Community intelligent charging control method and system based on optical storage and direct flexible

Abstract

The present application relates to community charging control technical field, a kind of community intelligent charging control method and system based on light storage direct flexible, comprising: based on community electric vehicle set carries out charging prediction model construction, obtains charging window prediction model, utilizes charging window prediction model and target charging date to carry out charging prediction to community electric vehicle set, obtains predicted charging window set, based on predicted charging window set, target charging time period carries out power scheduling to light storage direct flexible system, obtains charging scheduling strategy, utilizes charging scheduling strategy to carry out charging power scheduling to multiple original automobile charging piles, obtains multiple intelligent automobile charging piles, according to multiple intelligent automobile charging piles carries out charging regulation, obtains charging car.The present application can improve the accuracy of community charging control and energy utilization efficiency, reduce the dependence on traditional power grid.

Description

Technical Field

[0001] This invention relates to the field of community charging control technology, and in particular to a community smart charging control method and system based on photovoltaic-storage-DC-flexible technology. Background Technology

[0002] With the rapid popularization of electric vehicles in communities, the demand for community charging is becoming increasingly large-scale and centralized. Effective charging control is of great significance for balancing grid load, improving user charging experience, and promoting the localization and clean transformation of community energy.

[0003] Traditional technologies typically employ charging scheduling strategies based on fixed time or simple thresholds. These strategies suffer from drawbacks such as insufficient accuracy in predicting charging demand, inability to match fluctuations in renewable energy generation, and rigid power allocation of charging piles, which can easily lead to grid disruptions or waste of clean energy. Summary of the Invention

[0004] This invention provides a community smart charging control method based on photovoltaic-storage-DC-flexible technology and a computer-readable storage medium. Its main purpose is to improve the accuracy of community charging control and energy utilization efficiency, and reduce dependence on the traditional power grid.

[0005] To achieve the above objectives, the present invention provides a community smart charging control method based on photovoltaic-storage-direct-drive-flexible technology, comprising:

[0006] Identify community electric vehicle clusters and multiple original car charging stations, wherein the community electric vehicle clusters include multiple community electric vehicles;

[0007] A charging prediction model is constructed based on a community electric vehicle dataset to obtain a charging window prediction model.

[0008] Receive intelligent charging control commands, determine the target charging date based on the intelligent charging control commands, and use the charging window prediction model and the target charging date to predict the charging of the community electric vehicle set, thereby obtaining the predicted charging window set.

[0009] The target charging date is divided into multiple target charging time periods, and the target charging time periods are extracted sequentially from these multiple target charging time periods.

[0010] Based on the predicted charging window set and the extracted target charging time period, the power scheduling of the pre-constructed photovoltaic-storage-DC-flexible system is performed to obtain the charging scheduling strategy, which includes: photovoltaic power generation, predicted energy storage discharge power and external grid input power.

[0011] By using a charging scheduling strategy to schedule the charging power of multiple original car charging piles, multiple smart car charging piles are obtained.

[0012] By adjusting the charging of multiple smart car charging piles, charging vehicles are obtained. The charging vehicles corresponding to each target charging time period are summarized to obtain multiple charging vehicles, thus completing the community smart charging control based on photovoltaic, energy storage, direct current and flexible charging.

[0013] Optionally, the step of constructing a charging prediction model based on a community electric vehicle set to obtain a charging window prediction model includes:

[0014] Set the vehicle charging monitoring cycle, which includes multiple vehicle charging monitoring dates;

[0015] For each community electric vehicle cluster, the following operations shall be performed:

[0016] The vehicle charging monitoring dates are extracted sequentially during the vehicle charging monitoring cycle, and the extracted vehicle charging monitoring dates are recorded as historical monitoring dates.

[0017] Based on historical monitoring dates, charging data for electric vehicles in the community is queried to obtain historical charging windows;

[0018] Features are constructed from historical monitoring dates to obtain a historical date feature set; charging features are constructed from electric vehicles in the community to obtain a community electric vehicle charging feature set.

[0019] By merging the community vehicle charging feature set and the historical date feature set, a comprehensive vehicle charging feature set is obtained.

[0020] The historical charging window is used to mark the comprehensive feature set of vehicle charging to obtain historical charging marking data;

[0021] By summarizing the historical charging tag data corresponding to each historical monitoring date, multiple historical charging tag data sets are obtained;

[0022] By aggregating multiple historical charging tag data corresponding to electric vehicles in each community, a historical charging tag dataset is obtained;

[0023] A pre-built neural network is trained using a historical charging marker dataset to obtain a charging window prediction model.

[0024] Optionally, the step of using a charging window prediction model and a target charging date to predict the charging of the community's electric vehicle set, resulting in a predicted charging window set, includes:

[0025] Construct a target date feature set based on the target charging date;

[0026] The community electric vehicle set is denoted as the predictable electric vehicle set. Predictable electric vehicles are extracted sequentially from the predictable electric vehicle set to obtain the predictable charging feature set of the extracted predictable electric vehicles.

[0027] Merge the target date feature set and the predictable charging feature set to obtain a comprehensive predictive charging feature set.

[0028] The predicted charging feature set is input into the charging window prediction model to obtain the predicted charging window;

[0029] The predicted charging window set is obtained by summing up the predicted charging windows for each predictable electric vehicle.

[0030] Optionally, the step of performing power scheduling on the pre-constructed photovoltaic-storage-DC-flexible system based on the predicted charging window set and the extracted target charging time period to obtain a charging scheduling strategy includes:

[0031] Based on the predicted charging window set, the predicted charging vehicle set in the target charging time period is identified, wherein the predicted charging vehicle set includes multiple predicted charging vehicles.

[0032] Obtain the predicted charging power of each predicted charging vehicle in the predicted charging vehicle set to obtain the predicted charging power set.

[0033] The charging load power is obtained by summing the predicted vehicle charging power set.

[0034] Based on the target charging time period, the photovoltaic power generation of the photovoltaic-storage DC-flexible system is predicted to obtain the photovoltaic power generation. Based on the photovoltaic power generation and the charging load power, the discharge demand is predicted to obtain the predicted energy storage discharge power and the external grid input power.

[0035] By combining photovoltaic power generation, predicted energy storage discharge power, and external grid input power, a charging scheduling strategy is obtained.

[0036] Optionally, the step of controlling charging based on multiple smart car charging piles to obtain a charging vehicle includes:

[0037] Intelligent vehicle charging piles are extracted sequentially from multiple intelligent vehicle charging piles, including: target charging terminal cluster and charging node cluster.

[0038] Receive vehicle charging instructions, identify the current charging terminal in the target charging terminal cluster of smart vehicle charging piles based on the vehicle charging instructions, and obtain the vehicle to be charged corresponding to the vehicle charging instructions.

[0039] Determine the direct-connected charging node corresponding to the current charging terminal in the rechargeable node cluster;

[0040] Obtain the direct charging power of the direct charging node and read the current required charging power based on the vehicle to be charged;

[0041] Based on the direct charging power and the current required charging power, query the set of idle public nodes in the rechargeable node cluster. The set of idle public nodes includes one or more idle public nodes, or the set of idle public nodes is an empty set.

[0042] The vehicle to be charged is charged by using a set of idle public nodes and directly connected charging nodes.

[0043] Optionally, the step of querying the set of idle public nodes in the rechargeable node cluster based on the direct-connect charging power and the current required charging power includes:

[0044] Determine if the direct charging power is greater than the current required charging power;

[0045] If the direct charging power is not greater than the current required charging power, then a common charging node set is identified in the rechargeable node cluster, where the common charging node set includes multiple common charging nodes.

[0046] Idle public nodes are identified in the public charging node cluster, and the idle node power of the idle public nodes is obtained;

[0047] Calculate the overall charging power based on the power of idle nodes and the direct charging power.

[0048] Remove the idle public nodes from the rechargeable node cluster to obtain the remaining charging node cluster;

[0049] The remaining charging node cluster and the comprehensive charging power are respectively taken as the rechargeable node cluster and the direct-connected charging power, and the step of determining whether the direct-connected charging power is greater than the current required charging power is returned until the direct-connected charging power is greater than the current required charging power.

[0050] If the direct charging power is greater than the current required charging power, then the idle public nodes are aggregated to obtain a set of idle public nodes.

[0051] Optionally, identifying idle public nodes in the public charging node set includes:

[0052] Based on the current charging terminal, query the nearest public node in the public charging node cluster;

[0053] Determine if the nearest public node is in a preset idle state;

[0054] If the nearest public node is not idle, then retrieve the load charging terminal of the nearest public node from the target charging terminal cluster.

[0055] Based on the nearest public node, the node call determination is performed on the load charging terminal and the current charging terminal to obtain the call result, where the call result is either callable or not callable;

[0056] If the call result is callable, then the state of the nearest public node is reset to obtain the reset public node, the reset public node is used as the nearest public node, and the step of determining whether the nearest public node is in a preset idle state is returned, wherein the reset public node is in an idle state.

[0057] If the call result is that it cannot be called, the most recent public node will be removed from the public charging node set to obtain a candidate charging node cluster.

[0058] The candidate charging node cluster is treated as a public charging node set, and the step of querying the nearest public node in the public charging node set based on the current charging terminal is returned until the nearest public node is idle.

[0059] If the nearest public node is in an idle state, then the nearest public node is recorded as an idle public node.

[0060] Optionally, the step of determining the node call result based on the nearest common node for the load charging terminal and the current charging terminal, and obtaining the call result, includes:

[0061] Query the current terminal charging level of the current charging terminal and the load terminal charging level of the load charging terminal respectively;

[0062] If the current terminal's charging level is greater than the load terminal's charging level, then the callable state will be recorded as the call result.

[0063] If the current terminal charging level is equal to the load terminal charging level, then obtain the current node utilization rate of the nearest common node, and calculate the target node utilization rate based on the direct charging power, the current required charging power, and the nearest common node.

[0064] Calculate the call loss value based on the current node utilization and the target node utilization;

[0065] If the call overhead value is less than the preset call overhead threshold, then the callable value is recorded as the call result;

[0066] If the call overhead value is not less than the call overhead threshold, then the inability to call is recorded as the call result;

[0067] If the current terminal's charging level is lower than the load terminal's charging level, then the inability to call will be recorded as the call result.

[0068] Optionally, the step of calculating the call loss value based on the current node utilization and the target node utilization includes:

[0069] Obtain the cumulative number of switches to the nearest public node;

[0070] The call loss value is calculated based on the cumulative number of switches, the current node utilization, and the target node utilization. The call loss value is expressed as follows:

[0071] ;

[0072] in, This indicates that the loss value is being called. This represents the preset maximum loss value. This indicates the current node utilization rate. Indicates the utilization rate of the target node. This represents the preset cumulative switching coefficient. Indicates the cumulative number of handovers. This represents an exponential function with the natural constant as its base. This represents the preset utilization gain coefficient.

[0073] To achieve the above objectives, the present invention also provides a community smart charging control system based on photovoltaic energy storage, direct current and flexible charging, comprising:

[0074] The window model construction module is used to determine the community electric vehicle set and multiple original car charging piles. The community electric vehicle set includes multiple community electric vehicles. Based on the community electric vehicle set, a charging prediction model is constructed to obtain the charging window prediction model.

[0075] The charging window prediction module is used to receive intelligent charging control commands, determine the target charging date based on the intelligent charging control commands, and use the charging window prediction model and the target charging date to predict the charging of the community electric vehicle set, thereby obtaining the predicted charging window set.

[0076] The scheduling strategy acquisition module is used to divide the target charging date to obtain multiple target charging time periods. The target charging time periods are extracted sequentially from the multiple target charging time periods. Based on the predicted charging window set and the extracted target charging time periods, the power scheduling of the pre-constructed photovoltaic-storage-DC-flexible system is performed to obtain the charging scheduling strategy. The charging scheduling strategy includes: photovoltaic power generation, predicted energy storage discharge power and external grid input power.

[0077] The intelligent charging scheduling module is used to schedule the charging power of multiple original car charging piles using a charging scheduling strategy to obtain multiple intelligent car charging piles. Based on the multiple intelligent car charging piles, the module performs charging regulation to obtain charging cars. Finally, it summarizes the charging cars corresponding to each target charging time period to obtain multiple charging cars.

[0078] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0079] Memory, storing at least one instruction;

[0080] The processor executes the instructions stored in the memory to implement the aforementioned community smart charging control method based on optical energy storage, direct current and flexible charging.

[0081] To address the aforementioned issues, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned community smart charging control method based on optical storage, direct current, and flexible charging.

[0082] To address the problems described in the background, this invention first constructs a charging prediction model based on a community electric vehicle set, obtaining a charging window prediction model. This step improves the accuracy of charging time prediction by training a neural network model by fusing historical date features and vehicle charging characteristics, providing a reliable basis for subsequent power scheduling. Next, the charging window prediction model and target charging dates are used to predict charging demand for the community electric vehicle set, resulting in a predicted charging window set. This step enables personalized charging demand prediction for specific target charging dates, overcoming the coarse granularity of traditional methods and making charging plans more aligned with actual needs. Then, the target charging dates are divided into multiple target charging time periods. This step employs a dynamic division strategy based on photovoltaic output characteristics, achieving fine-grained segmentation of time periods, effectively matching the volatility of clean energy, and improving energy utilization. Furthermore, this solution utilizes the predicted charging window set and extracted target charging time periods to perform power scheduling on the pre-constructed photovoltaic-storage-DC-flexible system, resulting in a charging scheduling strategy. This step achieves multi-energy synergistic optimization by dynamically calculating photovoltaic power generation, energy storage discharge, and external grid input power, reducing dependence on the external grid. The solution then uses the charging scheduling strategy to schedule the charging power of multiple original car charging piles, resulting in multiple smart car charging piles. This step directly applies the power allocation strategy to the charging piles, enabling flexible adjustment of charging power and improving the response speed and adaptability of the charging system. Finally, the solution performs charging control based on the multiple smart car charging piles to obtain charging vehicles. This step optimizes the dynamic allocation of charging resources through node call discrimination and priority management, avoiding resource conflicts and improving the stability and efficiency of the charging process. Therefore, this invention can improve the accuracy of community charging control and energy utilization efficiency, reducing dependence on the traditional power grid. Attached Figure Description

[0083] Figure 1 A flowchart illustrating a community smart charging control method based on photovoltaic energy storage and direct current / flexible charging, provided in an embodiment of the present invention.

[0084] Figure 2 A functional block diagram of a community smart charging control system based on photovoltaic energy storage and direct current / flexible charging, provided in an embodiment of the present invention;

[0085] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the community smart charging control method based on optical energy storage, direct current and flexible charging, according to an embodiment of the present invention.

[0086] Explanation of reference numerals in the attached figures:

[0087] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0088] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0089] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0090] This application provides a community smart charging control method based on photovoltaic-storage-DC-Flexible (PV-SHU) architecture. 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 method provided in this application: a server, a terminal, etc. In other words, the community smart charging control method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0091] Reference Figure 1 The diagram shown is a flowchart illustrating a community smart charging control method based on photovoltaic-storage-DC-Flexible charging according to an embodiment of the present invention. In this embodiment, the community smart charging control method based on photovoltaic-storage-DC-Flexible charging includes:

[0092] S1. Identify the community electric vehicle cluster and multiple original car charging stations, wherein the community electric vehicle cluster includes multiple community electric vehicles.

[0093] Understandably, the term "community electric vehicle set" refers to a collection of electric vehicles from multiple communities. A community electric vehicle is an electric vehicle within a community that requires charging and possesses traceable historical charging data and relevant vehicle characteristics (such as vehicle identification number, historical average charging power, and battery capacity). The term "original charging station" refers to a charging station within the community that can charge electric vehicles.

[0094] S2. Based on the community electric vehicle set, a charging prediction model is constructed to obtain the charging window prediction model.

[0095] It is clear that the charging window prediction model refers to a neural network model that predicts the charging time of electric vehicles in a community electric vehicle cluster.

[0096] In detail, the construction of the charging prediction model based on the community electric vehicle set to obtain the charging window prediction model includes:

[0097] Set the vehicle charging monitoring cycle, which includes multiple vehicle charging monitoring dates;

[0098] For each community electric vehicle cluster, the following operations shall be performed:

[0099] The vehicle charging monitoring dates are extracted sequentially during the vehicle charging monitoring cycle, and the extracted vehicle charging monitoring dates are recorded as historical monitoring dates.

[0100] Based on historical monitoring dates, charging data for electric vehicles in the community is queried to obtain historical charging windows;

[0101] Features are constructed from historical monitoring dates to obtain a historical date feature set; charging features are constructed from electric vehicles in the community to obtain a community electric vehicle charging feature set.

[0102] By merging the community vehicle charging feature set and the historical date feature set, a comprehensive vehicle charging feature set is obtained.

[0103] The historical charging window is used to mark the comprehensive feature set of vehicle charging to obtain historical charging marking data;

[0104] By summarizing the historical charging tag data corresponding to each historical monitoring date, multiple historical charging tag data sets are obtained;

[0105] By aggregating multiple historical charging tag data corresponding to electric vehicles in each community, a historical charging tag dataset is obtained;

[0106] A pre-built neural network is trained using a historical charging marker dataset to obtain a charging window prediction model.

[0107] It should be explained that the vehicle charging monitoring period refers to a period of time set by the administrator for collecting historical charging data, such as 30 consecutive days or the past year. This vehicle charging monitoring period includes multiple vehicle charging monitoring dates, where each monitoring date is a specific date within the monitoring period used as a point in time for subsequent vehicle charging data collection, such as October 1st, October 2nd, etc. The historical charging window refers to the start and end time interval of actual charging of electric vehicles in a specific community within a specific historical monitoring date. For example, if an electric vehicle in a community starts charging at 21:00 on a certain historical monitoring date and continues until 6:00 the next day, then the historical charging window for that community's electric vehicles on that historical monitoring date is (21:00, 6:00 the next day).

[0108] Understandably, the historical date feature set refers to a set of parameters describing the attributes of historical monitoring dates. Since the nature of work (e.g., weekdays, weekends), weather conditions (temperature, relative humidity, rainfall, etc.), temperature conditions, and seasonal conditions of historical monitoring dates can influence users' charging behavior (i.e., historical charging windows), this historical date feature set needs to be introduced to improve the accuracy of the charging window prediction model. Optionally, this historical date feature set includes, but is not limited to: day of the week, whether it is a holiday, season, daily high / low temperature, weather type (sunny, rainy, snowy, etc.), humidity, etc. The community car charging feature set refers to a set of parameters describing the static and dynamic charging attributes of electric vehicles in the community. The community car charging features in this set can distinguish the charging behavior patterns of different electric vehicles; therefore, this community car charging feature set is a key factor in predicting their future charging windows. Optionally, the above-mentioned community car charging feature set includes, but is not limited to: vehicle code, historical average charging power, vehicle battery capacity, vehicle brand and model, current battery health, etc. The comprehensive car charging feature set refers to the set composed of data from the community car charging feature set and the historical date feature set.

[0109] Furthermore, the historical charging tag data refers to the comprehensive feature set of vehicle charging after being tagged with historical charging windows. Tagging the comprehensive feature set of vehicle charging using historical charging windows means pairing the historical charging windows as labels or target variables in supervised learning with the comprehensive feature set of vehicle charging as input features to form a complete training sample. Training the pre-constructed neural network using the historical charging tag dataset means using a large amount of labeled historical charging tag data and continuously adjusting the weight parameters inside the neural network through optimization algorithms (such as gradient descent), enabling the neural network to learn the complex mapping relationship between the comprehensive feature set of vehicle charging and the historical charging windows. Optionally, models that are adept at processing time series data, such as recurrent neural networks (RNNs), long short-term memory networks (LSTMs), or Transformers, can be selected as the neural network here.

[0110] S3. Receive intelligent charging control instructions, determine the target charging date based on the intelligent charging control instructions, and use the charging window prediction model and the target charging date to predict the charging of the community electric vehicle set, thereby obtaining the predicted charging window set.

[0111] Understandably, the intelligent charging control command refers to a human-initiated command to control multiple intelligent vehicle charging stations. The target charging date refers to a date set by the user that requires charging control. The predicted charging window set refers to the set of charging windows for each electric vehicle in the community's electric vehicle cluster on the target charging date.

[0112] In detail, the method of using a charging window prediction model and a target charging date to predict the charging of the community's electric vehicle set, resulting in a predicted charging window set, includes:

[0113] Construct a target date feature set based on the target charging date;

[0114] The community electric vehicle set is denoted as the predictable electric vehicle set. Predictable electric vehicles are extracted sequentially from the predictable electric vehicle set to obtain the predictable charging feature set of the extracted predictable electric vehicles.

[0115] Merge the target date feature set and the predictable charging feature set to obtain a comprehensive predictive charging feature set.

[0116] The predicted charging feature set is input into the charging window prediction model to obtain the predicted charging window;

[0117] The predicted charging window set is obtained by summing up the predicted charging windows for each predictable electric vehicle.

[0118] Understandably, the target date feature set refers to the date feature set of the target charging date. The construction method of this target date feature set is the same as that of the historical date feature set mentioned above, and will not be repeated here. The predictable charging feature set refers to the community car charging feature set corresponding to the predictable electric vehicle. The predictive charging comprehensive feature set refers to the data set of the target date feature set and the predictable charging feature set. The predictive charging window refers to the time window output by the charging window prediction model after inputting the predictive charging comprehensive feature set. This predictive charging window represents the charging time period of the predictable electric vehicle on the target charging date.

[0119] S4. Divide the target charging date into multiple target charging time periods, and extract the target charging time periods sequentially from the multiple target charging time periods.

[0120] It is clear that the target charging time period refers to a certain time period within the target charging date. Dividing the target charging date means: dividing the target charging date into multiple non-overlapping time periods according to a preset division strategy, i.e., multiple target charging time periods. The division strategy can be based on a fixed time length, for example, dividing the target charging date into 96 15-minute time periods or 24 1-hour time periods; or it can be based on the output characteristics of the photovoltaic power generation equipment in the photovoltaic-storage-DC-flexible system, for example, dividing it into "no-light period (nighttime)," "output-increasing period (morning)," "output-peak period (noon)," and "output-decreasing period (evening)," in order to better match the fluctuations of photovoltaic power generation and maximize the use of clean energy.

[0121] S5. Based on the predicted charging window set and the extracted target charging time period, power scheduling is performed on the pre-constructed photovoltaic-storage-DC-flexible system to obtain a charging scheduling strategy. The charging scheduling strategy includes: photovoltaic power generation, predicted energy storage discharge power and external grid input power.

[0122] Understandably, the aforementioned photovoltaic-storage-direct-current-flexible system refers to an integrated energy system that combines photovoltaic power generation, energy storage batteries, and flexible load control technologies. This system includes photovoltaic power generation equipment and energy storage equipment. The charging scheduling strategy refers to the set of photovoltaic power generation, predicted energy storage discharge power, and external grid input power. The specific methods for obtaining photovoltaic power generation, predicted energy storage discharge power, and external grid input power will be explained in detail later.

[0123] In detail, the step of performing power scheduling on the pre-constructed photovoltaic-storage-DC-flexible system based on the predicted charging window set and the extracted target charging time period to obtain a charging scheduling strategy includes:

[0124] Based on the predicted charging window set, the predicted charging vehicle set in the target charging time period is identified, wherein the predicted charging vehicle set includes multiple predicted charging vehicles.

[0125] Obtain the predicted charging power of each predicted charging vehicle in the predicted charging vehicle set to obtain the predicted charging power set.

[0126] The charging load power is obtained by summing the predicted vehicle charging power set.

[0127] Based on the target charging time period, the photovoltaic power generation of the photovoltaic-storage DC-flexible system is predicted to obtain the photovoltaic power generation. Based on the photovoltaic power generation and the charging load power, the discharge demand is predicted to obtain the predicted energy storage discharge power and the external grid input power.

[0128] By combining photovoltaic power generation, predicted energy storage discharge power, and external grid input power, a charging scheduling strategy is obtained.

[0129] It should be explained that the predicted charging vehicle set refers to a collection of multiple predicted charging vehicles, wherein a predicted charging vehicle refers to a community electric vehicle corresponding to a specific predicted charging window in the predicted charging window set, and this predicted charging vehicle will be charged during the corresponding predicted charging window. The predicted vehicle charging power refers to the charging power of the predicted charging vehicle during charging, which can be obtained by querying the vehicle's historical average charging power or based on its rated charging power of its battery management system (BMS).

[0130] It is clear that the charging load power refers to the sum of all predicted vehicle charging powers in the predicted vehicle charging power set. The photovoltaic power generation power refers to the power generation of the photovoltaic power generation equipment in the photovoltaic-storage-DC-flexible system during the target charging time period. Photovoltaic power generation prediction based on the target charging time period refers to: predicting the average power generation during this time period based on the season, weather forecast (solar intensity, cloud cover), historical power output data for the same period, and photovoltaic panel installation parameters. The prediction method is based on existing technology and specifically includes: selecting multiple historical time periods and monitoring the power generation characteristic data of the photovoltaic power generation equipment in each historical time period to obtain multiple power generation characteristic data. These power generation characteristic data include: environmental data and power generation data. The environmental data includes environmental parameters such as season, solar radiation intensity, rainfall, temperature, and humidity of the photovoltaic power generation equipment during a specific historical period. The power generation data refers to the power output of the photovoltaic power generation equipment during the corresponding historical period. Finally, the selected neural network (such as a convolutional neural network) is trained using the acquired power generation characteristic data. Backpropagation can be used for this training. The trained neural network is recorded as the power generation prediction model. Finally, the environmental data for the target charging period is input into this power generation prediction model, and the power output of the model is the aforementioned photovoltaic power generation. The predicted energy storage discharge power refers to the power value planned to be released by the energy storage equipment in the photovoltaic-storage-DC-flexible system to compensate for insufficient photovoltaic power generation. The external grid input power refers to the power value that needs to be transferred from the external grid when photovoltaic power generation and energy storage discharge still cannot meet the charging load demand.

[0131] Furthermore, the prediction of discharge demand based on photovoltaic power generation and charging load power means: if the photovoltaic power generation is greater than the charging load power, it indicates that the photovoltaic power generation can meet all charging needs and there is surplus energy to charge the energy storage device. In this case, the energy storage device does not need to discharge or transfer power from the external grid, i.e., the predicted energy storage discharge power and the external grid input power are both 0. If the photovoltaic power generation is not greater than the charging load power, it indicates that the photovoltaic power generation cannot meet all charging needs and there is a power deficit. In this case, the energy storage device needs to discharge to supplement the deficit. First, the discharge power of the energy storage device in the photovoltaic-storage-DC-flexible system is obtained. This discharge power can be obtained through the energy storage system. The current state of charge (SOC), rated power, and discharge efficiency are used to calculate the power. This calculation method is the existing method and will not be elaborated here. If the charging power cannot meet the power generation deficit between the photovoltaic power generation and the charging load power (i.e., the charging power is less than the absolute difference between the photovoltaic power generation and the charging load power), it means that the discharge of the energy storage device cannot completely make up for the power generation deficit. Power needs to be transferred from the external grid to make up for the deficit. Thus, the power input from the external grid is the absolute difference between the power generation deficit and the charging power. If the charging power meets the power generation deficit between the photovoltaic power generation and the charging load power, then no power needs to be input from the external grid, i.e., the power input from the external grid is 0.

[0132] S6. Utilize charging scheduling strategies to schedule the charging power of multiple original car charging piles to obtain multiple smart car charging piles.

[0133] It is clear that the intelligent vehicle charging pile refers to the original vehicle charging pile after charging power scheduling. The charging power scheduling of multiple original vehicle charging piles using the charging scheduling strategy means: allocating the photovoltaic power generation, predicted energy storage discharge power and external grid input power in the charging scheduling strategy to each original vehicle charging pile. The original vehicle charging pile after allocation is the intelligent vehicle charging pile.

[0134] S7. Based on multiple smart car charging piles, charge the vehicles to be charged, summarize the vehicles corresponding to each target charging time period, obtain multiple vehicles to complete the community smart charging control based on photovoltaic, energy storage, direct current and flexible charging.

[0135] It is clear that the term "charging vehicle" refers to a vehicle that is being charged.

[0136] Specifically, the process of controlling charging based on multiple smart car charging stations to obtain a charging vehicle includes:

[0137] Intelligent vehicle charging piles are extracted sequentially from multiple intelligent vehicle charging piles, including: target charging terminal cluster and charging node cluster.

[0138] Receive vehicle charging instructions, identify the current charging terminal in the target charging terminal cluster of smart vehicle charging piles based on the vehicle charging instructions, and obtain the vehicle to be charged corresponding to the vehicle charging instructions.

[0139] Determine the direct-connected charging node corresponding to the current charging terminal in the rechargeable node cluster;

[0140] Obtain the direct charging power of the direct charging node and read the current required charging power based on the vehicle to be charged;

[0141] Based on the direct charging power and the current required charging power, query the set of idle public nodes in the rechargeable node cluster. The set of idle public nodes includes one or more idle public nodes, or the set of idle public nodes is an empty set.

[0142] The vehicle to be charged is charged by using a set of idle public nodes and directly connected charging nodes.

[0143] It should be explained that the target charging terminal cluster refers to a collection of multiple target charging terminals, where a target charging terminal refers to an interface unit on a smart car charging pile that physically connects to a car and performs power transmission. The rechargeable node cluster includes multiple rechargeable nodes, where a rechargeable node refers to a power node capable of providing power output. Rechargeable nodes include directly connected nodes and common nodes. A directly connected node refers to a node that provides power to a specific target charging terminal individually and permanently in the electrical topology, and each target charging terminal corresponds to one directly connected node. The common node refers to a shared, flexible power node that can be dynamically allocated to any target charging terminal that requires additional power.

[0144] It is clear that the vehicle charging command refers to a human-initiated command to charge a specific vehicle. The vehicle to be charged refers to the vehicle requiring charging in the charging command, and the current charging terminal refers to the target charging terminal for the vehicle to be charged. The direct-connected charging node refers to the node directly connected to the current charging terminal. The direct-connected charging power refers to the maximum output power of the direct-connected charging node. The current required charging power refers to the charging power required for the vehicle to be charged. The idle public node set refers to a collection of multiple idle public nodes, where an idle public node is a public node capable of providing power to the current charging terminal to charge the vehicle to be charged. If the direct-connected charging node can meet the charging needs of the vehicle to be charged (i.e., the direct-connected charging power is greater than the current required charging power), then the idle public node set is empty.

[0145] Specifically, the step of querying the set of idle public nodes in the rechargeable node cluster based on the direct-connect charging power and the current required charging power includes:

[0146] Determine if the direct charging power is greater than the current required charging power;

[0147] If the direct charging power is not greater than the current required charging power, then a common charging node set is identified in the rechargeable node cluster, where the common charging node set includes multiple common charging nodes.

[0148] Idle public nodes are identified in the public charging node cluster, and the idle node power of the idle public nodes is obtained;

[0149] Calculate the overall charging power based on the power of idle nodes and the direct charging power.

[0150] Remove the idle public nodes from the rechargeable node cluster to obtain the remaining charging node cluster;

[0151] The remaining charging node cluster and the comprehensive charging power are respectively taken as the rechargeable node cluster and the direct-connected charging power, and the step of determining whether the direct-connected charging power is greater than the current required charging power is returned until the direct-connected charging power is greater than the current required charging power.

[0152] If the direct charging power is greater than the current required charging power, then the idle public nodes are aggregated to obtain a set of idle public nodes.

[0153] Understandably, if the direct charging power is not greater than the current required charging power, it means that the current direct charging power cannot meet the current required charging power. In this case, it is necessary to search for idle public nodes in the rechargeable node cluster to provide more charging power for the current charging terminal. The public charging node set refers to a collection of multiple public charging nodes, where a public charging node refers to a public node in the rechargeable node cluster. An idle public node refers to a public charging node that is not occupied by other target charging terminals. Idle node power refers to the maximum output power of an idle public node. The combined charging power refers to the sum of the idle node power and the direct charging power. The remaining charging node cluster refers to the rechargeable node cluster after removing idle public nodes.

[0154] Specifically, identifying idle public nodes in the public charging node set includes:

[0155] Based on the current charging terminal, query the nearest public node in the public charging node cluster;

[0156] Determine if the nearest public node is in a preset idle state;

[0157] If the nearest public node is not idle, then retrieve the load charging terminal of the nearest public node from the target charging terminal cluster.

[0158] Based on the nearest public node, the node call determination is performed on the load charging terminal and the current charging terminal to obtain the call result, where the call result is either callable or not callable;

[0159] If the call result is callable, then the state of the nearest public node is reset to obtain the reset public node, the reset public node is used as the nearest public node, and the step of determining whether the nearest public node is in a preset idle state is returned, wherein the reset public node is in an idle state.

[0160] If the call result is that it cannot be called, the most recent public node will be removed from the public charging node set to obtain a candidate charging node cluster.

[0161] The candidate charging node cluster is treated as a public charging node set, and the step of querying the nearest public node in the public charging node set based on the current charging terminal is returned until the nearest public node is idle.

[0162] If the nearest public node is in an idle state, then the nearest public node is recorded as an idle public node.

[0163] It should be explained that the "nearest public node" refers to the public charging node that is closest to the current charging terminal on the electrical connection path. The "idle state" means that the nearest public node is not currently assigned to any charging terminal and is in a standby state that is available and fault-free. The "load charging terminal" refers to the target charging terminal that the nearest public node is currently supplying power to. The "call result" refers to the result obtained after node call judgment, which is either callable or incallable. Callable means that the nearest public node can be disconnected from the load charging terminal, allowing the nearest public node to supply power to the current charging terminal. Incallable means that the switching loss is too high or does not meet the priority rules, and the connection between the nearest public node and the current load charging terminal should be maintained. If the call result is callable, the power supply connection object of the nearest public node needs to be switched from the load charging terminal to the current charging terminal. The "reset public node" refers to the nearest public node after a state reset. Resetting the state of the nearest public node means: releasing the binding relationship between the nearest public node and the original load charging terminal, marking its state as idle, and preparing it to accept new allocation tasks. The "candidate charging node cluster" refers to the set of public charging nodes after the nearest public node has been removed.

[0164] In detail, the step of determining the node call based on the nearest common node for the load charging terminal and the current charging terminal, and obtaining the call result, includes:

[0165] Query the current terminal charging level of the current charging terminal and the load terminal charging level of the load charging terminal respectively;

[0166] If the current terminal's charging level is greater than the load terminal's charging level, then the callable state will be recorded as the call result.

[0167] If the current terminal charging level is equal to the load terminal charging level, then obtain the current node utilization rate of the nearest common node, and calculate the target node utilization rate based on the direct charging power, the current required charging power, and the nearest common node.

[0168] Calculate the call loss value based on the current node utilization and the target node utilization;

[0169] If the call overhead value is less than the preset call overhead threshold, then the callable value is recorded as the call result;

[0170] If the call overhead value is not less than the call overhead threshold, then the inability to call is recorded as the call result;

[0171] If the current terminal's charging level is lower than the load terminal's charging level, then the inability to call will be recorded as the call result.

[0172] It is clear that the current terminal charging level refers to the charging service priority supported by the current charging terminal, and the load terminal charging level refers to the charging service priority supported by the load charging terminal. If the current terminal charging level is greater than the load terminal charging level, for example, if the current charging terminal is a supercharging terminal and the load charging terminal is a fast charging terminal, then the current terminal charging level is greater than the load terminal charging level, and in this case, the callable can be recorded as the call result. If the current terminal charging level is equal to the load terminal charging level, then the utilization rate of the current charging terminal and the load charging terminal for the nearest common node needs to be considered. The current node utilization rate refers to the utilization rate of the load charging terminal for the nearest common node. The current node utilization rate is calculated as follows: obtain the power output of the nearest common node for the load charging terminal, and take the ratio between the power output of the nearest common node for the load charging terminal and the maximum charging power of the nearest common node as the current node utilization rate. The target node utilization rate refers to the utilization rate of the current charging terminal for the nearest common node. The target node utilization rate is calculated as follows: ,in, Indicates the utilization rate of the target node. Indicates the current required charging power. Indicates the direct charging power. This indicates the maximum charging power.

[0173] Furthermore, since switching to the nearest common node will reduce its lifespan, this solution introduces a call loss value to quantify the loss of this switch operation. The call loss value refers to the numerical value that quantifies the loss incurred by switching to the nearest common node. The call loss threshold is a manually set constant. If the call loss value is not less than the call loss threshold, it indicates that the overall loss of this switch operation is too high, and the call result is "cannot be called".

[0174] In detail, the calculation of the call loss value based on the current node utilization and the target node utilization includes:

[0175] Obtain the cumulative number of switches to the nearest public node;

[0176] The call loss value is calculated based on the cumulative number of switches, the current node utilization, and the target node utilization. The call loss value is expressed as follows:

[0177] ;

[0178] in, This indicates that the loss value is being called. This represents the preset maximum loss value. This indicates the current node utilization rate. Indicates the utilization rate of the target node. This represents the preset cumulative switching coefficient. Indicates the cumulative number of handovers. This represents an exponential function with the natural constant as its base. This represents the preset utilization gain coefficient.

[0179] Understandably, the maximum loss value refers to a manually set constant, indicating that if the current node utilization is not less than the target node utilization, then being uncallable is recorded as a call result. The cumulative switching count refers to the number of times the most recent public node has switched within a past period (manually set, such as the past week). The cumulative switching coefficient refers to the weight of the manually set cumulative switching count, and the utilization gain coefficient refers to the manually set utilization gain (i.e.,... The weight of ).

[0180] It needs to be explained that in the above formula for calculating the call loss value: first, a basic performance determination is performed: if the current node utilization rate ( ) not lower than the target node utilization rate ( If a preset maximum loss value is assigned, the handover to the nearest common node will be rejected. If there is room for improvement in power utilization after handover to the nearest common node (i.e., ... Then, through a comprehensive evaluation model (i.e., when...), The call loss value is calculated using the formula (the formula for calculating the call loss value during the call). This comprehensive evaluation model is the ratio of device switching loss to expected performance gain, where device switching loss is... This term indicates that equipment switching losses are proportional to the square of the cumulative number of switching operations, where... This represents the cumulative number of times the nearest common node has been switched over. The expected performance gain is... This term indicates that the expected performance gain increases saturably with the difference between the target node utilization and the current node utilization.

[0181] To address the problems described in the background, this invention first constructs a charging prediction model based on a community electric vehicle set, obtaining a charging window prediction model. This step improves the accuracy of charging time prediction by training a neural network model by fusing historical date features and vehicle charging characteristics, providing a reliable basis for subsequent power scheduling. Next, the charging window prediction model and target charging dates are used to predict charging demand for the community electric vehicle set, resulting in a predicted charging window set. This step enables personalized charging demand prediction for specific target charging dates, overcoming the coarse granularity of traditional methods and making charging plans more aligned with actual needs. Then, the target charging dates are divided into multiple target charging time periods. This step employs a dynamic division strategy based on photovoltaic output characteristics, achieving fine-grained segmentation of time periods, effectively matching the volatility of clean energy, and improving energy utilization. Furthermore, this solution utilizes the predicted charging window set and extracted target charging time periods to perform power scheduling on the pre-constructed photovoltaic-storage-DC-flexible system, resulting in a charging scheduling strategy. This step achieves multi-energy synergistic optimization by dynamically calculating photovoltaic power generation, energy storage discharge, and external grid input power, reducing dependence on the external grid. The solution then uses the charging scheduling strategy to schedule the charging power of multiple original car charging piles, resulting in multiple smart car charging piles. This step directly applies the power allocation strategy to the charging piles, enabling flexible adjustment of charging power and improving the response speed and adaptability of the charging system. Finally, the solution performs charging control based on the multiple smart car charging piles to obtain charging vehicles. This step optimizes the dynamic allocation of charging resources through node call discrimination and priority management, avoiding resource conflicts and improving the stability and efficiency of the charging process. Therefore, this invention can improve the accuracy of community charging control and energy utilization efficiency, reducing dependence on the traditional power grid.

[0182] like Figure 2 The diagram shown is a functional block diagram of a community smart charging control system based on photovoltaic energy storage, direct current and flexible charging, provided in an embodiment of the present invention.

[0183] The community intelligent charging control system 100 based on photovoltaic energy storage, direct current and flexible charging, as described in this invention, can be installed in electronic devices. Depending on the functions implemented, the community intelligent charging control system 100 may include a window model construction module 101, a charging window prediction module 102, a scheduling strategy acquisition module 103, and an intelligent charging scheduling module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0184] The window model construction module 101 is used to determine the community electric vehicle set and multiple original car charging piles. The community electric vehicle set includes multiple community electric vehicles. A charging prediction model is constructed based on the community electric vehicle set to obtain a charging window prediction model.

[0185] The charging window prediction module 102 is used to receive intelligent charging control instructions, determine the target charging date based on the intelligent charging control instructions, and use the charging window prediction model and the target charging date to predict the charging of the community electric vehicle set, thereby obtaining the predicted charging window set.

[0186] The scheduling strategy acquisition module 103 is used to divide the target charging date to obtain multiple target charging time periods, extract the target charging time periods sequentially from the multiple target charging time periods, and perform power scheduling on the pre-constructed photovoltaic-storage-DC-flexible system based on the predicted charging window set and the extracted target charging time periods to obtain a charging scheduling strategy. The charging scheduling strategy includes: photovoltaic power generation, predicted energy storage discharge power and external grid input power.

[0187] The intelligent charging scheduling module 104 is used to schedule the charging power of multiple original car charging piles using a charging scheduling strategy to obtain multiple intelligent car charging piles, to regulate the charging based on the multiple intelligent car charging piles to obtain charging cars, and to summarize the charging cars corresponding to each target charging time period to obtain multiple charging cars.

[0188] In detail, the modules in the community smart charging control system 100 based on photovoltaic energy storage and direct current / flexible charging described in this embodiment of the invention employ the same methods as described above. Figure 1 The method used is the same as the community smart charging control method based on photovoltaic energy storage and direct current and flexible charging described in the article, and can produce the same technical effect, so it will not be repeated here.

[0189] like Figure 3 The diagram shown is a structural schematic of an electronic device that implements a community smart charging control method based on photovoltaic energy storage, direct current and flexible charging, according to an embodiment of the present invention.

[0190] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a community smart charging control method program based on optical energy storage, direct current and flexible charging.

[0191] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a community smart charging control method program based on optical storage direct current and flexible charging, but also to temporarily store data that has been output or will be output.

[0192] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a community smart charging control method program based on optical storage, direct current, and flexible charging), and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0193] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0194] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0195] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0196] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0197] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0198] The community smart charging control method program based on optical storage, direct current and flexible charging, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0199] Identify community electric vehicle clusters and multiple original car charging stations, wherein the community electric vehicle clusters include multiple community electric vehicles;

[0200] A charging prediction model is constructed based on a community electric vehicle dataset to obtain a charging window prediction model.

[0201] Receive intelligent charging control commands, determine the target charging date based on the intelligent charging control commands, and use the charging window prediction model and the target charging date to predict the charging of the community electric vehicle set, thereby obtaining the predicted charging window set.

[0202] The target charging date is divided into multiple target charging time periods, and the target charging time periods are extracted sequentially from these multiple target charging time periods.

[0203] Based on the predicted charging window set and the extracted target charging time period, the power scheduling of the pre-constructed photovoltaic-storage-DC-flexible system is performed to obtain the charging scheduling strategy, which includes: photovoltaic power generation, predicted energy storage discharge power and external grid input power.

[0204] By using a charging scheduling strategy to schedule the charging power of multiple original car charging piles, multiple smart car charging piles are obtained.

[0205] By adjusting the charging of multiple smart car charging piles, charging vehicles are obtained. The charging vehicles corresponding to each target charging time period are summarized to obtain multiple charging vehicles, thus completing the community smart charging control based on photovoltaic, energy storage, direct current and flexible charging.

[0206] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0207] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0208] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0209] Identify community electric vehicle clusters and multiple original car charging stations, wherein the community electric vehicle clusters include multiple community electric vehicles;

[0210] A charging prediction model is constructed based on a community electric vehicle dataset to obtain a charging window prediction model.

[0211] Receive intelligent charging control commands, determine the target charging date based on the intelligent charging control commands, and use the charging window prediction model and the target charging date to predict the charging of the community electric vehicle set, thereby obtaining the predicted charging window set.

[0212] The target charging date is divided into multiple target charging time periods, and the target charging time periods are extracted sequentially from these multiple target charging time periods.

[0213] Based on the predicted charging window set and the extracted target charging time period, the power scheduling of the pre-constructed photovoltaic-storage-DC-flexible system is performed to obtain the charging scheduling strategy, which includes: photovoltaic power generation, predicted energy storage discharge power and external grid input power.

[0214] By using a charging scheduling strategy to schedule the charging power of multiple original car charging piles, multiple smart car charging piles are obtained.

[0215] By adjusting the charging of multiple smart car charging piles, charging vehicles are obtained. The charging vehicles corresponding to each target charging time period are summarized to obtain multiple charging vehicles, thus completing the community smart charging control based on photovoltaic, energy storage, direct current and flexible charging.

[0216] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0217] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0218] 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.

[0219] 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.

[0220] Finally, it should be noted that the above 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 preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A community smart charging control method based on photovoltaic-storage-DC-flexible power supply, characterized in that, The method includes: Identify community electric vehicle clusters and multiple original car charging stations, wherein the community electric vehicle clusters include multiple community electric vehicles; A charging prediction model is constructed based on a community electric vehicle dataset to obtain a charging window prediction model. Receive intelligent charging control instructions, determine the target charging date based on the intelligent charging control instructions, and use the charging window prediction model and the target charging date to predict the charging of the community electric vehicle set, thereby obtaining the predicted charging window set. The target charging date is divided into multiple target charging time periods, and the target charging time periods are extracted sequentially from these multiple target charging time periods. Based on the predicted charging window set and the extracted target charging time period, the power scheduling of the pre-constructed photovoltaic-storage-DC-flexible system is performed to obtain the charging scheduling strategy, which includes: photovoltaic power generation, predicted energy storage discharge power and external grid input power. By using a charging scheduling strategy to schedule the charging power of multiple original car charging piles, multiple smart car charging piles are obtained. By adjusting the charging of multiple smart car charging piles, charging vehicles are obtained. The charging vehicles corresponding to each target charging time period are summarized to obtain multiple charging vehicles, thus completing the community smart charging control based on photovoltaic, energy storage, direct current and flexible charging.

2. The community smart charging control method based on photovoltaic energy storage, direct current and flexible charging as described in claim 1, characterized in that, The charging prediction model based on the community electric vehicle set is constructed to obtain the charging window prediction model, including: Set the vehicle charging monitoring cycle, which includes multiple vehicle charging monitoring dates; For each electric vehicle in a community's electric vehicle cluster, the following operations shall be performed: The vehicle charging monitoring dates are extracted sequentially during the vehicle charging monitoring cycle, and the extracted vehicle charging monitoring dates are recorded as historical monitoring dates. Based on historical monitoring dates, charging data for electric vehicles in the community is queried to obtain historical charging windows; Features are constructed from historical monitoring dates to obtain a historical date feature set; charging features are constructed from electric vehicles in the community to obtain a community electric vehicle charging feature set. By merging the community vehicle charging feature set and the historical date feature set, a comprehensive vehicle charging feature set is obtained. The historical charging window is used to mark the comprehensive feature set of vehicle charging to obtain historical charging marking data; By summarizing the historical charging tag data corresponding to each historical monitoring date, multiple historical charging tag data sets are obtained; By aggregating multiple historical charging tag data corresponding to electric vehicles in each community, a historical charging tag dataset is obtained; A pre-built neural network is trained using a historical charging marker dataset to obtain a charging window prediction model.

3. The community smart charging control method based on photovoltaic energy storage, direct current and flexible charging as described in claim 2, characterized in that, The method of using a charging window prediction model and a target charging date to predict the charging of the community's electric vehicle set yields a predicted charging window set, including: Construct a target date feature set based on the target charging date; The community electric vehicle set is denoted as the predictable electric vehicle set. Predictable electric vehicles are extracted sequentially from the predictable electric vehicle set to obtain the predictable charging feature set of the extracted predictable electric vehicles. Merge the target date feature set and the predictable charging feature set to obtain a comprehensive predictive charging feature set. The predicted charging feature set is input into the charging window prediction model to obtain the predicted charging window; The predicted charging window set is obtained by summing up the predicted charging windows for each predictable electric vehicle.

4. The community smart charging control method based on photovoltaic energy storage, direct current and flexible charging as described in claim 3, characterized in that, The power scheduling strategy for the pre-constructed photovoltaic-storage-DC-flexible system is obtained by performing power scheduling based on the predicted charging window set and the extracted target charging time period, including: Based on the predicted charging window set, the predicted charging vehicle set in the target charging time period is identified, wherein the predicted charging vehicle set includes multiple predicted charging vehicles. Obtain the predicted charging power of each predicted charging vehicle in the predicted charging vehicle set to obtain the predicted charging power set. The charging load power is obtained by summing the predicted vehicle charging power set. Based on the target charging time period, the photovoltaic power generation of the photovoltaic-storage DC-flexible system is predicted to obtain the photovoltaic power generation. Based on the photovoltaic power generation and the charging load power, the discharge demand is predicted to obtain the predicted energy storage discharge power and the external grid input power. By combining photovoltaic power generation, predicted energy storage discharge power, and external grid input power, a charging scheduling strategy is obtained.

5. The community smart charging control method based on photovoltaic energy storage, direct current and flexible charging as described in claim 4, characterized in that, The process of controlling charging based on multiple smart car charging piles to obtain a charging vehicle includes: Intelligent vehicle charging piles are extracted sequentially from multiple intelligent vehicle charging piles, including: target charging terminal cluster and charging node cluster. Receive vehicle charging instructions, identify the current charging terminal in the target charging terminal cluster of smart vehicle charging piles based on the vehicle charging instructions, and obtain the vehicle to be charged corresponding to the vehicle charging instructions. Determine the direct-connected charging node corresponding to the current charging terminal in the rechargeable node cluster; Obtain the direct charging power of the direct charging node and read the current required charging power based on the vehicle to be charged; Based on the direct charging power and the current required charging power, query the set of idle public nodes in the rechargeable node cluster. The set of idle public nodes includes one or more idle public nodes, or the set of idle public nodes is an empty set. The vehicle to be charged is charged by using a set of idle public nodes and directly connected charging nodes.

6. The community smart charging control method based on photovoltaic energy storage, direct current and flexible charging as described in claim 5, characterized in that, The step of querying the set of idle public nodes in the rechargeable node cluster based on the direct-connect charging power and the current required charging power includes: Determine if the direct charging power is greater than the current required charging power; If the direct charging power is not greater than the current required charging power, then a common charging node set is identified in the rechargeable node cluster, where the common charging node set includes multiple common charging nodes. Idle public nodes are identified in the public charging node cluster, and the idle node power of the idle public nodes is obtained; Calculate the overall charging power based on the power of idle nodes and the direct charging power. Remove the idle public nodes from the rechargeable node cluster to obtain the remaining charging node cluster; The remaining charging node cluster and the total charging power are respectively taken as the rechargeable node cluster and the direct-connected charging power, and the step of determining whether the direct-connected charging power is greater than the current required charging power is returned until the direct-connected charging power is greater than the current required charging power. If the direct charging power is greater than the current required charging power, then the idle public nodes are aggregated to obtain a set of idle public nodes.

7. The community smart charging control method based on photovoltaic energy storage, direct current and flexible charging as described in claim 6, characterized in that, The process of identifying idle public nodes in a public charging node cluster includes: Based on the current charging terminal, query the nearest public node in the public charging node cluster; Determine if the nearest public node is in a preset idle state; If the nearest public node is not idle, then retrieve the load charging terminal of the nearest public node from the target charging terminal cluster. Based on the nearest public node, the node call determination is performed on the load charging terminal and the current charging terminal to obtain the call result, where the call result is either callable or not callable; If the call result is callable, then the state of the nearest public node is reset to obtain the reset public node, the reset public node is used as the nearest public node, and the step of determining whether the nearest public node is in a preset idle state is returned, wherein the reset public node is in an idle state. If the call result is that it cannot be called, the most recent public node will be removed from the public charging node set to obtain a candidate charging node cluster. The candidate charging node cluster is treated as a public charging node set, and the step of querying the nearest public node in the public charging node set based on the current charging terminal is returned until the nearest public node is idle. If the nearest public node is in an idle state, then the nearest public node is recorded as an idle public node.

8. The community smart charging control method based on photovoltaic energy storage, direct current and flexible charging as described in claim 7, characterized in that, The node call determination based on the nearest common node for the load charging terminal and the current charging terminal, and the resulting call result, includes: Query the current terminal charging level of the current charging terminal and the load terminal charging level of the load charging terminal respectively; If the current terminal's charging level is greater than the load terminal's charging level, then the callable state will be recorded as the call result. If the current terminal charging level is equal to the load terminal charging level, then obtain the current node utilization rate of the nearest common node, and calculate the target node utilization rate based on the direct charging power, the current required charging power, and the nearest common node. Calculate the call loss value based on the current node utilization and the target node utilization; If the call overhead value is less than the preset call overhead threshold, then the callable value is recorded as the call result; If the call overhead value is not less than the call overhead threshold, then the inability to call is recorded as the call result; If the current terminal's charging level is lower than the load terminal's charging level, then the inability to call will be recorded as the call result.

9. The community smart charging control method based on photovoltaic energy storage, direct current and flexible charging as described in claim 8, characterized in that, The calculation of call loss value based on the current node utilization and the target node utilization includes: Obtain the cumulative number of switches to the nearest public node; The call loss value is calculated based on the cumulative number of switches, the current node utilization, and the target node utilization. The call loss value is expressed as follows: ； in, This indicates that the loss value is being called. This represents the preset maximum loss value. This indicates the current node utilization rate. Indicates the utilization rate of the target node. This represents the preset cumulative switching coefficient. Indicates the cumulative number of handovers. This represents an exponential function with the natural constant as its base. This represents the preset utilization gain coefficient.

10. A community intelligent charging control system based on photovoltaic energy storage, direct current, and flexible charging, characterized in that: The system includes: The window model construction module is used to determine the community electric vehicle set and multiple original car charging piles. The community electric vehicle set includes multiple community electric vehicles. Based on the community electric vehicle set, a charging prediction model is constructed to obtain the charging window prediction model. The charging window prediction module is used to receive intelligent charging control commands, determine the target charging date based on the intelligent charging control commands, and use the charging window prediction model and the target charging date to predict the charging of the community electric vehicle set, thereby obtaining the predicted charging window set. The scheduling strategy acquisition module is used to divide the target charging date to obtain multiple target charging time periods. The target charging time periods are extracted sequentially from the multiple target charging time periods. Based on the predicted charging window set and the extracted target charging time periods, the power scheduling of the pre-constructed photovoltaic-storage-DC-flexible system is performed to obtain the charging scheduling strategy. The charging scheduling strategy includes: photovoltaic power generation, predicted energy storage discharge power and external grid input power. The intelligent charging scheduling module is used to schedule the charging power of multiple original car charging piles using a charging scheduling strategy to obtain multiple intelligent car charging piles. Based on the multiple intelligent car charging piles, the module performs charging regulation to obtain charging cars. Finally, it summarizes the charging cars corresponding to each target charging time period to obtain multiple charging cars.

Images