Photovoltaic management method and system for improving photovoltaic power generation efficiency

Abstract

The invention relates to the technical field of photovoltaic power generation, and relates to a photovoltaic management method and system for improving photovoltaic power generation efficiency, and the method comprises the steps: obtaining the first power generation power at the current moment, obtaining the second power generation power at the next moment of the current moment in the predicted power generation power, and judging whether the first power generation power is greater than the second power generation power or not; sending a control signal for turning off the sun following system to the first photovoltaic panel of which the second power generation power is not greater than the first power generation power; and for the second photovoltaic panel of which the second generation power is greater than the first generation power, outputting a comparison value of the second photovoltaic panel based on the judgment model, and judging whether to start the sun following system of the second photovoltaic panel through the comparison threshold value and the comparison value. According to the method, whether the sun following system of the photovoltaic panel is started or not can be controlled, so that the currently output generated power is larger, and the situation that the generated power is wasted due to the fact that the effect of improving the generated power of the photovoltaic panel is not achieved when the photovoltaic power generation system is started is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and more particularly, to a photovoltaic management method and system for improving the efficiency of photovoltaic power generation. Background Art

[0002] Photovoltaic power generation is a clean energy technology that directly converts solar energy into electrical energy using the photovoltaic effect. Its core component is the photovoltaic cell, usually made of silicon materials, and is divided into types such as monocrystalline silicon, polycrystalline silicon, and thin-film cells. A photovoltaic power generation system usually consists of photovoltaic modules, inverters, controllers, and energy storage systems. The development of photovoltaic technology began in the 1950s. With the progress of materials science and manufacturing processes, the efficiency and production cost of photovoltaic cells have been continuously optimized, promoting the rapid development of this field.

[0003] Among them, the photovoltaic panel tracking system maximizes the reception of solar energy by adjusting the direction of the photovoltaic modules, thereby improving the power generation efficiency. This system is mainly divided into two types: single-axis and dual-axis. The single-axis tracker moves along one axis, while the dual-axis tracker can be adjusted in two directions to adapt to the changing trajectory of the sun. By achieving precise sun tracking, these systems can improve the energy capture efficiency of photovoltaic cells and are widely used in large-scale photovoltaic power generation projects, promoting the development of renewable energy.

[0004] However, in the current prior art, the photovoltaic panel tracking system also has a certain energy consumption. When the current power generation power of the photovoltaic panel is poor, the startup of the photovoltaic panel tracking system may not help the photovoltaic panel obtain more sunlight, greatly affecting the total electrical energy output and resulting in low power generation efficiency. Summary of the Invention

[0005] The purpose of the present invention is to provide a positioning method and system based on Beidou communication to solve the problems existing in the prior art.

[0006] The present invention is achieved through the following technical solutions:

[0007] In a first aspect, the present invention provides a photovoltaic management method for improving the efficiency of photovoltaic power generation, including:

[0008] Obtain the current weather data, obtain the current light intensity according to the current weather data, and obtain the predicted power generation power of the target photovoltaic panel based on the light intensity through a power generation power prediction model;

[0009] Obtain the first power generation power at the current moment, obtain the second power generation power at the next moment of the current moment in the predicted power generation power, and determine whether the first power generation power is greater than the second power generation power;

[0010] For the first photovoltaic panel whose second power generation power is not greater than the first power generation power, send a control signal to turn off the sun tracking system;

[0011] For a second photovoltaic panel with a second power generation greater than the first power generation, obtain the number of first photovoltaic panels around the second photovoltaic panel, establish a judgment model based on the number, the power generation of the second photovoltaic panel, and weather data, output a comparison value for the second photovoltaic panel based on the judgment model, and set a comparison threshold. Determine whether to activate the sun-tracking system of the second photovoltaic panel by comparing the threshold and the comparison value.

[0012] Preferably, the construction of the power generation prediction model includes:

[0013] Use a number of neural network prediction models to predict the power generation, select states according to the predicted power of each neural network prediction model to form a state set, and take actions related to the current state to form an action set;

[0014] By taking actions, fuse a number of neural network prediction models, give rewards or punishments according to the fusion result, and update the state and Q matrix;

[0015] M = ω1M1 + ω2M2 + … + ω n M n , ω1 + ω2 + … + ω n = 1

[0016] In the formula, M is the predicted power after fusion, ω1 + ω2 + … + ω n are the calculation weights of each neural network prediction model, and M1 + M2 + … + M n are the predicted powers of each neural network prediction model.

[0017] Preferably, the fusion of a number of neural network prediction models includes:

[0018] Obtain a state from the state set and select an action from the action set. After taking the action, the fusion system gives a reward value according to the reward function and transitions to the next state. The fusion system learns repeatedly until it reaches the termination state and the Q value converges to the maximum value;

[0019]

[0020] In the formula, is the updated Q value at time T, is the Q value before update at time t, is the current state, is the action taken in the current state, δ is the learning rate, γ is the discount factor, is the next state, is the action that can be taken in the state, r is the reward, a ′is an action in set A, where A is a set of actions.

[0021] Preferably, the taking of an action related to the current state includes:

[0022]

[0023] In the formula, Π is the selection strategy, Random() is random selection, P is the probability, and ε is the greedy coefficient. is to select the action corresponding to the current maximum Q value.

[0024] Preferably, the giving of rewards or punishments according to the fusion result includes:

[0025]

[0026] In the formula, is the state under the Fisher information, is the action under the Fisher information, I is the Fisher information, Γ is the set of prediction powers of each neural network prediction model, M i is the prediction power of the i-th neural network prediction model, σ i is the variance of the i-th neural network prediction model, and n is the number of neural network prediction models.

[0027] Preferably, the establishing of the judgment model includes:

[0028]

[0029] In the formula, E is the comparison value, S is the number of second photovoltaic panels, K is the number of first photovoltaic panels adjacent to the second photovoltaic panel, η a is the ratio of the first photovoltaic panel to the second photovoltaic panel, T is the light intensity, W B is the power consumption of the sun tracking system, W A is the predicted power generation, φ α is the probability of rain.

[0030] Preferably, the setting of the comparison threshold includes setting a comparison threshold model, including:

[0031]

[0032] In the formula, E s is the comparison threshold, W C is the power generation power of the first photovoltaic panel, W D is the power generation power of the second photovoltaic panel.

[0033] Second, the present invention also provides a photovoltaic management system for improving the photovoltaic power generation efficiency, including:

[0034] A data prediction module, configured to obtain current weather data, obtain the current light intensity according to the current weather data, and obtain the predicted power generation of the target photovoltaic panel through a power generation prediction model based on the light intensity; calculate the currently predicted power generation amount of the target photovoltaic panel through the predicted power generation, obtain the power consumption required by the sun tracking system of the target photovoltaic panel, and determine whether the currently predicted power generation amount is greater than the power consumption;

[0035] A judgment module, configured to send that the sun tracking system works normally for the first photovoltaic panel with power generation greater than power consumption; for the second photovoltaic panel with power generation not greater than power consumption, obtain the number of the first photovoltaic panels around the second photovoltaic panel, establish a judgment model based on the number, the power generation of the second photovoltaic panel and the weather data, output a comparison value for the second photovoltaic panel based on the judgment model, set a comparison threshold, and judge whether to start the sun tracking system of the second photovoltaic panel through the comparison threshold and the comparison value;

[0036] A main control module, connected to the data prediction module and the judgment module, and used to execute the above-mentioned photovoltaic management method for improving photovoltaic power generation efficiency.

[0037] In a third aspect, the present invention further provides an electronic device, including a wearable display device and a processor, the processor is electrically connected to the wearable display device, and the processor is used for a memory storing instructions executable by the processor to execute the above-mentioned photovoltaic management method for improving photovoltaic power generation efficiency.

[0038] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enabling the electronic device to execute the above-mentioned photovoltaic management method for improving photovoltaic power generation efficiency.

[0039] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:

[0040] By using the above method provided by the present invention, obtain the first power generation power at the current moment, obtain the second power generation power at the next moment of the current moment in the predicted power generation, and judge whether the first power generation power is greater than the second power generation power; for the first photovoltaic panel with the second power generation power not greater than the first power generation power, send a control signal to turn off the sun tracking system; for the second photovoltaic panel with the second power generation power greater than the first power generation power, output a comparison value for the second photovoltaic panel based on the judgment model, and judge whether to start the sun tracking system of the second photovoltaic panel through the comparison threshold and the comparison value. Through the above method, it is possible to control whether the sun tracking system of the photovoltaic panel is started, so that the currently output power generation power is greater, and it is avoided that the start of the photovoltaic power generation system does not play a role in improving the power generation power of the photovoltaic panel, resulting in a waste of power generation power. Brief Description of the Drawings

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other relevant drawings can also be obtained based on these drawings.

[0042] Figure 1 It is a schematic flow chart of the present invention. Detailed Embodiments

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and illustrated in the drawings here can be arranged and designed in various different configurations.

[0044] Terms such as "first" and "second" in the specification, claims, and the above drawings of this application are used to distinguish similar objects and do not necessarily need to be used to describe a specific order or sequence. The naming or numbering of steps that appear in this application does not mean that the steps in the method flow must be executed in the time / logical order indicated by the naming or numbering. The named or numbered process steps can be changed in the execution order according to the technical objectives to be achieved, as long as the same or similar technical effects can be achieved.

[0045] The independently described modules or sub-modules can be physically separated or not: they can be implemented in software or in hardware, and some of the modules or sub-modules can be implemented in software, and the functions of these modules or sub-modules are called by the processor, and other parts of the templates or sub-modules are implemented in hardware, for example, through a hardware circuit. In addition, some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this application.

[0046] Please refer to Figure 1 , a photovoltaic management method provided by the present invention for improving the photovoltaic power generation efficiency, includes:

[0047] S101: Obtain the current weather data, obtain the current light intensity according to the current weather data, and obtain the predicted power generation of the target photovoltaic panel through the power generation power prediction model based on the light intensity;

[0048] Among them, the acquisition of light intensity can rely on meteorological data. Usually, the light intensity on sunny days, cloudy days, and overcast days is different. Sunny days: The light intensity is relatively high, possibly above 100,000 Lux. Cloudy days: The light intensity will decrease, usually between 1000 and 20,000 Lux. Overcast days: The light intensity is even lower, possibly between 100 and 1000 Lux.

[0049] Online weather services: Some weather services may provide estimated values of light intensity, such as solar radiation (measured in watts per square meter). More accurate data can be obtained through these services.

[0050] Existing calculation models in the prior art can also be used: If there are detailed weather parameters (such as cloud cover, humidity, etc.), calculations can also be performed based on physical models.

[0051] S102: Obtain the first power generation power at the current moment, obtain the second power generation power at the next moment of the current moment in the predicted power generation power, and determine whether the first power generation power is greater than the second power generation power;

[0052] In this embodiment, the power consumption of the entire solar tracking system needs to be collected. The solar tracking system of the photovoltaic panel is a device that can optimize the power generation efficiency of photovoltaic power generation. By tracking the position of the sun in the sky, it maximizes the sunlight received by the photovoltaic panel, including single-axis tracking systems: Horizontal single-axis tracking: The device rotates in the east-west direction, following the sunrise and sunset of the sun. Vertical single-axis tracking: The device rotates in the north-south direction, suitable for some specific high-latitude regions. Dual-axis tracking system: This system can move simultaneously in both the east-west and north-south directions, and can more precisely follow the trajectory of the sun. The dual-axis system usually provides higher energy output, but has higher construction and maintenance costs.

[0053] S103: Send a control signal to turn off the solar tracking system for the first photovoltaic panel whose second power generation power is not greater than the first power generation power;

[0054] Among them, for the first photovoltaic panel whose second power generation power is not greater than the first power generation power, it indicates that the solar tracking system does not play the corresponding role at this time, that is, it drives the first photovoltaic panel to follow the sun's rotation, but due to external reasons such as weather, the power generation power cannot be increased. Therefore, there is no need to keep the solar tracking system turned on all the time, wasting the power generation efficiency of the photovoltaic panel.

[0055] S104: For the second photovoltaic panel whose second power generation power is greater than the first power generation power, obtain the number of the first photovoltaic panels around the second photovoltaic panel, establish a judgment model based on the number, the power generation of the second photovoltaic panel, and weather data, output a comparison value for the second photovoltaic panel based on the judgment model, set a comparison threshold, and determine whether to start the solar tracking system of the second photovoltaic panel by comparing the threshold and the comparison value.

[0056] When the second power generation power is greater than the first power generation power, it indicates that the solar tracking system has played a certain role at this time. However, whether turning on the solar tracking system can achieve better power generation effect requires further analysis. Therefore, the current situation of the photovoltaic panel is comprehensively analyzed through the judgment model provided by the solution, and the final judgment result is obtained to output the control instruction.

[0057] In this embodiment, the construction of the power generation power prediction model includes:

[0058] Use several neural network prediction models to predict the power generation power, select the states according to the predicted power of each neural network prediction model to form a state set, and take actions related to the current state to form an action set;

[0059] By taking actions, several neural network prediction models are fused, and rewards or punishments are given according to the fusion results, and the state and Q matrix are updated;

[0060] M = ω1M1 + ω2M2 + … + ω n M n , ω1 + ω2 + … + ω n = 1

[0061] In the formula, M is the predicted power after fusion, ω1 + ω2 + … + ω n are the calculation weights of each neural network prediction model, and M1 + M2 + … + M n are the predicted powers of each neural network prediction model.

[0062] In this embodiment, the fusion of several neural network prediction models includes:

[0063] Obtain a state from the state set and select an action from the action set. After taking the action, the fusion system gives a reward value according to the reward function and transitions to the next state. The fusion system learns repeatedly until it reaches the termination state and the Q value converges to the maximum value;

[0064]

[0065] In the formula, is the updated Q value at time T, is the Q value before update at time t, is the current state, is the action taken for the current state, δ is the learning rate, γ is the discount factor, is the next state, is the action that can be taken in the state, r is the reward, a ′is an action in set A, where A is a set of actions.

[0066] In this embodiment, the taking of an action related to the current state includes:

[0067]

[0068] where Π is the selection strategy, Random() is random selection, P is the probability, and ε is the greedy coefficient. is to select the action corresponding to the current maximum Q value.

[0069] In this embodiment, giving a reward or punishment according to the fusion result includes:

[0070]

[0071] where is the state under the Fisher information, is the action under the Fisher information, I is the Fisher information, Γ is the set of the prediction powers of each neural network prediction model, M i is the prediction power of the i-th neural network prediction model, σ i is the variance of the i-th neural network prediction model, and n is the number of neural network prediction models.

[0072] In this embodiment, establishing a judgment model includes:

[0073]

[0074] where E is the comparison value, S is the number of second photovoltaic panels, K is the number of first photovoltaic panels adjacent to the second photovoltaic panels, η a is the ratio of the first photovoltaic panel to the second photovoltaic panel, T is the light intensity, W B is the power consumption of the sun tracking system, W A is the predicted power generation, φ α is the probability of rain.

[0075] In this embodiment, the data related to the photovoltaic panels is comprehensively analyzed. Through the calculation of the judgment model and the comparison of the results, a relatively objective instruction to turn on or off is given to assist the operator in making the next judgment.

[0076] In this embodiment, setting a comparison threshold includes setting a comparison threshold model, including:

[0077]

[0078] where E s is the comparison threshold, W Cis the power generation power of the first photovoltaic panel, in W D is the power generation power of the second photovoltaic panel.

[0079] In a second aspect, a photovoltaic management system for improving the photovoltaic power generation efficiency includes:

[0080] A data prediction module, configured to obtain current weather data, obtain the current light intensity according to the current weather data, obtain the predicted power generation power of the target photovoltaic panel through a power generation power prediction model based on the light intensity; calculate the currently predicted power generation amount of the target photovoltaic panel through the predicted power generation power, obtain the power consumption required by the sun tracking system of the target photovoltaic panel, and determine whether the currently predicted power generation amount is greater than the power consumption;

[0081] A judgment module, configured to issue that the sun tracking system of the first photovoltaic panel with a power generation amount greater than the power consumption works normally; for the second photovoltaic panel with a power generation amount not greater than the power consumption, obtain the number of the first photovoltaic panels around the second photovoltaic panel, establish a judgment model based on the number, the power generation amount of the second photovoltaic panel and the weather data, output a comparison value for the second photovoltaic panel based on the judgment model, set a comparison threshold, and determine whether to start the sun tracking system of the second photovoltaic panel through the comparison threshold and the comparison value;

[0082] A main control module, connected to the data prediction module and the judgment module, for executing the above-mentioned photovoltaic management method for improving the photovoltaic power generation efficiency.

[0083] In addition, each functional unit in various embodiments of the present invention may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0084] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0085] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various modifications and variations can be made to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A photovoltaic management method for improving photovoltaic power generation efficiency, characterized in that: include: Obtain current weather data, obtain current light intensity based on the current weather data, and obtain predicted power generation of the target photovoltaic panel through a power generation prediction model based on the light intensity; Obtain a first power generation at the current moment, obtain a second power generation at the next moment of the current moment in the predicted power generation, and determine whether the first power generation is greater than the second power generation; Sending a control signal for shutting down a sun following system to the first photovoltaic panel whose second power generation is not greater than the first power generation; For the second photovoltaic panel whose second power generation power is greater than the first power generation power, the number of first photovoltaic panels around the second photovoltaic panel is obtained, and a judgment model is established based on the number, the power generation of the second photovoltaic panel and the weather data. A comparison value for the second photovoltaic panel is output based on the judgment model, and a comparison threshold is set. The comparison threshold and the comparison value are used to determine whether to start the sun following system of the second photovoltaic panel.

2. A photovoltaic management method for improving photovoltaic power generation efficiency according to claim 1, characterized in that: The construction of the power generation prediction model includes: Use several neural network prediction models to predict the power generation, select a state according to the predicted power of each neural network prediction model to form a state set, and take actions related to the current state to form an action set; By taking actions, several neural network prediction models are integrated, rewards or penalties are given according to the integration results, and the state and Q matrix are updated; M=ω1M1+ω2M2+…+ω n M n ,ω1+ω2+…+ω n =1 Where M is the predicted power after fusion, ω1+ω2+…+ω n is the calculation weight of each neural network prediction model, M1+M2+…+M n The prediction power of each neural network prediction model.

3. A photovoltaic management method for improving photovoltaic power generation efficiency according to claim 2, characterized in that: The fusing of several neural network prediction models includes: Obtain a state from the state set and select an action from the action set. After the action is taken, the fusion system gives a reward value according to the reward function and switches to the next state. The fusion system learns repeatedly until it reaches the terminal state and the Q value converges to the maximum value; In the formula, is the updated Q value at time T, is the Q value before updating at time t, is the current state, is the action taken in the current state, δ is the learning rate, γ is the discount factor, For the next state, for The actions that can be taken in the state, r is the reward, a ′ is an action in set A, and A is an action set.

4. A photovoltaic management method for improving photovoltaic power generation efficiency according to claim 3, characterized in that: The actions taken in accordance with the current state include: In the formula, Π is the selection strategy, Random() is the random selection, P is the probability, ε is the greedy coefficient, To select the action corresponding to the current maximum Q value.

5. A photovoltaic management method for improving photovoltaic power generation efficiency according to claim 4, characterized in that: The reward or punishment according to the fusion result includes: In the formula, Status Fisher information under, For Action The Fisher information under the condition, I is the Fisher information, Γ is the set of prediction power of each neural network prediction model, M i is the prediction power of the ith neural network prediction model, σ i is the variance of the ith neural network prediction model, and n is the number of neural network prediction models.

6. A photovoltaic management method for improving photovoltaic power generation efficiency according to claim 5, characterized in that: The establishment of the judgment model comprises: Where, E is the contrast value, S is the number of the second photovoltaic panels, K is the number of the first photovoltaic panels adjacent to the second photovoltaic panels, and η a is the ratio of the first photovoltaic panel to the second photovoltaic panel, T is the light intensity, W B is the power consumption of the sun following system, W A To predict the power generation, φ α is the probability of rain.

7. A photovoltaic management method for improving photovoltaic power generation efficiency according to claim 5, characterized in that: The setting of the contrast threshold includes setting a contrast threshold model, including: In the formula, E s is the comparison threshold, W C is the power generation of the second photovoltaic panel, W D is the power generation power of the first photovoltaic panel; If E>E s , then a control signal to start the sun following system is issued. If E≤E s , a control signal is sent to shut down the sun following system.

8. A photovoltaic management system for improving photovoltaic power generation efficiency, characterized in that: include: The data prediction module is configured to obtain current weather data, obtain current light intensity according to the current weather data, obtain predicted power generation of the target photovoltaic panel through a power generation prediction model based on the light intensity; obtain the current predicted power generation of the target photovoltaic panel through the predicted power generation calculation, obtain the power consumption required by the solar following system of the target photovoltaic panel, and determine whether the current predicted power generation is greater than the power consumption; The judgment module is configured to, for a first photovoltaic panel whose power generation is greater than power consumption, send a signal that the sun-following system is working normally; for a second photovoltaic panel whose power generation is not greater than power consumption, obtain the number of first photovoltaic panels around the second photovoltaic panel, establish a judgment model based on the number, the power generation of the second photovoltaic panel and weather data, output a comparison value for the second photovoltaic panel based on the judgment model, set a comparison threshold, and judge whether to start the sun-following system of the second photovoltaic panel through the comparison threshold and the comparison value; A main control module is connected to the data prediction module and the judgment module, and is used to execute a photovoltaic management method for improving photovoltaic power generation efficiency as described in any one of claims 1-7.

9. An electronic device, characterized in that: It includes a wearable display device and a processor, wherein the processor is electrically connected to the wearable display device, and the processor is used to store a memory of executable instructions of the processor to execute a photovoltaic management method for improving photovoltaic power generation efficiency as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement a photovoltaic management method for improving photovoltaic power generation efficiency as described in any one of claims 1 to 7.

Images