adjustment amplitude of the charging load cluster are determined based on the load power deviation. Analyze the power contribution of each of the charging load clusters to the total load power; The power adjustment ratio corresponding to the charging load cluster is analyzed based on the power contribution. The power adjustment value corresponding to the charging load cluster is generated based on the power adjustment direction, the power adjustment amplitude, and the power adjustment ratio.

[0046] In detail, the calculation of the total load power of all the charging load clusters is shown in the following formula:

[0047] in, Indicates total load power. This indicates the total number of charging load clusters. This represents the nth charging load cluster. This represents the nth charging load cluster.

[0048] In detail, the calculation of the load power deviation for each of the charging load clusters is shown in the following formula:

[0049] in, Indicates load power deviation. Indicates total load power. This indicates the load power setting value.

[0050] In this embodiment of the invention, the real-time power data of each charging load cluster is collected by a data acquisition system. The scattered power data are then integrated using a data aggregation method to calculate the total load power of all charging load clusters. Next, based on a preset load power setting value, a difference calculation method is used to subtract the load power setting value from the total load power to obtain the difference between the two. This difference is the load power deviation of each charging load cluster. In this way, the gap between the current overall power of the charging load cluster and the target setting can be intuitively understood.

[0051] In detail, based on the calculated load power deviation, logical judgment rules are applied. If the deviation is positive, it indicates that the total load power is higher than the set value, and the power needs to be reduced, thus determining the adjustment direction as "reduction". If the deviation is negative, it indicates that the total load power is lower than the set value, and the power should be increased, thus determining the adjustment direction as "increase". As for the adjustment range, referring to the adjustment experience under similar deviation conditions in historical data, combined with the current grid stability and the operating characteristics of the charging equipment, a reasonable adjustment range is roughly determined through proportional analysis, thereby clarifying the direction and approximate degree of power adjustment for each charging load cluster.

[0052] Specifically, based on the total load power, the proportion of power of each charging load cluster in the total load power is calculated. This proportion reflects the power contribution of the cluster to the total load. By comparing the power contribution of different clusters, we can clearly understand the degree of influence of each cluster on the overall power, providing an important basis for determining the power adjustment ratio in the future.

[0053] The process involves comprehensively considering factors such as power contribution, the operating status of charging equipment (e.g., current load and remaining charging demand), and the local stability requirements of the power grid. A weighted allocation method is used to assign a corresponding weight to each factor. Then, based on these weights and power contribution, the power adjustment ratio for each charging load cluster is determined through comprehensive analysis and calculation. For example, for clusters with a large power contribution and a light equipment load, the adjustment ratio can be appropriately increased.

[0054] Furthermore, the determined power adjustment direction, power adjustment amplitude, and power adjustment ratio are synthesized; the basic direction and range of adjustment are determined based on the adjustment direction and amplitude, and then combined with the adjustment ratio, the final power adjustment value of each charging load cluster is accurately calculated to achieve precise adjustment of the power of the charging load cluster.

[0055] In this embodiment of the invention, the load power setpoint is used as the adjustment target. Through distributed computing or constraint solving algorithms, it is efficiently decomposed into specific power adjustment instructions for each charging device. This process solves the "last mile" problem in the collaborative control of large-scale heterogeneous devices. It not only ensures the agility and accuracy of the cluster's overall response to the grid demand, but also avoids local overload by optimizing the allocation algorithm, significantly improving the computational decision-making efficiency and robustness of the entire control system.

[0056] S4. Based on the power adjustment value, predict the total load power of the charging load cluster and generate a load power prediction curve.

[0057] In this embodiment of the invention, the load power prediction curve is a curve plotted with time as the horizontal axis and predicted power value as the vertical axis. It can intuitively display the predicted total load power of the charging load cluster at different times. The trend of the curve can clearly show the power change trend over time, such as rising, falling, or fluctuating steadily, which helps relevant personnel to better grasp the dynamic changes of the charging load so as to make reasonable decisions.

[0058] In this embodiment of the invention, the step of predicting the total load power of the charging load cluster based on the power adjustment value and generating a load power prediction curve includes: Based on the power adjustment value, the power of the charging load cluster is simulated and adjusted to obtain the corresponding expected operating power; Based on the expected operating power, the preset load power prediction model is characterized and learned to obtain the target load power prediction model; The target load power prediction model is used to predict the power of the charging load cluster, and the predicted power value at each time point is obtained. Based on the predicted power value, a load power prediction curve for the charging load cluster at the corresponding time point is generated.

[0059] In this embodiment of the invention, a model of a charging load cluster is constructed in a virtual environment. This model includes the characteristic parameters of each charging device and the overall architecture of the cluster. Based on the power adjustment value, a virtual power adjustment operation is performed on the charging load cluster in the simulation system. By simulating the response of each device in the cluster under different power adjustment values, such as device start-up, stop, power increase and decrease, various data such as voltage, current, and power factor are collected and analyzed during the simulation operation to obtain the corresponding expected operating power. This method can predict the cluster operating status after power adjustment in advance without affecting the actual operation of the devices.

[0060] The model is based on a pre-defined load power prediction model, which may contain a multi-layer neural network structure. It takes the expected operating power as input data and automatically mines potential features related to load power prediction in the expected operating power through the feature extraction layer inside the model, such as the trend features and fluctuation features of power changes. During the model training process, the model parameters are continuously adjusted to optimize the model's ability to represent the expected operating power, so that the model can more accurately capture the pattern of power changes and finally obtain the target load power prediction model.

[0061] Furthermore, the current actual operating status information of the charging load cluster, such as the current power and equipment operating time, is input into the target load power prediction model. Based on the previously learned features and patterns, the model infers and calculates the power changes at different future time points. The model will comprehensively consider the influence of historical data, current status, and expected operating power to generate a predicted power value for each time point. These predicted values ​​reflect the power level that the charging load cluster may reach at various future times.

[0062] Specifically, the predicted power values ​​for each time point are collected, and these discrete data points are arranged in chronological order. With time as the horizontal axis and predicted power values ​​as the vertical axis, data visualization tools are used to connect these data points to form a continuous curve. The trend of the curve can intuitively show the load power change trend of the charging load cluster in the future, such as rising, falling, or fluctuating steadily, providing relevant personnel with clear and intuitive power prediction information.

[0063] In this embodiment of the invention, based on a predetermined power adjustment value, time series prediction or digital twin models are used to simulate and deduce the future total power change trajectory of the charging load cluster, thereby generating a load power prediction curve, which improves the accuracy and efficiency of load power coordination control for large-scale charging equipment.

[0064] S5. Extract the operating priority of the charging equipment from the load operating parameters, and use the power grid dispatch center to adjust the load power of the charging equipment according to the operating priority and the load power prediction curve.

[0065] In this embodiment of the invention, the operating priority of the charging equipment is an important indicator set for the charging equipment based on a comprehensive evaluation of multiple factors, including the equipment type of the charging equipment (such as equipment that supplies power to important public facilities may have a higher priority) and the user demand level (such as charging equipment for VIP users having a higher priority than that for ordinary users); the load power adjustment refers to the purposeful change of the power of the charging equipment according to the actual operation and demand of the power grid; when the power grid has excess power, it may be necessary to reduce the power of the charging equipment to reduce the load on the power grid; when the power grid has insufficient power, the power of the charging equipment should be appropriately increased to ensure the normal operation of important equipment.

[0066] The load power adjustment is based on the operation priority and the load power prediction curve. Priority is given to meeting the power demand of charging equipment with high operation priority. At the same time, the timing and magnitude of the power adjustment are reasonably arranged with reference to the prediction curve to ensure the stable operation of the power grid and the orderly charging of charging equipment.

[0067] In this embodiment of the invention, extracting the operating priority of the charging equipment from the load operating parameters includes: Extract charging equipment information from the load operation parameters, perform index analysis on the charging equipment information, and obtain equipment reliability indicators; Based on the equipment reliability indicators, a preliminary priority analysis is performed on the charging equipment to obtain an initial priority. The user behavior information corresponding to the charging device is converted into an indicator to obtain the user behavior urgency indicator. The initial priority is adjusted based on the user behavior urgency index to obtain the operating priority of the charging device.

[0068] In this embodiment of the invention, information related to the charging equipment is accurately located and extracted from the load operation parameters using data filtering and extraction techniques. This information covers multiple aspects such as equipment model, service life, past fault records, and maintenance status. Then, feature analysis methods are used to analyze the impact of each factor on the equipment reliability based on the extracted charging equipment information. For example, equipment with a longer service life may have relatively lower reliability; equipment with frequent past fault records will also have significantly reduced reliability. Through comprehensive consideration and analysis of these factors, an index that can quantitatively reflect the reliability of the charging equipment is finally obtained, namely, the equipment reliability index.

[0069] Based on equipment reliability indicators, different reliability level classification standards are set. For example, the reliability indicators are divided into three levels: high, medium, and low, or more detailed into multiple levels. Then, according to the reliability indicator value of each charging device, it is mapped to the corresponding level.

[0070] Within the same level, devices are further sorted according to certain rules, such as by the importance of the device or the frequency of use. Through this hierarchical evaluation and sorting method, a preliminary priority is determined for each charging device, namely the initial priority. The initial priority mainly reflects the relative importance of the device itself based on reliability.

[0071] Furthermore, user behavior information corresponding to charging devices is collected. This information includes the user's charging reservation time, remaining battery power, and usage scenario (such as whether it is for emergency travel or important events). Then, through information mapping technology, these different types of user behavior information are transformed into quantifiable indicators. For example, a situation with low remaining battery power and an urgent charging reservation time is mapped to a higher urgency value; while for users with sufficient remaining battery power and no urgent need for use, a lower urgency value is mapped. Through this quantitative assessment, user behavior information is transformed into user behavior urgency indicators that can intuitively reflect the urgency level of user behavior.

[0072] Specifically, a weighted adjustment and comprehensive decision-making technique is used to set the weights of user behavior urgency indicators and initial priorities in the final operation priority determination process. Considering that the urgency of user behavior may have a significant impact on actual use, a certain weight is given to the user behavior urgency indicators. Then, based on the value of the user behavior urgency indicators, the initial priority is adjusted according to the set weights.

[0073] If the user behavior urgency index is high, it means that the user's current need is more urgent, so the priority of the charging device will be appropriately increased during the adjustment; conversely, if the user behavior urgency index is low, its priority may be reduced or the initial priority may remain unchanged. Through this weight adjustment and comprehensive decision-making method, the final operating priority of the charging device is obtained by comprehensively considering the device reliability and the urgency of the user behavior.

[0074] In this embodiment of the invention, the step of adjusting the load power of the charging equipment using the power grid dispatch center based on the operating priority and the load power prediction curve includes: A load power allocation strategy corresponding to the charging equipment is generated based on the operating priority and the load power prediction curve. Multiple operational constraints of the charging device are extracted, and the load power allocation strategy is optimized based on the multiple operational constraints to obtain the target power allocation strategy; Generate a corresponding power adjustment command based on the target power allocation strategy; The power grid dispatch center adjusts the load power of the charging equipment according to the power adjustment command.

[0075] In this embodiment of the invention, the power grid dispatch center first receives the operation priority and load power prediction curve data of the charging equipment. The operation priority reflects the order in which the charging equipment is allocated resources, while the load power prediction curve shows the power demand trend of the charging equipment in the future. Based on this information, combined with the overall operation of the power grid (such as the current remaining power capacity of the power grid, the power demand of other electrical equipment, etc.), the power grid dispatch center adopts a comprehensive decision-making method.

[0076] This decision-making method comprehensively considers multiple factors, such as prioritizing the power demands of high-priority devices while ensuring that power changes reflected in the load power forecast curve do not impact the power grid. Through this comprehensive analysis and trade-off, a reasonable load power allocation strategy is developed for each charging device, clarifying the amount of power each device should be allocated in different time periods.

[0077] The process involves extracting multiple operational constraints from data related to charging equipment. These constraints may include the equipment's own power limits, voltage stability range, charging efficiency requirements, as well as grid-side power balance constraints and voltage fluctuation limits. These constraints are then used as input to optimize the previously generated load power allocation strategy. The optimization algorithm adjusts and improves the strategy while satisfying all constraints. For example, if a device's power allocation according to the initial strategy exceeds its power limit, the algorithm automatically reduces that device's power allocation value. Simultaneously, to ensure grid power balance, the algorithm adjusts the power allocation for other devices accordingly. Through continuous iteration and optimization, a target power allocation strategy that satisfies all operational constraints and allocates power reasonably is ultimately obtained.

[0078] Furthermore, based on the target power allocation strategy, the power allocation value of each charging device at different time points is encoded. The encoding process converts information such as power values ​​into a specific instruction format that can be recognized and executed by the power grid dispatch center and the charging devices. At the same time, other information related to power adjustment, such as adjustment time and adjustment method (e.g., slow or fast adjustment), is also integrated into the instruction. Through information conversion technology, it is ensured that this information can be accurately received and understood by the charging devices, thereby generating the corresponding power adjustment instruction.

[0079] Specifically, the power grid dispatch center sends the generated power adjustment command to the corresponding charging equipment through a pre-established communication network. The communication network can be a dedicated power communication line or a wireless communication network to ensure that the command can be transmitted to the equipment in a timely and accurate manner. After receiving the command, the charging equipment's internal control system will parse the command and adjust its own power according to the command requirements.

[0080] During the adjustment process, the charging equipment will monitor its own operating status and power changes in real time and send feedback information back to the power grid dispatch center. The dispatch center will monitor and evaluate the adjustment of the equipment based on the feedback information to ensure that the power adjustment achieves the expected target, thereby realizing the effective adjustment of the load power of the charging equipment.

[0081] In this embodiment of the invention, by introducing the key dimension of operation priority, the macroscopic load forecast curve is transformed into equipment-level control commands with business differentiation. Under the premise of meeting the total power constraint of the power grid, the load adjustment amount can be intelligently allocated according to the preset priority strategy. This not only improves the accuracy of load interaction power coordination control of large-scale charging equipment, but also improves the efficiency of load power coordination control.

[0082] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0083] like Figure 2 The diagram shown is a functional block diagram of a large-scale charging load power coordination control system provided in an embodiment of the present invention.

[0084] This disclosure provides a large-scale charging load power coordination control system, which corresponds one-to-one with the large-scale charging load power coordination control method described in the previous embodiment. For example... Figure 2 As shown, this large-scale charging load power coordination control system 100 can be installed in electronic devices. According to its functions, the large-scale charging load power coordination control system 100 includes an equipment cluster grouping module 101, a load power setting module 102, a load power analysis module 103, a load power prediction module 104, and a load power adjustment module 105. Detailed descriptions of each functional module are as follows: The device cluster grouping module 101 is used to collect real-time power grid operation data from the power grid dispatch center and load operation parameters of multiple charging devices, and to group the multiple charging devices into multiple charging load clusters based on the real-time power grid operation data and the load operation parameters. The load power setting module 102 is used to extract the real-time power balance demand information of the power grid from the real-time operation data of the power grid, and analyze the load power setting value of the charging load cluster based on the real-time power balance demand information of the power grid and the load operation parameters. The load power analysis module 103 is used to perform load power analysis on multiple charging load clusters based on the load power setpoint, and obtain the power adjustment value of the charging load cluster; The load power prediction module 104 is used to predict the total load power of the charging load cluster based on the power adjustment value and generate a load power prediction curve. The load power adjustment module 105 is used to extract the operating priority of the charging equipment from the load operating parameters, and use the power grid dispatch center to adjust the load power of the charging equipment according to the operating priority and the load power prediction curve.

[0085] In one embodiment, when the device cluster grouping module 101 performs device cluster grouping of multiple charging devices according to the real-time power grid operation data and the load operation parameters to obtain multiple charging load clusters, it is used to: The real-time power grid operation data and the load operation parameters are respectively subjected to data standardization and cleaning processing to obtain corresponding standard power grid operation data and standard load operation parameters; Extract the grid load characteristics from the standard grid operation data, and extract the charging load characteristics from the standard load operation parameters; Analyze the load characteristic similarity between the power grid load characteristics and the charging load characteristics, and determine the equipment similarity between each of the charging devices based on the load characteristic similarity; Based on the device similarity, multiple charging devices are clustered into groups to obtain multiple charging load clusters.

[0086] In one embodiment, when the load power setting module 102 performs analysis of the load power setting value of the charging load cluster based on the real-time power balance demand information of the power grid and the load operating parameters, it is used to: Extract the load power operating parameters from the load operating parameters; The initial power setting value of the charging load cluster is determined based on the real-time power balance demand information of the power grid and the load power operation parameters. An environmental analysis was performed on the charging load cluster to obtain multiple environmental impact parameters; The target setting model is obtained by weighting and optimizing the preset cluster load power setting model based on multiple environmental impact parameters. The load power is reset based on the initial power setting value and the target setting model to obtain the load power setting value of the charging load cluster.

[0087] In one embodiment, when the load power analysis module 103 performs load power analysis on multiple charging load clusters based on the load power setpoint to obtain the power adjustment value of the charging load cluster, it is used to: Calculate the total load power of all the charging load clusters, and calculate the load power deviation of each charging load cluster based on the total load power and the load power setpoint. The power adjustment direction and power adjustment amplitude of the charging load cluster are determined based on the load power deviation. Analyze the power contribution of each of the charging load clusters to the total load power; The power adjustment ratio corresponding to the charging load cluster is analyzed based on the power contribution. The power adjustment value corresponding to the charging load cluster is generated based on the power adjustment direction, the power adjustment amplitude, and the power adjustment ratio.

[0088] In one embodiment, when the load power prediction module 104 performs total load power prediction on the charging load cluster based on the power adjustment value and generates a load power prediction curve, it is used to: Based on the power adjustment value, the power of the charging load cluster is simulated and adjusted to obtain the corresponding expected operating power; Based on the expected operating power, the preset load power prediction model is characterized and learned to obtain the target load power prediction model; The target load power prediction model is used to predict the power of the charging load cluster, and the predicted power value at each time point is obtained. Based on the predicted power value, a load power prediction curve for the charging load cluster at the corresponding time point is generated.

[0089] In one embodiment, when the load power adjustment module 105 extracts the operating priority of the charging device from the load operating parameters, it is used to: Extract charging equipment information from the load operation parameters, perform index analysis on the charging equipment information, and obtain equipment reliability indicators; Based on the equipment reliability indicators, a preliminary priority analysis is performed on the charging equipment to obtain an initial priority. The user behavior information corresponding to the charging device is converted into an indicator to obtain the user behavior urgency indicator. The initial priority is adjusted based on the user behavior urgency index to obtain the operating priority of the charging device.

[0090] In one embodiment, when the load power adjustment module 105 performs load power adjustment on the charging equipment using the power grid dispatch center based on the operating priority and the load power prediction curve, it is configured to: A load power allocation strategy corresponding to the charging equipment is generated based on the operating priority and the load power prediction curve. Multiple operational constraints of the charging device are extracted, and the load power allocation strategy is optimized based on the multiple operational constraints to obtain the target power allocation strategy; Generate a corresponding power adjustment command based on the target power allocation strategy; The power grid dispatch center adjusts the load power of the charging equipment according to the power adjustment command.

[0091] In this invention, the specific limitations of a large-scale charging load power coordination control system can be found in the above-described limitations of a large-scale charging load power coordination control method, and will not be repeated here. Each module in the aforementioned large-scale charging load power coordination control system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0092] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: Collect real-time power grid operation data from the power grid dispatch center and load operation parameters of multiple charging devices. Based on the real-time power grid operation data and the load operation parameters, group the multiple charging devices into equipment clusters to obtain multiple charging load clusters. Extract the real-time power balance demand information of the power grid from the real-time operation data of the power grid, and analyze the load power setpoint of the charging load cluster based on the real-time power balance demand information of the power grid and the load operation parameters; Based on the load power setpoint, load power analysis is performed on multiple charging load clusters to obtain the power adjustment value of the charging load clusters; Based on the power adjustment value, the total load power of the charging load cluster is predicted, and a load power prediction curve is generated. The operating priority of the charging equipment is extracted from the load operating parameters, and the power grid dispatch center adjusts the load power of the charging equipment according to the operating priority and the load power prediction curve.

[0093] In the embodiments provided by this invention, it should be understood that the disclosed devices and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0094] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0095] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0096] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0097] In some embodiments of this example, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps of the method described in the above embodiments.

[0098] The readable storage medium of the present invention stores a computer program, which, when executed by a processor of an electronic device, can perform the following: Collect real-time power grid operation data from the power grid dispatch center and load operation parameters of multiple charging devices. Based on the real-time power grid operation data and the load operation parameters, group the multiple charging devices into equipment clusters to obtain multiple charging load clusters. Extract the real-time power balance demand information of the power grid from the real-time operation data of the power grid, and analyze the load power setpoint of the charging load cluster based on the real-time power balance demand information of the power grid and the load operation parameters; Based on the load power setpoint, load power analysis is performed on multiple charging load clusters to obtain the power adjustment value of the charging load clusters; Based on the power adjustment value, the total load power of the charging load cluster is predicted, and a load power prediction curve is generated. The operating priority of the charging equipment is extracted from the load operating parameters, and the power grid dispatch center adjusts the load power of the charging equipment according to the operating priority and the load power prediction curve.

[0099] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0100] Computer-readable storage media may also store at least one computer-executable program / instruction, such as computer-readable instructions. Computer-readable storage media include, but are not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Computer-readable storage media may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device executes the computer-readable instructions stored on the computer-readable storage medium, the various methods described above can be performed.

[0101] In addition, the computer device may include (but is not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (e.g., keyboard, mouse, speakers, etc.).

[0102] The processor can communicate with external devices via the I / O bus through wired or wireless networks.

[0103] In one embodiment, the at least one computer-executable instruction may also be compiled into or comprise a software product / computer program product, wherein one or more computer-executable instructions are executed by a processor to perform the steps of the various functions and / or methods in the embodiments described herein.

[0104] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0105] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0106] In the embodiments provided in this disclosure, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0107] It should be noted that, in this disclosure, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element limited by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0108] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for coordinated control of power for large-scale charging loads, characterized in that, The method includes: Collect real-time power grid operation data and charging equipment load operation parameters, and group the charging equipment into clusters based on the data to obtain charging load clusters; extract real-time power balance demand information of the power grid, and analyze the load power setpoints in combination with load operation parameters; analyze the power adjustment value of the charging load clusters based on the setpoints; predict the total load power based on the power adjustment value and generate a load power prediction curve; extract the operating priority of the charging equipment, and adjust the load power according to the priority and the prediction curve.

2. The large-scale charging load power coordination control method as described in claim 1, characterized in that, The process of grouping charging devices into clusters includes: Collect first data and perform standardization processing. The first data includes real-time power grid operation data and charging equipment load operation parameters. Extract grid load characteristics and charging load characteristics from the processed data; Analyze the similarity between the power grid load characteristics and the charging load characteristics to determine the equipment similarity between each charging device; Multiple charging devices are clustered and grouped according to their similarity to obtain multiple charging load clusters.

3. The large-scale charging load power coordination control method as described in claim 1, characterized in that, The extraction of real-time power balance demand information from the power grid, combined with analysis of load power setpoints using load operation parameters, includes: Extract the load power operating parameters from the load operating parameters; Based on the real-time power balance demand information of the power grid and the load power operation parameters, the initial power setpoint of the charging load cluster is determined; An environmental analysis was performed on the charging load cluster to obtain multiple environmental impact parameters; The target setting model is obtained by optimizing the preset cluster load power setting model based on environmental impact parameters. The load power is reset based on the initial power setting value and the target setting model to obtain the load power setting value of the charging load cluster.

4. The large-scale charging load power coordination control method as described in claim 1, characterized in that, The power regulation value of the charging load cluster analyzed based on the set value includes: Calculate the total load power of the charging load cluster; Calculate the load power deviation of each charging load cluster based on the total load power and the load power setpoint. The direction and magnitude of power regulation are determined based on the load power deviation. Analyze the power contribution of each charging load cluster to the total load power; The adjustment ratio is determined based on the power contribution. The adjustment ratio is determined based on the power contribution, and the power adjustment value is generated by combining the adjustment direction and amplitude.

5. The large-scale charging load power coordination control method as described in claim 1, characterized in that, The step of predicting the total load power based on the power regulation value and generating a load power prediction curve includes: Based on the power regulation value, the power of the charging load cluster is simulated and adjusted to obtain the expected operating power. The target prediction model is obtained by training the load power prediction model based on the expected operating power; The target prediction model is used to predict the power values ​​at each time point, generating a load power prediction curve.

6. The large-scale charging load power coordination control method as described in claim 1, characterized in that, The operating priority of the extraction charging device includes: Extract charging equipment information and analyze it to obtain equipment reliability indicators; Determine the initial priority based on the aforementioned equipment reliability indicators; Transform user behavior information into user behavior urgency indicators; The initial priority is adjusted based on the user behavior urgency index to obtain the running priority.

7. The large-scale charging load power coordination control method as described in claim 1, characterized in that, The adjustment of load power based on priority and forecast curve includes: A load power allocation strategy is generated based on the operation priority and load power prediction curve; Extract the operating constraints of the charging equipment, optimize the allocation strategy based on the constraints, and obtain the target power allocation strategy; Power adjustment instructions are generated according to the target power allocation strategy, and the power grid dispatch center executes the instructions to adjust the load power of the charging equipment.

8. A large-scale charging load power coordination control system, characterized in that, The system includes: The equipment cluster grouping module is used to collect real-time power grid operation data and charging equipment load operation parameters, and to group the charging equipment into clusters based on the data to obtain charging load clusters. The load power setting module is used to extract real-time power balance demand information of the power grid and analyze the load power setting value in combination with load operating parameters; The load power analysis module is used to analyze the power regulation value of the charging load cluster based on the set value; The load power prediction module is used to predict the total load power based on the power adjustment value and generate a load power prediction curve. The load power adjustment module is used to extract the operating priority of the charging equipment and adjust the load power according to the priority and the prediction curve.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a large-scale charging load power coordination control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements a large-scale charging load power coordination control method as described in any one of claims 1 to 7.

Images