Photovoltaic energy storage control method and photovoltaic energy storage control system

Abstract

The invention discloses a photovoltaic energy storage control method and a photovoltaic energy storage control system, and relates to the field of G06F30 / 27 machine learning. According to the method, a photovoltaic energy storage system trains a preset convolutional neural network model and a recurrent neural network model to obtain an optimal working point calculation model and a model for predicting electricity consumption in one hour in the future; the system obtains the current maximum power tracking point parameter and the electricity consumption in one hour in the future according to different data input models by using data collected in real time; when the energy storage proportion value of the predicted total electric quantity and the electricity consumption in one hour in the future does not exceed a preset threshold value, controlling the photovoltaic panel to generate power according to the maximum power tracking point parameter; if yes, the power generation duration proportion is controlled according to the proportion. By implementing the technical scheme provided by the invention, the power generation behavior of the photovoltaic panel is flexibly adjusted according to real-time power generation and power consumption conditions, so that the waste of electric energy is avoided, stable power supply of the system under different power consumption requirements can be ensured, and the adaptability and flexibility of the whole photovoltaic energy storage system are improved.

Description

Technical Field

[0001] The present application relates to the field of G06F30 / 27 machine learning, and in particular to a photovoltaic energy storage control method and a photovoltaic energy storage control system. Background Art

[0002] With the growth of global energy demand and the improvement of environmental awareness, photovoltaic energy storage, as an important way of utilizing new energy, is an important means to promote the transformation of energy structure and achieve sustainable development. It helps to reduce dependence on fossil energy and reduce greenhouse gas emissions, thereby responding to climate change and energy crisis.

[0003] At present, photovoltaic energy storage control systems are mainly composed of photovoltaic modules, energy storage devices (such as battery packs), power conversion devices (such as inverters) and control systems. Photovoltaic modules are responsible for capturing sunlight and converting it into electrical energy. The generated electrical energy first undergoes necessary voltage and current adjustments through the power conversion device to meet the needs of the power grid or direct load use. In order to improve the utilization rate of solar energy, the efficiency of photovoltaic modules is maximized as much as possible in the photovoltaic energy storage systems currently used.

[0004] However, since the intensity and distribution of sunlight can change significantly with time and weather conditions, the demand for electricity can also change significantly in different time periods. Existing photovoltaic energy storage control systems can often only be regulated based on simple rules and lack intelligent and flexible control strategies. As a result, photovoltaic energy storage systems cannot achieve efficient energy management and optimized scheduling when faced with complex power generation and power consumption scenarios, which may lead to power waste or insufficient power supply. Summary of the invention

[0005] The present application provides a photovoltaic energy storage control method and a photovoltaic energy storage control system, which are used to adjust the power generation behavior of photovoltaic panels, thereby achieving efficient utilization and optimized management of energy.

[0006] In a first aspect, the present application provides a photovoltaic energy storage control method, which is applied to a photovoltaic energy storage control system. The method includes: using a working point training data group to train a preset convolutional neural network to obtain an optimal working point calculation model for a photovoltaic panel, the optimal working point calculation model is used to output a maximum power tracking point parameter based on a set of historical power generation data, historical battery status data and historical lighting condition data input, the working point training data group includes multiple working point training data, each training data includes a historical power generation data, a historical battery status data and a historical lighting condition data and a corresponding marked correspondence between the maximum power tracking point parameter; using a predicted power consumption training data group to train a preset recurrent neural network model to obtain a predicted power consumption model for the next hour, the predicted power consumption model for the next hour is used to output the power consumption for the next hour based on a set of historical power consumption data and historical weather data input; the predicted power consumption training data group includes multiple predicted power consumption training data, each training data includes a historical power consumption data and a historical weather data and a corresponding marked correspondence between the power consumption for the next hour. Correspondence relationship; collect real-time illumination condition data through built-in sensors, and obtain real-time weather data, real-time power generation data, real-time power consumption data and real-time battery status data; retrieve the real-time power generation data, the real-time battery status data and the real-time illumination condition data, input the optimal working point calculation model, obtain the current maximum power tracking point parameter, and calculate the power generation in the next hour through the maximum power data that the current system can output corresponding to the current maximum power tracking point parameter; retrieve the real-time power consumption data and the real-time weather data, input the predicted power consumption model in the next hour, and confirm the power consumption in the next hour; when the energy storage ratio value of the estimated total power and the power consumption in the next hour does not exceed the preset ratio threshold, control the photovoltaic panel to use the current maximum power tracking point parameter for photovoltaic power generation, and the estimated total power is the sum of the power generation in the next hour and the real-time battery power in the real-time battery status data; when the energy storage ratio value of the estimated total power and the power consumption in the next hour exceeds the preset ratio threshold, control the photovoltaic panel to use the current maximum power tracking point parameter for photovoltaic power generation in the next hour according to the energy storage ratio value.

[0007] In the above embodiment, by training the preset convolutional neural network and recurrent neural network models, the optimal working point calculation model and the model for predicting the power consumption in the next hour are obtained respectively; the system uses built-in sensors to collect data, and obtains the current maximum power tracking point parameters and the power consumption in the next hour according to different data input models; when the energy storage ratio value of the total power consumption and the power consumption in the next hour does not exceed the preset threshold, the photovoltaic panel is controlled to generate electricity with the maximum power tracking point parameters; if it exceeds, the proportion of power generation time is controlled proportionally; the efficiency of photovoltaic power generation and the scientific nature of energy storage management are improved, the power generation behavior of photovoltaic panels is flexibly adjusted, and efficient utilization and optimized management of energy are achieved. It not only avoids the waste of electric energy, but also ensures the stable power supply of the system under different power demand, and improves the adaptability and flexibility of the entire photovoltaic energy storage system.

[0008] In combination with some embodiments of the first aspect, in some embodiments, when the energy storage ratio value of the estimated total power and the power consumption in the next hour does not exceed the preset ratio threshold, the photovoltaic panel is controlled to use the current maximum power tracking point parameters for photovoltaic power generation, specifically including: when the energy storage ratio value of the estimated total power and the power consumption in the next hour does not exceed the preset ratio threshold, by retrieving the real-time battery power data in the real-time battery status data, it is determined that the current state is not a low power state, and the low power state is that the real-time battery power data is less than the preset minimum power threshold; when the current state is not a low power state, the photovoltaic panel is controlled to use the current maximum power tracking point parameters for photovoltaic power generation.

[0009] In the above embodiment, by judging whether the battery power is lower than the low power threshold, the system can fully utilize the power generation capacity of the photovoltaic panel while ensuring that there is sufficient power reserve, avoiding overcharging due to low battery power, affecting battery performance, improving the efficiency and reliability of photovoltaic power generation, and achieving more efficient energy utilization and storage.

[0010] In combination with some embodiments of the first aspect, in some embodiments, when the energy storage ratio value of the estimated total electricity and the electricity consumption in the next hour exceeds the preset ratio threshold, the photovoltaic panel is controlled according to the energy storage ratio value to use the current maximum power tracking point parameters for photovoltaic power generation in the next hour. Specifically, the following steps are performed: when the energy storage ratio value of the estimated total electricity and the electricity consumption in the next hour exceeds the preset ratio threshold, the charge and discharge ratio value is calculated in real time, and the energy storage ratio value is compared with the real-time calculated charge and discharge ratio value, where the real-time charge and discharge ratio value is the ratio of the real-time power generation data to the real-time electricity consumption data; if the energy storage ratio value is greater than or equal to the real-time calculated charge and discharge ratio value, the photovoltaic panel is put into a sleep state; if the energy storage ratio value is less than the real-time calculated charge and discharge ratio value, the power point parameters are adjusted to the maximum power tracking point parameters for photovoltaic power generation.

[0011] In the above embodiments, by intelligently adjusting the working state of the photovoltaic panel according to actual conditions, the power generation and power consumption are effectively balanced, the energy utilization efficiency is improved, the stable operation of the system is ensured, and energy waste is reduced.

[0012] In combination with some embodiments of the first aspect, in some embodiments, after collecting real-time lighting condition data through built-in sensors and obtaining real-time weather data, real-time power generation data, real-time power consumption data and real-time battery status data, it also includes: retrieving the real-time battery status data, monitoring various indicators of the battery in real time through the battery management system, and confirming whether the battery temperature is greater than a preset battery temperature threshold; when the battery temperature is greater than or equal to the preset battery temperature threshold, shutting down the battery pack with abnormal temperature to protect the battery from overheating damage; when the battery temperature is less than the preset battery temperature threshold, confirming whether the battery voltage is within the preset battery voltage threshold range; when the battery voltage is not within the preset voltage range, reducing the charging and discharging current of the abnormal voltage battery pack.

[0013] In the above embodiments, by comprehensively monitoring and managing battery status data and monitoring whether the battery temperature and voltage are within the normal threshold range, battery safety is improved, battery life is extended, and the probability of safety accidents is effectively reduced.

[0014] In combination with some embodiments of the first aspect, in some embodiments, the method further includes: when a sharp increase in power demand is monitored, turning on a priority power supply mode; the priority power supply mode is to adjust the system's power supply priority for each device, and the power supply priority is a ranking of each device set in advance according to the importance of power supply. After turning on the priority power supply mode, power is first supplied to devices with high priority rankings; the power consumption of each device and the real-time battery power in the real-time battery status data are continuously monitored, and when it is detected that the power consumption of a device has increased, a power consumption margin ratio is calculated, and the power consumption margin ratio is the ratio of the real-time power consumption of the device with increased power consumption to the real-time battery power; when the power consumption margin ratio is greater than or equal to a set power consumption margin ratio threshold, power supply to the device with increased power consumption is turned off; when the power consumption margin ratio is less than a set power consumption margin ratio threshold, determining whether the power supply priority of the device with increased power consumption is within a preset high priority range; if the power supply priority of the device with increased power consumption is within the preset high priority range, power supply to devices whose power supply priority is not within the preset high priority range is turned off; if the power supply priority of the device with increased power consumption is not within the preset high priority range, power supply to the device with increased power consumption is turned off.

[0015] In the above embodiment, by calculating the priority power supply mode and the power consumption margin ratio, power resources are reasonably allocated to ensure the normal operation of key equipment, which effectively solves the problem that when the power demand suddenly increases, the power supply strategy cannot be adjusted quickly, resulting in an imbalance between supply and demand and even power outages, thereby avoiding power waste and improving the utilization rate of power resources.

[0016] In combination with some embodiments of the first aspect, in some embodiments, when a sharp increase in electricity demand is monitored, the priority power supply mode is turned on, specifically including: when a sharp increase in electricity demand is monitored, by retrieving real-time weather data, it is determined whether the current weather is extremely severe weather, and the extremely severe weather is several extremely severe weather conditions set in advance; in extremely severe weather conditions, the photovoltaic panels are turned off and the priority power supply mode is turned on.

[0017] In the above embodiment, when a sharp increase in electricity demand is detected, real-time weather data is retrieved to determine whether the current weather is extremely severe. If it is an extremely severe weather condition set in advance, the photovoltaic panel is turned off. In this way, changes in electricity demand and weather conditions can be responded to in a timely manner under special circumstances. Possible damage to photovoltaic panels in extremely severe weather is avoided, and the safety and stability of the system are improved. At the same time, it is also helpful to reasonably allocate power resources in emergency situations, ensure that the system can better respond to emergencies, ensure the reliability of power supply, and reduce the risk of equipment damage and energy supply interruption caused by severe weather.

[0018] In combination with some embodiments of the first aspect, in some embodiments, the method also includes: continuously obtaining new working point training samples and new predicted power consumption training samples from the real-time power generation data, real-time battery status data, real-time lighting condition data, real-time power consumption data and real-time weather data, and correcting the predicted optimal working point calculation model and the predicted power consumption model for the next hour based on the new working point training samples and the new predicted power consumption training samples.

[0019] In the above embodiment, by continuously collecting real-time data to generate new samples for correction, the model can be more accurately adapted to changes in actual conditions. This helps to improve the accuracy of photovoltaic panel maximum power tracking and more accurately predict the power consumption in the next hour, thereby optimizing the system's power generation and energy storage strategies, improving energy utilization efficiency, and ensuring stable and efficient operation of the system.

[0020] In a second aspect, an embodiment of the present application provides a photovoltaic energy storage control system, which includes: one or more system-level chips and a memory; the system-level chip includes one or more processors; the memory is coupled to the system-level chip, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the mobile terminal to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when executed on a photovoltaic energy storage control system, enables the photovoltaic energy storage control system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions. When the instructions are executed on a photovoltaic energy storage control system, the photovoltaic energy storage control system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0023] It can be understood that the photovoltaic energy storage control system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the photovoltaic energy storage control method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. This application predicts the power consumption in the next hour and the real-time maximum power tracking point through a pre-trained model, and then controls the system power generation power on demand according to the actual power generation and storage conditions. This effectively solves the problem of only focusing on the power generation status of the photovoltaic components themselves, while ignoring the charging status of the energy storage battery and the future power demand, thereby optimizing the energy utilization rate of the photovoltaic energy storage system and reducing unnecessary energy waste.

[0025] 2. This application improves battery safety, extends battery life, and effectively reduces the probability of safety accidents by comprehensively monitoring and managing battery status data and monitoring whether the battery temperature and voltage are within the normal threshold range.

[0026] 3. This application reasonably allocates power resources and ensures the normal operation of key equipment through the calculation of priority power supply mode and power consumption margin ratio. It effectively solves the problem that when the power demand suddenly increases, the power supply strategy cannot be adjusted quickly, resulting in an imbalance between supply and demand and even power outages. It avoids power waste and improves the utilization rate of power resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a structural diagram of a system architecture to which the photovoltaic energy storage control method in the embodiment of the present application can be applied; Figure 2 It is a flow chart of a photovoltaic energy storage control method in an embodiment of the present application; Figure 3 is another flow chart of the photovoltaic energy storage control method in the embodiment of the present application; Figure 4 It is a structural schematic diagram of a photovoltaic energy storage control system in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] The following is a description of the system architecture of the photovoltaic energy storage control method involved in this application: Figure 1 1 is a schematic diagram of a system architecture applicable to the photovoltaic energy storage control method in the embodiment of the present application, the system includes a controller 110, an inverter 120, a photovoltaic panel 130, a sensor 140 and an energy storage battery 150. The controller 110 includes a battery management system 111.

[0031] The controller 110 is the core control unit of the photovoltaic energy storage system, responsible for monitoring the operation of the entire system, including key parameters such as the power generation of photovoltaic modules, the power of energy storage equipment, and the working efficiency of the system. Among them, the battery management system 111 is a system specifically for managing energy storage equipment, mainly responsible for monitoring key parameters such as the battery's charge and discharge status, temperature, voltage, and internal resistance, to ensure that the battery operates under safe and efficient conditions.

[0032] Inverter 120 is a key device for converting direct current into alternating current in a photovoltaic energy storage system. It can not only convert the direct current generated by photovoltaic modules into the alternating current required by household appliances or industrial equipment, but also store excess electric energy in energy storage batteries or connect it to the city power grid when needed.

[0033] The photovoltaic panel 130 is the core part of the photovoltaic power generation system that absorbs sunlight and converts it into electrical energy. Its structure is composed of a certain number of photovoltaic cells that are connected in series and packaged, and mainly includes core parts such as cells, interconnecting strips, glass, film, and backplane.

[0034] The sensor 140 is mainly composed of a photovoltaic sensor or a photoelectric sensor, and is used to measure the solar radiation intensity or the light intensity in real time.

[0035] The energy storage battery 150 is used to store excess electrical energy. Commonly used energy storage batteries include lead-acid batteries and lithium-ion batteries, etc. Each battery has its own unique advantages and applicable scenarios.

[0036] This application provides a photovoltaic energy storage control method. The photovoltaic energy storage system can predict the power consumption and real-time maximum power tracking point in the next hour through a pre-trained model, and then control the system power generation power on demand according to the actual power generation and storage conditions. This can optimize the energy utilization rate of the photovoltaic energy storage system and reduce unnecessary energy waste.

[0037] The following is a description of a photovoltaic energy storage control method in one embodiment of the present application: like Figure 2 As shown, it is a schematic diagram of a process flow of a photovoltaic energy storage control method provided in an embodiment of the present application, which can be used for Figure 1 The photovoltaic energy storage control system architecture shown includes the following steps: S201, using the working point training data group to train the preset convolutional neural network to obtain an optimal working point calculation model for the photovoltaic panel; Prepare a large number of historical data sets. A historical data set consists of a corresponding set of historical power generation data, historical battery status data, historical lighting condition data, and a corresponding marked maximum power tracking point parameter. Use a large number of data sets to train the preset convolutional neural network model. After repeated iterations and optimization, the convolutional neural network learns how to accurately predict the optimal operating point of the photovoltaic panel under current conditions, that is, the maximum power tracking point parameter, from the input historical power generation data, battery status data, and lighting condition data. The fully trained convolutional neural network forms an optimal operating point calculation model with strong generalization ability, can process new and unseen data input, and quickly output the corresponding maximum power tracking point parameters.

[0038] The maximum power tracking point parameter is to maximize the power output of the power generation equipment under various circumstances. By adjusting the battery load and current direction, the efficiency of the solar panel can be improved and its current maximum power point can be tracked to ensure that the system continues to operate at this point.

[0039] In some embodiments of the present application, the convolutional neural network architecture is a convolutional long short-term memory network, which performs well in processing time series data and regression tasks, and is very suitable for tasks related to photovoltaic energy storage system technology optimization; in some embodiments, the convolutional neural network architecture can also be MobileNet, etc. MobileNet is a lightweight convolutional neural network architecture designed specifically for mobile and embedded devices. It uses deep separable convolution to reduce computational complexity and model size, which is not limited here.

[0040] S202, using the predicted power consumption training data set to train the preset recurrent neural network model to obtain a model for predicting power consumption in the next hour; Prepare a large number of historical data sets. A historical data set consists of a corresponding set of historical electricity consumption data, historical weather data, and a corresponding labeled electricity consumption for the next hour. Use a large number of data sets to train the preset recurrent neural network model. After repeated iterations and optimization, the recurrent neural network learns how to accurately predict the electricity consumption for the next hour from the input historical electricity consumption data and historical weather data. After sufficient training, the recurrent neural network forms a model for predicting electricity consumption for the next hour. It has strong generalization capabilities, can handle new and unseen data inputs, and quickly output the corresponding electricity consumption for the next hour.

[0041] In some embodiments of the present application, the recurrent neural network model is a bidirectional recurrent neural network, which is composed of two recurrent neural network models, which process forward and reverse sequence data respectively, while considering historical data and future data (although future data is unknown, the model can predict future trends by learning patterns in historical data) and the impact of current weather on electricity consumption, thereby improving the accuracy of the prediction; in some embodiments, the recurrent neural network model can also be a long short-term memory network, etc. The long short-term memory network is a special recurrent neural network variant that controls the flow of information by introducing three gates (input gate, forget gate and output gate), and can effectively process periodic features in the data, which are not limited here.

[0042] S203, collecting real-time light condition data through built-in sensors, and obtaining real-time weather data, real-time power generation data, real-time power consumption data and real-time battery status data; The built-in sensors measure key parameters such as solar radiation intensity, lighting angle, and lighting duration to provide real-time lighting condition data. By connecting to the external meteorological service interface, weather information from external data sources is indirectly obtained, including precipitation probability, cloud thickness, current weather conditions, etc., to provide real-time weather data. The photovoltaic inverter collects real-time power generation data. The smart meter monitors the power consumption of the entire system and each load to provide real-time power consumption data. The battery management system monitors battery voltage, current, temperature, remaining capacity and other data to provide real-time battery status data.

[0043] S204, obtaining the current maximum power tracking point parameters through the optimal working point calculation model, and calculating the corresponding power generation in the next hour; The real-time power generation data, the real-time battery status data and the real-time light condition data are retrieved, and the optimal working point calculation model is input to obtain the current maximum power tracking point parameters, and the power generation in the next hour is calculated through the maximum power data that the current system can output corresponding to the current maximum power tracking point parameters.

[0044] S205, confirming the power consumption in the next hour by predicting the power consumption model in the next hour; The real-time electricity consumption data and the real-time weather data are retrieved, and the electricity consumption model predicted for the next hour is input to obtain the electricity consumption for the next hour.

[0045] S206, determining whether the energy storage value of the estimated total power and the power consumption in the next hour exceeds a ratio threshold range; If not, execute the following step S207; If exceeded, the following step S208 is executed; The estimated total power is the sum of the power generation in the next hour and the real-time battery power in the real-time battery status data. After calculating the estimated total power, the energy storage value is obtained by calculating the ratio of the estimated total power and the power consumption in the next hour obtained in the above step S205 to determine whether the energy storage value is within the set ratio threshold range; if the energy storage value does not exceed the preset ratio threshold range, it is determined that the photovoltaic energy storage system cannot supply electricity in the next hour and needs to generate electricity at maximum power; if the energy storage value exceeds the preset ratio threshold range, it is determined that the photovoltaic energy storage system can supply electricity in the next hour, and the power generation power of the system can be controlled as needed.

[0046] S207, when the energy storage ratio value does not exceed the preset ratio threshold, controlling the photovoltaic panel to use the current maximum power tracking point parameter to perform photovoltaic power generation; When the energy storage ratio value does not exceed the preset ratio threshold, the controller will adjust the output voltage or current of the photovoltaic array to move it toward the maximum power point. The controller will adjust the output voltage or current of the photovoltaic array to move it toward the maximum power point. The adjustment process is usually achieved by changing the duty cycle of the pulse width modulation drive signal of the DC-DC converter, thereby changing the output voltage of the photovoltaic array.

[0047] S208. When the energy storage ratio value exceeds a preset ratio threshold, the photovoltaic panel is controlled according to the energy storage ratio value to use the current maximum power tracking point parameters for photovoltaic power generation in the next hour.

[0048] When the energy storage ratio value exceeds the preset ratio threshold, the proportion of photovoltaic power generation time of the photovoltaic panel in the next hour is linearly adjusted according to the excess ratio. Specifically, the system sets a linear relationship so that the magnitude of the excess ratio corresponds to the adjustment range of the photovoltaic power generation time ratio. For example, if the excess ratio is small, the adjustment range of the photovoltaic power generation time ratio is also relatively small; if the excess ratio is large, the adjustment range of the photovoltaic power generation time ratio will also increase accordingly. Based on the adjusted time ratio, the system controls the power generation of the photovoltaic panel in the next hour. If the adjusted time ratio is a higher value, the photovoltaic panel will perform photovoltaic power generation with the current maximum power tracking point parameters for most of the time; if the time ratio is reduced, the photovoltaic panel will reduce the power generation time or reduce the power generation power in the corresponding time period.

[0049] In some embodiments of the present application, the duration ratio of photovoltaic power generation is adjusted linearly according to the size of the energy storage ratio value, and the duration ratio is linearly increased according to the excess ratio amplitude; in other embodiments of the present application, a step-by-step adjustment method can also be used, for example, several energy storage ratio value intervals are set to correspond to different adjustment amplitudes of the duration ratio of photovoltaic power generation, and the adjustment is divided into intervals according to the size of the energy storage ratio value, etc., which is not limited here.

[0050] In the above embodiment, the power consumption in the next hour is predicted and the real-time maximum power tracking point is calculated through the pre-trained model, and then the working state of the photovoltaic panel is controlled as needed according to the actual power generation and storage conditions. By monitoring and adjusting the real-time environment and system, it is possible to better respond to changes in power demand, optimize the energy utilization rate of the photovoltaic energy storage system, and reduce unnecessary energy waste.

[0051] In some embodiments, when the photovoltaic energy storage control system is in some emergency situations, such as natural disasters, emergencies, etc., which cause a sharp increase in electricity demand, the photovoltaic energy storage system needs to give priority to ensuring the power supply of key equipment (for example, communication equipment, medical equipment, etc.). By turning on the priority power supply mode, the photovoltaic energy storage control system can ensure that these devices can continue to operate and improve emergency response capabilities. Figure 3 FIG. 1 is another flow chart of the photovoltaic energy storage control method provided in the embodiment of the present application, which can be used for Figure 1 The photovoltaic energy storage control system architecture shown includes the following steps: S301, using the working point training data group to train the preset convolutional neural network to obtain the optimal working point calculation model of the photovoltaic panel; S302, using the predicted power consumption training data set to train the preset recurrent neural network model to obtain a model for predicting power consumption in the next hour; S303, collecting real-time light condition data through built-in sensors, and obtaining real-time weather data, real-time power generation data, real-time power consumption data and real-time battery status data; S304, obtaining the current maximum power tracking point parameters through the optimal working point calculation model, and calculating the corresponding power generation in the next hour; S305, confirming the power consumption in the next hour by predicting the power consumption model in the next hour; S306, determining whether the energy storage value of the estimated total power and the power consumption in the next hour exceeds a ratio threshold range; If not, execute the following step S307; If exceeded, the following step S309 is executed; S307, determining that the current state is not a low battery state by retrieving the real-time battery power data in the real-time battery status data; When the energy storage ratio value of the estimated total power and the power consumption in the next hour does not exceed the preset ratio threshold, the real-time battery power data in the real-time battery status data is retrieved, and when the real-time battery power data is greater than or equal to the preset minimum power threshold, it is determined that the current state is not a low power state.

[0052] S308, controlling the photovoltaic panel to use the current maximum power tracking point parameters to perform photovoltaic power generation; S309, calculating the charge-discharge ratio value in real time, and comparing whether the energy storage ratio value exceeds the charge-discharge ratio value calculated in real time; If the energy storage ratio value is greater than or equal to the real-time calculated charge-discharge ratio value, the following step S310 is executed; If the energy storage ratio value is less than the real-time calculated charge-discharge ratio value, the above step S308 is executed; When the energy storage ratio value of the estimated total power and the power consumption in the next hour exceeds the preset ratio threshold, the real-time charge-discharge ratio value is calculated, and the real-time charge-discharge ratio is the ratio of the real-time power generation data to the real-time power consumption data, and then the energy storage ratio value and the real-time calculated charge-discharge ratio value are compared; if the energy storage ratio value is greater than or equal to the real-time calculated charge-discharge ratio value, the current power generation can meet the power consumption; if the energy storage ratio value is less than the real-time calculated charge-discharge ratio value, the current power generation cannot meet the power consumption.

[0053] S310, putting the photovoltaic panel into a dormant state; By comparing the energy storage ratio value and the real-time charge and discharge ratio value, when the energy storage ratio value is greater than or equal to the real-time calculated charge and discharge ratio value, it is judged that the current power generation and the power consumption can be met, and the photovoltaic panels are turned off and put into a dormant state, avoiding overcharging or over-discharging and extending the service life of the energy storage equipment.

[0054] S311, confirming whether the battery temperature exceeds a preset battery temperature threshold; If the battery temperature is greater than or equal to the preset battery temperature threshold, the following step S312 is executed; If the battery temperature is less than the preset battery temperature threshold, the following step S313 is executed; Retrieve real-time battery status data, monitor various battery indicators in real time through the battery management system, and determine whether the battery temperature exceeds the preset battery temperature threshold. If the battery temperature is greater than or equal to the preset battery temperature threshold, the battery temperature is judged to be abnormal; if the battery temperature is less than the preset battery temperature threshold, the battery temperature is judged to be normal, and then other indicators are judged.

[0055] S312, shut down the battery pack with abnormal temperature; When it is detected that the temperature of a battery pack is greater than or equal to the preset battery temperature threshold, the system can use communication methods such as Ethernet to quickly transmit the shutdown command to the battery management system. After receiving the shutdown command, the battery management system quickly cuts off the circuit connection between the abnormally hot battery pack and the photovoltaic system and load by controlling relays, contactors or other switching devices to protect battery performance and avoid damage to the electric vehicle or safety accidents.

[0056] S313, confirming whether the battery voltage is within a preset battery voltage threshold range; If the battery voltage is not within the preset battery voltage threshold range, the following step S314 is executed; If the battery voltage is within the preset battery voltage threshold range, return to execute the above step S304; When the battery temperature is in a normal state, the battery voltage data in the real-time battery status data is retrieved again to determine whether the battery voltage exceeds the preset battery voltage threshold. If the battery voltage is greater than or equal to the preset battery voltage threshold, the battery voltage is determined to be abnormal; if the battery voltage is less than the preset battery voltage threshold, the voltage and temperature are determined to be normal and the process returns to execute the above step S304.

[0057] S314, reducing the charge and discharge current of the abnormal voltage battery pack; When it is monitored that the battery voltage is greater than or equal to the preset battery voltage threshold, the charge and discharge current of the abnormal voltage battery pack is reduced to ensure that the battery pack can be charged and discharged normally, avoiding overcharging or over-discharging of the battery pack. Overcharging may cause dangerous situations such as battery heating, swelling, fire and even explosion; over-discharging may damage the battery's electrode structure and reduce the battery's capacity and life.

[0058] S315, when a sharp increase in electricity demand is detected, determining whether the current weather is extremely severe; If it is determined that the current weather is extremely bad, the following step S316 is executed; If it is determined that the current weather is not extremely bad weather, then the above step S304 is executed; The photovoltaic energy storage system is connected to the meteorological data source, and can obtain real-time weather data through the Internet connection to the professional meteorological service platform, and pre-set several extreme weather conditions, such as strong typhoons, heavy rain and snow, thunder and lightning, etc., and compare and judge based on the retrieved real-time weather data with the preset extreme weather conditions. For example, if the wind speed exceeds a certain level, the rainfall exceeds a specific value, or there is frequent lightning activity, it is judged as extreme weather.

[0059] In some embodiments of the present application, the photovoltaic energy storage system is connected to a professional meteorological service platform via the Internet to obtain real-time weather data; in some embodiments, the photovoltaic energy storage system can also receive wireless signals from local weather stations or use satellite meteorological data, etc., which are not limited here.

[0060] S316, turn off the photovoltaic panel and start the priority power supply mode; In extremely severe weather conditions, the system sends a shutdown signal to the photovoltaic inverter, which stops converting the DC power generated by the photovoltaic panels into AC power output and adjusts the angle of the photovoltaic panels through an electric drive to make them parallel to the ground to reduce the impact of strong winds, heavy rains, etc.

[0061] In some embodiments of the present application, shutting down the photovoltaic panel operation means stopping converting the direct current generated by the photovoltaic panel into alternating current output and adjusting the angle of the photovoltaic panel; in some embodiments, shutting down the photovoltaic panel operation may also be achieved by cutting off the connection between the photovoltaic array and the power grid, etc., which is not limited here.

[0062] S317, monitoring the power consumption of each device and the real-time battery power in the real-time battery status data, and calculating the power consumption surplus ratio when detecting that the power consumption of a device increases; By monitoring the power consumption data of each device and comparing the current power consumption with the historical power consumption data, the system determines whether the power consumption of any device has increased. Once the power consumption of any device is detected to have increased, the system immediately calculates the power consumption remaining ratio. The power consumption remaining ratio is the ratio of the real-time power consumption of the device with increased power consumption to the real-time battery power.

[0063] In some embodiments of the present application, determining whether the power consumption of a device has increased is done by comparing the current power consumption with historical power consumption data; in some embodiments, determining whether the power consumption of a device has increased can also be done by setting a threshold for the power consumption change rate, etc., which is not limited here.

[0064] S318, determining whether the power consumption margin ratio exceeds a set power consumption margin ratio threshold; If the power consumption margin ratio is greater than or equal to the set power consumption margin ratio threshold, the following step S319 is executed; If the power consumption margin ratio is less than the set power consumption margin ratio threshold, the following step S320 is executed; The calculated power consumption margin ratio is compared with the set power consumption margin ratio threshold. If the power consumption margin ratio is greater than or equal to the set power consumption margin ratio threshold, it is determined that the device has abnormal power consumption; if the power consumption margin ratio is less than the set power consumption margin ratio threshold, it is determined that the device has increased power consumption but no abnormality has occurred.

[0065] S319, shutting down the power supply to the equipment with increased power consumption; When the power consumption margin ratio of the device is greater than or equal to the set power consumption margin ratio threshold, the connection between the device and the power supply is cut off by controlling devices such as relays and intelligent switches, thereby shutting down the power supply to the device with increased power consumption.

[0066] S320, determining whether the power supply priority of the device with increased power consumption is within a preset high priority range; If the power supply priority of the power consumption increasing device is within the preset high priority range, the following step S321 is executed; If the power supply priority of the power consumption increasing device is not within the preset high priority range, then execute the above step S319; When the power consumption margin ratio of the device is less than the set power consumption margin ratio threshold, the system further determines whether the power supply priority of the device with increased power consumption is within the preset high priority range. If the power supply priority of the device with increased power consumption is within the preset high priority range, the device with increased power consumption should be powered on preferentially; if the power supply priority of the device with increased power consumption is not within the preset high priority range, the power supply of devices with higher priority should be guaranteed preferentially, and the above-mentioned operation of shutting down the power supply to the device with increased power consumption is performed.

[0067] S321, shutting down the power supply to the device whose power supply priority is not within the preset high priority range; When the power supply priority of the power consumption device is within the preset high priority range, in order to ensure that the extremely high priority devices can operate normally, the system controls relays and other devices to shut down the power supply to the devices whose power supply priority is not within the preset high priority range. For example, medical equipment is set as a high priority device. When the power consumption of a lighting device that is not within the preset high priority range increases and causes the power consumption margin ratio to be less than the threshold, the system will shut down the power supply to other non-high priority devices to ensure that the high priority devices can continue to operate when the battery power is limited, thereby improving energy efficiency.

[0068] S322, continuously obtain new working point training samples and new predicted power consumption training samples from the real-time power generation data, real-time battery status data, real-time lighting condition data, real-time power consumption data and real-time weather data, and calibrate the calculation model for predicting the optimal working point and the model for predicting power consumption in the next hour.

[0069] The photovoltaic energy storage system continuously collects real-time power generation data, real-time battery status data, real-time lighting condition data, real-time power consumption data, and real-time weather data. The collected data is sorted and classified into new working point training samples and new predicted power consumption training samples. The new working point training samples are used to train the prediction optimal working point calculation model; the input features in the new working point training samples are input into the model, and the model's output (predicted optimal working point) is made closer to the actual optimal working point by adjusting the model's weights and parameters. Similarly, the new predicted power consumption training samples are used to calibrate the model for predicting power consumption in the next hour. The model for predicting power consumption in the next hour can predict power consumption in the future based on historical power consumption data, real-time weather data, time factors, etc. By continuously calibrating the prediction optimal working point calculation model, the photovoltaic energy storage system can more accurately determine the optimal working point under different environmental conditions, thereby improving the power generation efficiency of the photovoltaic system.

[0070] In the above embodiment, the photovoltaic energy storage control system can start the priority power supply mode when the power demand is detected to be rising sharply. By continuously monitoring the power consumption of the equipment and the battery power, the system can dynamically adjust the power supply strategy according to the actual situation, realize the reasonable allocation of energy, ensure that the high-priority equipment can continue to operate when the battery power is limited, and improve the energy utilization efficiency. In addition, when the power demand rises sharply and the current weather is judged to be extremely bad, the system issues an instruction to shut down the photovoltaic panel, which can avoid continuing to operate the photovoltaic system in extremely bad weather, reduce the risk of system failure and power outage caused by weather reasons, and avoid the equipment from being subjected to physical shock, flooding, lightning strikes and other hazards, extend the service life of the equipment, and reduce maintenance costs. In addition, by using the battery management system to monitor the temperature and voltage data of the battery in real time, shut down the battery pack with abnormal temperature in time and reduce the current of the battery pack with abnormal voltage, the battery voltage can be kept within a suitable range, the performance and efficiency of the photovoltaic energy storage system can be improved, and the battery can be effectively prevented from being overcharged and over-discharged, thereby protecting the safety of the battery, avoiding the normal operation of the entire photovoltaic energy storage system due to the failure of a single battery pack, and improving the reliability and stability of the system. In addition, by comparing the energy storage ratio value with the preset ratio threshold, as well as the relationship with the real-time charge and discharge ratio value, the system can intelligently decide whether to let the photovoltaic panels work, thereby achieving optimal energy management, improving energy utilization efficiency, and maximizing the use of solar energy resources.

[0071] The following introduces an exemplary photovoltaic energy storage control system 400 provided in an embodiment of the present application. Figure 4 Schematic diagram of an exemplary hardware structure of a photovoltaic energy storage control system 400 provided in an embodiment of the present application.

[0072] In some embodiments, the photovoltaic energy storage control system 400 is a computer device or the photovoltaic energy storage control system 400 includes a computer device. The computer device includes a processor, a memory, and a network interface connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with other external terminals or servers through a network connection. In some embodiments, the network interface can be a wired network interface, and in some embodiments, the network interface can also be a wireless network interface. When the computer program is executed by the processor, the method in the embodiment of the present application is implemented.

[0073] Those skilled in the art will understand that Figure 4The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0074] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0075] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0076] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

[0077] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A photovoltaic energy storage control method, applied to a photovoltaic energy storage control system, characterized in that: The method comprises: Using the working point training data group to train the preset convolutional neural network, an optimal working point calculation model of the photovoltaic panel is obtained, wherein the optimal working point calculation model is used to output a maximum power tracking point parameter according to a set of historical power generation data, historical battery status data and historical illumination condition data inputted, wherein the working point training data group includes a plurality of working point training data, and each training data includes a corresponding relationship between a historical power generation data, a historical battery status data and a historical illumination condition data and a correspondingly marked completed maximum power tracking point parameter; The preset recurrent neural network model is trained using the predicted power consumption training data group to obtain a model for predicting power consumption in the next hour, wherein the model for predicting power consumption in the next hour is used to output power consumption in the next hour based on a set of historical power consumption data and historical weather data input; the predicted power consumption training data group includes a plurality of predicted power consumption training data, each of which includes a corresponding relationship between a piece of historical power consumption data and a piece of historical weather data and a correspondingly marked corresponding relationship between power consumption in the next hour; Collect real-time light condition data through built-in sensors, and obtain real-time weather data, real-time power generation data, real-time power consumption data and real-time battery status data; Retrieving the real-time power generation data, the real-time battery status data and the real-time light condition data, inputting the optimal working point calculation model, obtaining the current maximum power tracking point parameter, and calculating the power generation in the next hour through the maximum power data that the current system can output corresponding to the current maximum power tracking point parameter; Retrieving the real-time power consumption data and the real-time weather data, inputting the power consumption model predicted for the next hour, and confirming the power consumption for the next hour; When the energy storage ratio of the estimated total power and the power consumption in the next hour does not exceed the preset ratio threshold, the photovoltaic panel is controlled to use the current maximum power tracking point parameters for photovoltaic power generation; the estimated total power is the sum of the power generation in the next hour and the real-time battery power in the real-time battery status data; When the energy storage ratio value of the estimated total power and the power consumption in the next hour exceeds the preset ratio threshold, the photovoltaic panel is controlled according to the energy storage ratio value to use the current maximum power tracking point parameters for photovoltaic power generation in the next hour.

2. The method according to claim 1, characterized in that When the energy storage ratio of the estimated total power and the power consumption in the next hour does not exceed the preset ratio threshold, controlling the photovoltaic panel to use the current maximum power tracking point parameters to perform photovoltaic power generation specifically includes: In the case where the energy storage ratio value of the estimated total power and the power consumption in the next hour does not exceed the preset ratio threshold, by retrieving the real-time battery power data in the real-time battery status data, it is determined that the current state is not a low power state, and the low power state is that the real-time battery power data is less than the preset minimum power threshold; When the current state is not a low-battery state, the photovoltaic panel is controlled to use the current maximum power tracking point parameters to perform photovoltaic power generation.

3. The method according to claim 1, characterized in that When the energy storage ratio value of the estimated total power and the power consumption in the next hour exceeds the preset ratio threshold, controlling the proportion of the duration of photovoltaic panels using the current maximum power tracking point parameters for photovoltaic power generation in the next hour according to the energy storage ratio value specifically includes: When the energy storage ratio value of the estimated total power and the power consumption in the next hour exceeds the preset ratio threshold, the charge-discharge ratio value is calculated in real time, and the energy storage ratio value and the real-time calculated charge-discharge ratio value are compared, and the real-time charge-discharge ratio value is the ratio of the real-time power generation data to the real-time power consumption data; If the energy storage ratio is greater than or equal to the real-time calculated charge-discharge ratio, the photovoltaic panel is put into a dormant state; If the energy storage ratio value is less than the real-time calculated charge-discharge ratio value, the power point parameter is adjusted to the maximum power tracking point parameter for photovoltaic power generation.

4. The method according to claim 1, characterized in that: After collecting real-time light condition data through built-in sensors, and obtaining real-time weather data, real-time power generation data, real-time power consumption data, and real-time battery status data, it also includes: Retrieving the real-time battery status data, monitoring various indicators of the battery in real time through the battery management system, and confirming whether the battery temperature is greater than a preset battery temperature threshold; When the battery temperature is greater than or equal to the preset battery temperature threshold, the abnormal temperature battery pack is turned off to protect the battery from overheating damage; When the battery temperature is lower than a preset battery temperature threshold, confirming whether the battery voltage is within a preset battery voltage threshold range; When the battery voltage is not within the preset voltage range, the current of charging and discharging the abnormal voltage battery pack is reduced.

5. The method according to claim 1, characterized in that The method further comprises: In the case of a sharp increase in power demand, the priority power supply mode is turned on; the priority power supply mode is to adjust the power supply priority of the system to each device, and the power supply priority is a ranking of each device according to the importance of power supply set in advance. After the priority power supply mode is turned on, power is supplied to the device with a high priority ranking first; Continuously monitor the power consumption of each device and the real-time battery power in the real-time battery status data, and when it is detected that the power consumption of a device has increased, calculate the power consumption remaining ratio, which is the ratio of the real-time power consumption of the device with increased power consumption to the real-time battery power; When the power consumption margin ratio is greater than or equal to the set power consumption margin ratio threshold, power supply to the device with increased power consumption is turned off; When the power consumption margin ratio is less than the set power consumption margin ratio threshold, determining whether the power supply priority of the power consumption increased device is within a preset high priority range; If the power supply priority of the device with increased power consumption is within the preset high priority range, the power supply to the device whose power supply priority is not within the preset high priority range is turned off; If the power supply priority of the device with increased power consumption is not within the preset high priority range, the power supply to the device with increased power consumption is turned off.

6. The method according to claim 5, characterized in that When a sharp increase in power demand is detected, the priority power supply mode is turned on, specifically including: When a sharp increase in electricity demand is detected, the real-time weather data is retrieved to determine whether the current weather is extremely severe. The extremely severe weather refers to several extremely severe weather conditions set in advance. In extremely severe weather conditions, turn off the photovoltaic panels and turn on the priority power supply mode.

7. The method according to claim 1, characterized in that The method further comprises: New operating point training samples and new predicted power consumption training samples are continuously obtained from the real-time power generation data, real-time battery status data, real-time lighting condition data, real-time power consumption data and real-time weather data, and the optimal operating point prediction calculation model and the next hour power consumption prediction model are corrected based on the new operating point training samples and the new predicted power consumption training samples.

8. A photovoltaic energy storage control system, characterized in that: The photovoltaic energy storage control system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the photovoltaic energy storage control system to execute the method described in any one of claims 1-7.

9. A computer program product comprising instructions, characterized in that When the computer program product runs on a photovoltaic energy storage control system, the photovoltaic energy storage control system executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a photovoltaic energy storage control system, the photovoltaic energy storage control system executes the method according to any one of claims 1 to 7.

Images