A photovoltaic cell parameter identification system based on environmental parameter optimization

Abstract

The present invention relates to the field of photovoltaic cell technology, and more particularly to a photovoltaic cell parameter identification system based on environmental parameter optimization. A target function for the arc fault characteristics corresponding to the photovoltaic cell is derived from the pre-acquired output volt-ampere characteristics of the photovoltaic cell and the environmental parameters of the photovoltaic cell. The target function includes the arc fault characteristic parameters corresponding to the photovoltaic cell to be identified, and is optimized using a particle swarm optimization algorithm to identify the parameter values ​​of the arc fault characteristic parameters corresponding to the photovoltaic cell. The photovoltaic cell's volt-ampere characteristic parameters C1 and C2, the change in photovoltaic cell temperature ΔT, and the change in photovoltaic cell solar irradiance ΔS are selected. These four parameters can both reflect the photovoltaic condition after an arc fault and distinguish output fluctuations caused by environmental changes. This provides the best basis for determining whether the photovoltaic cell has loose connection contacts or damaged DC lines during operation, thereby improving the safety performance of the photovoltaic cell.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic cells, and in particular to a photovoltaic cell parameter identification system based on environmental parameter optimization. Background Art

[0002] With the continued promotion and application of photovoltaic power generation, its use cases have become more complex and diverse, placing stricter demands on fault detection technology. This is especially true for detecting arc faults on the DC side of photovoltaic systems. Photovoltaic panels are typically installed on rooftops, in remote areas, along roadsides, and in highlands or sparsely populated areas. These locations are prone to animal bites, aging wiring, and insulation peeling, leading to poor contact at connections and potentially DC arc faults. Once a DC arc is generated, it burns steadily, emitting significant amounts of light and heat energy, which can ignite surrounding combustibles and electrical equipment, potentially causing fires.

[0003] Therefore, when loose contacts or damaged DC lines occur in the system, DC arc faults are highly likely to occur. This has become one of the most dangerous faults in photovoltaic systems. Series arc faults are particularly difficult to detect and can be easily confused with output fluctuations caused by changes in light and temperature. A series arc acts like a resistor in series with the circuit. When a series arc occurs, it actually reduces the output current and voltage of the photovoltaic system. This phenomenon is very similar to the output reduction caused by temperature changes or changes in solar irradiance. Therefore, traditional protection devices cannot distinguish between a series arc fault and environmental fluctuations. For series DC arc faults in photovoltaic systems, specialized fault detection methods are required. Summary of the Invention

[0004] The purpose of the present invention is to address the problems existing in the background technology and to propose a photovoltaic cell parameter identification system based on environmental parameter optimization.

[0005] The technical solution of the present invention is a photovoltaic cell parameter identification system based on environmental parameter optimization, comprising:

[0006] A photovoltaic cell mathematical model construction module derives an objective function of arc fault characteristics corresponding to the photovoltaic cell based on the pre-acquired output volt-ampere characteristics of the photovoltaic cell and the environmental parameters of the photovoltaic cell, wherein the objective function includes arc fault characteristic parameters corresponding to the photovoltaic cell to be identified;

[0007] A data optimization module is constructed, and based on the objective function of the arc fault characteristic corresponding to the photovoltaic cell, the objective function is optimized by a particle swarm optimization algorithm to identify the parameter values ​​of the arc fault characteristic parameters corresponding to the photovoltaic cell.

[0008] Preferably, the photovoltaic cell mathematical model construction module includes the following steps:

[0009] S1: Build a mathematical model of photovoltaic cells;

[0010] S11: Based on the pre-obtained photosensitive current source and the parallel diode, according to Kirchhoff's current law, the current expression of the output volt-ampere characteristic of the photovoltaic cell is obtained as follows:

[0011] The current expression is:

[0012]

[0013] The voltage expression is:

[0014]

[0015] Among them, I is current, U is voltage, I SC is the photosensitive current source and the short-circuit current of the parallel diode, I VD is the total diffusion current of the photosensitive current source and the parallel diode through the pn junction, I DO is the saturation current of the photovoltaic cell in the absence of light, and q is the electron charge, which is 1.6×10 -19 C, K is the Boltzmann constant, which is 1.38×10-23J / K, A is the constant factor, and T refers to the temperature of the photovoltaic cell;

[0016] S12: Obtain the maximum power point voltage U of the photovoltaic cell under factory standard working conditions m , Maximum power point current I m , open circuit voltage U OC , and based on the above current expression and voltage expression, the model of photovoltaic cell output characteristics is obtained:

[0017]

[0018] Among them, C1 and C2 are the volt-ampere characteristic parameters of the photovoltaic cell, and the expression formulas of C1 and C2 are obtained by converting the model of the photovoltaic cell output characteristics:

[0019]

[0020] S13: The environmental parameters of the photovoltaic cell are the solar irradiance S and cell temperature T measured in real time by the photovoltaic cell, and also include the environmental parameters S under the standard working conditions of the photovoltaic cell when it leaves the factory. ref and T ref , obtain the change of photovoltaic cell temperature and solar irradiance, and obtain the maximum power point voltage U under any working condition based on the model of photovoltaic cell output characteristics m1 , Maximum power point current I m1 , open circuit voltage U OC1 and short-circuit current ISC1 , the specific calculation formula is:

[0021] △T=TT ref

[0022]

[0023]

[0024]

[0025] U OC1 =U OC (1-γ△T)ln(1+β△S)

[0026] U m1 =U m (1+γ△T)ln(1+β△S)

[0027] Where △T is the change in temperature of the photovoltaic cell, △S is the change in solar irradiance, S ref The irradiance is 1000W / M under standard working conditions. 2 , T ref is the battery temperature under standard operating conditions, which is 25°C, and α, β, and γ are coefficients;

[0028] S2: Determine the objective function based on the above-mentioned photovoltaic cell output characteristic model. The objective function includes arc fault characteristic parameters corresponding to the photovoltaic cell to be identified. The objective function formula is:

[0029]

[0030] Where RMSE is the root mean square error, N is the maximum power point voltage U obtained for the photovoltaic cell under any working condition m1 , Maximum power point current I m1 , open circuit voltage U OC1 and short-circuit current I SC1 The number of groups, is the maximum power point voltage U of group Q m1 , Maximum power point current I m1 , open circuit voltage U OC1 and short-circuit current I SC1 , Z is the arc fault characteristic parameter corresponding to the photovoltaic cell that needs to be identified in the photovoltaic cell output characteristic model, is the error function;

[0031] Preferably, the arc fault characteristic parameters corresponding to the photovoltaic cell to be identified include: the volt-ampere characteristic parameters C1 and C2 of the photovoltaic cell, and also include the change in temperature ΔT of the photovoltaic cell and the change in solar irradiance ΔS of the photovoltaic cell.

[0032] Preferably, the specific steps of building the data optimization module include:

[0033] S100: Randomly initialize the position and velocity of each particle in the population and calculate the fitness value of each particle:

[0034] S200: Initialize the optimal position of each particle and the global optimal position, and update the particle speed and position;

[0035] S300: Set the maximum number of iterations and the check termination condition, and determine the optimal parameters when each particle stops iterating.

[0036] Preferably, the steps of randomly initializing the position and velocity of each particle in the population and calculating the fitness value of each particle include the following steps:

[0037] S101: randomly generate an initialization position (A1, A2) for each particle, and the position can be uniformly distributed in the parameter space;

[0038] S1011: Record the initial position X of each particle i (0)=(A 1i (0),A 2i (0)), where i = 1, 2, ... n;

[0039] S102: Randomly generate an initial velocity V for each particle i (0)=(V 1i (0),V 2i (0));

[0040] S103: Setting a fitness function F to evaluate the position of each particle. The fitness function F is specifically calculated as follows:

[0041]

[0042] Where △T° is the expected temperature change, △S° is the expected solar irradiance change, is the desired volt-ampere characteristic parameter C1, is the desired volt-ampere characteristic parameter C2, and β1, β2, β3, and β4 are weight coefficients.

[0043] Preferably, the initialization of the optimal position of each particle and the global optimal position, and updating the particle speed and position, specifically includes the following steps:

[0044] S201: Record the initial position of each particle as the personal best position of each particle. The specific expression of the personal best position of each particle is: P best,i (0) = X i (0);

[0045] S202: Record the global optimal position of each particle. The specific expression of the global optimal position of each particle is: g best (0), and the initial value is the position of the particle with the lowest fitness among all particles;

[0046] S203: Update the specific expression of each particle velocity: V i (t+1);

[0047] S2031: Update the specific calculation formula for each particle velocity:

[0048] V i (t+1)=w·V i (t)+c1·r1·(P best (t))+c2·r2·(g best (t)-X i (t))

[0049] Among them, V i (t) is the velocity of particle i at the tth iteration, w is the inertia weight, whose value is 0.7-0.9, c1 and c2 are learning factors, whose value is 1.5, r1 and r2 are random numbers between 0 and 1, P best,i (t) is the best position of each particle at the tth iteration, X i (t) is the position of particle i at the tth iteration, g best (t) is the global optimal position of each particle at the tth iteration;

[0050] S204: The specific expression for updating the position of each particle is: i (t+1);

[0051] S2041: The specific calculation formula for updating the position of each particle is:

[0052] X i (t+1)=X i (t)+V i (t+1).

[0053] Preferably, the setting of the maximum number of iterations and the setting of the check termination condition specifically include the following steps:

[0054] S301: Set a reasonable maximum number of iterations T and calculate the fitness function F of each particle;

[0055] S302: If the fitness of the current particle F(X i (t+1)) is less than its personal best fitness F(P best,i (t)), then update the personal best position P best,i (t+1)=Xi (t+1);

[0056] S303: If the current particle fitness F(X i (t+1)) is less than its global optimal fitness F(g best (t)), then update the global optimal position g best (t+1)=X i (t+1);

[0057] S304: Use the above formula to update the speed and position of each particle. When the maximum number of iterations T is reached or the global optimal fitness no longer changes significantly, the iteration is stopped and the final global optimal position g is verified. best The parameters of (T) are the optimal parameters.

[0058] Compared with the existing technology, the beneficial effect of the present invention is: this solution selects the photovoltaic cell's volt-ampere characteristic parameters C1 and C2, the change in photovoltaic cell temperature △T, and the change in photovoltaic cell solar irradiance △S. These four parameters can not only reflect the photovoltaic condition after an arc fault occurs, but also distinguish output fluctuations caused by environmental changes, thereby ensuring that the photovoltaic cell has the best basis for judging whether the connection contacts are loose or the DC line is damaged during operation, thereby facilitating improving the safety performance of the photovoltaic cell. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 Schematic diagram of each module of the present invention;

[0060] Figure 2 Flowchart for building the data optimization module of the present invention;

[0061] Figure 3 This is an equivalent working circuit diagram of a photovoltaic cell with a photosensitive current source and a parallel diode of the present invention. DETAILED DESCRIPTION

[0062] 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 described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0063] Refer to the attached Figure 1-3 , a photovoltaic cell parameter identification system based on environmental parameter optimization, comprising:

[0064] A photovoltaic cell mathematical model construction module derives an objective function of arc fault characteristics corresponding to the photovoltaic cell based on the pre-acquired output volt-ampere characteristics of the photovoltaic cell and the environmental parameters of the photovoltaic cell, wherein the objective function includes arc fault characteristic parameters corresponding to the photovoltaic cell to be identified;

[0065] By confirming the output volt-ampere characteristics of photovoltaic cells and incorporating environmental parameters into them, the corresponding arc fault characteristics of the battery can be derived. The judgment of the corresponding arc fault characteristics of the battery is the best basis for determining whether the connection contacts are loose or the DC line is damaged during the operation of the photovoltaic cell, which is beneficial to improving the safety performance of the photovoltaic cell.

[0066] A data optimization module is constructed, and based on the objective function of the arc fault characteristic corresponding to the photovoltaic cell, the objective function is optimized by a particle swarm optimization algorithm to identify the parameter values ​​of the arc fault characteristic parameters corresponding to the photovoltaic cell.

[0067] By using the particle swarm optimization algorithm to optimize the objective function of the arc fault characteristics corresponding to the photovoltaic cells, not only the optimal parameters can be found, but also the performance improvement under different working conditions can be ensured.

[0068] Specifically, the photovoltaic cell mathematical model construction module includes the following steps:

[0069] S1: Build a mathematical model of photovoltaic cells;

[0070] S11: Based on the pre-acquired photosensitive current source and the parallel diode, according to Kirchhoff's current law, Figure 3 The current expression of the photovoltaic cell volt-ampere characteristic is obtained as follows:

[0071] The current expression is:

[0072]

[0073] The voltage expression is:

[0074]

[0075] Among them, I is current, U is voltage, I SC is the photosensitive current source and the short-circuit current of the parallel diode, I VD is the total diffusion current of the photosensitive current source and the parallel diode through the pn junction, I DO is the saturation current of the photovoltaic cell in the absence of light, and q is the electron charge, which is 1.6×10 -19 C, K is the Boltzmann constant, whose value is 1.38×10-23J / K, A is a constant factor (take 1 when the forward bias voltage is large, take 2 when the forward bias voltage is small, and generally take 1.3), and T refers to the temperature of the photovoltaic cell;

[0076] S12: Obtain the maximum power point voltage U of the photovoltaic cell under factory standard working conditions m , Maximum power point current I m , open circuit voltage U OC, and based on the above current expression and voltage expression, the model of photovoltaic cell output characteristics is obtained:

[0077]

[0078] Among them, C1 and C2 are the volt-ampere characteristic parameters of the photovoltaic cell, and the expression formulas of C1 and C2 are obtained by converting the model of the photovoltaic cell output characteristics:

[0079]

[0080] S13: The environmental parameters of the photovoltaic cell are the solar irradiance S and cell temperature T measured in real time by the photovoltaic cell, and also include the environmental parameters S under the standard working conditions of the photovoltaic cell when it leaves the factory. ref and T ref , obtain the change of photovoltaic cell temperature and solar irradiance, and obtain the maximum power point voltage U under any working condition based on the model of photovoltaic cell output characteristics m1 , Maximum power point current I m1 , open circuit voltage U OC1 and short-circuit current I SC1 , the specific calculation formula is:

[0081] △T=TT ref

[0082]

[0083]

[0084]

[0085] U OC1 =U OC (1-γ△T)ln(1+β△S)

[0086] U m1 =U m (1+γ△T)ln(1+β△S)

[0087] Where △T is the change in temperature of the photovoltaic cell, △S is the change in solar irradiance, S ref The irradiance is 1000W / M under standard working conditions. 2 , T ref is the battery temperature under standard operating conditions, which is 25°C, and α, β, and γ are coefficients;

[0088] S2: Determine the objective function based on the above-mentioned photovoltaic cell output characteristic model. The objective function includes arc fault characteristic parameters corresponding to the photovoltaic cell to be identified. The objective function formula is:

[0089]

[0090] Where RMSE is the root mean square error, N is the maximum power point voltage U obtained for the photovoltaic cell under any working condition m1 , Maximum power point current I m1 , open circuit voltage U OC1 and short-circuit current I SC1 The number of groups, is the maximum power point voltage U of group Q m1 , Maximum power point current I m1 , open circuit voltage U OC1 and short-circuit current I SC1 flow, Z is the arc fault characteristic parameter corresponding to the photovoltaic cell that needs to be identified in the photovoltaic cell output characteristic model, f(I SC1L ,I m1L ,U OC1L ,U m1L ,Z) is the error function;

[0091] In this embodiment, it should be noted that Figure 3 As shown, I SC Represents the current stimulated by photons in photovoltaic cells. Its magnitude depends on the solar irradiance S and the cell temperature T. Generally, manufacturers will mark the photovoltaic cell products under standard working conditions (AM1.5 standard spectrum, cell temperature 25℃, irradiance 1000W / M 2 ) next I SC The measured value of , which is also called the short-circuit current of the photovoltaic cell;

[0092] I VD (Diode current) is the total diffusion current through the pn junction, and its direction is the same as I SC On the contrary, its size is related to the electromotive force E of the photovoltaic cell and the temperature T;

[0093] R S is the series resistance, which is the comprehensive equivalent resistance of the photovoltaic cell body resistance, surface resistance, electrode conductor resistance, and contact resistance between the electrode and the silicon surface. Sh The parallel resistance formed by the accumulation of dust layer on the edge of crystalline silicon or defects inside crystalline silicon is called bypass resistance. L is the external load resistance of the photovoltaic cell, U and I are the output voltage and current of the photovoltaic cell;

[0094] Therefore, for a normal photovoltaic cell, its series resistance R S Very small, parallel resistance R Sh It is very large, so it can be ignored when calculating arc faults in ideal circuits.

[0095] Furthermore, the arc fault characteristic parameters corresponding to the photovoltaic cell to be identified include: the volt-ampere characteristic parameters C1 and C2 of the photovoltaic cell, and also include the change ΔT of the photovoltaic cell temperature and the change ΔS of the photovoltaic cell solar irradiance.

[0096] By selecting the volt-ampere characteristic parameters C1 and C2 of the photovoltaic cell, the change in the photovoltaic cell temperature △T, and the change in the photovoltaic cell solar irradiance △S, these four parameters can not only reflect the photovoltaic status after an arc fault occurs, but also distinguish the output fluctuations caused by environmental changes.

[0097] Specifically, the steps of building the data optimization module include:

[0098] S100: Randomly initialize the position and velocity of each particle in the population and calculate the fitness value of each particle:

[0099] S200: Initialize the optimal position of each particle and the global optimal position, and update the particle speed and position;

[0100] S300: Set the maximum number of iterations and the check termination condition, and determine the optimal parameters when each particle stops iterating.

[0101] Furthermore, the randomly initializing the position and velocity of each particle in the population and calculating the fitness value of each particle includes the following steps:

[0102] S101: randomly generate an initialization position (A1, A2) for each particle, and the position can be uniformly distributed in the parameter space;

[0103] S1011: Record the initial position X of each particle i (0)=(A 1i (0),A 2i (0)), where i = 1, 2, ... n;

[0104] S102: Randomly generate an initial velocity V for each particle i (0)=(V 1i (0),V 2i (0));

[0105] S103: Setting a fitness function F to evaluate the position of each particle. The fitness function F is specifically calculated as follows:

[0106]

[0107] Where △T° is the expected temperature change, △S° is the expected solar irradiance change, is the desired volt-ampere characteristic parameter C1, is the desired volt-ampere characteristic parameter C2, and β1, β2, β3, and β4 are weight coefficients.

[0108] Furthermore, the initialization of the optimal position of each particle and the global optimal position, and updating the particle speed and position, specifically includes the following steps:

[0109] S201: Record the initial position of each particle as the personal best position of each particle. The specific expression of the personal best position of each particle is: P best,i (0) = X i (0);

[0110] S202: Record the global optimal position of each particle. The specific expression of the global optimal position of each particle is: g best (0), and the initial value is the position of the particle with the lowest fitness among all particles;

[0111] S203: Update the specific expression of each particle velocity: V i (t+1);

[0112] S2031: Update the specific calculation formula for each particle velocity:

[0113] V i (t+1)=w·V i (t)+c1·r1·(P best (t))+c2·r2·(g best (t)-X i (t))

[0114] Among them, V i (t) is the velocity of particle i at the tth iteration, w is the inertia weight, whose value is 0.7-0.9, c1 and c2 are learning factors, whose value is 1.5, r1 and r2 are random numbers between 0 and 1, P best,i (t) is the best position of each particle at the tth iteration, X i (t) is the position of particle i at the tth iteration, g best (t) is the global optimal position of each particle at the tth iteration;

[0115] S204: The specific expression for updating the position of each particle is: i (t+1);

[0116] S2041: The specific calculation formula for updating the position of each particle is:

[0117] X i (t+1)=X i (t)+V i (t+1).

[0118] Furthermore, the setting of the maximum number of iterations and the setting of the check termination condition specifically include the following steps:

[0119] S301: Set a reasonable maximum number of iterations T and calculate the fitness function F of each particle;

[0120] S302: If the fitness of the current particle F(X i (t+1)) is less than its personal best fitness F(P best,i (t)), then update the personal best position P best,i (t+1)=X i (t+1);

[0121] S303: If the current particle fitness F(X i (t+1)) is less than its global optimal fitness F(g best (t)), then update the global optimal position g best (t+1)=X i (t+1);

[0122] S304: Use the above formula to update the speed and position of each particle. When the maximum number of iterations T is reached or the global optimal fitness no longer changes significantly, the iteration is stopped and the final global optimal position g is verified. best The parameters of (T) are the optimal parameters.

[0123] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A photovoltaic cell parameter identification system based on environmental parameter optimization, characterized in that: include: A photovoltaic cell mathematical model construction module derives an objective function of arc fault characteristics corresponding to the photovoltaic cell based on the pre-acquired output volt-ampere characteristics of the photovoltaic cell and the environmental parameters of the photovoltaic cell, wherein the objective function includes arc fault characteristic parameters corresponding to the photovoltaic cell to be identified; Building a data optimization module, based on the objective function of the arc fault characteristic corresponding to the photovoltaic cell, optimizing the objective function by a particle swarm optimization algorithm to identify the parameter values ​​of the arc fault characteristic parameters corresponding to the photovoltaic cell; The photovoltaic cell mathematical model construction module includes the following steps: S1: Build a mathematical model of photovoltaic cells; S11: Based on the pre-obtained photosensitive current source and the parallel diode, according to Kirchhoff's current law, the current expression of the output volt-ampere characteristic of the photovoltaic cell is obtained as follows: The current expression is: The voltage expression is: Among them, I is current, U is voltage, I SC is the photosensitive current source and the short-circuit current of the parallel diode, I VD is the total diffusion current of the photosensitive current source and the parallel diode through the pn junction, I DO is the saturation current of the photovoltaic cell in the absence of light, and q is the electron charge, which is 1.6×10 -19 C, K is the Boltzmann constant, which is 1.38×10-23J / K, A is the constant factor, and T refers to the temperature of the photovoltaic cell; S12: Obtain the maximum power point voltage U of the photovoltaic cell under factory standard working conditions m , Maximum power point current I m , open circuit voltage U OC , and based on the above current expression and voltage expression, the model of photovoltaic cell output characteristics is obtained: Among them, C1 and C2 are the volt-ampere characteristic parameters of the photovoltaic cell, and the expression formulas of C1 and C2 are obtained by converting the model of the photovoltaic cell output characteristics: S13: The environmental parameters of the photovoltaic cell are the solar irradiance S and cell temperature T measured in real time by the photovoltaic cell, and also include the environmental parameters S under the standard working conditions of the photovoltaic cell when it leaves the factory. ref and T ref , obtain the change of photovoltaic cell temperature and solar irradiance, and obtain the maximum power point voltage U under any working condition based on the model of photovoltaic cell output characteristics m1 , Maximum power point current I m1 , open circuit voltage U OC1 and short-circuit current I SC1 , the specific calculation formula is: ΔT=T-T ref U OC1 =U OC (1-γΔT)ln(1+βΔS) U m1 =U m (1+γΔT)ln(1+βΔS) Where ΔT is the change in photovoltaic cell temperature, ΔS is the change in solar irradiance, and S ref The irradiance is 1000W / M under standard working conditions. 2 , T ref is the battery temperature under standard operating conditions, which is 25°C, and α, β, and γ are coefficients; S2: Determine the objective function based on the above-mentioned photovoltaic cell output characteristic model. The objective function includes arc fault characteristic parameters corresponding to the photovoltaic cell to be identified. The objective function formula is: Where RMSE is the root mean square error, N is the maximum power point voltage U obtained for the photovoltaic cell under any working condition m1 , Maximum power point current I m1 , open circuit voltage U OC1 and short-circuit current I SC1 The number of groups, is the maximum power point voltage U of group Q m1 , Maximum power point current I m1 , open circuit voltage U OC1 and short-circuit current I SC1 , Z is the arc fault characteristic parameter corresponding to the photovoltaic cell that needs to be identified in the photovoltaic cell output characteristic model, is the error function; The arc fault characteristic parameters corresponding to the photovoltaic cell that need to be identified include: the volt-ampere characteristic parameters C1 and C2 of the photovoltaic cell, and also include the change ΔT of the photovoltaic cell temperature and the change ΔS of the photovoltaic cell solar irradiance.

2. A photovoltaic cell parameter identification system based on environmental parameter optimization according to claim 1, characterized in that: The specific steps of building the data optimization module include: S100: Randomly initialize the position and velocity of each particle in the population and calculate the fitness value of each particle: S200: Initialize the optimal position of each particle and the global optimal position, and update the particle speed and position; S300: Set the maximum number of iterations and the check termination condition, and determine the optimal parameters when each particle stops iterating.

3. A photovoltaic cell parameter identification system based on environmental parameter optimization according to claim 2, characterized in that: The steps of randomly initializing the position and velocity of each particle in the population and calculating the fitness value of each particle include the following: S101: randomly generate an initialization position (A1, A2) for each particle, and the position can be uniformly distributed in the parameter space; S1011: Record the initial position X of each particle i (0)=(A 1i (0),A 2i (0)), where i = 1, 2, ···n; S102: Randomly generate an initial velocity V for each particle i (0)=(V 1i (0),V 2i (0)); S103: Setting a fitness function F to evaluate the position of each particle. The fitness function F is specifically calculated as follows: Where ΔT° is the desired temperature change, ΔS° is the desired solar irradiance change, is the desired volt-ampere characteristic parameter C1, is the desired volt-ampere characteristic parameter C2, and β1, β2, β3, and β4 are weight coefficients.

4. The photovoltaic cell parameter identification system based on environmental parameter optimization according to claim 3, characterized in that: Initializing the optimal position of each particle and the global optimal position, and updating the particle speed and position, specifically includes the following steps: S201: Record the initial position of each particle as the personal best position of each particle. The specific expression of the personal best position of each particle is: P best,i (0) = X i (0); S202: Record the global optimal position of each particle. The specific expression of the global optimal position of each particle is: g best (0), and the initial value is the position of the particle with the lowest fitness among all particles; S203: Update the specific expression of each particle velocity: V i (t+1); S2031: The updated specific calculation formula for each particle velocity is: V i (t+1)=w·V i (t)+c1·r1·(P best (t))+c2·r2·(g best (t)-X i (t)) Among them, V i (t) is the velocity of particle i at the tth iteration, w is the inertia weight, whose value is 0.7-0.9, c1 and c2 are learning factors, whose value is 1.5, r1 and r2 are random numbers between 0 and 1, P best,i (t) is the best position of each particle at the tth iteration, X i (t) is the position of particle i at the tth iteration, g best (t) is the global optimal position of each particle at the tth iteration; S204: The specific expression for updating the position of each particle is: i (t+1); S2041: The specific calculation formula for the position of each particle after update is: X i (t+1)=X i (t)+V i (t+1)。 5. The photovoltaic cell parameter identification system based on environmental parameter optimization according to claim 4, characterized in that: The step of setting the maximum number of iterations and setting the check termination condition specifically includes the following steps: S301: Set a reasonable maximum number of iterations T and calculate the fitness function F of each particle; S302: If the fitness of the current particle F(X i (t+1)) is less than its personal best fitness F(P best,i (t)), then update the personal best position P best,i (t+1)=X i (t+1); S303: If the current particle fitness F(X i (t+1)) is less than its global optimal fitness F(g best (t)), then update the global optimal position g best (t+1)=X i (t+1); S304: Use the above formula to update the speed and position of each particle. When the maximum number of iterations T is reached or the global optimal fitness no longer changes significantly, the iteration is stopped and the final global optimal position g is verified. best The parameters of (T) are the optimal parameters.

Images