Photovoltaic inverter operation efficiency optimization method based on deep learning

Abstract

The invention discloses a photovoltaic inverter operation efficiency optimization method based on deep learning, and the method comprises the steps: quantifying main environment factors affecting the operation efficiency of a photovoltaic inverter, constructing an environment coupling model, calculating a comprehensive environment factor coupling each environment factor, setting an adjustable disturbance resistor, and constructing a loss model of the photovoltaic inverter. According to a loss model of the photovoltaic inverter, an objective function for calculating the operating efficiency of the photovoltaic inverter is determined, a calculation function relation between a comprehensive environmental factor and an adjustable disturbance resistor under efficiency maximization is calculated, and main environmental factors influencing the operating efficiency of the photovoltaic inverter are monitored in real time. Comprising environment temperature difference, environment wind speed and environment humidity, comprehensive environment factors are calculated in real time, feedback adjustment is carried out on the adjustable disturbance resistor according to a calculation function relation, and quantitative coupling calculation is carried out on main environment factors influencing the operation efficiency of the photovoltaic inverter. And by matching with an adjustable disturbance resistor, the control correction of various environmental factor deviations can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic inverters, and in particular to a method for optimizing the operating efficiency of photovoltaic inverters based on deep learning. Background Art

[0002] Photovoltaic inverters are the core equipment of photovoltaic power generation systems. Their main function is to convert the direct current generated by solar panels into alternating current that can be connected to the power grid or used by loads, and to achieve optimal control of system operation. As the core equipment of photovoltaic power generation systems, the optimization of the operating efficiency of photovoltaic inverters has a profound impact on the overall performance, economy and sustainability of the system.

[0003] The patent with the authorization announcement number CN118889541A discloses a method and system for optimizing the operating efficiency of a photovoltaic inverter. In the disclosed technical solution of the patent, the method includes: obtaining the output current and output voltage of the photovoltaic cell, the operating temperature and operating efficiency of the photovoltaic inverter, performing surface fitting operations respectively, obtaining the first reference domain and the second reference domain, and obtaining corresponding reference data based on the first reference domain and the second reference domain, and performing neural network training based on the reference data to obtain a neural network model, and using the surface fitting method to optimize the neural network model to obtain the optimal neural network model, and finally optimizing the operating efficiency of the photovoltaic inverter based on the optimal neural network model. The present invention uses surface fitting and neural networks to optimize the operating efficiency of the photovoltaic inverter from multiple dimensions. Through continuous optimization, the operating efficiency of the photovoltaic inverter can be kept in a relatively good or even optimal state for a long time, thereby improving the power generation and economic benefits of the entire system. However, in the technical solution of the patent, the impact of environmental and weather conditions on the operation of the photovoltaic inverter is not fully considered.

[0004] Regardless of whether the photovoltaic inverter is subject to its internal functions or the external installation environment, the impact of weather factors on it cannot be ignored. Most existing algorithm systems for managing the operating efficiency of photovoltaic inverters lack condition corrections based on weather and environmental factors. Different algorithms may have different effects under different weather conditions. Therefore, the present invention aims to provide a photovoltaic inverter operating efficiency optimization method based on deep learning, which can realize the control and correction of deviations of various environmental factors.

[0005] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgment or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method for optimizing the operating efficiency of a photovoltaic inverter based on deep learning. By performing quantitative coupling calculations on the main environmental factors affecting the operating efficiency of the photovoltaic inverter and cooperating with an adjustable disturbance resistor, it is possible to achieve control and correction of deviations of various environmental factors.

[0007] In order to solve the above technical problems, the present invention provides a photovoltaic inverter operating efficiency optimization method based on deep learning, comprising the following steps:

[0008] S1. Quantify the main environmental factors that affect the operating efficiency of photovoltaic inverters, including ambient temperature difference, ambient wind speed and ambient humidity, build an environmental coupling model, and calculate the comprehensive environmental factors that couple various environmental factors;

[0009] S2. Setting an adjustable disturbance resistance, associating the comprehensive environmental factor with the disturbance resistance, and constructing a loss model of the photovoltaic inverter;

[0010] S3. Determine the objective function of the photovoltaic inverter operation efficiency calculation according to the photovoltaic inverter loss model, and calculate the calculation function relationship between the comprehensive environmental factor and the adjustable disturbance resistance under the efficiency maximization;

[0011] S4. Real-time monitoring of the main environmental factors that affect the operating efficiency of the photovoltaic inverter, including ambient temperature difference, ambient wind speed and ambient humidity, real-time calculation of comprehensive environmental factors and feedback adjustment of the adjustable disturbance resistor based on the calculated function relationship.

[0012] Furthermore, in the technical solution of the present invention, in step S1, constructing the environment coupling model specifically includes:

[0013] S1-1. Obtaining ambient temperature , Ambient wind speed and ambient humidity , get the operating temperature of the photovoltaic inverter , get the ambient temperature difference , normalize the environmental parameters:

[0014] , , ;

[0015] Where: Expressed as the ambient temperature difference parameter, Expressed as the ambient wind speed parameter, Expressed as the ambient humidity parameter, Expressed as the maximum allowable ambient temperature difference, Expressed as the maximum allowable ambient wind speed, Expressed as the maximum allowable value of ambient humidity;

[0016] S1-2, according to the ambient temperature difference , Ambient wind speed , Ambient humidity The weights of the environmental factors affecting the operating efficiency of photovoltaic inverters are not equal. At the same time, there are nonlinear interactions between the environmental factors. The nonlinear coupling of the environmental factors is calculated by the weighted geometric mean:

[0017] ;

[0018] Where: Expressed as a comprehensive environmental factor, , , Respectively expressed as the ambient temperature difference , Ambient wind speed , Ambient humidity The weight coefficient of .

[0019] Furthermore, in the technical solution of the present invention, in step S2, constructing a loss model of the photovoltaic inverter specifically includes:

[0020] S2-1. Get the value of the adjustable disturbance resistor , calculate the power loss value of the disturbance resistor:

[0021] ;

[0022] Where: Expressed as the working current of the photovoltaic inverter, Expressed as the power loss of the disturbing resistor;

[0023] S2-2. Related comprehensive environmental factors get:

[0024] ;

[0025] Where: Expressed as the power loss of the PV inverter.

[0026] Further, in the technical solution of the present invention, in step S3, determining the objective function of the photovoltaic inverter operating efficiency calculation according to the loss model specifically includes:

[0027] S3-1. Calculate the output power of the photovoltaic inverter:

[0028] ;

[0029] Where: Expressed as open circuit voltage, Expressed as internal resistance, Expressed as the output power of the photovoltaic inverter;

[0030] The objective function of photovoltaic inverter operation efficiency calculation is obtained:

[0031] ;Right now

[0032] ;

[0033] Where: Expressed as the operating efficiency of the PV inverter;

[0034] S3-2, use the equivalent resistance method to calculate the optimal working current, and the working current The optimal working point is obtained by taking derivative:

[0035] ;

[0036] The comprehensive environmental factor is calculated based on the optimal working point The calculated functional relationship with the adjustable disturbance resistance is:

[0037] .

[0038] Further, in the technical solution of the present invention, in step S4, the adjustable disturbance resistor performs feedback adjustment specifically including:

[0039] Real-time monitoring of the main environmental factors that affect the operating efficiency of photovoltaic inverters, including ambient temperature differences , Ambient wind speed and ambient humidity ;

[0040] Calculate the comprehensive environmental factor ;

[0041] According to comprehensive environmental factors The calculated functional relationship between the adjustable disturbance resistance and the adjustable disturbance resistance The resistance value is large enough to make the photovoltaic inverter operate efficiently. maximum.

[0042] Furthermore, in the technical solution of the present invention, in step S1-2, , , Respectively expressed as the ambient temperature difference , Ambient wind speed , Ambient humidity The weight coefficient is calculated by the following steps:

[0043] take The measured environmental parameters and power loss of the group are based on The measured environmental parameters of the group are calculated as follows:

[0044]

[0045] Where: It is expressed as the ambient temperature difference parameter of the nth group of measured environmental parameters, The ambient wind speed parameter represented by the nth group of measured ambient parameters, The ambient humidity parameter represented by the nth group of measured ambient parameters;

[0046] according to The measured power loss of the group is Measured comprehensive environmental factors :

[0047] ;

[0048] Where: Expressed as The measured comprehensive environmental factors of the group;

[0049] and + + =1;

[0050] Calculated , , The value of .

[0051] Furthermore, in the technical solution of the present invention, by using the weighted geometric mean to calculate the comprehensive environmental factors The values ​​are compared with the comprehensive environmental factor values ​​calculated by measuring the losses of photovoltaic inverters to , Ambient wind speed , Ambient humidity The weight coefficient , , For further optimization.

[0052] Effective gain: In summary, the present invention provides a method for optimizing the operating efficiency of a photovoltaic inverter based on deep learning. In the technical solution of the present invention, by quantifying the main environmental factors affecting the operating efficiency of the photovoltaic inverter, an environmental coupling model is constructed, the comprehensive environmental factors coupled to the environmental factors are calculated, and an adjustable disturbance resistor is set to construct a loss model of the photovoltaic inverter. The objective function of the photovoltaic inverter operating efficiency calculation is determined according to the loss model of the photovoltaic inverter, and the calculation function relationship between the comprehensive environmental factor and the adjustable disturbance resistor under efficiency maximization is calculated. The main environmental factors affecting the operating efficiency of the photovoltaic inverter, including the ambient temperature difference, the ambient wind speed and the ambient humidity, are monitored in real time, the comprehensive environmental factor is calculated in real time, and the adjustable disturbance resistor is feedback-adjusted according to the calculation function relationship. The present invention adopts a normalization method to quantify the main environmental factors affecting the operating efficiency of the photovoltaic inverter, and adopts a weighted geometric mean method to perform nonlinear coupling calculation on the environmental factor parameters. By associating the coupled comprehensive environmental factor with the adjustable disturbance resistor, the adjustable disturbance resistor can be used to control and correct the deviations of various environmental factors.

[0053] Other features and advantages of the present invention will be set forth in the description which follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 This is a flow chart of a photovoltaic inverter operating efficiency optimization method based on deep learning in the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below 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 creative work are within the scope of protection of the present invention.

[0057] The core of the present invention is to provide a photovoltaic inverter operating efficiency optimization method based on deep learning. By quantitatively coupling and calculating the main environmental factors affecting the operating efficiency of the photovoltaic inverter, and cooperating with adjustable disturbance resistors, it is possible to control and correct the deviations of various environmental factors.

[0058] In order to solve the above technical problems, the embodiment of the present invention proposes a photovoltaic inverter operation efficiency optimization method based on deep learning. Figure 1 Flow chart of a photovoltaic inverter operating efficiency optimization method based on deep learning of the present invention, such as Figure 1 As shown, a photovoltaic inverter operating efficiency optimization method based on deep learning in this embodiment includes the following steps:

[0059] S1. Quantify the main environmental factors that affect the operating efficiency of photovoltaic inverters, including ambient temperature difference, ambient wind speed and ambient humidity, build an environmental coupling model, and calculate the comprehensive environmental factors that couple various environmental factors;

[0060] S2. Setting an adjustable disturbance resistance, associating the comprehensive environmental factor with the disturbance resistance, and constructing a loss model of the photovoltaic inverter;

[0061] S3. Determine the objective function of the photovoltaic inverter operation efficiency calculation according to the photovoltaic inverter loss model, and calculate the calculation function relationship between the comprehensive environmental factor and the adjustable disturbance resistance under the efficiency maximization;

[0062] S4. Real-time monitoring of the main environmental factors that affect the operating efficiency of the photovoltaic inverter, including ambient temperature difference, ambient wind speed and ambient humidity, real-time calculation of comprehensive environmental factors and feedback adjustment of the adjustable disturbance resistor based on the calculated function relationship.

[0063] Specifically, in this embodiment, in step S1, the main environmental factors affecting the operating efficiency of the photovoltaic inverter are quantified, an environmental coupling model is constructed, and the comprehensive environmental factors coupled with the environmental factors are calculated, which specifically include:

[0064] S1-1. Obtaining ambient temperature , Ambient wind speed and ambient humidity , get the operating temperature of the photovoltaic inverter , get the ambient temperature difference , normalize the environmental parameters to eliminate dimension differences and establish a dimensionless environmental parameter set:

[0065] , , ;

[0066] Where: Expressed as the ambient temperature difference parameter, Expressed as the ambient wind speed parameter, Expressed as the ambient humidity parameter, Expressed as the maximum allowable ambient temperature difference, Expressed as the maximum allowable ambient wind speed, It is expressed as the maximum allowable value of ambient humidity, where the maximum allowable value of each environmental parameter is calculated based on the local meteorological data limit value and the equipment allowable limit value of the photovoltaic inverter;

[0067] S1-2, according to the ambient temperature difference , Ambient wind speed , Ambient humidity The influence of different environmental factors on the operating efficiency of photovoltaic inverters is not equal. At the same time, there are nonlinear interactions among various environmental factors. Affects the junction temperature and heat dissipation of the photovoltaic inverter, resulting in an increase in on-resistance, a nonlinear increase in conduction loss, and an increase in ambient wind speed. Affects the heat dissipation efficiency of the photovoltaic inverter, changes the steady-state operating temperature of the photovoltaic inverter, causes indirect modulation loss, and environmental humidity This will cause the contact resistance of the photovoltaic inverter to slowly increase. The nonlinear coupling of various environmental factors is calculated by the weighted geometric mean:

[0068] ;

[0069] Where: Expressed as a comprehensive environmental factor, , , Respectively expressed as the ambient temperature difference , Ambient wind speed , Ambient humidity The weight coefficient of .

[0070] It should be noted that, in this embodiment, , , Respectively expressed as the ambient temperature difference , Ambient wind speed , Ambient humidity The weight coefficient is based on the ambient temperature difference , Ambient wind speed , Ambient humidity The weights of the influence on the operating efficiency of the photovoltaic inverter are not equal, and the values ​​are different. The specific values ​​are calculated by the following steps:

[0071] According to the historical operation data of photovoltaic inverters, A group of measured environmental parameters, each group of measured environmental parameters includes the ambient temperature difference , Ambient wind speed , Ambient humidity , according to the calculation formula:

[0072] , , ;

[0073] right The measured environmental parameters of the group are calculated as follows:

[0074]

[0075] Where: It is expressed as the ambient temperature difference parameter of the nth group of measured environmental parameters, The ambient wind speed parameter represented by the nth group of measured ambient parameters, The ambient humidity parameter represented by the nth group of measured ambient parameters;

[0076] take The actual power loss of the group is calculated according to the formula:

[0077] ;

[0078] Where: Expressed as the working current of the photovoltaic inverter, Expressed as the adjustable disturbance resistor value, Expressed as the power loss of the photovoltaic inverter;

[0079] right The measured power loss of the group is calculated Measured comprehensive environmental factors :

[0080] Among them, ;

[0081] Where: Expressed as The measured comprehensive environmental factors of the group;

[0082] and + + =1, that is, the comprehensive weight of environmental factors is 1, that is, 100%. The weight of each environmental factor is different. By solving the polynomial, it can be calculated , , The value of Calculate the comprehensive environmental factor .

[0083] Specifically, in this embodiment, the comprehensive environmental factors calculated by weighted geometric mean are The value is compared with the comprehensive environmental factor value calculated by measuring the loss of photovoltaic inverters to measure the ambient temperature difference in real time. , Ambient wind speed , Ambient humidity The weight coefficient , , Further optimization is done by recording the real-time measured data of the photovoltaic inverter during operation and correcting the calculated data, mainly including the weight coefficient , , , the correction calculation method is the same as above , , The calculation method of .

[0084] Specifically, in this embodiment, in step S2, an adjustable disturbance resistor is set, and the comprehensive environmental factor is associated with the disturbance resistor, and the loss model of the photovoltaic inverter is constructed, which specifically includes:

[0085] S2-1. Get the value of the adjustable disturbance resistor , calculate the power loss value of the disturbance resistor:

[0086] ;

[0087] Where: Expressed as the working current of the photovoltaic inverter, Expressed as the power loss of the disturbing resistor;

[0088] S2-2. Related comprehensive environmental factors , transforming loss control into The linear regulation is achieved by controlling Compensating for environmental impacts, we get:

[0089] ;

[0090] Where: The embodiment adopts the normalization method to quantify the main environmental factors affecting the operating efficiency of the photovoltaic inverter, and adopts the weighted geometric mean method to perform nonlinear coupling calculation on the environmental factor parameters. Associated with the adjustable disturbance resistor, the adjustable disturbance resistor can realize the control and correction of the deviation of various environmental factors. It should be noted that middle, It can be regarded as the resistance of the equivalent disturbance resistor under the influence of environmental factors.

[0091] Specifically, in this embodiment, in step S3, the objective function of calculating the operating efficiency of the photovoltaic inverter is determined according to the loss model of the photovoltaic inverter, and the calculation function relationship between the comprehensive environmental factor and the adjustable disturbance resistance under the efficiency maximization is calculated specifically including:

[0092] S3-1. Calculate the output power of the photovoltaic inverter:

[0093] ;

[0094] Where: Expressed as open circuit voltage, Expressed as internal resistance, Expressed as the output power of the photovoltaic inverter;

[0095] The objective function of photovoltaic inverter operation efficiency calculation is obtained:

[0096] ;Right now

[0097] ;

[0098] Where: Expressed as the operating efficiency of the PV inverter;

[0099] S3-2, use the equivalent resistance method to calculate the optimal working current:

[0100] ,in is the equivalent loss resistance after environmental modulation;

[0101] Working current And set the derivative to zero:

[0102]

[0103] The optimal working point is obtained by taking the derivative:

[0104] ;

[0105] Substitute the optimal working point into the objective function of the photovoltaic inverter operating efficiency calculation:

[0106] , ;

[0107] Calculate the comprehensive environmental factor The calculated functional relationship with the adjustable disturbance resistance is:

[0108] .

[0109] Specifically, in this embodiment, in step S4, the adjustable disturbance resistor performs feedback adjustment specifically including:

[0110] Real-time monitoring of the main environmental factors that affect the operating efficiency of photovoltaic inverters, including ambient temperature differences , Ambient wind speed and ambient humidity ;

[0111] Calculate the comprehensive environmental factor ;

[0112] According to comprehensive environmental factors The calculated functional relationship between the adjustable disturbance resistance and the adjustable disturbance resistance The resistance value is large enough to make the photovoltaic inverter operate efficiently. maximum.

[0113] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A photovoltaic inverter operating efficiency optimization method based on deep learning, characterized in that: The steps include: S1. Quantify the main environmental factors that affect the operating efficiency of photovoltaic inverters, including ambient temperature difference, ambient wind speed and ambient humidity, build an environmental coupling model, and calculate the comprehensive environmental factors that couple various environmental factors; S2. Setting an adjustable disturbance resistance, associating the comprehensive environmental factor with the disturbance resistance, and constructing a loss model of the photovoltaic inverter; S3. Determine the objective function of the photovoltaic inverter operation efficiency calculation according to the photovoltaic inverter loss model, and calculate the calculation function relationship between the comprehensive environmental factor and the adjustable disturbance resistance under the efficiency maximization; S4. Real-time monitoring of the main environmental factors that affect the operating efficiency of the photovoltaic inverter, including ambient temperature difference, ambient wind speed and ambient humidity, real-time calculation of comprehensive environmental factors and feedback adjustment of the adjustable disturbance resistor based on the calculated function relationship.

2. The photovoltaic inverter operation efficiency optimization method based on deep learning according to claim 1 is characterized in that: In step S1, constructing the environment coupling model specifically includes: S1-1. Obtaining ambient temperature , Ambient wind speed and ambient humidity , get the operating temperature of the photovoltaic inverter , get the ambient temperature difference , normalize the environmental parameters: ， , ； Where: Expressed as the ambient temperature difference parameter, Expressed as the ambient wind speed parameter, Expressed as the ambient humidity parameter, Expressed as the maximum allowable ambient temperature difference, Expressed as the maximum allowable ambient wind speed, Expressed as the maximum allowable value of ambient humidity; S1-2, according to the ambient temperature difference , Ambient wind speed , Ambient humidity The weights of the environmental factors affecting the operating efficiency of photovoltaic inverters are not equal. At the same time, there are nonlinear interactions between the environmental factors. The nonlinear coupling of the environmental factors is calculated by the weighted geometric mean: ； Where: Expressed as a comprehensive environmental factor, , , Respectively expressed as the ambient temperature difference , Ambient wind speed , Ambient humidity The weight coefficient of .

3. The photovoltaic inverter operation efficiency optimization method based on deep learning according to claim 2 is characterized in that: In step S2, constructing a loss model of a photovoltaic inverter specifically includes: S2-1. Get the value of the adjustable disturbance resistor , calculate the power loss value of the disturbance resistor: ； Where: Expressed as the working current of the photovoltaic inverter, Expressed as the power loss of the disturbing resistor; S2-2. Related comprehensive environmental factors get: ； Where: Expressed as the power loss of the PV inverter.

4. The photovoltaic inverter operation efficiency optimization method based on deep learning according to claim 3 is characterized in that: In step S3, determining the objective function of the photovoltaic inverter operating efficiency calculation according to the loss model specifically includes: S3-1. Calculate the output power of the photovoltaic inverter: ； Where: Expressed as open circuit voltage, Expressed as internal resistance, Expressed as the output power of the photovoltaic inverter; The objective function of photovoltaic inverter operation efficiency calculation is obtained: ;Right now ； Where: Expressed as the operating efficiency of the PV inverter; S3-2, use the equivalent resistance method to calculate the optimal working current, and the working current The optimal working point is obtained by taking the derivative: ； The comprehensive environmental factor is calculated based on the optimal working point The calculated functional relationship with the adjustable disturbance resistance is: 。 5. The photovoltaic inverter operation efficiency optimization method based on deep learning according to claim 4 is characterized in that: In step S4, the adjustable disturbance resistor performs feedback adjustment specifically including: Real-time monitoring of the main environmental factors that affect the operating efficiency of photovoltaic inverters, including ambient temperature differences , Ambient wind speed and ambient humidity ; Calculate the comprehensive environmental factor ; According to comprehensive environmental factors The calculated functional relationship between the adjustable disturbance resistance and the adjustable disturbance resistance The resistance value is large enough to make the photovoltaic inverter operate efficiently. maximum.

6. A photovoltaic inverter operating efficiency optimization method based on deep learning according to claim 2, characterized in that: In step S1-2, , , Respectively expressed as the ambient temperature difference , Ambient wind speed , Ambient humidity The weight coefficient is calculated by the following steps: take The measured environmental parameters and power loss of the group are based on The measured environmental parameters of the group are calculated as follows: Where: It is expressed as the ambient temperature difference parameter of the nth group of measured environmental parameters, The ambient wind speed parameter represented by the nth group of measured ambient parameters, The ambient humidity parameter represented by the nth group of measured ambient parameters; according to The measured power loss of the group is Measured comprehensive environmental factors : ； Where: Expressed as The measured comprehensive environmental factors of the group; and + + =1; Calculated , , The value of .

Images