Intelligent light storage charging detection energy collaborative optimization control method and system

Abstract

The invention relates to an intelligent light storage charging detection energy collaborative optimization control method and system. The method comprises the following steps: predicting a high-frequency fluctuation period of each charging station based on historical information; when photovoltaic power generation in the charging station is in a high-frequency fluctuation period at the current moment, the monitoring frequency of meteorological data is determined according to the average duration, predicted by the fluctuation prediction model, of each fluctuation, and a power supply mode is adjusted according to the meteorological data; and when the photovoltaic power generation in the charging station is not in the high-frequency fluctuation period at the current moment, judging that the monitoring frequency of the meteorological data is a fixed preset frequency. According to the invention, the monitoring frequency and the power supply mode are dynamically adjusted to cope with the fluctuation of photovoltaic power generation and the abnormity of meteorological data. The strategy optimization not only improves the stability and reliability of the system, but also reduces the operation cost and the impact on the power grid. The operation efficiency and stability of the charging station can be effectively improved, and the influence of photovoltaic power generation fluctuation and meteorological abnormity on charging of the electric vehicle is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of energy control, and particularly to an intelligent photovoltaic-storage-charging-detection energy collaborative optimization control method and system. Background Art

[0002] Photovoltaic-storage-charging-detection is a new generation of charging infrastructure integrating photovoltaic power generation, energy storage system, charging function, and battery detection. Among them, photovoltaic power generation: uses photovoltaic panels to generate solar power above parking spaces or within a specified range. Energy storage system: stores electrical energy through an intelligent energy storage battery system (such as a lithium iron phosphate battery) and releases it when needed. Charging function: the charging pile provides charging services for power-consuming terminals such as electric vehicles. Battery detection: synchronously detects the battery of an electric vehicle during the charging process and provides a battery health report and risk warning. However, solar power generation has the characteristics of intermittency and unpredictability. Especially in summer, the weather is unpredictable and may suddenly become unavailable. This is because solar power generation depends on sunlight, and the intensity and duration of sunlight are unstable, resulting in fluctuations in the power generation. Therefore, the present invention proposes an intelligent photovoltaic-storage-charging-detection energy collaborative optimization control method and system. Summary of the Invention

[0003] The present invention provides an intelligent photovoltaic-storage-charging-detection energy collaborative optimization control method and system to solve the technical problems mentioned in the above background art.

[0004] To achieve the above object, the present invention provides the following technical solutions: An intelligent photovoltaic-storage-charging-detection energy collaborative optimization control method, the method comprising the following steps: Collect historical information of photovoltaic power generation in a charging station, and predict the high-frequency fluctuation period of each charging station based on the historical information; When the photovoltaic power generation in the charging station is in the high-frequency fluctuation period at the current moment, determine the monitoring frequency of meteorological data according to the average duration of each fluctuation predicted by the fluctuation prediction model, and adjust the power supply mode according to the meteorological data, the power supply mode including a first power supply mode and a second power supply mode; When the photovoltaic power generation in the charging station is not in the high-frequency fluctuation period at the current moment, determine that the monitoring frequency of meteorological data is a fixed preset frequency, and adjust the power supply mode according to the meteorological data.

[0005] As a further technical solution of the present invention, the step of collecting historical information of photovoltaic power generation in a charging station and predicting the high-frequency fluctuation period of each charging station based on the historical information includes: Collect historical information of photovoltaic power generation in a charging station, and train a neural network model with the historical information of photovoltaic power generation in the charging station to obtain a fluctuation prediction model; The fluctuation information of photovoltaic power generation in each charging station within each period is predicted according to the fluctuation prediction model, and the fluctuation information includes the number of fluctuations of photovoltaic power generation in each charging station and the average duration of each fluctuation; Based on the number of fluctuations in the fluctuation information and a preset fluctuation threshold, it is determined whether the photovoltaic power generation in each power generation station is a high-frequency fluctuation period in each period; Among them, "fluctuation" means that the output power of photovoltaic power generation does not conform to the preset output power, and the fluctuation duration exceeds the preset duration, and it can be counted as one fluctuation.

[0006] As a further technical solution of the present invention, when the photovoltaic power generation in the charging station is in a high-frequency fluctuation period at the current moment, the monitoring frequency of meteorological data is determined according to the average duration of each fluctuation predicted by the fluctuation prediction model, and the power supply mode is adjusted according to the meteorological data. The steps of the power supply mode including a first power supply mode and a second power supply mode are as follows: When the photovoltaic power generation in the charging station is in a high-frequency fluctuation period at the current moment, the monitoring frequency of meteorological data is determined according to the average duration of each fluctuation predicted by the fluctuation prediction model; When it is detected that the meteorological data is abnormal, the power supply mode is adjusted to the second power supply mode until the th minute after the end of the abnormality, the power supply mode is restored from the second power supply mode to the first power supply mode, The value of is determined according to the number of fluctuations in the current high-frequency fluctuation period predicted by the fluctuation prediction model. The number of fluctuations is positively correlated with the value of, and the larger the number of fluctuations, the larger the corresponding value of ; Among them, the first power supply mode is: supplying power to electric vehicles mainly through photovoltaic power generation and supplemented by an energy storage system. At this time, if there is surplus electric energy generated by photovoltaic power generation after meeting the power supply to electric vehicles, the surplus electric energy of photovoltaic power generation is stored in the energy storage system; The second power supply mode is: supplying power to electric vehicles mainly through the energy storage system and supplemented by the power grid. At this time, photovoltaic power generation does not supply power to electric vehicles, and photovoltaic power generation stores electric energy through the energy storage system.

[0007] As a further technical solution of the present invention, when the photovoltaic power generation in the charging station is not in a high-frequency fluctuation period at the current moment, the steps of determining the monitoring frequency of meteorological data as a fixed preset frequency and adjusting the power supply mode according to the meteorological data are as follows: When the photovoltaic power generation in the charging station is not in a high-frequency fluctuation period, it is determined that the monitoring frequency of meteorological data is a fixed preset frequency; When it is detected that the meteorological data is abnormal, the power supply mode is the second power supply mode until the Restore the power supply mode from the second power supply mode to the first power supply mode within minutes; The value of is determined according to the number of fluctuations in the current period predicted by the fluctuation prediction model. The number of fluctuations here is positively correlated with the value of.

[0008] Another object of the present invention is to provide an intelligent optical storage charging inspection energy collaborative optimization control system, which includes: A high-frequency prediction module, configured to collect historical information of photovoltaic power generation in a charging station, and predict the high-frequency fluctuation period of each charging station based on the historical information; A high-frequency adjustment module, configured to determine the monitoring frequency of meteorological data according to the average duration of each fluctuation predicted by the fluctuation prediction model when the photovoltaic power generation in the charging station is in a high-frequency fluctuation period at the current moment, and adjust the power supply mode according to the meteorological data. The power supply mode includes a first power supply mode and a second power supply mode; A low-frequency adjustment module, configured to determine that the monitoring frequency of meteorological data is a fixed preset frequency when the photovoltaic power generation in the charging station is not in a high-frequency fluctuation period at the current moment, and adjust the power supply mode according to the meteorological data.

[0009] As a further technical solution of the present invention, the high-frequency prediction module includes: A prediction model establishment unit, configured to collect historical information of photovoltaic power generation in a charging station, and train a neural network model with the historical information of photovoltaic power generation in the charging station to obtain a fluctuation prediction model; A fluctuation information prediction unit, configured to predict the fluctuation information of photovoltaic power generation in each charging station in each period according to the fluctuation prediction model. The fluctuation information includes the number of fluctuations of photovoltaic power generation in each charging station and the average duration of each fluctuation; A high-frequency period determination unit, configured to determine whether the photovoltaic power generation of each power generation station is in a high-frequency fluctuation period in each period based on the number of fluctuations in the fluctuation information and a preset fluctuation threshold; Among them, "fluctuation" means that the output power of photovoltaic power generation does not meet the preset output power, and the fluctuation duration exceeds the preset duration, and it can be counted as one fluctuation.

[0010] As a further technical solution of the present invention, the high-frequency adjustment module includes: A first monitoring frequency determination unit, configured to determine the monitoring frequency of meteorological data according to the average duration of each fluctuation predicted by the fluctuation prediction model when the photovoltaic power generation in the charging station is in a high-frequency fluctuation period at the current moment; A first power supply mode switching unit, configured to adjust the power supply mode to the second power supply mode when it is detected that the meteorological data is abnormal, until the Restore the power supply mode from the second power supply mode to the first power supply mode within minutes The value of is determined according to the number of fluctuations in the current high-frequency fluctuation period predicted by the fluctuation prediction model. The number of fluctuations is positively correlated with the value of, and the greater the number of fluctuations, the greater the corresponding value of ; Among them, the first power supply mode is: supply power to the electric vehicle mainly through photovoltaic power generation and supplemented by an energy storage system. At this time, if there is surplus power generated by photovoltaic power generation after meeting the power supply to the electric vehicle, the surplus power of photovoltaic power generation will be stored in the energy storage system; The second power supply mode is: supply power to the electric vehicle mainly through the energy storage system and supplemented by the power grid. At this time, photovoltaic power generation does not supply power to the electric vehicle, and photovoltaic power generation stores electrical energy through the energy storage system.

[0011] As a further technical solution of the present invention, the low-frequency adjustment module includes: A second monitoring frequency determination unit, configured to determine that the monitoring frequency of meteorological data is a fixed preset frequency when the photovoltaic power generation in the charging station is not in a high-frequency fluctuation period; A second power supply mode switching unit, configured to make the power supply mode be the second power supply mode when it is detected that the meteorological data is abnormal, until the power supply mode is restored from the second power supply mode to the first power supply mode at the th minute after the abnormality ends; The value of is determined according to the number of fluctuations in the current period predicted by the fluctuation prediction model. Here, the number of fluctuations is positively correlated with the value of.

[0012] Compared with the prior art, the beneficial effects of the present invention are: The present invention provides an intelligent optical storage charging and inspection energy collaborative optimization control method and system. In the present invention, based on the fluctuation prediction model, the fluctuation information of photovoltaic power generation in each charging station in each period is predicted, and based on the fluctuation information, it is determined whether each period is a high-frequency fluctuation period. When the photovoltaic power generation in the charging station is in a high-frequency fluctuation period at the current moment, the monitoring frequency of meteorological data is determined by the average monitoring duration of each fluctuation. When the photovoltaic power generation in the charging station is not in a high-frequency fluctuation period at the current moment, it is determined that the monitoring frequency of meteorological data is a fixed preset frequency, and the power supply mode is adjusted according to the meteorological data. In the present invention, the monitoring frequency and the power supply mode are dynamically adjusted to cope with the volatility of photovoltaic power generation and the abnormality of meteorological data. This strategy optimization not only improves the stability and reliability of the system, but also reduces the operation cost and the impact on the power grid; it can effectively improve the operation efficiency and stability of the charging station, and reduce the impact on electric vehicle charging caused by the fluctuation of photovoltaic power generation and meteorological anomalies. Description of the Drawings

[0013] Figure 1 It is a flow chart of an intelligent optical storage charging inspection energy collaborative optimization control method.

[0014] Figure 2 It is a flow chart of the step of predicting the high-frequency fluctuation period in an intelligent optical storage charging inspection energy collaborative optimization control method.

[0015] Figure 3 It is a flow chart of the power supply adjustment step within the high-frequency fluctuation period in an intelligent optical storage charging inspection energy collaborative optimization control method.

[0016] Figure 4 It is a flow chart of the power supply adjustment step within the non-high-frequency fluctuation period in an intelligent optical storage charging inspection energy collaborative optimization control method.

[0017] Figure 5 It is a structural block diagram of an intelligent optical storage charging inspection energy collaborative optimization control system. Detailed implementation manners

[0018] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0019] As Figure 1 shown, the embodiment of the present invention provides an intelligent optical storage charging inspection energy collaborative optimization control method, and the method includes the following steps: Step S100, collect the historical information of photovoltaic power generation in the charging station, and predict the high-frequency fluctuation period of each charging station based on the historical information; for details, please refer to Figure 2 .

[0020] Step S101, collect the historical information of photovoltaic power generation in the charging station, and train a neural network model with the historical information of photovoltaic power generation in the charging station to obtain a fluctuation prediction model; The specific steps to establish the fluctuation prediction model are as follows: Collect historical information data of photovoltaic power generation from the monitoring systems of each charging station. These data should include the output power of photovoltaic power generation and the corresponding timestamps. The data collection period can be set according to actual needs, such as weekly, monthly, etc. Clean the collected data to remove outliers, missing values, duplicate values, etc., and ensure the accuracy and integrity of the data. Preprocess the data according to the preset output power and fluctuation duration thresholds. Identify the data segments where the output power of photovoltaic power generation does not meet the preset output power and the fluctuation duration exceeds the preset time length, and mark them as one fluctuation. Count the number of fluctuations and the average duration of each fluctuation in each charging station within each historical period. Divide the preprocessed data into a training set and a validation set. Extract features from the preprocessed data. These features can include the historical number of fluctuations, average duration, time (such as hours, dates, seasons), weather conditions (such as sunny, cloudy, rainy), temperature, humidity, etc. The selection of features should be based on the actual situation and the requirements of the neural network model. The model can choose models suitable for processing time series data, such as Recurrent Neural Network (RNN), Long Short-Term Memory Network (LSTM), Gated Recurrent Unit (GRU), etc. Use a deep learning framework (such as TensorFlow, PyTorch, etc.) to build a neural network model. Use the training set data to train the neural network model, and use the validation set data to evaluate the performance of the model until the preset performance requirements are met, then the trained fluctuation prediction model can be obtained.

[0021] Step S102: Predict the fluctuation information of photovoltaic power generation in each charging station within each period according to the fluctuation prediction model. The fluctuation information includes the number of fluctuations and the average duration of each fluctuation in the photovoltaic power generation of each charging station. In this step, by inputting the time corresponding to each period within a year into the fluctuation prediction model, the fluctuation information of photovoltaic power generation in each charging station within each period of the year can be output.

[0022] Step S103: Determine whether the photovoltaic power generation of each power station is a high-frequency fluctuation period in each period based on the number of fluctuations in the fluctuation information and the preset fluctuation threshold. Among them, "fluctuation" means that when the output power of photovoltaic power generation does not meet the preset output power and the fluctuation duration exceeds the preset time length, it can be counted as one fluctuation. The time step of a period may be a week, a month, or a season. A high-frequency fluctuation period refers to a period in which the number of fluctuations within a period exceeds the preset fluctuation threshold and is determined as a high-frequency fluctuation period.

[0023] Step S200, when the photovoltaic power generation in the charging station is in a high-frequency fluctuation cycle at the current moment, determine the monitoring frequency of meteorological data according to the average duration of each fluctuation predicted by the fluctuation prediction model, and adjust the power supply mode according to the meteorological data. The power supply mode includes a first power supply mode and a second power supply mode; for details, please refer to Figure 3 .

[0024] Step S201, when the photovoltaic power generation in the charging station is in a high-frequency fluctuation cycle at the current moment, determine the monitoring frequency of meteorological data according to the average duration of each fluctuation predicted by the fluctuation prediction model; the average duration here refers to the average duration of each fluctuation within the current high-frequency fluctuation cycle predicted by the fluctuation prediction model; the larger the average duration, the lower the corresponding monitoring frequency, and the smaller the average duration, the higher the corresponding monitoring frequency. There is a negative correlation between the average duration and the monitoring frequency. Step S202, when it is detected that the meteorological data is abnormal, adjust the power supply mode to the second power supply mode until the th minute after the abnormality ends, restore the power supply mode from the second power supply mode to the first power supply mode. The value of is determined according to the number of fluctuations within the current high-frequency fluctuation cycle predicted by the fluctuation prediction model. Here, the number of fluctuations has a positive correlation with the value. The larger the number of fluctuations, the larger the corresponding value; determining whether the meteorological data is abnormal includes the following steps: continuously collect meteorological data such as sunlight intensity using sensors or weather stations and preprocess it: clean the collected data, remove noise and outliers (such as extreme values caused by sensor failures), and perform necessary smoothing processing; set the abnormal conditions for sunlight intensity according to historical data and business requirements. For example, if the sunlight intensity suddenly drops below a certain threshold and remains for a preset duration (such as continuously for several minutes), it is considered abnormal; perform real-time monitoring on the preprocessed meteorological data to ensure the accuracy and real-time nature of the data. Compare the real-time monitored sunlight intensity with the set threshold. If it meets the abnormal conditions, determine that the meteorological data is abnormal and adjust the power supply mode.

[0025] Among them, the first power supply mode is: supply power to the electric vehicle mainly through photovoltaic power generation and supplemented by an energy storage system (specifically, preferentially use the electric energy generated by photovoltaic power generation. When the electric energy generated by photovoltaic power generation is insufficient to support the power supply to the electric vehicle, the energy storage system assists in supplying power to the electric vehicle to meet the charging demand). At this time, if there is surplus electric energy generated by photovoltaic power generation after meeting the power supply to the electric vehicle, store the surplus electric energy of photovoltaic power generation in the energy storage system. The second power supply mode is: mainly using the energy storage system and supplemented by the power grid to supply power to electric vehicles (specifically: preferentially using the energy storage system to supply power to electric vehicles, and when the remaining power in the energy storage system is less than the preset power, using the power grid to supply power to electric vehicles). At this time, the photovoltaic power generation does not supply power to electric vehicles, and the photovoltaic power generation stores electrical energy through the energy storage system).

[0026] Step S300, when the photovoltaic power generation in the charging station is not in the high-frequency fluctuation period at the current moment, determine that the monitoring frequency of the meteorological data is the fixed preset frequency, and adjust the power supply mode according to the meteorological data. For details, please refer to Figure 4 .

[0027] Step S301, when the photovoltaic power generation in the charging station is not in the high-frequency fluctuation period, determine that the monitoring frequency of the meteorological data is the fixed preset frequency; the fixed preset frequency is usually less than the monitoring frequency determined according to the average duration. Step S302, when it is detected that the meteorological data is abnormal, make the power supply mode the second power supply mode until the th minute after the abnormality ends, restore the power supply mode from the second power supply mode to the first power supply mode; The value of is determined according to the number of fluctuations in the current period predicted by the fluctuation prediction model. The number of fluctuations is positively correlated with the value of. The larger the number of fluctuations, the larger the corresponding value of. Usually is less than .

[0028] In the present invention, based on the fluctuation prediction model, the fluctuation information of the photovoltaic power generation in each charging station in each period is predicted. Based on the fluctuation information, it is determined whether each period is a high-frequency fluctuation period. When the photovoltaic power generation in the charging station is in the high-frequency fluctuation period at the current moment, the monitoring frequency of the meteorological data is determined by the average monitoring duration of each fluctuation. When the photovoltaic power generation in the charging station is not in the high-frequency fluctuation period at the current moment, it is determined that the monitoring frequency of the meteorological data is the fixed preset frequency, and the power supply mode is adjusted according to the meteorological data. In the present invention, the monitoring frequency and the power supply mode are dynamically adjusted to cope with the volatility of the photovoltaic power generation and the abnormality of the meteorological data. This strategy optimization not only improves the stability and reliability of the system, but also reduces the operating cost and the impact on the power grid; it can effectively improve the operation efficiency and stability of the charging station, and reduce the impact of photovoltaic power generation fluctuations and meteorological anomalies on electric vehicle charging.

[0029] Please refer to Figure 5 , Another object of the present invention is to provide an intelligent optical storage charging and inspection energy collaborative optimization control system, the system includes: A high-frequency prediction module 100, which is used to collect historical information of photovoltaic power generation in a charging station and predict the high-frequency fluctuation period of each charging station based on the historical information; A high-frequency adjustment module 200, which is used to determine the monitoring frequency of meteorological data according to the average duration of each fluctuation predicted by the fluctuation prediction model when the photovoltaic power generation in the charging station is in the high-frequency fluctuation period at the current moment, and adjust the power supply mode according to the meteorological data, where the power supply mode includes a first power supply mode and a second power supply mode; A low-frequency adjustment module 300, which is used to determine that the monitoring frequency of meteorological data is a fixed preset frequency when the photovoltaic power generation in the charging station is not in the high-frequency fluctuation period at the current moment, and adjust the power supply mode according to the meteorological data.

[0030] As a preferred embodiment of the present invention, the high-frequency prediction module 100 includes: A prediction model establishment unit, which is used to collect historical information of photovoltaic power generation in a charging station and train a neural network model with the historical information of photovoltaic power generation in the charging station to obtain a fluctuation prediction model; A fluctuation information prediction unit, which is used to predict the fluctuation information of photovoltaic power generation in each charging station in each period according to the fluctuation prediction model, where the fluctuation information includes the number of fluctuations of photovoltaic power generation in each charging station and the average duration of each fluctuation; A high-frequency period determination unit, which is used to determine whether the photovoltaic power generation of each power generation station is in the high-frequency fluctuation period in each period based on the number of fluctuations in the fluctuation information and a preset fluctuation threshold; Among them, "fluctuation" means that the output power of photovoltaic power generation does not conform to the preset output power and the fluctuation duration exceeds the preset duration, and it can be counted as one fluctuation; the high-frequency fluctuation period may be one month or one season.

[0031] As a preferred embodiment of the present invention, the high-frequency adjustment module 200 includes: A first monitoring frequency determination unit, which is used to determine the monitoring frequency of meteorological data according to the average duration of each fluctuation predicted by the fluctuation prediction model when the photovoltaic power generation in the charging station is in the high-frequency fluctuation period at the current moment; the longer the average duration, the lower the corresponding monitoring frequency, and the shorter the average duration, the higher the corresponding monitoring frequency, and there is a negative correlation between the average duration and the monitoring frequency; A first power supply mode switching unit, which is used to adjust the power supply mode to the second power supply mode when it is detected that the meteorological data is abnormal, until the th minute after the end of the abnormality, and restore the power supply mode from the second power supply mode to the first power supply mode, The value of is determined according to the number of fluctuations in the current high-frequency fluctuation period predicted by the fluctuation prediction model, and the number of fluctuations is related to The value of has a positive correlation, and the greater the number of fluctuations, the corresponding The first power supply mode is as follows: mainly supplying power to the electric vehicle through photovoltaic power generation and supplemented by an energy storage system (specifically, preferentially using the electric energy generated by photovoltaic power generation. When the electric energy generated by photovoltaic power generation is insufficient to support the power supply to the electric vehicle, the energy storage system assists in supplying power to the electric vehicle to meet the charging demand). At this time, if there is surplus electric energy generated by photovoltaic power generation after meeting the power supply to the electric vehicle, the surplus electric energy of photovoltaic power generation is stored in the energy storage system; The second power supply mode is as follows: mainly supplying power to the electric vehicle through the energy storage system and supplemented by the power grid (specifically: preferentially using the energy storage system to supply power to the electric vehicle. When the remaining power in the energy storage system is less than the preset power, the power grid is used to supply power to the electric vehicle). At this time, photovoltaic power generation does not supply power to the electric vehicle, and photovoltaic power generation stores electric energy through the energy storage system.

[0032] As a preferred embodiment of the present invention, the low-frequency adjustment module 300 includes: A second monitoring frequency determination unit, configured to determine that the monitoring frequency of meteorological data is a fixed preset frequency when the photovoltaic power generation in the charging station is not in a high-frequency fluctuation period; the fixed preset frequency is usually less than the monitoring frequency determined according to the average duration; A second power supply mode switching unit, configured to, when it is detected that the meteorological data is abnormal, make the power supply mode be the second power supply mode until the minute after the end of the abnormality, restore the power supply mode from the second power supply mode to the first power supply mode; The value of is determined according to the number of fluctuations in the current period predicted by the fluctuation prediction model. The number of fluctuations and The value of

[0033] It should be noted that in this article, the term "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including that element.

[0034] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be similarly included in the patent protection scope of the present invention.

Claims

1. An intelligent photovoltaic storage charging and testing energy coordinated optimization control method, characterized in that: The method comprises the following steps: Collect historical information of photovoltaic power generation in charging stations, and predict the high-frequency fluctuation period of each charging station based on the historical information; When the photovoltaic power generation in the charging station is in a high-frequency fluctuation cycle at the current moment, the monitoring frequency of the meteorological data is determined according to the average duration of each fluctuation predicted by the fluctuation prediction model, and the power supply mode is adjusted according to the meteorological data, and the power supply mode includes a first power supply mode and a second power supply mode; When the photovoltaic power generation in the charging station is not in a high-frequency fluctuation cycle at the current moment, it is determined that the monitoring frequency of the meteorological data is a fixed preset frequency, and the power supply mode is adjusted according to the meteorological data.

2. According to claim 1, a smart photovoltaic storage charging and testing energy coordinated optimization control method is characterized in that: The step of collecting historical information of photovoltaic power generation in the charging stations and predicting the high-frequency fluctuation period of each charging station based on the historical information includes: Collect historical information of photovoltaic power generation in the charging station, and use the historical information of photovoltaic power generation in the charging station to train the neural network model to obtain a fluctuation prediction model; Predicting the fluctuation information of photovoltaic power generation in each charging station in each cycle according to the fluctuation prediction model, wherein the fluctuation information includes the number of fluctuations of photovoltaic power generation in each charging station and the average duration of each fluctuation; Based on the number of fluctuations in the fluctuation information and a preset fluctuation threshold, it is determined whether the photovoltaic power generation of each power station is a high-frequency fluctuation period in each period.

3. The intelligent photovoltaic storage charging and testing energy coordinated optimization control method according to claim 1 is characterized in that: When the photovoltaic power generation in the charging station is in a high-frequency fluctuation cycle at the current moment, the monitoring frequency of the meteorological data is determined according to the average duration of each fluctuation predicted by the fluctuation prediction model, and the power supply mode is adjusted according to the meteorological data, and the power supply mode includes the first power supply mode and the second power supply mode. The steps include: When the photovoltaic power generation in the charging station is in a high-frequency fluctuation cycle at the current moment, the monitoring frequency of the meteorological data is determined according to the average duration of each fluctuation predicted by the fluctuation prediction model; When the meteorological data is detected to be abnormal, the power supply mode is adjusted to the second power supply mode until the abnormality ends. minutes to restore the power supply mode from the second power supply mode to the first power supply mode, The value of is determined based on the number of fluctuations in the current high-frequency fluctuation period predicted by the fluctuation prediction model; The first power supply mode is to supply power to the electric vehicle mainly through photovoltaic power generation and supplemented by the energy storage system. At this time, if the electricity generated by photovoltaic power generation is sufficient to supply power to the electric vehicle, the surplus electricity generated by photovoltaic power generation is stored in the energy storage system. The second power supply mode is: powering the electric vehicle mainly by the energy storage system and supplemented by the power grid. At this time, photovoltaic power generation does not supply power to the electric vehicle, and photovoltaic power generation stores electrical energy through the energy storage system.

4. The intelligent photovoltaic storage charging and testing energy coordinated optimization control method according to claim 3 is characterized in that: When the photovoltaic power generation in the charging station is not in a high-frequency fluctuation cycle at the current moment, determining that the monitoring frequency of the meteorological data is a fixed preset frequency, and adjusting the power supply mode according to the meteorological data comprises: When the photovoltaic power generation in the charging station is not in a high-frequency fluctuation period, the monitoring frequency of the meteorological data is determined to be a fixed preset frequency; When the meteorological data is detected to be abnormal, the power supply mode is changed to the second power supply mode until the abnormality ends. The power supply mode is restored from the second power supply mode to the first power supply mode within 10 minutes.

5. The intelligent photovoltaic storage charging and testing energy coordinated optimization control method according to claim 3 is characterized in that: Determining whether the meteorological data is abnormal includes the following steps: collecting meteorological data and preprocessing it; comparing the preprocessed meteorological data with the set abnormal conditions, and if the abnormal conditions are met, determining that the meteorological data is abnormal and adjusting the power supply mode.

6. An intelligent photovoltaic storage charging and testing energy coordinated optimization control system, characterized in that: The system comprises: A high-frequency prediction module, used to collect historical information of photovoltaic power generation in charging stations, and predict the high-frequency fluctuation period of each charging station based on the historical information; A high-frequency adjustment module, used for determining the monitoring frequency of meteorological data according to the average duration of each fluctuation predicted by the fluctuation prediction model when the photovoltaic power generation in the charging station is in a high-frequency fluctuation period at the current moment, and adjusting the power supply mode according to the meteorological data, the power supply mode including the first power supply mode and the second power supply mode; The low-frequency adjustment module is used to determine that the monitoring frequency of meteorological data is a fixed preset frequency when the photovoltaic power generation in the charging station is not in a high-frequency fluctuation cycle at the current moment, and adjust the power supply mode according to the meteorological data.

7. The intelligent photovoltaic storage charging and testing energy coordinated optimization control system according to claim 6 is characterized in that: The high frequency prediction module comprises: A prediction model building unit is used to collect historical information of photovoltaic power generation in the charging station, and use the historical information of photovoltaic power generation in the charging station to train a neural network model to obtain a fluctuation prediction model; A fluctuation information prediction unit, used to predict the fluctuation information of photovoltaic power generation in each charging station in each cycle according to the fluctuation prediction model, wherein the fluctuation information includes the number of fluctuations of photovoltaic power generation in each charging station and the average duration of each fluctuation; A high-frequency cycle determination unit, configured to determine whether the photovoltaic power generation of each power station is a high-frequency fluctuation cycle in each cycle based on the number of fluctuations in the fluctuation information and a preset fluctuation threshold; Among them, "fluctuation" means: the output power of photovoltaic power generation does not meet the preset output power, and the fluctuation duration exceeds the preset time, which can be counted as a fluctuation.

8. The intelligent photovoltaic storage charging and testing energy coordinated optimization control system according to claim 6 is characterized in that: The high frequency adjustment module comprises: a first monitoring frequency determination unit, configured to determine the monitoring frequency of meteorological data according to the average duration of each fluctuation predicted by the fluctuation prediction model when the photovoltaic power generation in the charging station is in a high-frequency fluctuation period at the current moment; The first power supply mode switching unit is used to adjust the power supply mode to the second power supply mode when the meteorological data is detected to be abnormal, until the first power supply mode after the abnormality ends. minutes to restore the power supply mode from the second power supply mode to the first power supply mode, The value of is determined based on the number of fluctuations in the current high-frequency fluctuation period predicted by the fluctuation prediction model; The first power supply mode is to supply power to the electric vehicle mainly through photovoltaic power generation and supplemented by the energy storage system. At this time, if the electricity generated by photovoltaic power generation is sufficient to supply power to the electric vehicle, the surplus electricity generated by photovoltaic power generation is stored in the energy storage system. The second power supply mode is: powering the electric vehicle mainly by the energy storage system and supplemented by the power grid. At this time, photovoltaic power generation does not supply power to the electric vehicle, and photovoltaic power generation stores electrical energy through the energy storage system.

9. The intelligent photovoltaic storage charging and testing energy coordinated optimization control system according to claim 8 is characterized in that: The low frequency adjustment module comprises: A second monitoring frequency determination unit, configured to determine that the monitoring frequency of meteorological data is a fixed preset frequency when the photovoltaic power generation in the charging station is not in a high-frequency fluctuation period; The second power supply mode switching unit is used to switch the power supply mode to the second power supply mode when the meteorological data is detected to be abnormal, until the second power supply mode after the abnormality ends. minutes to restore the power supply mode from the second power supply mode to the first power supply mode; The value of is determined according to the number of fluctuations in the current period predicted by the fluctuation prediction model.

Images