Photovoltaic grid-connected low-light power generation intelligent control system based on multi-parameter dynamic regulation and control

Abstract

The invention discloses a photovoltaic grid-connected low-light power generation intelligent control system based on multi-parameter dynamic regulation and control, and belongs to the technical field of photovoltaic power generation. According to the system, a multi-parameter acquisition module, a dynamic threshold calculation module, a staged logic judgment module, a boost operation module and a feedback learning module work cooperatively, and the low-light power generation efficiency and the system stability are improved through parameter acquisition, threshold adjustment, operation mode control and boost operation and feedback learning optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and more particularly to an intelligent control system for photovoltaic grid-connected micro-photovoltaic power generation based on multi-parameter dynamic regulation. Background Art

[0002] With the rapid development of renewable energy, photovoltaic power generation has gained widespread application as a clean and sustainable energy source. However, traditional methods for controlling grid-connected photovoltaic power generation face numerous challenges in low-light conditions. These methods typically rely solely on a single voltage threshold to determine grid connection. This simplistic control approach is unable to adapt to complex and changing environmental conditions, resulting in low power generation efficiency and poor adaptability in low-light conditions.

[0003] For example, when light intensity is low or component temperature is high, using a fixed voltage threshold to determine grid connection may cause the system to frequently and unnecessarily perform voltage boosts, increasing losses. Alternatively, when power generation conditions are available, improper threshold settings may cause missed power generation opportunities, resulting in energy waste. Therefore, a photovoltaic grid-connected micro-photovoltaic power generation control method and system that can comprehensively consider multiple environmental factors and dynamically adjust the control strategy is urgently needed to improve the performance of photovoltaic systems in low-light conditions.

[0004] Therefore, how to provide a photovoltaic grid-connected micro-photovoltaic power generation intelligent control system based on multi-parameter dynamic regulation is a problem that those skilled in the art urgently need to solve. Summary of the Invention

[0005] In view of this, the present invention provides a photovoltaic grid-connected micro-photovoltaic power generation intelligent control system based on multi-parameter dynamic regulation to solve the technical problems existing in the above-mentioned prior art.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] A photovoltaic grid-connected micro-photovoltaic power generation intelligent control system based on multi-parameter dynamic regulation, comprising:

[0008] Multi-parameter acquisition module, real-time acquisition of multi-dimensional parameters that affect photovoltaic grid-connected power generation;

[0009] A dynamic threshold calculation module, connected to the multi-parameter acquisition module, dynamically adjusts the grid-connected voltage threshold based on the multi-dimensional parameters;

[0010] a staged logic judgment module, connected to the dynamic threshold calculation module, performing staged logic judgment based on the grid-connected voltage threshold to control the operation mode of the photovoltaic system, the operation modes including standby mode, boost prediction mode and grid-connected mode;

[0011] A boost operation module is connected to the staged logic judgment module, performs an inverter boost-rectification operation in a boost prediction mode, and dynamically controls the rectification according to load demand;

[0012] The feedback learning module is connected to the boost operation module, evaluates the power generation efficiency after the boost, predicts the lighting trend through the machine learning model, dynamically adjusts the threshold and boost strategy, and performs fault self-detection and circuit switching.

[0013] Preferably, it also includes an energy storage collaborative control module, which is connected to the staged logic judgment module. The energy storage collaborative control module gives priority to charging the energy storage battery in standby mode, and starts the hybrid power supply mode when the charge state of the energy storage battery is greater than the preset value and the voltage is in the boost range.

[0014] Preferably, the multi-dimensional parameters include photovoltaic output voltage, light intensity and component temperature.

[0015] Preferably, the dynamic threshold calculation module corrects the basic voltage threshold according to component temperature and light intensity.

[0016] Preferably, the phased logic judgment module includes:

[0017] When the base voltage is less than the first threshold after correction, the system enters standby mode, stops connecting to the grid, and starts energy storage charging;

[0018] When the corrected first threshold value ≤ the base voltage < the corrected second threshold value, the system enters the boost prediction mode;

[0019] When the basic voltage is ≥ the corrected second threshold, the grid-connected mode is entered.

[0020] Preferably, the staged logic judgment module optimizes the timing and amplitude of voltage boosting according to the light intensity variation trend and component temperature in the voltage boosting prediction mode.

[0021] Preferably, the boost operation module adopts a high-frequency inverter and an adaptive boost topology to perform inversion boost-rectification, and the efficiency of the high-frequency inverter is greater than a preset value.

[0022] Through the above technical solutions, it can be seen that compared with the existing technology, the present invention discloses a photovoltaic grid-connected micro-photovoltaic power generation intelligent control system based on multi-parameter dynamic regulation, which can significantly improve the efficiency and reliability of the photovoltaic system under weak light conditions. The specific beneficial effects are: through multi-dimensional dynamic threshold adjustment, the voltage threshold is dynamically corrected in combination with temperature, light and historical data, so that the system can better adapt to different environmental conditions and improve environmental adaptability; the staged prediction mechanism optimizes the timing and amplitude of voltage boosting through light trend analysis and temperature compensation, reduces unnecessary energy loss, and improves power generation efficiency; uses machine learning models to predict light changes and realize forward-looking control, further improving the intelligence and reliability of the system; the hybrid power supply mode combines the energy storage system under low-light conditions to maximize energy utilization and ensure stable energy output. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] 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 description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0024] Figure 1 It is a structural schematic diagram of the present invention. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 making creative efforts are within the scope of protection of the present invention.

[0026] The purpose of the present invention is to provide a photovoltaic grid-connected micro-photovoltaic power generation intelligent control system based on multi-parameter dynamic regulation. By introducing multi-dimensional environmental parameters, dynamic threshold adjustment and feedback optimization mechanism, combined with machine learning models, a staged, multi-level complex logic control strategy is formed to solve the problems of poor adaptability and low power generation efficiency of photovoltaic systems under weak light conditions in the existing technology, thereby improving energy utilization and system reliability.

[0027] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0028] Example 1:

[0029] See also Figure 1Embodiment 1 of the present invention discloses an intelligent control system for photovoltaic grid-connected micro-photovoltaic power generation based on multi-parameter dynamic regulation, comprising:

[0030] A multi-parameter acquisition module is used to collect photovoltaic output voltage, light intensity, component temperature, and historical power generation data in real time; wherein the photovoltaic output voltage is obtained by collecting the DC side voltage using a voltage sensor, the light intensity is monitored in real time using a photosensor, and the component temperature is obtained by a temperature sensor. The historical power generation data uses historical power generation efficiency, boost times, and loss data stored in a database;

[0031] a dynamic threshold calculation module, connected to the multi-parameter acquisition module, dynamically adjusting the voltage threshold based on the collected environmental parameters and historical data, the voltage threshold including a basic threshold and a threshold corrected according to component temperature and light intensity;

[0032] A phased logic judgment module, connected to the dynamic threshold calculation module, performs phased logic judgment based on the corrected voltage threshold, including a basic voltage judgment phase and a boost prediction phase; in the basic voltage judgment phase, controls the system to enter standby mode, boost prediction phase, or direct grid connection based on the relationship between the photovoltaic output voltage and the corrected threshold; in the boost prediction phase, optimizes the boost timing and amplitude based on changes in light intensity and component temperature;

[0033] A boost operation module, connected to the staged logic judgment module, uses a high-frequency inverter and an adaptive boost topology to perform inverter boost-rectification, and switches between full-bridge and half-bridge rectification modes for dynamic rectification control according to load requirements;

[0034] A feedback learning module, connected to the boost operation module, is used to evaluate the power generation efficiency after each boost, predict the sunlight trend in the next hour through a machine learning model, and dynamically adjust the threshold and boost strategy. If the boost efficiency fails to meet the standard for three consecutive times, a system self-check is triggered and a backup circuit is switched;

[0035] The energy storage collaborative control module is connected to the staged logic judgment module. In standby mode, it controls the priority charging of the energy storage battery. When the energy storage SOC is greater than 80% and the voltage is in the boost range, the hybrid power supply mode is started.

[0036] In a specific embodiment, multi-parameter real-time acquisition includes:

[0037] Photovoltaic output voltage: The DC side voltage is collected through a voltage sensor.

[0038] Light intensity: Use a light sensor to monitor the ambient light intensity in real time (unit: W / m2).

[0039] Component temperature: The surface temperature of the photovoltaic panel is obtained through the temperature sensor.

[0040] In a specific embodiment, dynamic threshold calculation includes:

[0041] Dynamically adjust voltage thresholds based on environmental parameters and historical data:

[0042] Basic threshold (initial value: 150V, 250V).

[0043] Temperature correction: If the component temperature is >45°C, the threshold is lowered by 5% (to compensate for reduced efficiency).

[0044] Light correction: If the light intensity is less than 200W / m 2 , the threshold is lowered by 10% (prioritizing the preservation of low-light power generation).

[0045] Specifically, in the dynamic threshold calculation module, the initial values ​​of the basic threshold are 150V and 250V; if the component temperature is >45°C, the basic threshold is lowered by 5% for temperature correction; if the light intensity is <200W / m2, the basic threshold is lowered by 10% for light correction.

[0046] In a specific embodiment, the staged logical judgment includes:

[0047] Phase 1: Determination of basic voltage V:

[0048] V<the first threshold after correction: enter standby mode, stop grid connection, and start energy storage charging.

[0049] The corrected first threshold ≤ V < the corrected second threshold: the voltage boost prediction stage is entered.

[0050] V ≥ the second threshold after correction: direct grid connection.

[0051] Phase 2: Voltage boost prediction (triggered only in the middle range of Phase 1):

[0052] Light intensity analysis:

[0053] If the light intensity continues to decrease (slope <-5W / m2 / s), start the voltage boost in advance.

[0054] If the light intensity fluctuates greatly (standard deviation > 50W / m 2 ), delay the boost and wait for stabilization.

[0055] Temperature efficiency compensation:

[0056] If the temperature is >45°C, the boost voltage is reduced by 20% to reduce losses.

[0057] If the temperature is < 25°C, the boost voltage is increased by 10% to maximize the output.

[0058] Specifically, in the boost prediction stage of the staged logic judgment module, if the light intensity continues to decline and the decline slope is <-5W / m2 / s, the boost is started in advance; if the light fluctuates violently and the standard deviation is >50W / m2, the boost is delayed and waits for stabilization; if the temperature is >45℃, the boost amplitude is reduced by 20%; if the temperature is <25℃, the boost amplitude is increased by 10%.

[0059] In one specific embodiment, the boost operation optimizes:

[0060] Inverter-Boost-Rectifier: Uses a high-frequency inverter (efficiency > 98%) and an adaptive boost topology.

[0061] Dynamic rectification control: Switches between full-bridge and half-bridge rectification modes according to load requirements to reduce losses.

[0062] Feedback learning mechanism:

[0063] Efficiency evaluation: record the power generation efficiency after each boost (boost loss ≤ 5% is qualified).

[0064] Model iteration: Use machine learning models to predict light trends for the next hour and dynamically adjust thresholds and boost strategies.

[0065] Fault self-healing: If the boost efficiency fails to meet the standard for three consecutive times, the system will trigger a self-check and switch to the backup circuit.

[0066] Energy storage collaborative control:

[0067] In standby mode, priority is given to charging the energy storage battery;

[0068] If the energy storage SOC is greater than 80% and the voltage is in the boost range, the hybrid power supply mode (boost + energy storage supplement) is started.

[0069] Specifically, this invention dynamically adjusts voltage thresholds based on temperature, light, and historical data to improve environmental adaptability. It optimizes the timing and magnitude of voltage boosts through light trend analysis and temperature compensation. It also uses machine learning models to predict light changes, enabling proactive control. In low-light conditions, it integrates energy storage systems to maximize energy utilization, significantly improving the efficiency and reliability of photovoltaic systems in these conditions.

[0070] Example 2:

[0071] Embodiment 2 of the present invention discloses an intelligent control system for photovoltaic grid-connected micro-photovoltaic power generation based on multi-parameter dynamic regulation, comprising:

[0072] Multi-parameter acquisition module: This module collects real-time data on PV output voltage, light intensity, module temperature, and historical power generation data. PV output voltage is acquired using a voltage sensor to measure the DC voltage, light intensity is monitored in real time using a photosensor, and module temperature is acquired using a temperature sensor. Historical power generation data utilizes a database containing historical data on power generation efficiency, boost times, and losses. This module provides comprehensive data support for subsequent dynamic threshold calculations and logical judgments.

[0073] Dynamic Threshold Calculation Module: Dynamically adjusts voltage thresholds based on collected environmental parameters and historical data. Voltage thresholds include base thresholds (initial values: 150V and 250V) and thresholds modified based on module temperature and light intensity. Specifically, if module temperature exceeds 45°C, the base threshold is adjusted downward by 5% to compensate for the reduced power generation efficiency caused by the temperature increase. If light intensity is less than 200W / m², the base threshold is adjusted downward by 10% to prioritize power generation in low-light conditions. Phased Logic Judgment Module: Based on the modified voltage thresholds, the module performs phased logic judgments, divided into a base voltage judgment phase and a boost prediction phase. During the base voltage judgment phase, the relationship between the PV output voltage and the modified thresholds determines whether the module enters standby mode, a boost prediction phase, or direct grid connection. When the PV output voltage V < the modified first threshold, the module enters standby mode, disconnects from the grid, and initiates energy storage charging. When the modified first threshold ≤ V < the modified second threshold, the module enters the boost prediction phase. When V ≥ the modified second threshold, direct grid connection is initiated. During the voltage boost prediction phase, the timing and magnitude of the voltage boost are optimized based on changes in light intensity and component temperature. If light intensity continues to decline, with a rate of decline less than -5W / m² / s, the voltage boost is initiated early. If light intensity fluctuates dramatically, with a standard deviation greater than 50W / m², the voltage boost is delayed until stabilization occurs. If the temperature is greater than 45°C, the voltage boost is reduced by 20% to minimize losses. If the temperature is less than 25°C, the voltage boost is increased by 10% to maximize output.

[0074] Boost operation module: uses a high-frequency inverter (efficiency > 98%) and an adaptive boost topology for inverter boost-rectification, and switches between full-bridge / half-bridge rectification modes according to load requirements for dynamic rectification control, reducing energy loss during the boost process and improving power conversion efficiency.

[0075] Feedback Learning Module: This module evaluates power generation efficiency after each boost (boost loss ≤ 5% is considered acceptable), uses an LSTM model to predict the next hour's sunlight trends, and dynamically adjusts thresholds and boost strategies. If boost efficiency falls short of the target for three consecutive times, a system self-check is triggered and the backup circuit is switched, enabling self-healing and optimized control.

[0076] Energy storage collaborative control module: In standby mode, the control prioritizes charging the energy storage battery; when the energy storage SOC is greater than 80% and the voltage is in the boost range, the hybrid power supply mode is activated, combining the energy storage system and boost power generation to maximize energy utilization.

[0077] In one specific embodiment, the multi-parameter acquisition module continuously collects PV output voltage, light intensity, module temperature, and historical power generation data. For example, at a certain moment, the voltage sensor detects a DC voltage of 200V, the light sensor monitors a light intensity of 180W / m², and the temperature sensor detects a module temperature of 50°C. Simultaneously, the module retrieves historical power generation efficiency, boost times, and power loss data from a database.

[0078] The dynamic threshold calculation module calculates the threshold based on the collected data. Because the light intensity of 180W / m² is less than 200W / m², the basic threshold is adjusted down by 10%. Because the component temperature of 50°C is greater than 45°C, the threshold is adjusted down by another 5%, resulting in the corrected voltage threshold.

[0079] The phased logic judgment module determines based on the revised thresholds that the PV output voltage of 200V is between the revised first and second thresholds, entering the boost pre-judgment phase. During this phase, the boost operation is initiated early due to the continued decline in light intensity, with a slope of decline less than -5W / m² / s. Furthermore, considering that the module temperature is 50°C > 45°C, the boost amplitude is reduced by 20%.

[0080] The boost operation module uses a high-frequency inverter with an efficiency of >98% and an adaptive boost topology for inverter boost-rectification, and switches between full-bridge / half-bridge rectification modes for dynamic rectification control according to load requirements.

[0081] The feedback learning module records the power generation efficiency after the boost. If the efficiency meets the standard, the current strategy continues. If the boost efficiency fails to meet the standard for three consecutive times, a system self-check is triggered and the backup circuit is switched. Simultaneously, an LSTM model predicts the sunlight trend for the next hour and dynamically adjusts subsequent thresholds and boost strategies.

[0082] In standby mode, the energy storage collaborative control module gives priority to charging the energy storage battery; when the energy storage SOC>80% and the voltage is in the boost range, the hybrid power supply mode is started to achieve efficient energy utilization.

[0083] At the same time, this embodiment 2 also provides a photovoltaic grid-connected micro-photovoltaic power generation intelligent control method based on multi-parameter dynamic regulation, which is applied to the above-mentioned intelligent control system. The specific steps are as follows:

[0084] Collect photovoltaic output voltage, light intensity, component temperature and historical power generation data in real time.

[0085] Dynamically adjust voltage thresholds based on collected environmental parameters and historical data.

[0086] Based on the corrected voltage threshold, phased logical judgment is performed, including the basic voltage judgment phase and the boost prediction phase. In the basic voltage judgment phase, the system controls the system to enter standby mode, the boost prediction phase, or direct grid connection based on the relationship between the photovoltaic output voltage and the corrected threshold. In the boost prediction phase, the timing and amplitude of the boost are optimized based on changes in light intensity and component temperature.

[0087] A high-frequency inverter and adaptive boost topology are used for inverter boost-rectification, and full-bridge / half-bridge rectification mode is switched according to load requirements for dynamic rectification control.

[0088] Evaluate the power generation efficiency after each boost, predict the sunlight trend in the next hour through the LSTM model, and dynamically adjust the threshold and boost strategy. If the boost efficiency fails to meet the standard for three consecutive times, the system will trigger self-check and switch to the backup circuit.

[0089] In standby mode, the control gives priority to charging the energy storage battery. When the energy storage SOC is greater than 80% and the voltage is in the boost range, the hybrid power supply mode is started.

[0090] Through the above implementation process, the present invention can effectively improve the adaptability and power generation efficiency of the photovoltaic system under weak light conditions, verifying the feasibility and effectiveness of the present invention.

[0091] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0092] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A photovoltaic grid-connected micro-photovoltaic power generation intelligent control system based on multi-parameter dynamic regulation, characterized in that: include: Multi-parameter acquisition module, real-time acquisition of multi-dimensional parameters that affect photovoltaic grid-connected power generation; A dynamic threshold calculation module, connected to the multi-parameter acquisition module, dynamically adjusts the grid-connected voltage threshold based on the multi-dimensional parameters; a staged logic judgment module, connected to the dynamic threshold calculation module, performing staged logic judgment based on the grid-connected voltage threshold to control the operation mode of the photovoltaic system, the operation modes including standby mode, boost prediction mode and grid-connected mode; A boost operation module is connected to the staged logic judgment module, performs an inverter boost-rectification operation in a boost prediction mode, and dynamically controls the rectification according to load demand; The feedback learning module is connected to the boost operation module, evaluates the power generation efficiency after the boost, predicts the lighting trend through the machine learning model, dynamically adjusts the threshold and boost strategy, and performs fault self-detection and circuit switching.

2. The photovoltaic grid-connected micro-photovoltaic power generation intelligent control system based on multi-parameter dynamic regulation according to claim 1, characterized in that: It also includes an energy storage collaborative control module, which is connected to the staged logic judgment module. The energy storage collaborative control module gives priority to charging the energy storage battery in standby mode. When the charge state of the energy storage battery is greater than a preset value and the voltage is in the boost range, the hybrid power supply mode is started.

3. The photovoltaic grid-connected micro-photovoltaic power generation intelligent control system based on multi-parameter dynamic regulation according to claim 1, characterized in that: The multi-dimensional parameters include photovoltaic output voltage, light intensity and component temperature.

4. The photovoltaic grid-connected micro-photovoltaic power generation intelligent control system based on multi-parameter dynamic regulation according to claim 1, characterized in that: The dynamic threshold calculation module modifies the basic voltage threshold according to the component temperature and light intensity.

5. The photovoltaic grid-connected micro-photovoltaic power generation intelligent control system based on multi-parameter dynamic regulation according to claim 1, characterized in that: The phased logic judgment module includes: When the base voltage is less than the first threshold after correction, the system enters standby mode, stops connecting to the grid, and starts energy storage charging; When the corrected first threshold value ≤ the base voltage < the corrected second threshold value, the system enters the boost prediction mode; When the basic voltage is ≥ the corrected second threshold, the grid-connected mode is entered.

6. The photovoltaic grid-connected micro-photovoltaic power generation intelligent control system based on multi-parameter dynamic regulation according to claim 5, characterized in that: In the boost prediction mode, the staged logic judgment module optimizes the boost timing and amplitude according to the light intensity change trend and component temperature.

7. The photovoltaic grid-connected micro-photovoltaic power generation intelligent control system based on multi-parameter dynamic regulation according to claim 1, characterized in that: The boost operation module adopts a high-frequency inverter and an adaptive boost topology to perform inversion, boost and rectification.

Images