A highly efficient solar energy conversion and storage system

Abstract

A high-efficiency solar energy conversion and storage system comprises an environmental data collection module, a photovoltaic unit module, an environmental prediction module, an adjustment strategy module, an adjustment transmission module, an energy storage module, and a data display module; the solar energy conversion and storage system proposed in the present invention installs an adjustable solar photovoltaic panel, adjusts the direction of the solar photovoltaic panel, predicts future atmospheric meteorological data based on historical atmospheric meteorological data, and then optimizes the solar photovoltaic panel working strategy to find the optimal working direction of the solar photovoltaic panel in the future and makes corresponding adjustments.

Description

Technical Field

[0001] The present invention relates to the field of new energy, and in particular to a high-efficiency solar energy conversion and storage system. Background Art

[0002] With the development of science and technology, solar energy has attracted much attention as a clean and renewable energy source. However, despite the huge potential of solar energy, its utilization is still limited by a series of technical challenges. This paper will explore the background technology of solar energy conversion and storage system and introduce a new system that aims to overcome the limitations of existing technology and achieve efficient solar energy conversion and storage.

[0003] Traditional solar energy conversion systems are mainly composed of solar photovoltaic panels, inverters and batteries. Photovoltaic panels convert solar energy into direct current through the photoelectric effect, inverters convert it into alternating current and connect it to the grid, and batteries are used to store excess electricity for use when needed. Although these systems have achieved certain success, there are still some challenges.

[0004] First, the traditional system has limited solar energy conversion efficiency. The conversion efficiency of solar photovoltaic panels is affected by many factors, including light intensity, sun angle, temperature, etc. Traditional systems lack intelligent adjustment functions and cannot adjust the angle and direction of photovoltaic panels according to real-time environmental conditions, thus failing to maximize the absorption of solar energy.

[0005] Secondly, the energy storage efficiency of the traditional system is low. Although batteries can provide electricity when the solar energy supply is insufficient, they have low energy density, limited lifespan, and problems such as charge and discharge losses. In addition, the manufacturing and recycling process of batteries will also cause environmental pollution.

[0006] In response to the problems of traditional systems, people have put forward new requirements for solar energy conversion and storage systems. First, the new system needs to have intelligent adjustment functions, which can adjust the angle and direction of photovoltaic panels according to real-time environmental conditions to maximize the absorption of solar energy. Second, the new system needs to have efficient energy storage capabilities, be able to make full use of excess solar energy, and provide stable and reliable power output. Summary of the invention

[0007] The object of the present invention is to provide a high-efficiency solar energy conversion and storage system, aiming to solve the problems mentioned in the above background.

[0008] In order to achieve the above-mentioned purpose, the present invention proposes a high-efficiency solar energy conversion and storage system, including an environmental data collection module, a photovoltaic unit module, an environmental prediction module, an adjustment strategy module, an adjustment transmission module, an energy storage module, and a data display module; the environmental data collection module organizes and collects the meteorological data of the surrounding atmosphere; the photovoltaic unit module designs an adjustable solar photovoltaic panel; the environmental prediction module proposes a data generation algorithm to predict the atmospheric meteorological data in the future; the adjustment strategy module constructs a solar photovoltaic panel working strategy library, proposes a target algorithm, and optimizes the best strategy; the adjustment transmission module adjusts the solar photovoltaic panel according to the working strategy output by the adjustment strategy module; the energy storage module transmits the electric energy converted by the solar photovoltaic panel, a part of which is directly connected to the grid, and a part is stored through a battery; the data display module displays the current working status of the solar photovoltaic panel through a display screen.

[0009] Furthermore, the environmental data collection module collects and pre-processes historical atmospheric meteorological data through the atmospheric meteorological website where the solar photovoltaic panels work, and removes atmospheric meteorological data that does not affect the power generation efficiency of the solar photovoltaic panels.

[0010] Furthermore, the adjustable solar photovoltaic panel is equipped with a universal adjuster between the solar photovoltaic panel and the vertical pole, which can perform universal adjustment on the solar photovoltaic panel, and the adjustment methods include electric control adjustment and manual adjustment.

[0011] Furthermore, the environmental prediction module proposes a data generation algorithm, constructs a simulation model of atmospheric meteorological data at future times, analyzes the dynamic change characteristics of the data based on the collected historical atmospheric meteorological data, and then optimizes the simulation model of atmospheric meteorological data at future times through data classification cross entropy.

[0012] Furthermore, the detailed process of the atmospheric meteorological data simulation model at the future moment is as follows:

[0013] The atmospheric meteorological data collected by the environmental data collection module is used to predict the meteorological changes after a certain period of time. The collected atmospheric meteorological data X is expressed as:

[0014] X=[x1,x2,…,xi,…,xn]

[0015] Among them, x1, x2, xi, and xn represent the atmospheric meteorological data vector at the first moment, the atmospheric meteorological data vector at the second moment, the atmospheric meteorological data vector at the i-th moment, and the atmospheric meteorological data vector at the n-th moment, respectively. The atmospheric meteorological data is time series data. For the atmospheric meteorological data vector at each moment, it is expressed as:

[0016] xi=[xi,1,xi,2,…,xi,j,…,xi,n]

[0017] Among them, xi,1, xi,2, xi,j, and xi,n represent the first value of the atmospheric meteorological data vector at the i-th moment, the second value of the atmospheric meteorological data vector at the i-th moment, the j-th value of the atmospheric meteorological data vector at the i-th moment, and the n-th value of the atmospheric meteorological data vector at the i-th moment, respectively. First, based on the atmospheric meteorological data vector at each moment, the time-varying parameter αj of the atmospheric meteorological data vector is calculated, and the calculation formula is:

[0018]

[0019] Among them, xi+1,j represents the jth value of the atmospheric meteorological data vector at the i+1th time. Based on the time-varying parameters, the dynamic characteristics of the atmospheric meteorological data at each moment are obtained. The formula is as follows:

[0020]

[0021] Among them, y represents the time series deviation of the atmospheric meteorological data vector, f(·) represents the dynamic characteristic function of the atmospheric meteorological data at each moment, based on the dynamic characteristic function of the atmospheric meteorological data at each moment, the time series deviation of the atmospheric meteorological data at the future moment is analyzed, and the atmospheric meteorological data simulation model at the future moment is constructed to simulate the atmospheric meteorological data in the future period of time, which is defined as the simulated data X′, expressed as:

[0022] X′=[x1′,x′2,…,xi′,…,x′n]

[0023] Among them, x1′, x′2, xi′, and x′n represent the simulated atmospheric meteorological data vector at the first moment in the future, the simulated atmospheric meteorological data vector at the second moment in the future, the simulated atmospheric meteorological data vector at the ith moment in the future, and the simulated atmospheric meteorological data vector at the nth moment in the future, respectively. For the atmospheric meteorological data simulation model at the future moment, a discriminant function is constructed, and the simulated data generated by the atmospheric meteorological data simulation model at the future moment is analyzed to train the atmospheric meteorological data simulation model at the future moment. During the training process of the atmospheric meteorological data simulation model at the future moment, the real atmospheric meteorological data vector corresponding to the simulated atmospheric meteorological data vector within a period of time in the future is also collected. Through the data cross entropy, the classification cross entropy of the simulated atmospheric meteorological data vector and the real atmospheric meteorological data vector is calculated. The calculation formula is as follows:

[0024]

[0025] Among them, xi″ represents the real atmospheric meteorological data vector corresponding to the simulated atmospheric meteorological data vector at the i-th moment in the future, xi′,j represents the j-th value of the simulated atmospheric meteorological data vector at the i-th moment in the future, and xi″,j represents the j-th value of the real atmospheric meteorological data vector corresponding to the simulated atmospheric meteorological data vector at the i-th moment in the future. Based on the classification cross entropy of the simulated atmospheric meteorological data vector and the real atmospheric meteorological data vector, the atmospheric meteorological data simulation model at the future moment is optimized. The process formula is as follows:

[0026]

[0027] The training process seeks to minimize After reaching the set goal, the training of the atmospheric meteorological data simulation model at the future moment is completed. The present invention proposes a data generation algorithm to construct a simulation model of atmospheric meteorological data at the future moment. Based on the collected historical atmospheric meteorological data, the time-varying parameters are calculated, the dynamic change characteristics of the data are analyzed, and then the atmospheric meteorological data simulation model at the future moment is optimized through data classification cross entropy. The data generation algorithm proposed by the present invention can accurately predict future atmospheric meteorological data.

[0028] Furthermore, the adjustment strategy module constructs a solar photovoltaic panel working strategy optimization model, and optimizes the solar photovoltaic panel working strategy based on the objective function.

[0029] Furthermore, the solar photovoltaic panel working strategy is optimized, and the detailed process is as follows:

[0030] For all working conditions of solar photovoltaic panels, a solar photovoltaic panel working strategy library β is constructed, which is expressed as:

[0031] β=[β1,β2,…,βi,…,βn]

[0032] Among them, β1, β2, βi, and βn represent the first solar photovoltaic panel working strategy, the second solar photovoltaic panel working strategy, the i-th solar photovoltaic panel working strategy, and the n-th solar photovoltaic panel working strategy, respectively. The objective function is constructed, and the strategy optimization is performed in the solar photovoltaic panel working strategy library β based on the objective function. The objective function is as follows:

[0033]

[0034] Wherein, F represents the objective function, ti represents the power generation working time of the i-th solar photovoltaic panel, ηi represents the power generation working efficiency of the i-th solar photovoltaic panel, δi represents the power generation working cost of the i-th solar photovoltaic panel, based on the objective function, the strategy optimization is carried out in the solar photovoltaic panel working strategy library β, and the optimization network of all solar photovoltaic panel working strategies is constructed. Each node in the optimization network represents a solar photovoltaic panel working strategy. In the optimization process, an update evolution matrix is ​​constructed, and the strategy of the solar photovoltaic panel working strategy library β is updated. The update evolution matrix χ is expressed as follows:

[0035]

[0036] Among them, χ1,1, χ1,n, χi,j, χn,1, χn,n represent the updated value of the 1st row and 1st column of the evolution matrix χ, the updated value of the 1st row and nth column of the evolution matrix χ, the updated value of the ith row and jth column of the evolution matrix χ, the updated value of the nth row and 1st column of the evolution matrix χ, and the updated value of the nth row and nth column of the evolution matrix χ, respectively. The values ​​in the updated evolution matrix are related to the position of the solar photovoltaic panel working strategy in the optimization network. The values ​​in the updated evolution matrix are determined by the following formula:

[0037]

[0038] Among them, χi,j,β i represents the value of the updated evolution matrix χ in the i-th row and j-th column of the solar photovoltaic panel working strategy βi, rk,β i Represents the kth edge of the solar photovoltaic panel working strategy βi in the optimization network node, rj,β i Represents the solar photovoltaic panel working strategy βi in the optimization network node j-th edge, ri,β i represents the i-th edge of the solar photovoltaic panel working strategy βi in the optimization network node, cos<·> represents the vector product, and the solar photovoltaic panel working strategy library is optimized and updated by updating the evolution matrix to expand the optimization range. In the strategy optimization process, the apoptosis intensity θ is defined. At the initial moment, the apoptosis intensity is assigned to each strategy. Based on the apoptosis intensity, the optimization process is as follows:

[0039]

[0040] Among them, pi → j represents the probability of the optimization process transferring from network node i to network node j, θj represents the apoptosis strength of strategy βj, rl,β j Indicates that the solar photovoltaic panel working strategy βj is on the lth edge of the optimization network node. During the optimization process, the apoptosis strength of the strategy is updated, and the update equation is expressed as follows:

[0041]

[0042] Among them, θj′ represents the updated value of apoptosis intensity θj, φ represents the residual degree of apoptosis intensity, D(βi,βj) represents the distance from strategy βi to strategy βj in the optimization network, and the strategy is automatically apoptotic in the optimization process by updating the apoptosis intensity. The solar photovoltaic panel working strategy optimization model proposed in the present invention builds a solar photovoltaic panel working strategy library, performs strategy optimization through the objective function, updates the solar photovoltaic panel working strategy library based on the updated evolution matrix, defines apoptosis intensity, and constructs optimization rules and strategy elimination based on apoptosis reinforcement. The solar photovoltaic panel working strategy optimization model proposed in the present invention can perform strategy optimization on a large scale, and the strategy optimization quality is high.

[0043] Furthermore, after the adjustment strategy module performs strategy optimization, the adjustment transmission module electrically adjusts the solar photovoltaic panel according to the output optimal strategy, and automatically adjusts it to the working direction corresponding to the optimal strategy. When the electric control fails, the solar photovoltaic panel is adjusted by manual adjustment.

[0044] Furthermore, the energy storage module controls the voltage of the solar photovoltaic panel through a voltage stabilizer, and a portion of the electricity is directly connected to the grid, while a portion of the electricity is stored in a battery.

[0045] Furthermore, the data display module displays detailed working information of the solar photovoltaic panels through a display, and the detailed working information of the solar photovoltaic panels includes power generation efficiency, working temperature, and power consumption for regulation of each solar photovoltaic panel.

[0046] Beneficial Effects

[0047] The present invention proposes a highly efficient solar energy conversion and storage system, including an environmental data collection module, a photovoltaic unit module, an environmental prediction module, an adjustment strategy module, an adjustment transmission module, an energy storage module, and a data display module; the environmental prediction module proposes a data generation algorithm, constructs a future atmospheric meteorological data simulation model, calculates time-varying parameters based on the collected historical atmospheric meteorological data, analyzes the dynamic change characteristics of the data, and then optimizes the future atmospheric meteorological data simulation model through data classification cross entropy. The data generation algorithm proposed by the present invention can accurately predict future atmospheric meteorological data; the adjustment strategy module proposes a solar photovoltaic panel working strategy optimization model, constructs a solar photovoltaic panel working strategy library, performs strategy optimization through an objective function, updates the solar photovoltaic panel working strategy library based on an updated evolutionary matrix, defines apoptosis intensity, constructs optimization rules and strategy elimination based on apoptosis reinforcement, and the solar photovoltaic panel working strategy optimization model proposed by the present invention can perform strategy optimization on a large scale, and the strategy optimization quality is high; the system of the present invention can make full use of solar energy resources through intelligent adjustment functions and environmental prediction technology, and improves the conversion efficiency and utilization rate of solar energy. The adjustability of the photovoltaic unit module enables the photovoltaic panel to be adjusted according to real-time environmental conditions to absorb solar energy to the greatest extent. The optimization algorithms of the regulation strategy module and the environmental prediction module further improve the performance of the system, enabling efficient conversion and storage under different environmental conditions. This can not only meet the energy needs of daily life and industrial production, but also provide reliable power supply for remote areas and developing countries, and promote the sustainable development of global energy; it is of great significance to mitigate climate change and improve air quality. The high-efficiency solar energy conversion and storage system of the present invention further improves the utilization efficiency of solar energy, fundamentally reduces dependence on fossil energy, reduces greenhouse gas emissions, helps protect the earth's ecological environment, and slows down the trend of global warming. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings in the following description are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 It is a schematic diagram of the structure of the present invention;

[0050] Figure 2 It is a schematic diagram of the strategy optimization model of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] In order to achieve the above-mentioned purpose, the present invention proposes a high-efficiency solar energy conversion and storage system, including an environmental data collection module, a photovoltaic unit module, an environmental prediction module, an adjustment strategy module, an adjustment transmission module, an energy storage module, and a data display module; the environmental data collection module organizes and collects the meteorological data of the surrounding atmosphere; the photovoltaic unit module designs an adjustable solar photovoltaic panel; the environmental prediction module proposes a data generation algorithm to predict the atmospheric meteorological data in the future; the adjustment strategy module constructs a solar photovoltaic panel working strategy library, proposes a target algorithm, and optimizes the best strategy; the adjustment transmission module adjusts the solar photovoltaic panel according to the working strategy output by the adjustment strategy module; the energy storage module transmits the electric energy converted by the solar photovoltaic panel, a part of which is directly connected to the grid, and a part is stored through a battery; the data display module displays the current working status of the solar photovoltaic panel through a display screen.

[0053] Specifically, the environmental data collection module collects and pre-processes historical atmospheric meteorological data through the atmospheric meteorological website where the solar photovoltaic panels work, and removes atmospheric meteorological data that does not affect the power generation efficiency of the solar photovoltaic panels.

[0054] Specifically, the adjustable solar photovoltaic panel is equipped with a universal adjuster between the solar photovoltaic panel and the vertical pole, which can perform universal adjustment on the solar photovoltaic panel, and the adjustment methods include electric control adjustment and manual adjustment.

[0055] Specifically, the environmental prediction module proposes a data generation algorithm, constructs a simulation model of atmospheric meteorological data at future times, analyzes the dynamic change characteristics of the data based on the collected historical atmospheric meteorological data, and then optimizes the simulation model of atmospheric meteorological data at future times through data classification cross entropy.

[0056] Specifically, the atmospheric meteorological data simulation model at the future moment has the following detailed process:

[0057] The atmospheric meteorological data collected by the environmental data collection module predicts the meteorological changes and sunlight changes after a certain period of time. The collected atmospheric meteorological data X is expressed as:

[0058] X=[x1,x2,…,xi,…,xn]

[0059] Among them, x1, x2, xi, and xn represent the atmospheric meteorological data vector at the first moment, the atmospheric meteorological data vector at the second moment, the atmospheric meteorological data vector at the i-th moment, and the atmospheric meteorological data vector at the n-th moment, respectively. The atmospheric meteorological data is time series data. For the atmospheric meteorological data vector at each moment, it is expressed as:

[0060] xi=[xi,1,xi,2,…,xi,j,…,xi,n]

[0061] Among them, xi,1, xi,2, xi,j, and xi,n represent the first value of the atmospheric meteorological data vector at the i-th moment, the second value of the atmospheric meteorological data vector at the i-th moment, the j-th value of the atmospheric meteorological data vector at the i-th moment, and the n-th value of the atmospheric meteorological data vector at the i-th moment, respectively. First, based on the atmospheric meteorological data vector at each moment, the time-varying parameter αj of the atmospheric meteorological data vector is calculated, and the calculation formula is:

[0062]

[0063] Among them, xi+1,j represents the jth value of the atmospheric meteorological data vector at the i+1th time. Based on the time-varying parameters, the dynamic characteristics of the atmospheric meteorological data at each moment are obtained. The formula is as follows:

[0064]

[0065] Among them, y represents the time series deviation of the atmospheric meteorological data vector, f(·) represents the dynamic characteristic function of the atmospheric meteorological data at each moment, based on the dynamic characteristic function of the atmospheric meteorological data at each moment, the time series deviation of the atmospheric meteorological data at the future moment is analyzed, and the atmospheric meteorological data simulation model at the future moment is constructed to simulate the atmospheric meteorological data in the future period of time, which is defined as the simulated data X′, expressed as:

[0066] X′=[x1′,x′2,…,xi′,…,x′n]

[0067] Among them, x1′, x′2, xi′, and x′n represent the simulated atmospheric meteorological data vector at the first moment in the future, the simulated atmospheric meteorological data vector at the second moment in the future, the simulated atmospheric meteorological data vector at the ith moment in the future, and the simulated atmospheric meteorological data vector at the nth moment in the future, respectively. For the atmospheric meteorological data simulation model at future moments, a discriminant function is constructed, and the simulated data generated by the atmospheric meteorological data simulation model at future moments is analyzed to train the atmospheric meteorological data simulation model at future moments. During the training process of the atmospheric meteorological data simulation model at future moments, the real atmospheric meteorological data vectors corresponding to the simulated atmospheric meteorological data vectors within a period of time in the future are also collected. Through the data cross entropy, the classification cross entropy of the simulated atmospheric meteorological data vector and the real atmospheric meteorological data vector is calculated. The calculation formula is as follows:

[0068]

[0069] Among them, xi″ represents the real atmospheric meteorological data vector corresponding to the simulated atmospheric meteorological data vector at the i-th moment in the future, xi′,j represents the j-th value of the simulated atmospheric meteorological data vector at the i-th moment in the future, and xi″,j represents the j-th value of the real atmospheric meteorological data vector corresponding to the simulated atmospheric meteorological data vector at the i-th moment in the future. Based on the classification cross entropy of the simulated atmospheric meteorological data vector and the real atmospheric meteorological data vector, the atmospheric meteorological data simulation model at the future moment is optimized. The process formula is as follows:

[0070]

[0071] The training process seeks to minimize After reaching the set goal, the training of the atmospheric meteorological data simulation model for future moments is completed.

[0072] Specifically, the adjustment strategy module constructs a solar photovoltaic panel working strategy library and optimizes the solar photovoltaic panel working strategy based on the objective function.

[0073] Specifically, the optimization process of the solar photovoltaic panel working strategy is as follows:

[0074] For all working conditions of solar photovoltaic panels, a solar photovoltaic panel working strategy library β is constructed, which is expressed as:

[0075] β=[β1,β2,…,βi,…,βn]

[0076] Among them, β1, β2, βi, and βn represent the first solar photovoltaic panel working strategy, the second solar photovoltaic panel working strategy, the i-th solar photovoltaic panel working strategy, and the n-th solar photovoltaic panel working strategy, respectively. The objective function is constructed, and the strategy optimization is performed in the solar photovoltaic panel working strategy library β based on the objective function. The objective function is as follows:

[0077]

[0078] Wherein, F represents the objective function, ti represents the power generation working time of the i-th solar photovoltaic panel, ηi represents the power generation working efficiency of the i-th solar photovoltaic panel, δi represents the power generation working cost of the i-th solar photovoltaic panel, based on the objective function, the strategy optimization is carried out in the solar photovoltaic panel working strategy library β, and the optimization network of all solar photovoltaic panel working strategies is constructed. Each node in the optimization network represents a solar photovoltaic panel working strategy. In the optimization process, an update evolution matrix is ​​constructed, and the strategy of the solar photovoltaic panel working strategy library β is updated. The update evolution matrix χ is expressed as follows:

[0079]

[0080] Among them, χ1,1, χ1,n, χi,j, χn,1, χn,n represent the updated value of the 1st row and 1st column of the evolution matrix χ, the updated value of the 1st row and nth column of the evolution matrix χ, the updated value of the ith row and jth column of the evolution matrix χ, the updated value of the nth row and 1st column of the evolution matrix χ, and the updated value of the nth row and nth column of the evolution matrix χ, respectively. The values ​​in the updated evolution matrix are related to the position of the solar photovoltaic panel working strategy in the optimization network. The values ​​in the updated evolution matrix are determined by the following formula:

[0081]

[0082] in, represents the value of the updated evolution matrix χ in the i-th row and j-th column of the solar photovoltaic panel working strategy βi, represents the kth edge of the solar photovoltaic panel working strategy βi in the optimization network node, represents the jth edge of the solar photovoltaic panel working strategy βi in the optimization network node, represents the i-th edge of the solar photovoltaic panel working strategy βi in the optimization network node, cos<·> represents the vector product, and the solar photovoltaic panel working strategy library is optimized and updated by updating the evolution matrix to expand the optimization range. In the strategy optimization process, the apoptosis intensity θ is defined. At the initial moment, the apoptosis intensity is assigned to each strategy. Based on the apoptosis intensity, the optimization process is as follows:

[0083]

[0084] Among them, pi → j represents the probability of the optimization process transferring from network node i to network node j, θj represents the apoptosis strength of strategy βj, Indicates that the solar photovoltaic panel working strategy βj is on the lth edge of the optimization network node. During the optimization process, the apoptosis strength of the strategy is updated, and the update equation is expressed as follows:

[0085]

[0086] Among them, θj′ represents the updated value of apoptosis intensity θj, φ represents the residual degree of apoptosis intensity, and D(βi,βj) represents the distance from strategy βi to strategy βj in the optimization network. By updating the apoptosis intensity, the strategy in the optimization process is automatically apoptotic.

[0087] Specifically, after the adjustment strategy module performs strategy optimization, the adjustment transmission module electrically adjusts the solar photovoltaic panel according to the output optimal strategy, and automatically adjusts it to the working direction corresponding to the optimal strategy. When the electric control fails, the solar photovoltaic panel is adjusted by manual adjustment.

[0088] Specifically, the energy storage module controls the voltage of the solar photovoltaic panel through a voltage stabilizer, and a portion of the electricity is directly connected to the grid, while a portion of the electricity is stored in a battery.

[0089] 10. A high-efficiency solar energy conversion and storage system according to claim 1, characterized in that the data display module displays detailed working information of the solar photovoltaic panels through a display, and the detailed working information of the solar photovoltaic panels includes the power generation efficiency, working temperature, and power consumption of each solar photovoltaic panel.

Claims

1. A highly efficient solar energy conversion and storage system, comprising an environmental data collection module, a photovoltaic unit module, an environmental prediction module, an adjustment strategy module, an adjustment transmission module, an energy storage module, and a data display module; the environmental data collection module collects and organizes the meteorological data of the surrounding atmosphere; the photovoltaic unit module designs an adjustable solar photovoltaic panel; the environmental prediction module proposes a data generation algorithm to predict the atmospheric meteorological data in the future; The adjustment strategy module builds a solar photovoltaic panel working strategy library, proposes a target algorithm, and searches for the best strategy; The regulating transmission module regulates the solar photovoltaic panel according to the working strategy output by the regulating strategy module; the energy storage module transmits the electric energy converted by the solar photovoltaic panel, part of which is directly connected to the grid and part of which is stored in the battery; the data display module displays the current working status of the solar photovoltaic panel through the display screen; The adjustment strategy module constructs a solar photovoltaic panel working strategy library and optimizes the solar photovoltaic panel working strategy based on the objective function; The detailed process of optimizing the working strategy of the solar photovoltaic panel is as follows: For all working conditions of solar photovoltaic panels, a solar photovoltaic panel working strategy library β is constructed, and strategy optimization is performed in the solar photovoltaic panel working strategy library β based on the objective function. The objective function is as follows: Wherein, F represents the objective function, ti represents the power generation working time of the ith solar photovoltaic panel, ηi represents the power generation working efficiency of the ith solar photovoltaic panel, δi represents the power generation working cost of the ith solar photovoltaic panel, based on the objective function, the strategy optimization is performed in the solar photovoltaic panel working strategy library β, and the optimization network is constructed for all solar photovoltaic panel working strategies. Each node in the optimization network represents a solar photovoltaic panel working strategy. In the optimization process, an update evolution matrix χ is constructed, and the solar photovoltaic panel working strategy library β is updated. The values ​​in the update evolution matrix are related to the position of the solar photovoltaic panel working strategy in the optimization network. The values ​​in the update evolution matrix are determined by the following formula: in, represents the value of the updated evolution matrix χ in the i-th row and j-th column of the solar photovoltaic panel working strategy βi, represents the kth edge of the solar photovoltaic panel working strategy βi in the optimization network node, represents the jth edge of the solar photovoltaic panel working strategy βi in the optimization network node, represents the i-th edge of the solar photovoltaic panel working strategy βi in the optimization network node, cos<·> represents the vector product, and the solar photovoltaic panel working strategy library is optimized and updated by updating the evolution matrix to expand the optimization range. In the strategy optimization process, the apoptosis intensity θ is defined. At the initial moment, the apoptosis intensity is assigned to each strategy. Based on the apoptosis intensity, the optimization process is as follows: Among them, pi → j represents the probability of the optimization process transferring from network node i to network node j, θj represents the apoptosis strength of strategy βj, Indicates that the solar photovoltaic panel working strategy βj is on the lth edge of the optimization network node. During the optimization process, the apoptosis strength of the strategy is updated, and the update equation is expressed as follows: Among them, θj′ represents the updated value of apoptosis intensity θj, φ represents the residual degree of apoptosis intensity, and D(βi,βj) represents the distance from strategy βi to strategy βj in the optimization network. By updating the apoptosis intensity, the strategy in the optimization process is automatically apoptotic.

2. A high-efficiency solar energy conversion and storage system according to claim 1, characterized in that: The environmental data collection module collects and pre-processes historical atmospheric meteorological data through the atmospheric meteorological website where the solar photovoltaic panels work, and removes atmospheric meteorological data that does not affect the power generation efficiency of the solar photovoltaic panels.

3. The high-efficiency solar energy conversion and storage system according to claim 1, characterized in that: The adjustable solar photovoltaic panel is equipped with a universal adjuster at the solar photovoltaic panel and the vertical pole, which can perform universal adjustment on the solar photovoltaic panel. The adjustment methods include electric control adjustment and manual adjustment.

4. The high-efficiency solar energy conversion and storage system according to claim 1, characterized in that: The environmental prediction module proposes a data generation algorithm, constructs a simulation model for atmospheric meteorological data at future times, analyzes the dynamic change characteristics of the data based on the collected historical atmospheric meteorological data, and then optimizes the simulation model for atmospheric meteorological data at future times through data classification cross entropy.

5. A high-efficiency solar energy conversion and storage system according to claim 4, characterized in that: The detailed process of the atmospheric meteorological data simulation model at the future moment is as follows: The atmospheric meteorological data collected by the environmental data collection module is used to predict meteorological changes after a certain period of time. The collected atmospheric meteorological data X is time series data. For the atmospheric meteorological data vector at each moment, the time-varying parameter αj of the atmospheric meteorological data vector is calculated. The calculation formula is: Among them, xi,j represents the jth value of the atmospheric meteorological data vector at the i-th moment, and xi+1,j represents the jth value of the atmospheric meteorological data vector at the i+1-th moment. Based on the time-varying parameters, the dynamic characteristics of the atmospheric meteorological data at each moment are obtained, and the formula is as follows: Wherein, y represents the time series deviation of the atmospheric meteorological data vector, f(·) represents the dynamic characteristic function of the atmospheric meteorological data at each moment, based on the dynamic characteristic function of the atmospheric meteorological data at each moment, the time series deviation of the atmospheric meteorological data at the future moment is analyzed, and a simulation model of the atmospheric meteorological data at the future moment is constructed to simulate the atmospheric meteorological data in a certain period of time in the future, which is defined as the simulated data X′. For the simulation model of the atmospheric meteorological data at the future moment, a discriminant function is constructed, and the simulated data generated by the simulation model of the atmospheric meteorological data at the future moment is analyzed to train the simulation model of the atmospheric meteorological data at the future moment. In the process of training the simulation model of the atmospheric meteorological data at the future moment, the real atmospheric meteorological data vector corresponding to the simulated atmospheric meteorological data vector in a certain period of time in the future is also collected, and the classification cross entropy of the simulated atmospheric meteorological data vector and the real atmospheric meteorological data vector is calculated through the data cross entropy. The calculation formula is as follows: Among them, xi′ represents the simulated atmospheric meteorological data vector at the i-th moment in the future, xi″ represents the real atmospheric meteorological data vector corresponding to the simulated atmospheric meteorological data vector at the i-th moment in the future, xi′,j represents the j-th value of the simulated atmospheric meteorological data vector at the i-th moment in the future, xi″,j represents the j-th value of the real atmospheric meteorological data vector corresponding to the simulated atmospheric meteorological data vector at the i-th moment in the future. Based on the classification cross entropy of the simulated atmospheric meteorological data vector and the real atmospheric meteorological data vector, the atmospheric meteorological data simulation model at future moments is optimized. The process formula is as follows: The training process seeks to minimize After reaching the set goal, the training of the atmospheric meteorological data simulation model for future moments is completed.

6. The high-efficiency solar energy conversion and storage system according to claim 1, characterized in that: The regulating transmission module electrically regulates the solar photovoltaic panel according to the output optimal strategy after the regulating strategy module performs strategy optimization, and automatically adjusts the solar photovoltaic panel to the working direction corresponding to the optimal strategy. When the electric control fails, the solar photovoltaic panel is adjusted manually.

7. The high-efficiency solar energy conversion and storage system according to claim 1, characterized in that: The energy storage module controls the voltage of the solar photovoltaic panel through a voltage stabilizer, and a portion of the electricity is directly connected to the grid, while a portion of the electricity is stored in a battery.

8. The high-efficiency solar energy conversion and storage system according to claim 1, characterized in that: The data display module displays the detailed working information of the solar photovoltaic panels through a display, and the detailed working information of the solar photovoltaic panels includes the power generation efficiency, working temperature and power consumption of each solar photovoltaic panel.

Images