Description:FIELD OF THE INVENTION

[0001] The present invention relates to a photovoltaic system for maximizing power output of solar panels that is capable of increase the overall power output of a photovoltaic system under different environmental conditions and enabling accurate prediction of the maximum power point for improved energy extraction, thereby delivering more consistent and higher energy output regardless of environmental changes.

BACKGROUND OF THE INVENTION

[0002] Solar energy is one of the most widely used renewable energy sources. Photovoltaic (PV) systems convert sunlight into electricity using solar panels. These systems are commonly used in both residential and commercial applications to reduce reliance on conventional energy sources. The efficiency of a PV system depends on how well it can extract power from the solar panels under different environmental conditions such as sunlight intensity and temperature.

[0003] Traditionally, PV systems use Maximum Power Point Tracking (MPPT) methods to improve power output. Common MPPT techniques include Perturb and Observe (P&O), Incremental Conductance (INC), and Constant Voltage (CV) methods. These techniques work by adjusting the operating point of the PV panel to find the level at which maximum power is delivered. While these methods are widely used, they rely on fixed rules or repeated measurements, which can cause slow response to changes and may not perform well under rapidly changing environmental conditions such as cloud cover or partial shading.

[0004] One major drawback of traditional MPPT methods is their limited ability to adapt to varying and complex operating conditions. These methods often assume stable environmental inputs, and as a result, they may not track the true maximum power point in dynamic environments. In addition, they may oscillate around the optimal point, leading to power loss. Further, they do not account for factors like long-term panel degradation, which also affects overall system efficiency. These limitations result in reduced energy harvest and system performance over time.

[0005] US20150188415A1 discloses about a system and a method provide a photovoltaic system which regenerates the output characteristics of the photovoltaic at different ambient condition with high precision under all environmental conditions. The photovoltaic system includes a photovoltaic array, a buck/boost converter, a DC link capacitor to connect the buck/booster converter to a load/inverter, an adaptive network-based fuzzy inference maximum power point tracking controller, a voltage control loop, a proportional integral controller to maintain the output voltage of the photovoltaic array to the reference voltage by adjusting the duty ratio of buck/boost converter.

[0006] WO2021002539A1 discloses about the present invention relates to a solar module serial-to-parallel switching system for optimizing MPPT operating voltage on the basis of machine learning and, more specifically, to a solar module serial-to-parallel switching system for optimizing MPPT operating voltage on the basis of machine learning, wherein even if input power equal to or lower than a maximum power point (MPP) is input to inverters connected to multiple solar panels or multiple solar panel groups, respective outputs from the multiple solar panels or multiple solar panel groups are collected, so that the inverters are normally operated even when the solar panels generate low power, such as during cloudy weather or at sunrise or sunset, and thus daily power production time can be increased.

[0007] Conventionally, many systems are available for maximizing power output of solar panels. However, the cited inventions show certain limitations, where these systems lack adaptability to rapidly changing environmental conditions, do not effectively handle partial shading, and have limited ability to account for panel aging or degradation. Additionally, the prediction accuracy of existing models may decrease under dynamic scenarios, affecting overall energy efficiency and long-term performance of the photovoltaic system.

[0008] In order to overcome the aforementioned drawbacks, there exists a need in the art to develop a system that uses real-time environmental and operational data with machine learning to accurately predict the maximum power point. Such a system should dynamically adjust converter settings, adapt to partial shading and panel aging, and improve overall energy harvesting efficiency under varying and unpredictable environmental conditions.

OBJECTS OF THE INVENTION

[0009] The principal object of the present invention is to overcome the disadvantages of the prior art.

[0010] An object of the present invention is to develop a system that is capable of increase the overall power output of a photovoltaic system under different environmental conditions in view of delivering more consistent and higher energy output regardless of environmental changes.

[0011] Another object of the present invention is to develop a system that ensures stable and efficient system performance during rapid changes in sunlight and temperature, thereby ensuring smooth operation.

[0012] Another object of the present invention is to develop a system that is capable of improving power tracking performance in situations where parts of the solar panel are shaded, thereby ensuring maximum possible power is still extracted from the unaffected areas.

[0013] The foregoing and other objects, features, and advantages of the present invention will become readily apparent upon further review of the following detailed description of the preferred embodiment as illustrated in the accompanying drawings.

SUMMARY OF THE INVENTION

[0014] The present invention relates to a photovoltaic system for maximizing power output of solar panels that is capable of enable accurate prediction of the maximum power point for improved energy extraction and ensuring stable and efficient system performance during rapid changes in sunlight and temperature, thereby ensuring that the system always operates close to its highest potential, thus reducing energy losses.

[0015] According to an embodiment of the present invention, a photovoltaic system for maximizing power output of solar panels comprising of a solar photovoltaic (PV) panel, associated with the system, configured to convert solar energy into electrical energy, a sensing module operatively coupled to the PV panel, configured to measure operational and environmental parameters, a machine learning (ML) module configured to process the measured parameters to predict a maximum power point, based on voltage, current, irradiance, and temperature as detected by the sensing module, a DC-DC converter operatively coupled to the PV panel and the ML module, configured to adjust its reference voltage and duty cycle based on the predicted maximum power point to maximize power output under varying conditions.

[0016] According to another embodiment of the present invention, where the system further includes the sensing module includes but not limited to a voltage sensor, current sensor, irradiance sensor, temperature sensor, configured to measure an output voltage of the PV panel, an output current of the PV panel, solar irradiance incident on the PV panel and temperature of the PV panel, respectively, the machine learning model is configured to adapt to changing environmental conditions, including variations in solar irradiance and temperature, the machine learning model is configured to account for partial shading effects on the PV panel to optimize the maximum power point prediction and the DC-DC converter is configured to adjust its operation to compensate for performance degradation due to panel aging, based on the maximum power point predicted by the machine learning model.

[0017] While the invention has been described and shown with particular reference to the preferred embodiment, it will be apparent that variations might be possible that would fall within the scope of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS

[0018] These and other features, aspects, and advantages of the present invention will become better understood with regard to the following description, appended claims, and accompanying drawings where:
Figure 1 illustrates an isometric view of a photovoltaic system for maximizing power output of solar panels.

DETAILED DESCRIPTION OF THE INVENTION

[0019] The following description includes the preferred best mode of one embodiment of the present invention. It will be clear from this description of the invention that the invention is not limited to these illustrated embodiments but that the invention also includes a variety of modifications and embodiments thereto. Therefore, the present description should be seen as illustrative and not limiting. While the invention is susceptible to various modifications and alternative constructions, it should be understood, that there is no intention to limit the invention to the specific form disclosed, but, on the contrary, the invention is to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of the invention as defined in the claims.

[0020] In any embodiment described herein, the open-ended terms "comprising," "comprises,” and the like (which are synonymous with "including," "having” and "characterized by") may be replaced by the respective partially closed phrases "consisting essentially of," consists essentially of," and the like or the respective closed phrases "consisting of," "consists of, the like.

[0021] As used herein, the singular forms “a,” “an,” and “the” designate both the singular and the plural, unless expressly stated to designate the singular only.

[0022] The present invention relates to a photovoltaic system for maximizing power output of solar panels that is capable of improving power tracking performance in situations where parts of the panel are shaded and maintaining high energy efficiency over time by adjusting for the effects of panel, thereby ensuring power output remains as high as possible throughout the system's operational life.

[0023] Referring to Figure 1, an isometric view of a photovoltaic system for maximizing power output of solar panels is illustrated comprising of a solar photovoltaic (PV) panel 101, a sensing module 102 operatively coupled to the PV panel 101 and a DC-DC converter 103 operatively coupled to the PV panel 101.

[0024] The system disclosed herein comprising of a solar photovoltaic (PV) panel 101, associated with the system, configured to convert solar energy into electrical energy. The solar photovoltaic (PV) panel 101 consists of solar panels 101 that capture sunlight and convert it into electrical energy using the photovoltaic effect. These panels 101 generate direct current (DC) electricity, that is stored in a battery and later converted into alternating current (AC) for use.

[0025] The solar panel 101 mentioned herein generates electricity through the photovoltaic effect. The solar panel 101 consists of multiple photovoltaic (PV) cells made from semiconductor materials, typically silicon. When sunlight strikes the surface of these cells, photons transfer energy to electrons in the semiconductor, freeing them from atoms. This movement of electrons creates an electric current. The PV cells are connected in series and parallel to produce the desired voltage and current. Metal contacts on the top and bottom of each cell collect and direct the flow of electrons, generating direct current (DC) electricity. However, the efficiency of energy generation from solar panels 101 is significantly influenced by varying environmental conditions such as solar irradiance, shading, temperature fluctuations, and angle of sunlight.

[0026] In an embodiment the system may include a push button installed on the panel 101, associated with the system to activate the system. The push button is pressed by the user for the activation of the system. The button is typically connected to the system’s internal circuitry, allowing the user to activate or deactivate the system through a simple press. Upon pressing of the button, the push force leads to completing of an internal circuit, that in turn sends an electrical signal to an MPPT (maximum power point tracking) controller embedded in a charge controller of the panel 101. The MPPT (maximum power point tracking) controller receives the signal from button and executes instructions to initiate the working of the system.

[0027] After the activation of the system The MPPT (maximum power point tracking) controller activates a sensing module 102 operatively coupled to the PV panel 101, configured to measure operational and environmental parameters. The sensing module 102 includes but not limited to a voltage sensor, current sensor, irradiance sensor, temperature sensor, configured to measure an output voltage of the PV panel 101, an output current of the PV panel 101, solar irradiance incident on the PV panel 101 and temperature of the PV panel 101, respectively.

[0028] The sensing module 102 operatively coupled to the PV panel 101 is configured to monitor both operational and environmental parameters critical to system performance. It measures variables such as voltage, current, temperature, irradiance, and humidity in real time. By capturing these data points, the module 102 enables accurate assessment of panel 101 efficiency, fault detection, and environmental influences affecting energy output. The sensing module 102 supports continuous performance optimization and facilitates predictive maintenance. Its integration with the PV panel 101 ensures that relevant metrics are collected at the source, allowing downstream systems to make informed decisions for energy management, diagnostics, and system control in various operating conditions.

[0029] The voltage sensor is configured to continuously measure the output voltage of the PV panel 101 by detecting the potential difference between its terminals. It converts the analog voltage signal into a digital format for processing, enabling real-time monitoring of panel 101 voltage under varying load and irradiance conditions. This helps assess panel 101 performance and detect anomalies like partial shading or degradation.

[0030] The current sensor measures the output current of the PV panel 101 by detecting the flow of electric charge through the circuit. It utilizes a Hall-effect or shunt-based sensing arrangements to provide accurate current readings, essential for evaluating power generation, load response, and identifying electrical faults.

[0031] The irradiance sensor measures the solar irradiance incident on the PV panel 101 surface, typically in watts per square meter. It uses a calibrated photodiode or pyrometer to detect the intensity of sunlight. This data is critical for determining the efficiency of energy conversion and assessing the impact of weather or shading conditions on PV output.

[0032] The temperature sensor measures the surface temperature of the PV panel 101 using a thermocouple, RTD, or thermistor. It provides real-time thermal data essential for evaluating panel 101 efficiency, as temperature variations directly affect the voltage output and overall performance. It also helps identify overheating issues or environmental stress on the panel 101.

[0033] To process the measured parameters a machine learning (ML) module configured to process the measured parameters to predict a maximum power point, based on voltage, current, irradiance, and temperature as detected by the sensing module. The machine learning model is configured to adapt to changing environmental conditions, including variations in solar irradiance and temperature. The machine learning model is configured to account for partial shading effects on the PV panel 101 to optimize the maximum power point prediction.

[0034] The machine learning (ML) module predict the maximum power point (MPP) of the PV panel 101 in real time. Using historical and real-time data, the ML module applies trained module to model the complex, nonlinear relationship between environmental and electrical conditions and the PV panel’s power output.

[0035] By continuously analyzing the input parameters, the ML module dynamically identifies the optimal operating point where the panel 101 can generate maximum power. This predictive capability enhances energy harvesting efficiency, especially under rapidly changing conditions such as cloud cover, shading, or temperature fluctuations. The ML module eliminates the need for traditional iterative methods, enabling faster, more adaptive MPP tracking.

[0036] The machine learning model is designed to dynamically adjust its performance based on changing environmental factors such as solar irradiance and temperature. By continuously monitoring these variables, the model updates its parameters in real-time to maintain accuracy and efficiency. This adaptability allows it to predict or respond effectively despite fluctuations, ensuring reliable operation in diverse conditions. For example, in solar energy applications, the model can optimize power output predictions by accounting for varying sunlight intensity and ambient temperature.

[0037] The machine learning model is specifically designed to handle partial shading effects on photovoltaic (PV) panels 101, which can significantly impact their power output. By analyzing shading patterns and their impact on the panel’s electrical characteristics, the model accurately predicts the maximum power point (MPP) under varying shading conditions. This enables the system to optimize energy extraction even when parts of the panel 101 receive less sunlight. The model continuously learns from real-time data to adjust its predictions, ensuring efficient performance despite complex shading scenarios.

[0038] To adjust the detected parameters a DC-DC converter 103 operatively coupled to the PV panel 101 and the ML module, configured to adjust its reference voltage and duty cycle based on the predicted maximum power point to maximize power output under varying conditions. The DC-DC converter 103 is configured to adjust its operation to compensate for performance degradation due to panel 101 aging, based on the maximum power point predicted by the machine learning model.

[0039] The DC-DC converter 103 is operatively connected to both the PV panel 101 and the machine learning (ML) module, forming an integrated system for optimized power management. It adjusts its reference voltage and duty cycle dynamically based on the maximum power point (MPP) predicted by the ML model. By continuously receiving updated MPP information, the converter 103 fine-tunes its operating parameters to ensure the PV panel 101 operates at peak efficiency, even under varying environmental conditions such as changes in solar irradiance, temperature, and partial shading. This real-time adjustment maximizes power output by minimizing energy losses and maintaining optimal voltage and current levels. As a result, the converter 103 enhances overall system performance, reliability, and energy harvest from the PV panel 101 across diverse operating scenarios.

[0040] The present invention works best in the following manner, where the system incudes the solar photovoltaic (PV) panel 101 connected to the system, configured to convert solar energy into electrical energy using the photovoltaic effect. The solar panel 101 consists of multiple PV cells connected in series and parallel, generating direct current (DC) electricity, which is stored in the battery and later converted to alternating current (AC). The push button installed on the panel 101 connects to the system to activate it by sending the signal to the MPPT (maximum power point tracking) controller embedded in the charge controller. The MPPT controller connects to the sensing module 102 to activate it, configured to monitor operational and environmental parameters. The sensing module 102 comprises the voltage sensor, current sensor, irradiance sensor, and temperature sensor, connected to the PV panel 101, configured to measure output voltage, output current, incident solar irradiance, and panel 101 temperature respectively. The sensing module 102 provides real-time data for performance optimization and diagnostics. The machine learning (ML) module connected to the sensing module 102 is configured to process measured parameters and predict the maximum power point (MPP), dynamically adapting to changing irradiance, temperature, and partial shading effects. The ML module uses real-time and historical data to optimize power output without relying on traditional iterative methods. The DC-DC converter 103 connected to the PV panel 101 and ML module is configured to adjust its reference voltage and duty cycle based on the predicted MPP, compensating for environmental variations and panel 101 aging to ensure efficient energy harvesting.

[0041] Although the field of the invention has been described herein with limited reference to specific embodiments, this description is not meant to be construed in a limiting sense. Various modifications of the disclosed embodiments, as well as alternate embodiments of the invention, will become apparent to persons skilled in the art upon reference to the description of the invention. , Claims:1) A photovoltaic system for maximizing power output of solar panels, comprising:

i) a solar photovoltaic (PV) panel 101, associated with the system, configured to convert solar energy into electrical energy;
ii) a sensing module 102 operatively coupled to the PV panel 101, configured to measure operational and environmental parameters;
iii) a machine learning (ML) module configured to process the measured parameters to predict a maximum power point, based on voltage, current, irradiance, and temperature as detected by the sensing module 102; and
iv) a DC-DC converter 103 operatively coupled to the PV panel 101 and the ML module, configured to adjust its reference voltage and duty cycle based on the predicted maximum power point to maximize power output under varying conditions.

2) The system as claimed in claim 1, wherein the sensing module 102 includes but not limited to a voltage sensor, current sensor, irradiance sensor, temperature sensor, configured to measure an output voltage of the PV panel 101, an output current of the PV panel 101, solar irradiance incident on the PV panel 101 and temperature of the PV panel 101, respectively.

3) The system as claimed in claim 1, wherein the machine learning model is configured to adapt to changing environmental conditions, including variations in solar irradiance and temperature.

4) The system as claimed in claim 1, wherein the machine learning model is configured to account for partial shading effects on the PV panel 101 to optimize the maximum power point prediction.

5) The system as claimed in claim 1, wherein the DC-DC converter 103 is configured to adjust its operation to compensate for performance degradation due to panel 101 aging, based on the maximum power point predicted by the machine learning model.