Energy dynamic intelligent scheduling control system and method in light-heat-electricity-storage coupling process
Through the energy dynamic intelligent scheduling control system of the photothermal and electrical storage coupling process, the LSTM+ attention mechanism model is used to predict photovoltaic power generation, solving the problem of inaccurate prediction in the existing technology, and improving the stability and energy efficiency of the power grid.
Patent Information
- Application Number
- CN202411318594.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-20
- Publication Date
- 2025-01-07
AI Technical Summary
The existing photovoltaic power generation prediction methods are difficult to effectively deal with extreme anomalies and environmental factors, and are difficult to capture the complex nonlinear characteristics of photovoltaic power generation, resulting in inaccurate predictions and affecting the stable operation of the power grid.
The energy dynamic intelligent scheduling control system adopts the coupling process of photothermal and electrical storage, and uses the LSTM neural network model to combine the attention mechanism to predict the photovoltaic power generation, and under the regulation of the data control module, intelligent power storage and output are realized to balance the supply and demand of the power grid.
It improves the accuracy of photovoltaic power generation prediction and the stability of the power grid, reduces power waste, reduces operating costs, and improves energy utilization efficiency and system safety.
Smart Images
Figure CN119275876A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of dynamic intelligent energy scheduling, and specifically relates to a dynamic intelligent energy scheduling control system and method for a photothermal electricity storage coupling process. Background Art
[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.
[0003] With the acceleration of social industrialization and the continuous rise of economic development, people's demand for energy resources is increasing. The excessive demand and development of fossil energy has led to the gradual deterioration of the earth's environment and the gradual energy crisis. In the face of the increasingly serious pollution of fossil energy to the environment and the depletion of its reserves, the development of renewable energy and various green energy sources is an important means for mankind to achieve sustainable development.
[0004] As a clean and renewable energy source, the development and utilization of solar energy is attracting much attention, and solar photovoltaic power generation technology is also receiving widespread attention. A solar photovoltaic power generation system is a device that converts sunlight into electrical energy. It is a clean and renewable energy solution that not only helps reduce dependence on traditional energy, but also greatly reduces the impact on the environment.
[0005] However, the existing traditional technology mainly converts direct current from solar radiation into alternating current through an inverter and then sends it to the power grid through a transformer. Photovoltaic power generation is one of the efficient forms of new energy utilization and occupies an important position in the energy structure. However, solar energy has problems such as low energy density, instability, high efficiency and low cost. At the same time, solar irradiance, temperature, relative humidity, cloud thickness, wind speed, etc. make photovoltaic power generation power have strong volatility and uncontrollability. Large-scale photovoltaic grid connection will greatly affect the stable operation of the power system, causing voltage surge / current distribution changes and other problems.
[0006] At present, the existing research methods for photovoltaic power generation prediction are mainly divided into: prediction methods based on traditional physical models, prediction methods based on statistical analysis, and methods based on artificial intelligence. The prediction method based on traditional physical models predicts by establishing physical equations of solar radiation amplitude and photovoltaic power station output. The prediction method based on statistical analysis predicts by discovering the statistical laws between input data and future power generation. Common statistical models include AR and ARIMA. The prediction method based on artificial intelligence realizes prediction by automatically learning the high-dimensional expression of data through powerful nonlinear mapping capabilities. The prediction method based on traditional physical models belongs to indirect prediction, which requires detailed geographic information, component parameters, meteorological parameters and other data of photovoltaic power stations. It has strong interpretability, but the model construction is complex, the anti-interference ability is poor, and it cannot effectively handle some extreme abnormal weather conditions and environmental factors; the method based on statistical analysis often needs to model the statistical laws of data from a large amount of historical information, and it is difficult to capture the complex nonlinear characteristics of photovoltaic power generation: early artificial intelligence prediction method models such as SVR and decision trees are limited by the dependence on manual features and the ability to mine data features, and it is difficult to achieve accurate photovoltaic power generation prediction. Summary of the invention
[0007] In order to solve the above problems, the present invention proposes an energy dynamic intelligent scheduling control system and method for the photovoltaic, thermal, electric and storage coupling process. The present invention can effectively predict the future power generation of photovoltaic power stations and the future power supply needs of users, improve the stability of power supply, and realize the intelligent development of power grids.
[0008] According to some embodiments, the present invention adopts the following technical solutions:
[0009] An energy dynamic intelligent scheduling and control system for a photothermal electricity storage coupling process includes a photovoltaic power generation module, an energy storage module, an external power supply module, a data acquisition module, a data output module, a data control module and an output terminal module, wherein:
[0010] The photovoltaic power generation module is connected to the energy storage module, the data acquisition module and the output module, the data output module is connected to the data acquisition module and the data control module, and the data control module is connected to the external power supply module and the energy storage module;
[0011] The data acquisition module is used to acquire the equipment characteristics, location characteristics, meteorological characteristics of the photovoltaic panels, and time characteristics of photovoltaics, and to predict the power of the photovoltaic power generation module based on the acquired data;
[0012] The data control module is used to control the external power supply module to supply power to the energy storage module according to the predicted power, and realize the intelligent power storage of the energy storage module. The output end module is connected with the external power supply module, the energy storage module and the photovoltaic power generation module to output electric energy and realize the intelligent power regulation of the system.
[0013] The energy storage module, photovoltaic power generation module, external power supply module and output end module are controlled by the data control module to store excess photovoltaic power generation energy and external electric energy and output the stored energy to the output end module.
[0014] As an optional implementation, the data acquisition module is also used to obtain historical power consumption and power consumption patterns of the user end.
[0015] As an optional embodiment, the equipment characteristics include the power of the photovoltaic panels, the surface cleanliness and the number of photovoltaic panels.
[0016] As an optional implementation manner, the location characteristics and climate characteristics include setting longitude and latitude, altitude, sunshine duration, temperature, irradiance, wind speed, rainfall and cloud thickness.
[0017] As an optional implementation, the data acquisition module forms training data based on the acquired data, constructs an LSTM neural network model, and weights all states output by the LSTM neural network model according to the attention weight to form a model that integrates LSTM and attention mechanism, trains the model using the training data, and uses the trained model for prediction.
[0018] As a further limited implementation method, the LSTM neural network model includes several LSTM layers, each layer includes an input gate, a forget gate, an output gate and a memory unit, the input gate is used to determine the information to be stored in the memory unit, the forget gate is used to determine the information to be forgotten from the memory unit, and the output gate is used to determine the next hidden state. Through the interaction between the forget gate and the input gate, the memory unit can selectively remember or forget information. Through the interaction of the above-mentioned gating mechanisms, the LSTM neural network model can capture the long-term and short-term dependencies in time series data and generate reliable time feature representations, which will serve as inputs to subsequent attention mechanism layers.
[0019] As a further limited implementation method, the attention mechanism layer calculates the score of each time step state output by each LSTM layer in the LSTM neural network model, and then uses a function to convert the score into an attention weight. Through weighted summation, all states output by the LSTM layer are weighted according to the attention weight to form a new feature vector. The new feature vector is passed to the fully connected layer for further processing and prediction. The fully connected layer maps the high-dimensional features to the output space by setting weights and biases to generate the final prediction result.
[0020] As an optional implementation, the photovoltaic power generation module, energy storage module, external power supply module, data acquisition module, data output module and output end module are all provided with sensors and signal transmission units. The sensors are used to monitor the voltage, current and / or temperature information of the corresponding modules. The signal transmission unit is used to transmit the information collected by the sensors to the control module. The control module is used to determine whether the corresponding modules are in normal working state based on the collected information.
[0021] As an optional implementation, the data control module is configured to control the excess electricity to be stored in the energy storage module when the electricity generated by the photovoltaic power generation module exceeds the electricity required by the output end module; when the electricity generated by the photovoltaic power generation module is less than the set value, the electric energy in the energy storage module is supplemented to the output end module to balance the supply and demand of the power grid.
[0022] A method for dynamic intelligent scheduling and control of energy in a photothermal power storage coupling process comprises the following steps:
[0023] Obtain the equipment characteristics, location characteristics, meteorological characteristics of the photovoltaic panels, and time characteristics of photovoltaics;
[0024] According to the acquired data, the power of the photovoltaic power generation module is predicted. According to the predicted power, the external power supply module is regulated to supply power to the energy storage module, and the intelligent power storage of the energy storage module is realized. The output end module is connected with the external power supply module, the energy storage module and the photovoltaic power generation module to output electric energy and realize the intelligent power regulation of the system.
[0025] When the amount of electricity generated by the photovoltaic power generation module exceeds the amount of electricity required by the output end module, the excess electricity is regulated and stored in the energy storage module. When the amount of electricity generated by the photovoltaic power generation module is less than the set value, the electricity in the energy storage module is supplemented to the output end module to balance the supply and demand of the power grid.
[0026] Compared with the prior art, the present invention has the following beneficial effects:
[0027] The present invention provides sensors and signal transmission units in each module unit to monitor and transmit the voltage, current and temperature information of each unit, judge whether each module is in a normal working state, and connect the external power supply module with the output end module at the same time. When a system failure occurs, the external power supply module automatically supplies power to the output end module, and timely inspects and repairs the photovoltaic power generation system to ensure that the system can still operate normally and smoothly, thereby improving the stability and safety of the system operation.
[0028] The present invention sets a data control module. When the power generated by the photovoltaic power generation module exceeds the power required by the output end, the excess power can be stored in the energy storage module. When the power supply of the photovoltaic power generation module is reduced due to factors such as solar irradiance, temperature, relative humidity, cloud thickness, wind speed, etc., the electric energy in the energy storage module is supplemented to the output end module, so as to balance the supply and demand of the power grid and reduce the waste of electric energy.
[0029] The present invention is provided with an external power supply module. When the power of the energy storage module is low and the power supply of the photovoltaic power generation module is insufficient, the energy storage module is supplied with power through the external power supply module, so that the output end module can stably output power and maintain the power supply stability of the power grid. By providing a data control module, the on-off between the photovoltaic power generation module, the energy storage module and the external power supply module is regulated to realize the intelligent storage and output of power, improve the energy utilization efficiency while reducing the cost, improve the stability of the power supply network, and ensure the overall safety of the system.
[0030] The present invention builds an LSTM+attention mechanism model and uses input features to predict the future power generation of the target photovoltaic power station and the future power supply demand of the user end. Then, according to the intelligently predicted power generation, the photovoltaic power generation module, energy storage module and external power supply module are intelligently switched on and off to reduce the operating cost of the power grid, improve the stability of power supply, and realize the intelligent development of the power grid.
[0031] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.
[0033] Figure 1 is a control system structure diagram of an embodiment;
[0034] Figure 2 is a flow chart of power prediction of an embodiment;
[0035] Figure 3 The topological diagram of a neural network model of an embodiment. DETAILED DESCRIPTION
[0036] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0037] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.
[0038] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.
[0039] In the absence of conflict, the embodiments in this application and the features in the embodiments may be combined with each other.
[0040] Embodiment 1
[0041] An energy dynamic intelligent scheduling control system for the solar-thermal-electricity-storage coupling process, such as Figure 1 As shown, it includes: a photovoltaic power generation module, an energy storage module, an external power supply module, a data acquisition module, a data output module, a data control module, and an output end module. The photovoltaic power generation module is connected to the energy storage module, the data acquisition module and the output end module. The data output module is connected to the data acquisition module and the data control module. The power predicted by data processing is input into the data control module. The data control module is connected to the external power supply module and the energy storage module. According to the predicted power, the external power supply module is regulated to supply power to the energy storage module, and the intelligent power storage of the energy storage module is realized. The output end module is connected to the external power supply module, the energy storage module and the photovoltaic power generation module to realize the output of electric energy.
[0042] The energy storage module, photovoltaic power generation module, external power supply module and output end module are controlled by the data control module to realize the storage of excess photovoltaic power generation and external electric energy and output the stored energy to the output end module. The data control module realizes the intelligent power regulation of the system based on the power prediction of the photovoltaic power generation module.
[0043] Among them, the photovoltaic power generation module, data acquisition module, and data output module constitute the data acquisition unit of photovoltaic power generation. The data acquisition module acquires information about the historical power consumption and power consumption pattern of the user end by acquiring information about the location characteristics of the photovoltaic panels, the meteorological characteristics of the photovoltaic panels, and the time characteristics of the photovoltaic panels. The obtained relevant data constitutes training data, and a unique data preprocessing and feature engineering are used to build an LSTM+attention mechanism model. The best model is trained using strategies such as cross-validation, and the input features are used to predict the future power generation of the target photovoltaic power station and the future power supply demand of the user end. The predicted amount is then input into the data control module through the data output module.
[0044] The energy storage module, external power supply module, data control module, output module and photovoltaic power generation module constitute the intelligent control unit of photovoltaic power generation. Under the control of the data control module, the photovoltaic power generation module, energy storage module and external power supply module intelligently output electrical energy to the output module, realizing dynamic and intelligent scheduling of system energy.
[0045] In this embodiment, through the data acquisition module, such as Figure 2 As shown in the figure, the characteristics of photovoltaic and users are obtained, data preprocessing and feature processing are used to build an LSTM+attention mechanism model, and the input features are used to predict the future power generation of the target photovoltaic power station and the future power supply demand of the user end.
[0046] The equipment characteristics of this embodiment include the power of the photovoltaic panels, the surface cleanliness and the number of photovoltaic panels.
[0047] Location characteristics and climate characteristics include setting longitude and latitude, altitude, sunshine duration, temperature, irradiance, wind speed, rainfall and cloud thickness.
[0048] The photovoltaic time characteristics include the historical meteorological data and electricity supply demand for the past N days, where N is an integer and can be set.
[0049] The data obtained from the user side include electricity consumption (including daily electricity consumption and electricity consumption during peak hours) and electricity consumption patterns.
[0050] When the photovoltaic location characteristics and photovoltaic meteorological characteristics are good and the photovoltaic power generation module has sufficient power generation, under the control of the data control module, a part of the electric energy is directly output from the photovoltaic power generation module to the output end module, while the other excess electric energy is input from the photovoltaic power generation module to the energy storage module to store the excess electric energy and avoid waste of resources.
[0051] When the photovoltaic location characteristics and photovoltaic meteorological characteristics are normal, such as rainy days, and the photovoltaic power generation module generates insufficient power, the power stored in the energy storage module and the photovoltaic power generation module are output to the output module under the control of the data control module for user use. When the power stored in the energy storage module and the power generated by the photovoltaic power generation module on that day are not enough to meet the needs of the user, or when the system fails and needs to be repaired, the output module can be directly powered by the external power supply module to solve the inconvenience and trouble caused by system maintenance.
[0052] Specifically, this embodiment establishes feature cross-combinations based on photovoltaic location features and photovoltaic meteorological features. The cross-combinations of photovoltaic panel power with sunshine duration, temperature, irradiance intensity, relative humidity, cloud thickness, wind speed, air quality and rainfall can generate new features, etc. The above features, as well as the historical power consumption and power consumption patterns of the user end are used to predict the power generation and power supply required by the user end.
[0053] The data quality is ensured by collecting characteristic data related to photovoltaic power generation and user electricity consumption, processing missing values, outliers and data consistency problems in the data, and then standardizing the characteristic data to meet the model input requirements. The processed data is input into the LSTM layer, such as Figure 3 shown.
[0054] The LSTM layer includes three gates: input gate, forget gate, output gate, and a memory unit. The input gate determines which new information will be stored in the memory unit, the forget gate determines which information will be forgotten from the memory unit, and the output gate determines the next hidden state. Through the interaction between the forget gate and the input gate, the memory unit can selectively remember or forget information. Through the interaction of the above gating mechanism, the LSTM layer can effectively capture the long-term and short-term dependencies in the data when processing long-term series data, thereby generating reliable temporal feature representations, which will serve as the input of the subsequent attention mechanism layer. The attention mechanism layer calculates the score of each time step state output by the LSTM layer, and then uses a function to convert the score into an attention weight. Through the weighted summation method, all states output by the LSTM layer are weighted according to the attention weight to form a new feature vector. The new feature vector is passed to the fully connected layer for further processing and prediction. The fully connected layer maps the high-dimensional features to the output space through a series of weights and biases to generate the final prediction results.
[0055] Embodiment 2
[0056] Based on the system provided in the first embodiment, a method for dynamic intelligent scheduling and control of energy in a photothermal power storage coupling process includes the following steps:
[0057] Obtain the equipment characteristics, location characteristics, meteorological characteristics of the photovoltaic panels, and time characteristics of photovoltaics;
[0058] According to the acquired data, the power of the photovoltaic power generation module is predicted. According to the predicted power, the external power supply module is regulated to supply power to the energy storage module, and the intelligent power storage of the energy storage module is realized. The output end module is connected with the external power supply module, the energy storage module and the photovoltaic power generation module to output electric energy and realize the intelligent power regulation of the system.
[0059] When the amount of electricity generated by the photovoltaic power generation module exceeds the amount of electricity required by the output end module, the excess electricity is regulated and stored in the energy storage module. When the amount of electricity generated by the photovoltaic power generation module is less than the set value, the electricity in the energy storage module is supplemented to the output end module to balance the supply and demand of the power grid.
[0060] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0061] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0062] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0064] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principle of the present invention without creative labor shall be included in the protection scope of the present invention.
Claims
1. An energy dynamic intelligent dispatching and control system for a photothermal power storage coupling process, characterized in that: It includes photovoltaic power generation module, energy storage module, external power supply module, data acquisition module, data output module, data control module and output terminal module, among which: The photovoltaic power generation module is connected to the energy storage module, the data acquisition module and the output module, the data output module is connected to the data acquisition module and the data control module, and the data control module is connected to the external power supply module and the energy storage module; The data acquisition module is used to acquire the equipment characteristics, location characteristics, meteorological characteristics of the photovoltaic panels, and time characteristics of photovoltaics, and to predict the power of the photovoltaic power generation module based on the acquired data; The data control module is used to control the external power supply module to supply power to the energy storage module according to the predicted power, and realize the intelligent power storage of the energy storage module. The output end module is connected with the external power supply module, the energy storage module and the photovoltaic power generation module to output electric energy and realize the intelligent power regulation of the system. The energy storage module, photovoltaic power generation module, external power supply module and output end module are controlled by the data control module to store excess photovoltaic power generation energy and external electric energy and output the stored energy to the output end module.
2. The energy dynamic intelligent dispatching and control system of the photovoltaic, thermal, electricity and energy storage coupling process according to claim 1 is characterized in that: The data acquisition module is also used to obtain the historical power consumption and power consumption mode of the user end.
3. The energy dynamic intelligent dispatching and control system of the photovoltaic, thermal, electricity and energy storage coupling process according to claim 1 is characterized in that: The equipment characteristics include the power of the photovoltaic panels, the surface cleanliness and the number of photovoltaic panels.
4. The energy dynamic intelligent dispatching and control system of the photovoltaic, thermal, electricity and energy storage coupling process according to claim 1 is characterized in that: The location characteristics and climate characteristics include setting longitude and latitude, altitude, sunshine duration, temperature, irradiance, wind speed, rainfall and cloud thickness.
5. The energy dynamic intelligent dispatching and control system of the photovoltaic, thermal, electricity and energy storage coupling process according to claim 1 is characterized in that: The data acquisition module forms training data based on the acquired data, constructs an LSTM neural network model, and weights all states output by the LSTM neural network model according to the attention weight to form a model that integrates LSTM and attention mechanism, trains the model using the training data, and uses the trained model for prediction.
6. The energy dynamic intelligent dispatching and control system of the photovoltaic, thermal, electricity and energy storage coupling process as claimed in claim 5 is characterized by: The LSTM neural network model includes several LSTM layers, each layer includes an input gate, a forget gate, an output gate and a memory unit, the input gate is used to determine the information to be stored in the memory unit, the forget gate is used to determine the information to be forgotten from the memory unit, and the output gate is used to determine the next hidden state. Through the interaction between the forget gate and the input gate, the memory unit can selectively remember or forget information. Through the interaction of the above-mentioned gating mechanisms, the LSTM neural network model can capture the long-term and short-term dependencies in time series data and generate reliable time feature representations, which will serve as inputs for subsequent attention mechanism layers.
7. An energy dynamic intelligent dispatching and control system for a photovoltaic, thermal, electric and energy storage coupling process as claimed in claim 5 or 6, characterized in that: The attention mechanism layer calculates the score of each time step state output by each LSTM layer of the LSTM neural network model, and then uses a function to convert the score into an attention weight. Through weighted summation, all states output by the LSTM layer are weighted according to the attention weight to form a new feature vector. The new feature vector is passed to the fully connected layer for further processing and prediction. The fully connected layer maps high-dimensional features to the output space by setting weights and biases to generate the final prediction result.
8. The energy dynamic intelligent dispatching and control system of the photovoltaic, thermal, electricity and energy storage coupling process according to claim 1 is characterized in that: The photovoltaic power generation module, energy storage module, external power supply module, data acquisition module, data output module and output end module are all provided with sensors and signal transmission units. The sensors are used to monitor the voltage, current and / or temperature information of the corresponding modules. The signal transmission unit is used to transmit the information collected by the sensors to the control module. The control module is used to determine whether the corresponding modules are in normal working state according to the collected information.
9. The energy dynamic intelligent dispatching and control system of the photovoltaic, thermal, electricity and energy storage coupling process according to claim 1 is characterized in that: The data control module is configured to control the excess power to be stored in the energy storage module when the power generated by the photovoltaic power generation module exceeds the power required by the output end module, and to supplement the power in the energy storage module to the output end module when the power generated by the photovoltaic power generation module is less than the set value, so as to balance the supply and demand of the power grid.
10. A method for dynamic intelligent scheduling and control of energy in a photothermal power storage coupling process, characterized in that: The following steps are involved: Obtain the equipment characteristics, location characteristics, meteorological characteristics of the photovoltaic panels, and time characteristics of photovoltaics; According to the acquired data, the power of the photovoltaic power generation module is predicted. According to the predicted power, the external power supply module is regulated to supply power to the energy storage module, and the intelligent power storage of the energy storage module is realized. The output end module is connected with the external power supply module, the energy storage module and the photovoltaic power generation module to output electric energy and realize the intelligent power regulation of the system. When the amount of electricity generated by the photovoltaic power generation module exceeds the amount of electricity required by the output end module, the excess electricity is regulated and stored in the energy storage module. When the amount of electricity generated by the photovoltaic power generation module is less than the set value, the electricity in the energy storage module is supplemented to the output end module to balance the supply and demand of the power grid.