A control method and system of an intelligent photovoltaic charging pile

Abstract

The application relates to the field of information technology, in particular to a control method and system of an intelligent photovoltaic charging pile in the technical field of automobile charging piles, which comprises the following steps: acquiring charging demand and residual power information of multiple electric vehicles, combining a power distribution algorithm, dynamically adjusting the charging power of each vehicle, and ensuring reasonable distribution of power resources; acquiring real-time load data through a power grid load monitoring system, combining a historical load curve, predicting future power grid load change trends, and judging whether the charging strategy needs to be adjusted; according to historical data and real-time data, adopting a machine learning algorithm to optimize the cooperative working parameters of photovoltaic power generation and battery storage, and improving the overall efficiency of the system; through an intelligent optimization algorithm, the cooperative working mode of photovoltaic power generation, battery storage and power grid power supply is dynamically adjusted; if the light fluctuation is large, a standby power supply is started to supplement power supply, the charging process is ensured not to be affected, the energy storage efficiency is optimized, and power resource waste is reduced.

Description

Technical Field

[0001] This invention relates to the field of information technology, specifically to the field of electric vehicle charging piles, and particularly to a control method and system for an intelligent photovoltaic charging pile. Background Technology

[0002] In existing technologies, the coordinated operation of photovoltaic (PV) power generation and battery energy storage mainly relies on preset fixed parameters and manual adjustments, lacking the ability to dynamically respond to real-time environmental changes. When sunlight conditions fluctuate significantly, existing systems cannot accurately predict PV power generation, leading to overly conservative or aggressive charging strategies that fail to maximize the utilization of PV energy. For example, on cloudy or overcast days, PV power generation drops significantly, but the system may still over-rely on PV, resulting in low charging efficiency. Furthermore, when handling multiple electric vehicles charging simultaneously, existing technologies cannot dynamically allocate power resources based on each vehicle's charging needs and remaining power, easily leading to situations where some vehicles charge too slowly or power resources are wasted. While existing systems can supplement grid power through batteries and PV generation when grid power is insufficient, the lack of real-time monitoring and prediction of grid load prevents intelligent adjustment of charging strategies during peak grid demand periods, potentially further increasing grid load. When handling the coordinated operation of PV power generation, battery energy storage, and grid power supply, existing technologies lack intelligent algorithm support and cannot optimize based on historical and real-time data, resulting in overall system inefficiency and failing to meet the demands of a fast-paced lifestyle. Summary of the Invention

[0003] This invention provides a control method for intelligent photovoltaic charging piles, comprising the following steps:

[0004] S101. Acquire real-time environmental data of light intensity, temperature and humidity through a sensor network, combine them with the physical characteristics of photovoltaic modules, establish a photovoltaic power generation prediction model, and output the predicted power generation value.

[0005] S102. Based on the predicted power generation and the current capacity of the battery, determine whether the charging strategy needs to be adjusted. If the predicted value is lower than the preset threshold, reduce the charging power to avoid over-reliance on photovoltaic power generation.

[0006] S103. Obtain the charging needs and remaining power information of multiple electric vehicles, and dynamically adjust the charging power of each vehicle in conjunction with the power allocation algorithm to ensure the rational allocation of power resources.

[0007] S104. Obtain real-time load data through the power grid load monitoring system, combine it with historical load curves, predict future power grid load change trends, and determine whether it is necessary to adjust the charging strategy.

[0008] S106. If the predicted grid load exceeds the preset threshold, the intelligent optimization algorithm will be activated to adjust the collaborative working mode of photovoltaic power generation, battery energy storage and grid power supply to reduce the grid load.

[0009] S107. Based on historical and real-time data, machine learning algorithms are used to optimize the collaborative working parameters of photovoltaic power generation and battery energy storage to improve the overall system efficiency.

[0010] S108. Through intelligent optimization algorithms, the collaborative working mode of photovoltaic power generation, battery energy storage and grid power supply is dynamically adjusted to ensure that the system operates efficiently under different environmental conditions.

[0011] S109. If there are large fluctuations in sunlight, the backup power supply will be activated to supplement the power supply, ensuring that the charging process is not affected, while optimizing energy storage efficiency and reducing the waste of power resources.

[0012] This invention provides an intelligent photovoltaic charging system and its optimization system, mainly comprising:

[0013] The environmental data acquisition module is used to acquire real-time environmental data such as light intensity, temperature and humidity through a sensor network, and, in combination with the physical characteristics of the photovoltaic module, to establish a photovoltaic power generation prediction model and output the predicted power generation value.

[0014] The power generation prediction module is used to determine whether the charging strategy needs to be adjusted based on the predicted power generation value and the current capacity of the battery. If the predicted value is lower than the preset threshold, the charging power is reduced to avoid over-reliance on photovoltaic power generation.

[0015] The charging strategy adjustment module is used to obtain the charging needs and remaining power information of multiple electric vehicles, and dynamically adjust the charging power of each vehicle in combination with the power allocation algorithm to ensure the rational allocation of power resources.

[0016] The electric vehicle charging management module is used to obtain real-time load data through the power grid load monitoring system, combine it with historical load curves, predict future power grid load change trends, and determine whether the charging strategy needs to be adjusted.

[0017] The power grid load monitoring module is used to activate an intelligent optimization algorithm if the predicted power grid load exceeds a preset threshold, thereby adjusting the collaborative working mode of photovoltaic power generation, battery energy storage, and power grid supply to reduce the power grid load.

[0018] The intelligent optimization module is used to optimize the collaborative working parameters of photovoltaic power generation and battery energy storage based on historical and real-time data using machine learning algorithms, thereby improving the overall system efficiency.

[0019] The collaborative work optimization module is used to dynamically adjust the collaborative work mode of photovoltaic power generation, battery energy storage and grid power supply through intelligent optimization algorithms to ensure that the system operates efficiently under different environmental conditions;

[0020] The backup power management module is used to activate the backup power supply to supplement the power supply if there are large fluctuations in light intensity, ensuring that the charging process is not affected, while optimizing energy storage efficiency and reducing the waste of power resources.

[0021] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0022] This invention discloses a control method and system for intelligent photovoltaic charging piles. It collects environmental data in real time through a sensor network and establishes a power generation prediction model based on the characteristics of photovoltaic modules. Based on the prediction results and battery capacity, the charging strategy is dynamically adjusted to avoid over-reliance on photovoltaic power generation. Simultaneously, the system acquires charging demand and remaining battery power information from multiple electric vehicles and uses a power allocation algorithm to rationally allocate charging power. Furthermore, this invention integrates a power grid load monitoring system to predict future load change trends and activates an intelligent optimization algorithm when the load is too high, adjusting the collaborative working mode of photovoltaic power generation, battery energy storage, and grid power supply. Through machine learning algorithms, this invention continuously optimizes system parameters, improving overall efficiency. When there are large fluctuations in sunlight, a backup power source can be activated to ensure charging stability. This intelligent collaborative working mode significantly improves the efficiency and reliability of the photovoltaic charging system, realizing the rational utilization and intelligent management of power resources. Attached Figure Description

[0023] Figure 1 This is a flowchart of a control method for an intelligent photovoltaic charging pile according to the present invention.

[0024] Figure 2 This is a schematic diagram of a control method and system for an intelligent photovoltaic charging pile according to the present invention.

[0025] Figure 3 This is another schematic diagram of a control method and system for an intelligent photovoltaic charging pile according to the present invention.

[0026] Figure 4 This is a schematic diagram of the control method and system for an intelligent photovoltaic charging pile according to the present invention. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and thoroughly described below with reference to the accompanying drawings. The described embodiments are merely some embodiments of the present invention.

[0028] like Figure 1-4 The control method for an intelligent photovoltaic charging pile in this embodiment may specifically include:

[0029] S101. Acquire real-time environmental data on light intensity, temperature, and humidity through a sensor network, combine this data with the physical characteristics of the photovoltaic module, establish a photovoltaic power generation prediction model, and output the predicted power generation value.

[0030] The system acquires real-time illuminance, temperature, and humidity data collected by a sensor network; matches this data with pre-stored physical parameters of the photovoltaic module to obtain matching data; analyzes the matching data using a regression algorithm to establish a photovoltaic power generation prediction model; determines the theoretical power generation prediction value under the current environmental conditions based on the photovoltaic power generation prediction model; if the real-time illuminance, temperature, and humidity data change, updates the data and re-determines the theoretical power generation prediction value under the current environmental conditions based on the updated data; and compares the theoretical power generation prediction value with historical power generation data to determine its accuracy.

[0031] For example, illuminance data is primarily collected using a radiometer. Solar radiation intensity can reach approximately 1 kilowatt per square meter at midday on a sunny day, but may drop below 200 watts in the morning and evening. Temperature and humidity sensors typically employ an integrated design, simultaneously measuring two parameters. The temperature measurement range is usually between -40°C and 80°C, while the humidity measurement range is between 0% and 100%. The physical parameters of photovoltaic modules include key indicators such as open-circuit voltage, short-circuit current, maximum power point voltage, and current. Taking a monocrystalline silicon module as an example, under standard testing conditions, the open-circuit voltage is approximately 40 volts, the short-circuit current can reach 9 amperes, and the maximum power can reach 300 watts. When matching these parameters with real-time environmental data, the influence of the temperature coefficient must be considered; for example, for every degree Celsius increase in temperature, the output power will decrease by approximately 0.4%. In regression algorithm analysis, a multiple linear regression model can be used, with illuminance, temperature, and humidity as independent variables and power generation as the dependent variable. The model training data should include historical data under different weather conditions; for example, on a cloudy day, illuminance may be around 200 watts per square meter, at which point power generation is approximately 20% of the rated power. The establishment of a predictive model needs to consider component degradation, which typically ranges from 0.5% to 1% annually. Theoretical power generation calculations also need to consider system efficiency, including inverter efficiency, which is usually above 95%, and line loss of approximately 2%. A data update frequency of five minutes can be set to ensure the real-time nature of the predictions. Validation of the prediction results can be accomplished by comparing them with historical data from the same period. For example, under similar weather conditions, if the deviation between the predicted value and the historical actual value is within 5%, the prediction can be considered accurate. For abnormal data, such as a sudden decrease in illuminance without a corresponding change in temperature, the system should identify potential shading or sensor malfunction. During data matching, a mapping relationship between environmental parameters and power generation efficiency needs to be established. For example, when the illuminance is 800 watts per square meter, the temperature is 25 degrees Celsius, and the humidity is 60%, the power generation efficiency of photovoltaic modules can reach 17%. In this case, if the module area is two square meters, the theoretical power generation should be approximately 270 watts. The accuracy of the predictive model is closely related to the time span of data sampling. It is recommended to use at least one year of historical data for model training to fully account for the impact of seasonal variations. For example, electricity generation during midday in summer is usually more than twice that in winter, and this seasonal difference needs to be fully reflected in the model.

[0032] S102. Based on the predicted power generation and the current capacity of the battery, determine whether the charging strategy needs to be adjusted. If the predicted value is lower than the preset threshold, reduce the charging power to avoid over-reliance on photovoltaic power generation.

[0033] The system acquires the predicted photovoltaic power generation and the current battery capacity. It compares the predicted photovoltaic power generation with a preset threshold. If the predicted photovoltaic power generation is less than the preset threshold, it calculates the reduction in charging power and generates a new charging power value based on this reduction. Based on the new charging power value, it generates an updated charging strategy value. Using the updated charging strategy value, it controls the battery charging process to obtain an adjusted charging power. It monitors the changes in the predicted photovoltaic power generation and the current battery capacity in real time to determine if further adjustments to the charging strategy value are needed. If the predicted photovoltaic power generation remains below the preset threshold, it gradually reduces the charging power value to prevent overcharging of the battery. Through cyclical monitoring and adjustment, it maintains the battery within its current capacity range.

[0034] For example, the predicted photovoltaic (PV) power generation is closely related to battery charging management, requiring real-time adjustments to the charging strategy to adapt to the fluctuating characteristics of PV power generation. Data such as light intensity obtained from sensors can predict PV power generation over a future period. For instance, in cloudy weather, the predicted power generation may drop to 60% of the normal value. At this point, the predicted value needs to be compared with a preset threshold. Assuming the system's preset threshold is 70% of peak power generation, when the predicted value falls below this threshold, the charging strategy adjustment mechanism is triggered. Adjusting the charging power needs to consider the current battery capacity. For example, if the battery capacity is at 85%, the charging power can be appropriately reduced. The calculation of the reduction in charging power must comprehensively consider factors such as predicted power generation, battery capacity, and electricity demand. For example, when the predicted power generation drops to 80% of the threshold, the charging power can be reduced by 20% to make the system operate more smoothly. The new charging strategy needs to be dynamically generated based on the adjusted charging power. Assuming the original charging strategy was constant power charging, the adjustment may switch to variable power charging mode. This strategy adjustment can reduce dependence on PV power generation; when PV power generation is insufficient, the system can automatically reduce the charging power to avoid impacting the power grid. During real-time monitoring, the system continuously evaluates the effectiveness of the charging strategy. If the predicted value remains below a threshold for a certain period, such as being below 60% of the preset threshold for three consecutive hours, the system will further reduce the charging power. This gradual adjustment prevents overcharging of the battery and extends its lifespan. Throughout the process, the adjustment of the charging strategy needs to keep the battery capacity within a reasonable range. For example, when the capacity is above 90%, even if photovoltaic power generation is sufficient, the charging power should be appropriately reduced. The system continuously monitors the predicted value and capacity status to ensure that the charging strategy is always in the optimal state. This dynamic adjustment mechanism improves system stability, extends battery lifespan, and ensures that electricity demand is met. By establishing the correlation between predicted values, thresholds, charging power, and battery capacity, the system can achieve intelligent charging management. This management method not only improves energy utilization efficiency but also extends equipment lifespan and reduces operation and maintenance costs. For example, on cloudy days with frequent changes in sunlight intensity, the system can adjust the charging strategy in advance using a predictive model to avoid damage to the battery from frequent charge-discharge cycles.

[0035] S103. Obtain the charging needs and remaining battery power information of multiple electric vehicles, and dynamically adjust the charging power of each vehicle in conjunction with the power allocation algorithm to ensure the rational allocation of power resources.

[0036] The system acquires remaining battery power and charging demand information for multiple electric vehicles to establish a vehicle information database. Based on this database, it calculates the charging priority of each electric vehicle. Using a preset power allocation algorithm, it determines an initial charging power allocation scheme for electric vehicles with different charging priorities. It acquires real-time grid load information and determines whether the load exceeds a preset threshold. If so, it dynamically adjusts the initial charging power allocation scheme based on the preset power allocation algorithm and the real-time grid load information to obtain an updated scheme. Based on the updated scheme, it recalculates the charging power for each electric vehicle and generates an updated charging command. The updated command is then sent to each electric vehicle via a charging pile controller to control the charging operation. The system continuously monitors the battery power changes of each electric vehicle and the grid load during charging, and iteratively executes the dynamic adjustment and power allocation process.

[0037] For example, the intelligent charging system first establishes a vehicle information database containing basic information about each electric vehicle. Taking a residential community as an example, there are fifty electric vehicles in the community. The database records the model, battery capacity, remaining battery percentage, and estimated usage time for each vehicle. A certain model has a battery capacity of 70 kWh, currently has 30% remaining battery, and the user plans to use it at 8:00 AM the next day. Charging priority calculation needs to consider multiple factors. For example, if one vehicle has 20% remaining battery and is expected to be used in two hours, and another vehicle has 15% remaining battery and is expected to be used in six hours, the system will prioritize allocating higher charging power to the vehicle used two hours later. Priority scoring uses a weighted method: remaining battery weight 0.4, usage time weight 0.4, and user special needs weight 0.2. The initial charging power allocation scheme is based on total power limitations. Assuming the community's power distribution capacity is 500 kW and the current grid base load is 200 kW, the total power available for electric vehicle charging is 300 kW. High-priority vehicles can receive 11 kW of charging power, medium-priority vehicles 7 kW, and low-priority vehicles 3.5 kW. Grid load monitoring uses real-time data acquisition. If the grid load exceeds the preset threshold of 450 kilowatts during a certain period, the system immediately activates a dynamic adjustment mechanism. High-priority vehicles are reduced to 7 kilowatts, medium-priority vehicles to 3.5 kilowatts, and low-priority vehicles suspend charging. This adjustment ensures stable grid operation and avoids overload tripping. Charging power redistribution uses a decreasing method. For example, a high-priority vehicle originally allocated 11 kilowatts of charging power is reduced to 7 kilowatts, resulting in a calculated charging time extension of approximately 57%. Simultaneously, the system estimates the time required to complete charging at this power level to ensure that the user's set usage time requirements are met. Charging command issuance employs a tiered control strategy. After receiving a new charging power command, the charging pile controller uses a soft-start method, gradually adjusting to the target power within 30 seconds to avoid impacting the grid from sudden large power changes. Each charging pile is equipped with a power metering device, providing real-time feedback of actual charging power data. During charging process monitoring, the system collects data every minute, recording information including charging power, charging quantity, and battery temperature. If an anomaly is detected, such as the charging power exceeding the set value by 10%, the system automatically issues an alarm and, if necessary, performs a protective power reduction operation. Through continuous monitoring and dynamic adjustments, safe and efficient management of the electric vehicle charging process can be achieved.

[0038] S104. Obtain real-time load data through the power grid load monitoring system, combine it with historical load curves, predict future power grid load change trends, and determine whether it is necessary to adjust the charging strategy.

[0039] The system acquires real-time load data and historical load curve data from the power grid. It then preprocesses the real-time and historical load data using time series analysis to obtain preprocessed load data. This preprocessed load data is input into a pre-established load forecasting model, and a long short-term memory (LSTM) network algorithm is used to predict the load change trend for the next 24 hours. The system determines whether the predicted result exceeds a preset load threshold; if so, it triggers a charging strategy adjustment mechanism. A decision tree algorithm is used to analyze the current charging strategy, and combined with the predicted load change trend, the optimal charging strategy adjustment scheme is determined. This optimal scheme is then sent to the charging pile control system, and the adjusted charging strategy is executed. The system monitors the power grid load changes in real time and determines whether the load value continuously exceeds the preset load threshold. If so, the load forecasting and strategy adjustment process is re-executed until the load value returns to the normal range.

[0040] For example, a power grid load monitoring system integrates data acquisition devices at multiple measuring points to obtain raw data such as voltage and current, which are then processed through data fusion to form real-time load data. For instance, the load data for a regional power grid at 9:00 AM on a weekday is 8,000 kilowatts, and this value is compared with historical data for the same period. Historical load curve data typically includes electricity consumption data from the same time period and similar weather conditions over the past year. Outliers, such as sudden high load records due to equipment failure, are removed through data cleaning. Time series analysis uses a sliding window method to smooth the data; the window size can be set to four hours, and short-term fluctuations are eliminated by calculating a moving average. Long Short-Term Memory (LSTM) network algorithms have significant advantages in load forecasting, as they can simultaneously consider short-term load changes and long-term electricity consumption patterns. The forecast model input includes features such as temperature, date type, and historical load, and outputs time-segmented load forecasts for the next 24 hours. In practical applications, load forecasts for a commercial area on a summer weekday show that the load may exceed the warning threshold of 10,000 kilowatts between 2:00 PM and 4:00 PM. This triggers a charging strategy adjustment mechanism, where a decision tree algorithm constructs judgment rules based on factors such as charging priority, remaining power, and user demand. For example, electric vehicles can be categorized into three types: emergency vehicles, public transport vehicles, and private cars, each assigned a different charging weight. Charging strategy adjustment schemes can include two dimensions: power limiting and time shifting. When the predicted load approaches a threshold, the charging power of private cars is limited, shifting some charging demand to off-peak hours at night. For example, the original 20 kW charging power is reduced to 10 kW, extending the charging time. Emergency vehicles maintain their original charging strategy to ensure emergency service needs. A continuous load monitoring mechanism sets multi-level early warning thresholds, initiating response measures at each level when the load reaches the warning value. For instance, if an industrial park's load exceeds the warning value for 30 minutes during peak electricity consumption, the system automatically re-executes predictive analysis and dynamically adjusts the charging power allocation scheme based on the updated load trend. This dynamic adjustment mechanism can smooth load fluctuations, improve grid stability, and simultaneously meet the charging needs of electric vehicle users.

[0041] S105. If the predicted grid load exceeds the preset threshold, the intelligent optimization algorithm will be activated to adjust the collaborative working mode of photovoltaic power generation, battery energy storage and grid power supply to reduce the grid load.

[0042] The system acquires real-time predicted values ​​of the grid load and compares these values ​​with a preset threshold. If the predicted values ​​exceed the preset threshold, an intelligent optimization algorithm is activated to calculate the optimal coordination mode for photovoltaic (PV) power generation, battery storage, and grid power supply. The output power of the PV power generation is adjusted according to the optimal coordination mode to obtain the adjusted PV power output. The charging and discharging strategy of the battery is adjusted according to the optimal coordination mode to obtain an optimized battery charging and discharging strategy. An optimized grid power supply allocation strategy is determined according to the optimal coordination mode. Based on the adjusted PV power output, the optimized battery charging and discharging strategy, and the optimized grid power supply allocation strategy, the grid load is reduced to obtain an adjusted grid load value. It is then determined whether the adjusted grid load value meets the preset threshold requirement. If so, the adjusted PV power output, the optimized battery charging and discharging strategy, and the optimized grid power supply allocation strategy are output.

[0043] For example, grid load forecasting is a key aspect of smart grid management. Real-time load data from key nodes such as substations and distribution rooms is acquired through data acquisition equipment, combined with historical load curves and weather forecasts, and then deep learning algorithms are used for load forecasting. A preset threshold is typically set at 85% of the substation's rated capacity, ensuring both power supply security and full utilization of power resources. When the predicted load reaches 1200 kilowatt-hours per hour, approaching the preset threshold, the system automatically activates the intelligent optimization algorithm. The coordinated optimization of photovoltaic power generation, battery energy storage, and grid power supply involves multiple aspects. Taking an industrial park as an example, the park has a rooftop photovoltaic power generation system with a total installed capacity of 1000 kilowatts, equipped with a 500 kilowatt-hour energy storage system. During peak electricity consumption periods, increasing the output power of photovoltaic power generation can alleviate the pressure on the grid. The photovoltaic power generation system dynamically adjusts the inverter's operating parameters based on solar irradiance and temperature conditions to maintain optimal power generation. The battery energy storage system plays a crucial role in grid peak shaving. During the day, when photovoltaic power generation is sufficient, excess electricity is stored in batteries. During peak electricity consumption periods, battery discharge supplements the electricity demand, significantly reducing the grid load. The energy storage system employs a smart charging and discharging strategy, charging during periods of lower electricity prices and discharging during peak periods, ensuring both power supply reliability and reduced electricity costs. The grid power supply optimization strategy primarily considers load balancing and economy. During the peak electricity consumption period from 7:00 AM to 9:00 AM on weekdays, the system prioritizes energy storage power while increasing the grid-connected power of photovoltaic (PV) power generation. At midday, when PV power generation reaches its peak, the proportion of grid power supply is reduced, and excess electricity is stored in the energy storage system. In the evening, the power supply ratio of the three power sources is rationally allocated based on load forecasts. The load monitoring system collects data from each electricity consumption stage in real time and analyzes the data to determine the optimization effect. Taking a commercial complex as an example, after adopting the smart optimization strategy, the peak grid load decreased from 800 kilowatts to 600 kilowatts, reducing electricity costs by 20%. The system continuously monitors load changes, and when the load value exceeds the threshold, it immediately initiates a new round of optimization calculations to ensure the power supply system is always in optimal operating condition. This dynamic optimization mechanism ensures both power supply quality and efficient energy utilization.

[0044] S106. Based on historical and real-time data, machine learning algorithms are used to optimize the collaborative working parameters of photovoltaic power generation and battery energy storage to improve the overall system efficiency.

[0045] Historical and real-time operating data of the photovoltaic system and the battery system are acquired, and a data integration model is established to obtain integrated operating data. Features are extracted from the integrated operating data to obtain a feature data set. The feature data set is then optimized using a random forest algorithm to obtain optimized feature parameters. Based on the optimized feature parameters, the optimal collaborative working mode of the photovoltaic system and the battery system is determined. The optimal collaborative working mode is then tested for stability using a support vector machine algorithm to obtain the test results. If the test results indicate that the optimal collaborative working mode is unstable, it is corrected to obtain a corrected optimal collaborative working mode. The corrected optimal collaborative working mode is then used to establish a dynamic balance model between photovoltaic power generation and battery energy storage. The dynamic balance model is iteratively optimized using a gradient boosting decision tree algorithm to obtain an optimized dynamic balance model. Based on the optimized dynamic balance model, the final control strategy parameters for the photovoltaic system and the battery system are generated.

[0046] For example, data integration models are fundamental to understanding the operational patterns of photovoltaic (PV) and battery systems. By collecting historical data such as PV power generation, battery charge / discharge status, ambient temperature, and light intensity, and combining this with real-time monitoring data, a system operation feature database is constructed. This includes data on the variation of PV power generation under different seasons and weather conditions, as well as the performance of batteries at different temperatures and charge / discharge depths. The random forest algorithm extracts system features by constructing multiple decision trees. For PV systems, features such as the relationship between light intensity and power generation efficiency, and the impact of temperature on power generation efficiency can be extracted. For battery systems, features such as the relationship between charge / discharge cycle count and capacity decay, and the impact of ambient temperature on charging efficiency can be extracted. For example, analysis shows that when the ambient temperature exceeds 35 degrees Celsius, battery charging efficiency decreases by 15%. Determining the optimal collaborative working mode requires considering multiple factors. When sunlight is abundant, PV power generation should be prioritized for supplying electricity while simultaneously charging the battery. During peak electricity consumption periods, the ratio of PV power generation to battery discharge should be rationally allocated. For example, at midday when sunlight is strongest, 70% of PV power generation could be used for load power supply, and 30% for battery charging. Support Vector Machine (SVM) algorithms are used to detect the stability of operating modes. By establishing a multi-dimensional feature space, it determines whether the current operating mode will lead to system instability. For example, when a rapid change in light intensity is detected, the power allocation ratio between photovoltaic (PV) power generation and battery storage is adjusted in a timely manner to avoid power fluctuations. Dynamic equilibrium models primarily address the intermittency of PV power generation. On cloudy days, the battery discharge power is increased to supplement insufficient power supply. When there is sufficient sunlight, excess power generation is stored in the battery. For example, if a cloudy day is predicted within the next four hours, the battery charging is increased in advance to prepare for subsequent power shortages. Gradient boosting decision tree algorithms improve system performance through continuous iterative optimization. Each iteration is based on the results of the previous iteration, specifically improving the control strategy. For example, if analysis reveals that electricity consumption gradually increases from 6:00 AM to 8:00 AM, the algorithm automatically adjusts the battery discharge strategy during this period to ensure stable power supply. The final control strategy parameters include the PV power generation power curve and the battery charge / discharge schedule. These parameters are dynamically adjusted according to seasonal changes and variations in electricity demand. For example, when the air conditioning load increases in summer, the power output of photovoltaic power generation will be increased before 9:00 a.m. to prepare for the peak electricity consumption during the day.

[0047] S107. Through intelligent optimization algorithms, the collaborative working mode of photovoltaic power generation, battery energy storage and grid power supply is dynamically adjusted to ensure that the system operates efficiently under different environmental conditions.

[0048] The system acquires real-time data on photovoltaic (PV) power generation, including the PV cell's power output; acquires energy storage status data on the battery, including the battery's charge and discharge power; acquires load demand data on grid power supply, including the power demand of electrical equipment; based on the real-time data, the energy storage status data, and the load demand data, a preset optimization algorithm is used to determine whether the system's operating mode is in its optimal state; if the operating mode is not optimal, the coordinated operating mode of PV power generation, battery energy storage, and grid power supply is dynamically adjusted according to the current environmental conditions; when adjusting the coordinated operating mode, new system operating parameters corresponding to the current environmental conditions are acquired, including PV power generation, battery charge and discharge power, and grid power supply; based on the new system operating parameters, a coordinated operating strategy for PV power generation, battery energy storage, and grid power supply is determined to obtain the adjusted coordinated operating mode; it is determined whether the adjusted coordinated operating mode is an efficient mode; if yes, the control system operates according to the adjusted coordinated operating mode; if not, the process returns to the step of dynamically adjusting the coordinated operating mode until an efficient coordinated operating mode is obtained.

[0049] For example, the real-time photovoltaic power generation data collected by intelligent algorithms includes environmental parameters such as solar irradiance, temperature, and humidity, as well as operating parameters such as output voltage, current, and power of photovoltaic modules. For instance, on sunny summer days, the photovoltaic system adjusts its maximum power point tracking control according to changes in light intensity. When the irradiance reaches 1 kilowatt-hour per square meter, the system's output power can reach over 90% of its design rating. Battery energy storage status monitoring mainly focuses on core indicators such as depth of charge / discharge, state of charge, and operating temperature. For example, lithium iron phosphate batteries can maximize their lifespan when operating within a state of charge range of 20% to 80%. When the energy storage system detects a battery temperature exceeding 40 degrees Celsius, it needs to activate the cooling system for temperature regulation. The analysis of grid power load demand is based on the characteristics of the electricity load curve. For example, industrial areas have higher electricity loads during the day and lower loads at night; in this case, energy storage scheduling can be optimized based on load forecast results. When peak electricity demand is predicted, the system will arrange battery charging in advance to prepare for peak power supply. The evaluation of system operating status uses multi-dimensional indicators, including photovoltaic power generation efficiency, energy storage conversion efficiency, and load response speed. When photovoltaic (PV) power generation efficiency falls below the expected target, the system automatically checks whether the component surfaces need cleaning and monitors whether the system is functioning properly. If the energy storage system's charging and discharging efficiency drops below 85%, power regulation or equipment maintenance is required. Dynamic adjustments to the collaborative working mode are based on real-time data and predictive models. For example, during cloudy or rainy weather, the system adjusts the PV power generation plan according to weather forecasts, increasing the energy storage system's discharge power to ensure a stable supply of electricity to the load. When a sudden drop in PV power generation is detected, the energy storage system can respond in milliseconds to promptly fill the power gap. System parameter adjustments due to changes in environmental conditions involve multiple levels. For example, during the spring and autumn seasons with large diurnal temperature variations, the system adjusts the PV module's operating voltage according to temperature changes to optimize power generation efficiency. The energy storage system also adjusts the charging and discharging current according to ambient temperature changes to protect battery life. The final collaborative working strategy needs to balance the needs of the generation, storage, and consumption sides. When PV power generation is sufficient, priority is given to meeting the electricity load, with excess power used for energy storage charging. When the electricity load exceeds the PV power generation capacity, the energy storage system works with the grid to share the load, achieving the most economical power supply solution.

[0050] S108. If there are large fluctuations in sunlight, the backup power supply will be activated to supplement the power supply, ensuring that the charging process is not affected, while optimizing energy storage efficiency and reducing the waste of power resources.

[0051] The system acquires the current illuminance value, calculates its fluctuation rate, and compares it with a preset threshold. If the fluctuation rate exceeds the threshold, it calculates the required additional power and determines the activation value of the backup power supply based on this required additional power. It then acquires the current energy storage capacity of the backup power supply. Based on the required additional power and the current energy storage capacity, it determines whether the backup power supply meets the power supply requirements. If it does, it activates and supplies power. If not, it calculates the optimal energy storage efficiency value, adjusts the operating parameters of the energy storage device based on this value, and acquires the adjusted energy storage capacity. Based on the adjusted energy storage capacity, it reassesses the power supply capacity of the backup power supply, determines the final required additional power, and activates and supplies power. Finally, it acquires the power consumption of the backup power supply during power supply, calculates the amount of wasted power resources, and determines whether the wasted power exceeds a preset range. If it does, it adjusts the power supply strategy of the backup power supply to optimize energy storage efficiency and reduce power resource waste.

[0052] For example, irradiance fluctuation detection is an important indicator for measuring the stability of photovoltaic (PV) power generation. Irradiance data is collected in real time by PV array sensors, and the fluctuation rate is calculated by comparing changes in irradiance values ​​over adjacent time periods. For instance, on a sunny day with many clouds, irradiance may drop from 1 kilowatt per square meter to 300 watts per square meter in a short period, with a fluctuation rate reaching 70%, far exceeding the normal operating threshold of 20%. The system needs to calculate the required supplementary power to maintain a stable power supply. When irradiance fluctuations cause insufficient PV output power, the actual power gap needs to be calculated and the startup parameters of the backup power supply determined. For example, if the load is 50 kilowatts, but the actual PV output is only 30 kilowatts, a backup power supply is needed to provide 20 kilowatts of supplementary power. The backup power supply typically uses a battery energy storage system, and its energy storage status needs to be monitored in real time. Assuming the battery bank has a rated capacity of 100 kilowatts and the current remaining capacity is 60 kilowatts, it can meet the 20 kilowatt supplementary demand. However, if the remaining capacity is lower than the required supplementary capacity, energy storage efficiency needs to be optimized. Energy storage efficiency optimization includes adjusting charging and discharging strategies and temperature management. By controlling the charging and discharging current and adjusting battery temperature, batteries can be kept in optimal operating condition. For example, reducing the charging current from 0.5 times the rated current to 0.3 times the rated current can reduce heat loss and improve charging efficiency by about 5%. Monitoring power consumption during the power supply process is crucial for energy conservation and consumption reduction. The system records the power curves of each electrical device to analyze whether there is unnecessary energy waste. If some devices are detected to have significant power consumption in standby mode, or if the supply voltage is too high, causing additional losses, the power supply strategy needs to be adjusted promptly. Dynamically adjusting the backup power supply strategy can significantly improve system efficiency. For example, when there is sufficient sunlight, photovoltaic power generation is prioritized while charging the battery. When cloudy or rainy weather is predicted, battery energy storage is increased in advance to prepare for subsequent power supply fluctuations. This proactive adjustment method can improve the overall system operating efficiency by more than 15%, effectively reducing the waste of electrical resources.

[0053] This invention provides an intelligent photovoltaic charging system and its optimization system, mainly comprising:

[0054] The environmental data acquisition module is used to acquire real-time environmental data such as light intensity, temperature and humidity through a sensor network, and, in combination with the physical characteristics of the photovoltaic module, to establish a photovoltaic power generation prediction model and output the predicted power generation value.

[0055] The power generation prediction module is used to determine whether the charging strategy needs to be adjusted based on the predicted power generation value and the current capacity of the battery. If the predicted value is lower than the preset threshold, the charging power is reduced to avoid over-reliance on photovoltaic power generation.

[0056] The charging strategy adjustment module is used to obtain the charging needs and remaining power information of multiple electric vehicles, and dynamically adjust the charging power of each vehicle in combination with the power allocation algorithm to ensure the rational allocation of power resources.

[0057] The electric vehicle charging management module is used to obtain real-time load data through the power grid load monitoring system, combine it with historical load curves, predict future power grid load change trends, and determine whether the charging strategy needs to be adjusted.

[0058] The power grid load monitoring module is used to activate an intelligent optimization algorithm if the predicted power grid load exceeds a preset threshold, thereby adjusting the collaborative working mode of photovoltaic power generation, battery energy storage, and power grid supply to reduce the power grid load.

[0059] The intelligent optimization module is used to optimize the collaborative working parameters of photovoltaic power generation and battery energy storage based on historical and real-time data using machine learning algorithms, thereby improving the overall system efficiency.

[0060] The collaborative work optimization module is used to dynamically adjust the collaborative work mode of photovoltaic power generation, battery energy storage and grid power supply through intelligent optimization algorithms to ensure that the system operates efficiently under different environmental conditions;

[0061] The backup power management module is used to activate the backup power supply to supplement the power supply if there are large fluctuations in light intensity, ensuring that the charging process is not affected, while optimizing energy storage efficiency and reducing the waste of power resources.

[0062] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A control method for an intelligent photovoltaic charging pile, characterized in that, The method includes the following steps: S101. Acquire real-time environmental data of light intensity, temperature and humidity through a sensor network, combine them with the physical characteristics of photovoltaic modules, establish a photovoltaic power generation prediction model, and output the predicted power generation value. S102. Based on the predicted power generation and the current capacity of the battery, determine whether the charging strategy needs to be adjusted. If the predicted value is lower than the preset threshold, reduce the charging power to avoid over-reliance on photovoltaic power generation. S102 includes: acquiring a predicted photovoltaic power generation value and a current battery capacity value; comparing the predicted photovoltaic power generation value with a preset threshold; if the predicted photovoltaic power generation value is less than the preset threshold, calculating the reduction in charging power and generating a new charging power value based on the reduction in charging power; generating an updated charging strategy value based on the new charging power value; using the updated charging strategy value to control the charging process of the battery and obtain an adjusted charging power; monitoring the changes in the predicted photovoltaic power generation value and the current battery capacity value in real time to determine whether further adjustment of the charging strategy value is needed; if the predicted photovoltaic power generation value continues to be lower than the preset threshold, gradually reducing the charging power value to avoid overcharging of the battery; and maintaining the battery within its current capacity range through cyclic monitoring and adjustment. S103. Obtain the charging needs and remaining power information of multiple electric vehicles, and dynamically adjust the charging power of each vehicle in conjunction with the power allocation algorithm to ensure the rational allocation of power resources. S103 includes: acquiring remaining battery power information and charging demand information of multiple electric vehicles, and establishing a vehicle information database for the electric vehicles; calculating the charging priority of each electric vehicle based on the remaining battery power information and charging demand information of each electric vehicle in the vehicle information database; determining an initial charging power allocation scheme for electric vehicles with different charging priorities using a preset power allocation algorithm; acquiring real-time grid load information and determining whether the real-time grid load exceeds a preset threshold; if so, dynamically adjusting the initial charging power allocation scheme based on the preset power allocation algorithm and the real-time grid load information to obtain an updated charging power allocation scheme; recalculating the charging power of each electric vehicle according to the updated charging power allocation scheme and generating an updated charging command; sending the updated charging command to each electric vehicle through a charging pile controller to control the execution of the charging operation; continuously monitoring the changes in battery power of each electric vehicle and the grid load information during the charging process, and cyclically executing the dynamic adjustment and power allocation process; S104. Obtain real-time load data through the power grid load monitoring system, combine it with historical load curves, predict future power grid load change trends, and determine whether it is necessary to adjust the charging strategy. S104 includes: acquiring real-time load data and historical load curve data of the power grid; preprocessing the real-time load data and historical load data using a time series analysis method to obtain preprocessed load data; inputting the preprocessed load data into a pre-established load prediction model; performing load prediction using a long short-term memory network algorithm to obtain a load change trend prediction result for the next 24 hours; determining whether the prediction result exceeds a preset load threshold; if so, triggering a charging strategy adjustment mechanism; analyzing the current charging strategy using a decision tree algorithm; combining the predicted load change trend to determine the optimal charging strategy adjustment scheme; sending the optimal charging strategy adjustment scheme to the charging pile control system and executing the adjusted charging strategy; monitoring the power grid load change in real time; determining whether the load value continuously exceeds the preset load threshold; if so, re-executing the load prediction and strategy adjustment process until the load value returns to the normal range. S105. If the predicted grid load exceeds the preset threshold, the intelligent optimization algorithm will be activated to adjust the collaborative working mode of photovoltaic power generation, battery energy storage and grid power supply to reduce the grid load. S106. Based on historical and real-time data, machine learning algorithms are used to optimize the collaborative working parameters of photovoltaic power generation and battery energy storage to improve the overall system efficiency. S107. Through intelligent optimization algorithms, the collaborative working mode of photovoltaic power generation, battery energy storage and grid power supply is dynamically adjusted to ensure that the system operates efficiently under different environmental conditions; S108. If there are large fluctuations in light intensity, the backup power supply will be activated to supplement the power supply, ensuring that the charging process is not affected, while optimizing energy storage efficiency and reducing the waste of power resources. S108 includes: acquiring the current illuminance value, calculating the fluctuation rate of the current illuminance value, comparing the fluctuation rate with a preset threshold, if the fluctuation rate exceeds the threshold, calculating the amount of electricity that needs to be replenished, determining the start-up value of the backup power supply based on the amount of electricity that needs to be replenished, acquiring the current energy storage of the backup power supply, determining whether the backup power supply meets the power supply requirements based on the amount of electricity that needs to be replenished and the current energy storage, if it does, controlling the backup power supply to start and supply power, if it does not, calculating the optimal energy storage efficiency value, adjusting the operating parameters of the energy storage device based on the optimal energy storage efficiency value, acquiring the energy storage of the adjusted energy storage device, re-evaluating the power supply capacity of the backup power supply based on the adjusted energy storage of the energy storage device, determining the final amount of electricity that needs to be replenished, controlling the backup power supply to start and supply power, acquiring the power consumption of the backup power supply during the power supply process, calculating the amount of power wastage, determining whether the amount of wastage exceeds a preset range, if it exceeds, adjusting the power supply strategy of the backup power supply, optimizing the energy storage efficiency, and reducing the waste of power resources.

2. The control method for an intelligent photovoltaic charging pile according to claim 1, characterized in that, S101 includes: acquiring real-time illuminance, temperature and humidity data collected by the sensor network; The real-time illuminance, temperature, and humidity data are matched with pre-stored physical parameters of the photovoltaic modules to obtain matching data. A regression algorithm is used to analyze the matching data to establish a photovoltaic power generation prediction model. Based on the photovoltaic power generation prediction model, the theoretical power generation prediction value under the current environmental conditions is determined. If the real-time illuminance, temperature, and humidity data change, the real-time illuminance, temperature, and humidity data are updated, and the theoretical power generation prediction value under the current environmental conditions is re-determined based on the updated real-time illuminance, temperature, and humidity data. The theoretical power generation prediction value is compared with historical power generation data to determine the accuracy of the theoretical power generation prediction value.

3. The control method for an intelligent photovoltaic charging pile according to any one of claims 1-2, characterized in that, S105 includes: acquiring a real-time predicted value of the grid load; comparing the real-time predicted value with a preset threshold; if the real-time predicted value exceeds the preset threshold, then activating an intelligent optimization algorithm to calculate the optimal coordination mode of photovoltaic power generation, battery energy storage, and grid power supply; adjusting the output power of photovoltaic power generation according to the optimal coordination mode to obtain the adjusted photovoltaic power generation output power; adjusting the charging and discharging strategy of the battery according to the optimal coordination mode to obtain the optimized battery charging and discharging strategy; determining the optimized allocation strategy of grid power supply according to the optimal coordination mode; reducing the grid load according to the adjusted photovoltaic power generation output power, the optimized battery charging and discharging strategy, and the optimized allocation strategy of grid power supply to obtain the adjusted grid load value; determining whether the adjusted grid load value meets the preset threshold requirement; if so, outputting the adjusted photovoltaic power generation output power, the optimized battery charging and discharging strategy, and the optimized allocation strategy of grid power supply.

4. The control method for an intelligent photovoltaic charging pile according to any one of claims 1-2, characterized in that, S106 includes: acquiring historical and real-time operating data of the photovoltaic system and the battery system, establishing a data integration model, and obtaining integrated operating data; extracting features from the integrated operating data to obtain a feature data set; optimizing the features data set using a random forest algorithm to obtain optimized feature parameters; determining the optimal collaborative working mode of the photovoltaic system and the battery system based on the optimized feature parameters; performing stability testing on the optimal collaborative working mode using a support vector machine algorithm to obtain a testing result; if the testing result indicates that the optimal collaborative working mode is unstable, correcting the optimal collaborative working mode to obtain a corrected optimal collaborative working mode; acquiring the corrected optimal collaborative working mode and establishing a dynamic balance model of photovoltaic power generation and battery energy storage; iteratively optimizing the dynamic balance model using a gradient boosting decision tree algorithm to obtain an optimized dynamic balance model; and generating the final control strategy parameters of the photovoltaic system and the battery system based on the optimized dynamic balance model.

5. The control method for an intelligent photovoltaic charging pile according to any one of claims 1-2, characterized in that, S107 includes: acquiring real-time data of photovoltaic power generation, the real-time data including the power generation power of photovoltaic cells; acquiring energy storage status data of batteries, the energy storage status data including the battery's charge and discharge power; acquiring load demand data of grid power supply, the load demand data including the power demand of electrical equipment; determining whether the system's operating mode is in the optimal state using a preset optimization algorithm based on the real-time data, the energy storage status data, and the load demand data; if the operating mode is not in the optimal state, dynamically adjusting the collaborative working mode of photovoltaic power generation, battery energy storage, and grid power supply according to the current environmental conditions; when adjusting the collaborative working mode, acquiring new system operating parameters corresponding to the current environmental conditions, the new system operating parameters including photovoltaic power generation power, battery charge and discharge power, and grid power supply power; determining the collaborative working strategy of photovoltaic power generation, battery energy storage, and grid power supply based on the new system operating parameters, obtaining the adjusted collaborative working mode; determining whether the adjusted collaborative working mode is an efficient mode; if yes, controlling the system to operate according to the adjusted collaborative working mode; if not, returning to the step of dynamically adjusting the collaborative working mode until an efficient collaborative working mode is obtained.

6. A control system for an intelligent photovoltaic charging pile, characterized in that, This system is used to implement the control method for an intelligent photovoltaic charging pile according to any one of claims 1-5, the system comprising: The environmental data acquisition module is used to acquire real-time environmental data such as light intensity, temperature and humidity through a sensor network, and, in combination with the physical characteristics of the photovoltaic module, to establish a photovoltaic power generation prediction model and output the predicted power generation value. The power generation prediction module is used to determine whether the charging strategy needs to be adjusted based on the predicted power generation value and the current capacity of the battery. If the predicted value is lower than the preset threshold, the charging power is reduced to avoid over-reliance on photovoltaic power generation. The charging strategy adjustment module is used to obtain the charging needs and remaining power information of multiple electric vehicles, and dynamically adjust the charging power of each vehicle in combination with the power allocation algorithm to ensure the rational allocation of power resources. The electric vehicle charging management module is used to obtain real-time load data through the power grid load monitoring system, combine it with historical load curves, predict future power grid load change trends, and determine whether the charging strategy needs to be adjusted. The power grid load monitoring module is used to activate an intelligent optimization algorithm if the predicted power grid load exceeds a preset threshold, thereby adjusting the collaborative working mode of photovoltaic power generation, battery energy storage, and power grid supply to reduce the power grid load. The intelligent optimization module is used to optimize the collaborative working parameters of photovoltaic power generation and battery energy storage based on historical and real-time data using machine learning algorithms, thereby improving the overall system efficiency. The collaborative work optimization module is used to dynamically adjust the collaborative work mode of photovoltaic power generation, battery energy storage and grid power supply through intelligent optimization algorithms to ensure that the system operates efficiently under different environmental conditions; The backup power management module is used to activate the backup power supply to supplement the power supply if there are large fluctuations in light intensity, ensuring that the charging process is not affected, while optimizing energy storage efficiency and reducing the waste of power resources.

Images