Photovoltaic power generation energy storage intelligent control method and system

Abstract

The invention discloses an intelligent control method and system for photovoltaic power generation and energy storage, and relates to the technical field of deep learning, a charging load index Cfzs is calculated and evaluated through a charging load prediction module, and the load demand in a fixed period can be predicted more accurately; the discharge load index Ffzs is calculated and evaluated, so that the discharge load of the battery is accurately predicted, and the uncertainty caused by load fluctuation is reduced; the power generation prediction module calculates a power generation index Fdzs according to the charging load index Cfzs and the discharging load index Ffzs and evaluates the power generation index Fdzs, so that a more accurate power generation prediction result is obtained; and the battery management control module performs secondary correction according to the prediction results and the environmental data, and dynamically adjusts a charging priority control strategy, a discharging priority control strategy and a charging and discharging balance control strategy of the battery, so that the system can reasonably distribute charging and discharging loads when the fluctuation of the generating capacity is relatively large, and the stability of power supply is ensured.

Description

Technical Field

[0001] The present invention relates to the field of deep learning technology, and in particular to a photovoltaic power generation and energy storage intelligent control method and system. Background Art

[0002] Photovoltaic power generation and energy storage systems have become an important means to solve energy shortages and environmental problems by converting solar energy into electrical energy and storing it in batteries for use when needed. However, traditional energy storage control methods have defects such as low control accuracy and slow response speed, making it difficult to cope with complex and changeable practical application scenarios. In recent years, the introduction of deep learning technology has provided a new solution for photovoltaic power generation and energy storage control. By analyzing and predicting a large amount of historical data, the discharge strategy of energy storage batteries can be optimized to improve the overall efficiency and reliability of the system.

[0003] In the invention patent with application number 202410056800.9, the application involves the field of deep learning technology, and discloses a photovoltaic power generation energy storage control method and system. The method includes: performing potential change and current density analysis on the energy storage battery in the photovoltaic power generation energy storage system to obtain first potential change data and first current density data; performing potential change prediction to obtain second potential change data and second current density data; performing characteristic curve conversion and feature extraction to obtain a potential change feature set and a current density feature set; performing feature encoding and vector conversion to obtain a potential change feature vector, a current density feature vector and a target fusion feature vector; performing abnormal analysis of the discharge behavior of the energy storage battery through the energy storage battery discharge analysis model to obtain abnormal discharge behavior prediction data; performing energy storage discharge control strategy analysis to obtain a target energy storage discharge control strategy. This application improves the accuracy of photovoltaic power generation energy storage control.

[0004] However, the above invention still has some technical shortcomings when applied to electric vehicle charging stations on highways; since the load fluctuations of charging stations on highways are large, the charging behavior of electric vehicles is highly random and uncertain, resulting in increased prediction errors; and the photovoltaic power generation on highways is affected by multiple factors such as sunlight intensity and weather conditions, and the power generation fluctuates greatly, resulting in unstable power supply. Summary of the invention

[0005] Technical issues solved

[0006] In view of the deficiencies in the prior art, the present invention provides a photovoltaic power generation and energy storage intelligent control method and system, which solves the technical defects mentioned in the above background technology.

[0007] Technical Solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a photovoltaic power generation and energy storage intelligent control system, including a data acquisition and processing module, a car charging load prediction module, a battery discharge load prediction module, a power generation prediction module, a battery management control module and a result visualization module;

[0009] The data acquisition and processing module is used to collect relevant data of electric vehicle charging stations, photovoltaic power generation systems and energy storage systems in real time, including charging demand data of vehicle charging stations, power generation data of photovoltaic power generation systems, power data of battery energy storage systems and environmental parameters, and perform preprocessing;

[0010] The vehicle charging load prediction module is used to establish and use a deep learning model to dynamically predict the charging load of the electric vehicle; obtain the charging load index Cfzs by calculation, and evaluate the charging load index Cfzs at the same time, predict the load demand of the electric vehicle within a fixed period based on the evaluation result, and generate the vehicle charging load prediction result;

[0011] The battery discharge load prediction module is used to establish a charging load prediction model based on historical charging data, vehicle data and environmental data using a machine learning algorithm; at the same time, the discharge load index Ffzs is calculated and evaluated, and the battery discharge load in a future fixed period is predicted based on the evaluation result, and a battery discharge load prediction result is generated;

[0012] The power generation prediction module is used to calculate and evaluate the power generation index Fdzs according to the charging load index Cfzs and the discharging load index Ffzs, and finally obtain the power generation prediction result according to the evaluation result of the power generation index Fdzs;

[0013] The battery management control module is used to obtain a secondary correction scheme for the power generation prediction result according to the fitting of the power generation index Fdzs and the environmental data; and then dynamically adjust the battery charging and discharging strategy according to the vehicle charging load prediction result, the battery discharging load prediction result and the power generation prediction result, including the charging priority control strategy, the discharging priority control strategy and the charging and discharging balance control strategy;

[0014] The result visualization module is used to provide a visualization interface and tools for users to display the charging priority control strategy, the discharging priority control strategy and the charge-discharge balance control strategy.

[0015] Preferably, the data acquisition and processing module includes an acquisition unit and a preprocessing unit; the acquisition unit monitors and records the charging demand of each charging station in real time through the metering equipment installed in the charging station; collects the power generation data of the photovoltaic panel in real time by reading the inverter and the electric meter in the photovoltaic power generation system; obtains the battery power data by reading the battery management system of the energy storage system; and monitors the environmental parameters in real time through the installed environmental sensors;

[0016] The preprocessing unit is used to denoise, eliminate outliers and perform dimensionless processing on the data collected by the acquisition unit, and then construct a charging data set, a power generation data set, an energy storage power data set and an environmental data set respectively; the charging data set includes charging power, charging voltage, total charging time within a fixed period and charging status; the power generation data set includes power generation power, power generation, power generation efficiency and inverter efficiency; the energy storage power data set includes current power, charging and discharging rate and charging and discharging times; the environmental data set includes temperature, humidity, light intensity and wind speed.

[0017] Preferably, the automobile charging load prediction module includes a charging load calculation unit and a charging load evaluation unit; the charging load calculation unit calculates and obtains the charging load index Cfzs by extracting the charging data set, and the specific calculation formula is as follows:

[0018]

[0019] Where Cdy i represents the charging voltage at the i-th time point, Cgl i represents the charging power at the i-th time point, Csc represents the total charging time in a fixed cycle, Czt represents the charging state value, T max Indicates the maximum temperature allowed by the device, Csb j represents the temperature of the charging device at the Jth time point;

[0020] a1 represents the charging voltage Cdy used to adjust the i-th time point i , the charging power Cgl at the i-th time point i and the weight value of the calculation result of the total charging time Csc in a fixed cycle, a2 represents the maximum temperature T allowed by the device max and the charging device temperature Csb at the Jth time point j The weight value of the calculation result, the specific value is adjusted by the user.

[0021] Preferably, the charging load evaluation unit performs evaluation by preset load threshold Q1 and load threshold Q2 and charging load index Cfzs, and load threshold Q1>load threshold Q2. The specific evaluation contents are as follows:

[0022] If the charging load index Cfzs ≥ the load threshold Q1, a first charging load result is generated, and load reduction measures are taken at this time, including adjusting the charging power, staggered charging, and load transfer;

[0023] If the load threshold Q1> the charging load index Cfzs> the load threshold Q2, a second charging load result is generated, and the monitoring frequency of the charging load condition is adjusted, including increasing the number of monitoring times by 10% within a fixed period;

[0024] If the load threshold Q2 ≥ the charging load index Cfzs, a third charging load result is generated. At this time, the current charging station is marked as a low load state and the existing operation strategy is maintained.

[0025] Preferably, the battery discharge load prediction module includes a discharge load calculation unit and a discharge load evaluation unit; the discharge load calculation unit extracts power generation data and fits the charging load index Cfzs to calculate and obtain the discharge load index Ffzs, and the specific calculation formula is as follows:

[0026]

[0027] In the formula, Fgl represents the power generation, Fdl represents the power generation, Fxl represents the power generation efficiency, and Nxl represents the inverter efficiency;

[0028] s1 represents the weight value of the charging load index Cfzs, and s2 represents the weight value of the discharge load index Ffzs combined with the power generation power Fgl, the power generation amount Fdl, the power generation efficiency Fxl and the inverter efficiency Nxl, and the specific value is adjusted by the user.

[0029] Preferably, the discharge load evaluation unit evaluates the discharge load index Ffzs by presetting a discharge threshold E1 and a discharge threshold E2, and the discharge threshold E1>the discharge threshold E2. The specific evaluation content is as follows:

[0030] If the discharge load index Ffzs ≥ the discharge threshold E1, a first discharge load result is generated, and the discharge power is reduced, including giving priority to photovoltaic power generation;

[0031] If the discharge threshold E1> the discharge load index Ffzs> the discharge threshold E2, a second discharge load result is generated, and preventive maintenance is performed at this time, including adjusting the frequency of checking the equipment and system status, and increasing the number of inspections by 5% within a fixed period;

[0032] If the discharge threshold E2 ≥ the discharge load index Ffzs, a third discharge load result is generated, and the current discharge strategy is maintained.

[0033] Preferably, the power generation prediction module extracts the energy storage power data set and fits the charging load index Cfzs and the discharging load index Ffzs to calculate the power generation index Fdzs. The specific calculation formula is as follows:

[0034]

[0035] Wherein, Cnzs represents the energy storage index, Dl represents the current power, Dsl represents the charge and discharge rate, and Dcs represents the number of charge and discharge times; the power generation prediction module evaluates the power generation index Fdzs by presetting the power generation threshold E, and the specific contents are as follows:

[0036] If the power generation threshold T ≥ the power generation index Fdzs, it means that the predicted power generation meets the expected demand, and the first power generation result is generated;

[0037] If the power generation threshold T is less than the power generation index Fdzs, it means that the predicted power generation does not meet the expected demand. At this time, a second power generation result is generated and a second confirmation is performed in combination with the environmental data set.

[0038] Preferably, the battery management control module includes a correction unit and a strategy adjustment unit; the correction unit obtains a secondary correction scheme by fitting the environmental data set, the charging load index Cfzs and the discharging load index Ffzs according to the power generation prediction result, and the specific contents obtained are as follows:

[0039]

[0040] Wherein, Fdzs2 represents the secondary power generation index; Wd represents temperature, Sd represents humidity, Gqd represents light intensity, and Fs represents wind speed; d1, d2, d3, and d4 represent the weight values ​​of temperature Wd, humidity Sd, light intensity Gqd, and wind speed Fs, respectively; e represents the exponential function;

[0041] The preset correction threshold R1 and correction threshold R2 are evaluated with the secondary power generation index Fdzs2, and the correction threshold R1>correction threshold R2. The specific evaluation content is as follows:

[0042] If the secondary power generation index Fdzs2 ≥ the correction threshold R1, a first correction result is generated, indicating that the power generation does not meet the expected demand. At this time, the strategy adjustment unit performs analysis and adjusts the control strategy;

[0043] If the correction threshold R1> the secondary power generation index Fdzs2> the correction threshold R2, a second correction result is generated, indicating that the power generation does not meet the expected demand. At this time, the strategy adjustment unit is used to analyze and adjust the priority control order;

[0044] If the correction threshold R2 ≥ the secondary power generation index Fdzs2, a third correction result is generated, indicating that the power generation meets the expected demand and no adjustment is required.

[0045] A photovoltaic power generation energy storage intelligent control method comprises the following steps:

[0046] Step 1: collect relevant data of electric vehicle charging stations, photovoltaic power generation systems and energy storage systems in real time through the data acquisition and processing module, including charging demand data of the car charging station, power generation data of the photovoltaic power generation system, power data of the battery energy storage system and environmental parameters, and perform preprocessing;

[0047] Step 2: Establish and use a deep learning model through the vehicle charging load prediction module to dynamically predict the charging load of the electric vehicle; obtain the charging load index Cfzs by calculation, and evaluate the charging load index Cfzs at the same time, predict the load demand of the electric vehicle within a fixed period based on the evaluation results, and generate the vehicle charging load prediction result;

[0048] Step 3: Using the battery discharge load prediction module, a charging load prediction model is established based on historical charging data, vehicle data and environmental data using a machine learning algorithm; at the same time, the discharge load index Ffzs is calculated and evaluated, and the battery discharge load in a future fixed period is predicted based on the evaluation results, and a battery discharge load prediction result is generated;

[0049] Step 4: The power generation prediction module calculates and evaluates the power generation index Fdzs according to the charging load index Cfzs and the discharging load index Ffzs, and finally obtains the power generation prediction result according to the evaluation result of the power generation index Fdzs;

[0050] Step 5. The battery management control module obtains a secondary correction scheme for the power generation prediction result according to the power generation index Fdzs and the environmental data fitting; then dynamically adjusts the battery charging and discharging strategy according to the vehicle charging load prediction result, the battery discharging load prediction result and the power generation prediction result, including the charging priority control strategy, the discharging priority control strategy and the charging and discharging balance control strategy;

[0051] Step 6: Provide users with a visualization interface and tools through the result visualization module to display the charging priority control strategy, the discharging priority control strategy and the charge-discharge balance control strategy.

[0052] Beneficial Effects

[0053] The present invention provides a photovoltaic power generation and energy storage intelligent control method and system. It has the following beneficial effects:

[0054] (1) The data acquisition and processing module can collect and pre-process relevant data of charging stations, photovoltaic power generation systems and energy storage systems in real time to ensure the accuracy and timeliness of the data; the charging load prediction module uses a deep learning model to dynamically predict the charging load. By calculating and evaluating the charging load index Cfzs, it can more accurately predict the load demand within a fixed period; the discharge load prediction module is based on historical data, vehicle data and environmental data, and uses machine learning algorithms to establish a prediction model. By calculating and evaluating the discharge load index Ffzs, it can accurately predict the battery discharge load. Through the effective combination of these modules, the system can significantly improve the prediction accuracy of electric vehicle charging behavior and reduce the uncertainty caused by load fluctuations.

[0055] (2) The power generation prediction module calculates and evaluates the power generation index Fdzs based on the charging load index Cfzs and the discharging load index Ffzs, thereby obtaining a more accurate power generation prediction result; the battery management control module makes secondary corrections based on these prediction results and environmental data, and dynamically adjusts the battery charging and discharging strategies, including charging priority control strategy, discharging priority control strategy, and charging and discharging balance control strategy. Through the above adjustments, the system can reasonably allocate charging and discharging loads when the power generation fluctuates greatly, ensuring the stability of power supply; the result visualization module provides a user-friendly interface to display and analyze the execution of various strategies, helping users understand and adjust the charging and discharging strategies, thereby realizing the efficient and stable operation of the photovoltaic power generation and energy storage system in highway car charging stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A schematic diagram of the process structure of a photovoltaic power generation and energy storage intelligent control system of the present invention;

[0057] Figure 2 The figure is a schematic diagram of the steps of a photovoltaic power generation and energy storage intelligent control method of the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] Example 1

[0060] See also Figure 1 , a photovoltaic power generation and energy storage intelligent control system, including a data acquisition and processing module, a vehicle charging load prediction module, a battery discharge load prediction module, a power generation prediction module, a battery management control module and a result visualization module;

[0061] The data acquisition and processing module is used to collect relevant data of electric vehicle charging stations, photovoltaic power generation systems and energy storage systems in real time, including charging demand data of vehicle charging stations, power generation data of photovoltaic power generation systems, power data of battery energy storage systems and environmental parameters, and perform preprocessing;

[0062] The vehicle charging load prediction module is used to establish and use a deep learning model to dynamically predict the charging load of the electric vehicle; obtain the charging load index Cfzs by calculation, and evaluate the charging load index Cfzs at the same time, predict the load demand of the electric vehicle within a fixed period based on the evaluation result, and generate the vehicle charging load prediction result;

[0063] The battery discharge load prediction module is used to establish a charging load prediction model based on historical charging data, vehicle data and environmental data using a machine learning algorithm; at the same time, the discharge load index Ffzs is calculated and evaluated, and the battery discharge load in a future fixed period is predicted based on the evaluation result, and a battery discharge load prediction result is generated;

[0064] The power generation prediction module is used to calculate and evaluate the power generation index Fdzs according to the charging load index Cfzs and the discharging load index Ffzs, and finally obtain the power generation prediction result according to the evaluation result of the power generation index Fdzs;

[0065] The battery management control module is used to obtain a secondary correction scheme for the power generation prediction result according to the fitting of the power generation index Fdzs and the environmental data; and then dynamically adjust the battery charging and discharging strategy according to the vehicle charging load prediction result, the battery discharging load prediction result and the power generation prediction result, including the charging priority control strategy, the discharging priority control strategy and the charging and discharging balance control strategy;

[0066] The result visualization module is used to provide a visualization interface and tools for users to display the charging priority control strategy, the discharging priority control strategy and the charge-discharge balance control strategy.

[0067] In this embodiment, the data acquisition and processing module is used to realize real-time data acquisition and preprocessing of electric vehicle charging stations, photovoltaic power generation systems and energy storage systems, so as to ensure the accuracy and timeliness of the data and provide a basis for subsequent predictions; the deep learning model is used to dynamically predict the charging load of electric vehicles through the vehicle charging load prediction module, and the charging load prediction results are generated to help optimize the load management of the charging station; the battery discharge load prediction module is based on historical data and environmental data and uses a machine learning algorithm to predict the battery discharge load, generate the discharge load prediction results, and improve the accuracy of the discharge strategy; the power generation index Fdzs is calculated and evaluated through the power generation prediction module to predict future power generation and provide a basis for energy management; the battery management control module is used to dynamically adjust the battery charging and discharging strategy to improve system efficiency and battery life; the result visualization module provides a visual interface and tools to display and help users understand and manage the charging and discharging strategy, so as to improve the operability and user experience of the system.

[0068] Example 2

[0069] See also Figure 1 The data acquisition and processing module includes an acquisition unit and a preprocessing unit; the acquisition unit monitors and records the charging demand of each charging station in real time through the metering equipment installed at the charging station; collects the power generation data of the photovoltaic panel in real time by reading the inverter and the electric meter in the photovoltaic power generation system; obtains the battery power data by reading the battery management system of the energy storage system; and monitors the environmental parameters in real time through the installed environmental sensors;

[0070] The preprocessing unit is used to denoise, eliminate outliers and perform dimensionless processing on the data collected by the acquisition unit, and then construct a charging data set, a power generation data set, an energy storage power data set and an environmental data set respectively; the charging data set includes charging power, charging voltage, total charging time within a fixed period and charging status; the power generation data set includes power generation power, power generation, power generation efficiency and inverter efficiency; the energy storage power data set includes current power, charging and discharging rate and charging and discharging times; the environmental data set includes temperature, humidity, light intensity and wind speed.

[0071] In this embodiment, the charging demand is monitored and recorded in real time through the metering equipment of the charging station, the data of the inverter and the meter in the photovoltaic power generation system are read, and the power generation information of the photovoltaic panel is collected; the battery power data is obtained through the battery management system, and the environmental parameters such as temperature, humidity, light intensity and wind speed are monitored through environmental sensors; four data sets are constructed to ensure that the system has an accurate and reliable data foundation, which provides solid support for subsequent load prediction and management, thereby improving the overall performance and management efficiency of the system.

[0072] Example 3

[0073] See also Figure 1 The vehicle charging load prediction module includes a charging load calculation unit and a charging load evaluation unit; the charging load calculation unit obtains the charging load index Cfzs by extracting the charging data set, and the specific calculation formula is as follows:

[0074]

[0075] Where Cdy i represents the charging voltage at the i-th time point, Cgl i represents the charging power at the i-th time point, Csc represents the total charging time in a fixed cycle, Czt represents the charging state value, T max Indicates the maximum temperature allowed by the device, Csb j represents the temperature of the charging device at the Jth time point;

[0076] a1 represents the charging voltage Cdy used to adjust the i-th time point i , the charging power Cgl at the i-th time point i and the weight value of the calculation result of the total charging time Csc in a fixed cycle, a2 represents the maximum temperature T allowed by the device max and the charging device temperature Csb at the Jth time point j The weight value of the calculation result, the specific value is adjusted by the user.

[0077] The charging load evaluation unit performs evaluation by preset load threshold Q1 and load threshold Q2 and charging load index Cfzs, and load threshold Q1>load threshold Q2. The specific evaluation contents are as follows:

[0078] If the charging load index Cfzs ≥ the load threshold Q1, a first charging load result is generated, and load reduction measures are taken at this time, including adjusting the charging power, staggered charging, and load transfer;

[0079] If the load threshold Q1> the charging load index Cfzs> the load threshold Q2, a second charging load result is generated, and the monitoring frequency of the charging load condition is adjusted, including increasing the number of monitoring times by 10% within a fixed period;

[0080] If the load threshold Q2 ≥ the charging load index Cfzs, a third charging load result is generated. At this time, the current charging station is marked as a low load state and the existing operation strategy is maintained.

[0081] In this embodiment, the charging power Cgl reflects the charging speed of the electric vehicle at each moment. The charging power Cgl is understood to optimize the power distribution of the charging station, ensure the efficiency and stability of the charging process, and avoid resource waste or load overload caused by improper power distribution; monitoring the charging voltage Cdy helps to ensure the safety of the charging process. Too high or too low voltage will damage the battery and even cause safety accidents. Real-time monitoring of the charging voltage Cdy can adjust the charging parameters in time to protect the battery and extend its service life; the total charging time Csc within a fixed period records the duration of each charge, which is helpful for analyzing the charging behavior and mode. Through the total charging time Csc within a fixed period, the scheduling and operation of the charging station can be optimized, the utilization rate of the charging station can be improved, and the user waiting time can be reduced; the charging status value Czt includes charging, full and battery abnormality, which provides real-time feedback on the charging process. Monitoring the charging status value Czt helps to timely discover and handle abnormal situations, ensure the smooth progress of the charging process, and improve user experience.

[0082] Example 4

[0083] See also Figure 1 The battery discharge load prediction module includes a discharge load calculation unit and a discharge load evaluation unit; the discharge load calculation unit extracts the power generation data set and fits the charging load index Cfzs to calculate the discharge load index Ffzs. The specific calculation formula is as follows:

[0084]

[0085] In the formula, Fgl represents the power generation, Fdl represents the power generation, Fxl represents the power generation efficiency, and Nxl represents the inverter efficiency;

[0086] s1 represents the weight value of the charging load index Cfzs, and s2 represents the weight value of the discharge load index Ffzs combined with the power generation power Fgl, the power generation amount Fdl, the power generation efficiency Fxl and the inverter efficiency Nxl, and the specific value is adjusted by the user.

[0087] The discharge load evaluation unit evaluates the discharge load index Ffzs by presetting the discharge threshold E1 and the discharge threshold E2, and the discharge threshold E1>the discharge threshold E2. The specific evaluation content is as follows:

[0088] If the discharge load index Ffzs ≥ the discharge threshold E1, a first discharge load result is generated, and the discharge power is reduced, including giving priority to photovoltaic power generation;

[0089] If the discharge threshold E1> the discharge load index Ffzs> the discharge threshold E2, a second discharge load result is generated, and preventive maintenance is performed at this time, including adjusting the frequency of checking the equipment and system status, and increasing the number of inspections by 5% within a fixed period;

[0090] If the discharge threshold E2 ≥ the discharge load index Ffzs, a third discharge load result is generated, and the current discharge strategy is maintained.

[0091] In this embodiment, the power generation Fgl reflects the power generation capacity of the photovoltaic system at each moment. Understanding the power generation Fgl helps to monitor the performance of the photovoltaic system in real time, ensure that the system operates under the best working conditions, and promptly discover and solve power abnormality problems, thereby improving the overall power generation efficiency and stability; the power generation Fdl represents the total amount of electricity generated by the photovoltaic system in a certain period of time. Recording the power generation Fdl helps to evaluate the overall output of the photovoltaic system, conduct long-term performance analysis and investment return evaluation, and provide data support for system maintenance and optimization; the power generation efficiency Fxl is the ratio of power generation to light intensity, reflecting the efficiency of the photovoltaic system in converting solar energy into electrical energy. Monitoring the power generation efficiency Fxl helps to identify performance changes or failures of photovoltaic modules and ensure that the system maintains efficient operation; the inverter efficiency Nxl represents the efficiency of the inverter in converting direct current into alternating current. The inverter efficiency Nxl directly affects the overall power generation efficiency of the system. By monitoring the inverter efficiency Nxl, the performance problems of the inverter can be promptly discovered and solved, ensuring that the loss in the power conversion process is minimized and the overall efficiency of the system is improved.

[0092] Example 5

[0093] See also Figure 1 The power generation prediction module extracts the energy storage data set, and fits the charging load index Cfzs and the discharging load index Ffzs to calculate the power generation index Fdzs. The specific calculation formula is as follows:

[0094]

[0095] In the formula, Cnzs represents the energy storage capacity index, Dl represents the current capacity, Dsl represents the charge and discharge rate, and Dcs represents the number of charge and discharge times;

[0096] The power generation prediction module evaluates the power generation index Fdzs by presetting the power generation threshold E. The specific contents are as follows:

[0097] If the power generation threshold T ≥ the power generation index Fdzs, it means that the predicted power generation meets the expected demand, and the first power generation result is generated;

[0098] If the power generation threshold T is less than the power generation index Fdzs, it means that the predicted power generation does not meet the expected demand. At this time, a second power generation result is generated and a second confirmation is performed in combination with the environmental data set.

[0099] In this embodiment, the current power D1 represents the real-time remaining power of the battery. Monitoring the current power D1 helps to understand the available capacity of the battery, ensure that the battery operates within a reasonable working range, and avoid damage to the battery caused by over-discharge or over-charging. Real-time power information is crucial to the energy management system and helps to optimize the battery charging and discharging strategy and improve the operating efficiency of the system; the charge and discharge rate Dsl reflects the charging or discharging speed of the battery in a specific time period. Understanding the charge and discharge rate Dsl helps to identify the health status and performance changes of the battery and prevent the impact of the charge and discharge rate Dsl being too high or too low on the battery life and safety. By optimizing the charge and discharge rate Dsl, the battery life and the efficiency of the overall system are improved; the charge and discharge number Dcs records the number of charge and discharge cycles of the battery, which is an important indicator for evaluating the battery life and health status. As the charge and discharge number Dcs increases, the capacity and performance of the battery will gradually decrease. By monitoring the charge and discharge number Dcs, the remaining life of the battery is predicted, and a maintenance and replacement plan is formulated to ensure the long-term stable operation of the system.

[0100] Example 6

[0101] See also Figure 1 The battery management control module includes a correction unit and a strategy adjustment unit; the correction unit obtains a secondary correction scheme by fitting the environmental data set, the charging load index Cfzs and the discharging load index Ffzs according to the power generation prediction result. The specific contents are as follows:

[0102]

[0103] Wherein, Fdzs2 represents the secondary power generation index; Wd represents temperature, Sd represents humidity, Gqd represents light intensity, and Fs represents wind speed; d1, d2, d3, and d4 represent the weight values ​​of temperature Wd, humidity Sd, light intensity Gqd, and wind speed Fs, respectively; e represents the exponential function;

[0104] The preset correction threshold R1 and correction threshold R2 are evaluated with the secondary power generation index Fdzs2, and the correction threshold R1>correction threshold R2. The specific evaluation content is as follows:

[0105] If the secondary power generation index Fdzs2 ≥ the correction threshold R1, a first correction result is generated, indicating that the power generation does not meet the expected demand. At this time, the strategy adjustment unit performs analysis and adjusts the control strategy;

[0106] If the correction threshold R1> the secondary power generation index Fdzs2> the correction threshold R2, a second correction result is generated, indicating that the power generation does not meet the expected demand. At this time, the strategy adjustment unit is used to analyze and adjust the priority control order;

[0107] If the correction threshold R2 ≥ the secondary power generation index Fdzs2, a third correction result is generated, indicating that the power generation meets the expected demand and no adjustment is required.

[0108] The strategy adjustment unit adjusts the charging and discharging strategy according to the first correction result and the second correction result, combined with the vehicle charging load prediction result, the battery discharging load prediction result and the power generation prediction result. The specific adjustment content is as follows:

[0109] When the first correction result is generated, the first charging strategy of the charging control strategy is adjusted to use the power of the photovoltaic power generation system for charging load demand; the first discharging strategy of the discharging control strategy is adjusted to use excess power for battery charging; the first balancing strategy of the charging and discharging balancing control strategy is adjusted to regulate battery charging;

[0110] In this embodiment, the temperature Wd directly affects the efficiency of the photovoltaic cell and the performance of the battery. High temperature will reduce the output power of the photovoltaic cell and affect the charging and discharging efficiency and life of the battery. By monitoring the temperature Wd, the operating parameters of the system are optimized to ensure that the photovoltaic system and the battery work within the optimal temperature range, thereby improving the efficiency and stability of the system; the humidity Sd affects the reliability of the photovoltaic system and the life of the battery. The high humidity Sd environment causes corrosion and failure of electrical components, affecting the safety and stability of the system. Monitoring the humidity Sd helps to take moisture-proof measures to protect system components and extend the service life of the equipment; the light intensity Gqd is a direct factor of photovoltaic power generation and determines the power generation of the photovoltaic system. Real-time monitoring of the light intensity Gqd helps to evaluate the power generation efficiency of the photovoltaic system, optimize power generation scheduling and power management, and ensure that the system operates efficiently under different lighting conditions; the wind speed Fs affects the heat dissipation effect of the photovoltaic panel and the stability of the system. The appropriate wind speed Fs helps the photovoltaic panel to dissipate heat and maintain its working efficiency; but too high a wind speed Fs will damage the photovoltaic panel and the support structure. By monitoring the wind speed Fs, the heat dissipation design and structural protection measures are optimized to ensure that the system operates within a safe range.

[0111] Example 7

[0112] See also Figure 2 , a photovoltaic power generation energy storage intelligent control method, comprising the following steps:

[0113] Step 1: collect relevant data of electric vehicle charging stations, photovoltaic power generation systems and energy storage systems in real time through the data acquisition and processing module, including charging demand data of the car charging station, power generation data of the photovoltaic power generation system, power data of the battery energy storage system and environmental parameters, and perform preprocessing;

[0114] Step 2: Establish and use a deep learning model through the vehicle charging load prediction module to dynamically predict the charging load of the electric vehicle; obtain the charging load index Cfzs by calculation, and evaluate the charging load index Cfzs at the same time, predict the load demand of the electric vehicle within a fixed period based on the evaluation results, and generate the vehicle charging load prediction result;

[0115] Step 3: Using the battery discharge load prediction module, a charging load prediction model is established based on historical charging data, vehicle data and environmental data using a machine learning algorithm; at the same time, the discharge load index Ffzs is calculated and evaluated, and the battery discharge load in a future fixed period is predicted based on the evaluation results, and a battery discharge load prediction result is generated;

[0116] Step 4: The power generation prediction module calculates and evaluates the power generation index Fdzs according to the charging load index Cfzs and the discharging load index Ffzs, and finally obtains the power generation prediction result according to the evaluation result of the power generation index Fdzs;

[0117] Step 5. The battery management control module obtains a secondary correction scheme for the power generation prediction result according to the power generation index Fdzs and the environmental data fitting; then dynamically adjusts the battery charging and discharging strategy according to the vehicle charging load prediction result, the battery discharging load prediction result and the power generation prediction result, including the charging priority control strategy, the discharging priority control strategy and the charging and discharging balance control strategy;

[0118] Step 6: Provide users with a visualization interface and tools through the result visualization module to display the charging priority control strategy, the discharging priority control strategy and the charge-discharge balance control strategy.

[0119] In this embodiment, step one ensures the accuracy and timeliness of data, and provides reliable basic data support for subsequent prediction and management; step two helps to optimize the load management of charging stations, improve the operating efficiency and user satisfaction of charging stations; step three helps to formulate reasonable discharge strategies, extend battery life, and improve system stability and efficiency; step four predicts the power generation of the photovoltaic system, provides a basis for energy management, ensures the balance of energy supply and demand, and improves the utilization rate of the photovoltaic system; step five combines the charging and discharging load prediction results to dynamically adjust the battery charging and discharging strategy, optimize system operation, and improve energy utilization efficiency and battery life; step six helps users intuitively understand and manage the system, and improves user experience and management efficiency.

[0120] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A photovoltaic power generation and energy storage intelligent control system, characterized in that: It includes data acquisition and processing module, vehicle charging load prediction module, battery discharge load prediction module, power generation prediction module, battery management control module and result visualization module; The data acquisition and processing module is used to collect relevant data of electric vehicle charging stations, photovoltaic power generation systems and energy storage systems in real time, including charging demand data of vehicle charging stations, power generation data of photovoltaic power generation systems, power data of battery energy storage systems and environmental parameters, and perform preprocessing; The vehicle charging load prediction module is used to establish and use a deep learning model to dynamically predict the charging load of the electric vehicle; The charging load index Cfzs is obtained by calculation, and the charging load index Cfzs is evaluated at the same time. The load demand of the electric vehicle in a fixed period is predicted based on the evaluation result, and the vehicle charging load prediction result is generated; The battery discharge load prediction module is used to establish a charging load prediction model based on historical charging data, vehicle data and environmental data using a machine learning algorithm; at the same time, the discharge load index Ffzs is calculated and evaluated, and the battery discharge load in a future fixed period is predicted based on the evaluation result, and a battery discharge load prediction result is generated; The power generation prediction module is used to calculate and evaluate the power generation index Fdzs according to the charging load index Cfzs and the discharging load index Ffzs, and finally obtain the power generation prediction result according to the evaluation result of the power generation index Fdzs; The battery management control module is used to obtain a secondary correction scheme for the power generation prediction result according to the power generation index Fdzs and the environmental data fitting; and then dynamically adjust the battery charging and discharging strategy according to the vehicle charging load prediction result, the battery discharging load prediction result and the power generation prediction result, including the charging control strategy, the discharging control strategy and the charging and discharging balance control strategy; The result visualization module is used to provide a visualization interface and tools for users to display the charging priority control strategy, the discharging priority control strategy and the charge-discharge balance control strategy.

2. The photovoltaic power generation and energy storage intelligent control system according to claim 1 is characterized by: The data acquisition and processing module includes an acquisition unit and a preprocessing unit; the acquisition unit monitors and records the charging demand of each charging station in real time through the metering equipment installed at the charging station; collects the power generation data of the photovoltaic panel in real time by reading the inverter and electric meter in the photovoltaic power generation system; obtains the battery power data by reading the battery management system of the energy storage system; and monitors the environmental parameters in real time through the installed environmental sensors; The preprocessing unit is used to denoise, eliminate outliers and perform dimensionless processing on the data collected by the acquisition unit, and then construct a charging data set, a power generation data set, an energy storage power data set and an environmental data set respectively; the charging data set includes charging power, charging voltage, total charging time within a fixed period and charging status; the power generation data set includes power generation power, power generation, power generation efficiency and inverter efficiency; the energy storage power data set includes current power, charging and discharging rate and charging and discharging times; the environmental data set includes temperature, humidity, light intensity and wind speed.

3. The photovoltaic power generation and energy storage intelligent control system according to claim 1 is characterized by: The vehicle charging load prediction module includes a charging load calculation unit and a charging load evaluation unit; the charging load calculation unit calculates and obtains the charging load index Cfzs by extracting the charging data set, and the specific calculation formula is as follows: Where Cdy i represents the charging voltage at the i-th time point, Cgl i represents the charging power at the i-th time point, Csc represents the total charging time in a fixed cycle, Czt represents the charging state value, T max Indicates the maximum temperature allowed by the device, Csb j represents the temperature of the charging device at the Jth time point; a1 represents the charging voltage Cdy used to adjust the i-th time point i , the charging power Cgl at the i-th time point i and the weight value of the calculation result of the total charging time Csc in a fixed cycle, a2 represents the maximum temperature T allowed by the device max and the charging device temperature Csb at the Jth time point j The weight value of the calculation result, the specific value is adjusted by the user.

4. A photovoltaic power generation and energy storage intelligent control system according to claim 3, characterized in that: The charging load evaluation unit performs evaluation by preset load threshold Q1 and load threshold Q2 and charging load index Cfzs, and load threshold Q1>load threshold Q2. The specific evaluation contents are as follows: If the charging load index Cfzs ≥ the load threshold Q1, a first charging load result is generated, and load reduction measures are taken at this time, including adjusting the charging power, staggered charging, and load transfer; If the load threshold Q1> the charging load index Cfzs> the load threshold Q2, a second charging load result is generated, and the monitoring frequency of the charging load condition is adjusted, including increasing the number of monitoring times by 10% within a fixed period; If the load threshold Q2 ≥ the charging load index Cfzs, a third charging load result is generated. At this time, the current charging station is marked as a low load state and the existing operation strategy is maintained.

5. A photovoltaic power generation and energy storage intelligent control system according to claim 4, characterized in that: The battery discharge load prediction module includes a discharge load calculation unit and a discharge load evaluation unit; the discharge load calculation unit extracts power generation data and combines and fits the charging load index Cfzs to calculate and obtain the discharge load index Ffzs, and the specific calculation formula is as follows: In the formula, Fgl represents the power generation, Fdl represents the power generation, Fxl represents the power generation efficiency, and Nxl represents the inverter efficiency; s1 represents the weight value of the charging load index Cfzs, and s2 represents the weight value of the discharge load index Ffzs combined with the power generation power Fgl, the power generation amount Fdl, the power generation efficiency Fxl and the inverter efficiency Nxl, and the specific value is adjusted by the user.

6. A photovoltaic power generation and energy storage intelligent control system according to claim 5, characterized in that: The discharge load evaluation unit evaluates the discharge load index Ffzs by presetting the discharge threshold E1 and the discharge threshold E2, and the discharge threshold E1>the discharge threshold E2. The specific evaluation content is as follows: If the discharge load index Ffzs ≥ the discharge threshold E1, a first discharge load result is generated, and the discharge power is reduced, including giving priority to photovoltaic power generation; If the discharge threshold E1> the discharge load index Ffzs> the discharge threshold E2, a second discharge load result is generated, and preventive maintenance is performed at this time, including adjusting the frequency of checking the equipment and system status, and increasing the number of inspections by 5% within a fixed period; If the discharge threshold E2 ≥ the discharge load index Ffzs, a third discharge load result is generated, and the current discharge strategy is maintained.

7. A photovoltaic power generation and energy storage intelligent control system according to claim 6, characterized in that: The power generation prediction module extracts the energy storage power data set and fits the charging load index Cfzs and the discharging load index Ffzs to calculate the power generation index Fdzs. The specific calculation formula is as follows: Wherein, Cnzs represents the energy storage index, Dl represents the current power, Dsl represents the charge and discharge rate, and Dcs represents the number of charge and discharge times; the power generation prediction module evaluates the power generation index Fdzs by presetting the power generation threshold E, and the specific contents are as follows: If the power generation threshold T ≥ the power generation index Fdzs, it means that the predicted power generation meets the expected demand, and the first power generation result is generated; If the power generation threshold T is less than the power generation index Fdzs, it means that the predicted power generation does not meet the expected demand. At this time, a second power generation result is generated and a second confirmation is performed in combination with the environmental data set.

8. The photovoltaic power generation and energy storage intelligent control system according to claim 7, characterized in that: The battery management control module includes a correction unit and a strategy adjustment unit; the correction unit obtains a secondary correction scheme by fitting the environmental data set, the charging load index Cfzs and the discharging load index Ffzs according to the power generation prediction result. The specific contents are as follows: Wherein, Fdzs2 represents the secondary power generation index; Wd represents temperature, Sd represents humidity, Gqd represents light intensity, and Fs represents wind speed; d1, d2, d3, and d4 represent the weight values ​​of temperature Wd, humidity Sd, light intensity Gqd, and wind speed Fs, respectively; e represents the exponential function; The preset correction threshold R1 and correction threshold R2 are evaluated with the secondary power generation index Fdzs2, and the correction threshold R1>correction threshold R2. The specific evaluation content is as follows: If the secondary power generation index Fdzs2 ≥ the correction threshold R1, a first correction result is generated, indicating that the power generation does not meet the expected demand. At this time, the strategy adjustment unit performs analysis and adjusts the control strategy; If the correction threshold R1> the secondary power generation index Fdzs2> the correction threshold R2, a second correction result is generated, indicating that the power generation does not meet the expected demand. At this time, the strategy adjustment unit is used to analyze and adjust the priority control order; If the correction threshold R2 ≥ the secondary power generation index Fdzs2, a third correction result is generated, indicating that the power generation meets the expected demand and no adjustment is required.

9. A photovoltaic power generation and energy storage intelligent control system according to claim 8, characterized in that: The strategy adjustment unit adjusts the charging and discharging strategy according to the first correction result and the second correction result, combined with the vehicle charging load prediction result, the battery discharging load prediction result and the power generation prediction result. The specific adjustment content is as follows: When the first correction result is generated, the first charging strategy of the charging control strategy is adjusted to use the power of the photovoltaic power generation system for charging load demand; the first discharging strategy of the discharging control strategy is adjusted to use excess power for battery charging; the first balancing strategy of the charging and discharging balancing control strategy is adjusted to regulate battery charging; When the second correction result is generated, the first charging strategy of the charging control strategy is adjusted to regulate the power of the charging load and the energy storage system; the first discharging strategy of the discharging control strategy is adjusted to change the battery charging strategy; the first balancing strategy of the charge and discharge balance control strategy is adjusted to change the battery discharge amount and reserve the battery power for future load requirements.

10. A photovoltaic power generation and energy storage intelligent control method, according to a photovoltaic power generation and energy storage intelligent control system according to claims 1 to 9, characterized in that: The following steps are involved: Step 1: collect relevant data of electric vehicle charging stations, photovoltaic power generation systems and energy storage systems in real time through the data acquisition and processing module, including charging demand data of the car charging station, power generation data of the photovoltaic power generation system, power data of the battery energy storage system and environmental parameters, and perform preprocessing; Step 2: Establish and use a deep learning model through the vehicle charging load prediction module to dynamically predict the charging load of electric vehicles; The charging load index Cfzs is obtained by calculation, and the charging load index Cfzs is evaluated at the same time. The load demand of the electric vehicle in a fixed period is predicted based on the evaluation result, and the vehicle charging load prediction result is generated; Step 3: Using the battery discharge load prediction module, a charging load prediction model is established based on historical charging data, vehicle data and environmental data using a machine learning algorithm; at the same time, the discharge load index Ffzs is calculated and evaluated, and the battery discharge load in a future fixed period is predicted based on the evaluation results, and a battery discharge load prediction result is generated; Step 4: The power generation prediction module calculates and evaluates the power generation index Fdzs according to the charging load index Cfzs and the discharging load index Ffzs, and finally obtains the power generation prediction result according to the evaluation result of the power generation index Fdzs; Step 5. The battery management control module obtains a secondary correction scheme for the power generation prediction result according to the power generation index Fdzs and the environmental data fitting; then dynamically adjusts the battery charging and discharging strategy according to the vehicle charging load prediction result, the battery discharging load prediction result and the power generation prediction result, including the charging priority control strategy, the discharging priority control strategy and the charging and discharging balance control strategy; Step 6: Provide users with a visualization interface and tools through the result visualization module to display the charging priority control strategy, the discharging priority control strategy and the charge-discharge balance control strategy.

Images