Lightning algorithm-based photovoltaic module cleaning cycle optimization method and related device

Abstract

The application discloses a lightning algorithm-based photovoltaic module cleaning period optimization method and related device, and relates to the field of photovoltaic module cleaning period optimization.The method comprises the following steps: establishing a rain cleaning factor, an installation height cleaning factor and an installation angle cleaning factor based on rainfall, photovoltaic module installation height and photovoltaic module installation angle; obtaining power generation loss and cleaning and maintenance cost factors in the cleaning period according to electricity price, daily effective operation time, power station installed capacity and dust accumulation condition; establishing a target model with total cleaning economic benefits of the photovoltaic module as the target; and solving the target model by using a lightning algorithm to obtain the optimal cleaning period.The application comprehensively considers the influence of rainfall, installation height and installation angle on the cleaning period of the photovoltaic module, combines the economic influence of power generation loss and cleaning and maintenance cost in the cleaning period on the cleaning of the photovoltaic module, establishes a total cleaning economic benefit target, and obtains the optimal cleaning benefit method by using the lightning algorithm, so that the cleaning period of the photovoltaic module can be comprehensively obtained.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of photovoltaic module cleaning, and particularly relates to a photovoltaic module cleaning cycle optimization method based on a lightning algorithm and a related device. BACKGROUND

[0002] Dust accumulation has a significant impact on the operating efficiency of photovoltaic modules, and the cleaning work of photovoltaic modules is very complex, and needs to consider multiple factors such as cleaning time, cleaning method, cleaning cycle, etc. The dust accumulation degree of photovoltaic modules is easily affected by factors such as weather and support height, which further increases the difficulty of photovoltaic module cleaning work. In previous actual projects, photovoltaic modules are generally cleaned by manual observation or engineer experience method, and the cleaning cycle lacks flexibility and scientificity. Photovoltaic modules are long-term exposed to external environment, and factors such as geographical location, weather, and season will significantly change the dust accumulation degree, and the use of unscientific cycle setting method will cause economic loss. SUMMARY

[0003] The purpose of the present application is to provide a photovoltaic module cleaning cycle optimization method based on a lightning algorithm and a related device to solve the problem that photovoltaic modules are long-term exposed to external environment, and factors such as geographical location, weather, and season will significantly change the dust accumulation degree, and the use of unscientific cycle setting method will cause economic loss.

[0004] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0005] The photovoltaic module cleaning cycle optimization method based on the lightning algorithm comprises the following steps:

[0006] Based on the rainfall, the installation height of the photovoltaic module, and the installation inclination angle of the photovoltaic module, a rainy day cleaning factor, an installation height cleaning factor, and an installation inclination angle cleaning factor are established;

[0007] According to the electricity price, the daily effective operating time, the installed capacity of the power station, and the dust accumulation condition, the power generation loss in the cleaning cycle and the cleaning and maintenance cost factor are obtained;

[0008] According to the rainy day cleaning factor, the installation height cleaning factor, the installation inclination angle cleaning factor, the power generation loss in the cleaning cycle, and the cleaning and maintenance cost factor, a target model is established with the total cleaning economic benefit of the photovoltaic module as the target;

[0009] The lightning algorithm is used to solve the target model to obtain the optimal cleaning cycle.

[0010] Specifically, the rainy day cleaning factor D for evaluating the rainfall on the dust accumulation of the photovoltaic module is constructed from the rainfall, and the rainy day cleaning factor D is specifically as follows:

[0011]

[0012] Wherein, d1 is the number of non-rainy days in a season, d is the total number of days in a season.

[0013] Specifically, the installation height cleaning factor G of the dust accumulation amount of the photovoltaic module from the installation height evaluation height is as follows:

[0014]

[0015] Wherein, y x (h1) is the dust accumulation density of the different installation height h1 on the photovoltaic module; y x (h) is the dust accumulation density of the photovoltaic module with the installation height h as the standard height in a season.

[0016] Specifically, the installation inclination cleaning factor Q of the dust accumulation amount of the photovoltaic module from the installation inclination evaluation angle is as follows:

[0017]

[0018] Wherein, q x (θ1) is the dust accumulation density of the different installation inclination θ1 on the photovoltaic module; q x (θ) is the dust accumulation density of the photovoltaic module with the installation inclination θ as the standard angle in a season.

[0019] Specifically, the power generation loss and cleaning maintenance cost factor in the cleaning period are as follows:

[0020] According to the electricity price, daily effective operation time, power station installed capacity and dust accumulation, the daily average power generation loss cost in the cleaning period is:

[0021] F=P·η x ·Y·J

[0022] Wherein, P is the installed capacity of the photovoltaic module; η x is the dust accumulation density in a season, Y is the daily effective operation time of the photovoltaic module, and J is the local electricity price.

[0023] If the cleaning maintenance cost is collected according to the area of the module, then the cleaning maintenance factor is:

[0024] W=S·C

[0025] Wherein, W is the single cleaning maintenance cost of the photovoltaic module; S is the area of the photovoltaic module; and C is the cleaning cost per unit area.

[0026] Specifically, the total cleaning economic benefit of the photovoltaic module is calculated as follows:

[0027]

[0028] Wherein, M is the cleaning benefit of the component, D is the rain cleaning factor; G is the installation height cleaning factor; Q is the installation angle cleaning factor; F is the loss cost of daily average power generation in a season; is the cleaning frequency, t x is the running time of the system in a season; T is the optimal cleaning period;

[0029] The constraint condition is that the cleaning benefit of the power generation is greater than the comprehensive maintenance cost of the photovoltaic system, and the cleaning benefit of the power generation is greater than 0:

[0030]

[0031] Specifically, the lightning algorithm is used to solve the optimal cleaning period model, which is specifically:

[0032] In the lightning algorithm, the step leader is used as the total cleaning economic benefit of the photovoltaic component, and the lightning algorithm is used to obtain the optimal charge to obtain the total cleaning economic benefit of the photovoltaic component:

[0033] The initial population of the lightning algorithm is a set of charges with different positions, which are randomly assigned in a bounded interval; Among the randomly assigned charges, n optimal charges are selected as the step leaders, and the n step leaders and the remaining charges are evenly distributed in n lightning channels; This process corresponds to the physical process of cloud ionization;

[0034] I=I min +r(I max -I min )

[0035] Wherein, I max and I min are the maximum and minimum values in the charge individual, and r is a random value between 0 and 1;

[0036] After a group of charges are randomly initialized, the optimal solution is found by iteration; First, all the charges after initialization move along the channel to the ground, and each charge updates its charge value in the direction of the step leader; If the updated charge is better than the step leader, the step leader is replaced by the current individual as the total cleaning economic benefit of the photovoltaic component, otherwise, the original step leader is kept as the current total cleaning economic benefit of the photovoltaic component;

[0037] J ij (t)=w·J ij (t-1)+C1·r·[X i (t-1)-X ij (t-1)]

[0038] X ij (t)=X ij (t-1)+J ij (t)

[0039] wherein w is the inertial weight of the charge down-movement; J ij is the jump value of charge j in channel i, X i is the ladder leader of channel i, X ij is the value of charge j in channel i;

[0040] Then, the distance d between the optimal charge and the worst charge in all channels is measured as the decision parameter of the charge jump process;

[0041] d i =X i (t)-X iw (t)

[0042] wherein X iw (t) represents the worst charge in channel i;

[0043] Before the charge jump, the ladder leader will absorb and assimilate all the charges in the channel, i.e., all the charges are equal to the ladder leader; finally, the charge jump process, the direction of the charge jump is not the same, after the charge value is updated, if the charge is better than the ladder leader, it is replaced, otherwise, the original value is retained; thus, a complete optimization process is completed; the optimal value is solved as the total cleaning economic benefit of the photovoltaic module, and the above process is repeated until the set iteration number or error precision is reached;

[0044] X ij (t)=X i (t)

[0045] X ij (t)=X ij (t)+r·d i ·α

[0046] wherein α represents the lightning speed;

[0047] The total cleaning economic benefit of the photovoltaic module is solved, and the photovoltaic module cleaning period is obtained.

[0048] In a second aspect, the embodiment of the present application provides a photovoltaic module cleaning period optimization system based on a lightning algorithm, comprising:

[0049] A photovoltaic module cleaning obtaining module is configured to establish a rainy day cleaning factor, an installation height cleaning factor and an installation angle cleaning factor based on rainfall, photovoltaic module installation height and photovoltaic module installation angle;

[0050] A power generation loss and cleaning maintenance cost factor obtaining module is configured to obtain the power generation loss and cleaning maintenance cost factor in the cleaning period according to the electricity price, daily effective operation time, power station installed capacity and dust accumulation condition;

[0051] The target model establishing module is configured to establish a target model with total cleaning economic benefits of the photovoltaic module as a target according to the rain cleaning factor, the installation height cleaning factor, the installation angle cleaning factor, the power generation loss in the cleaning period and the cleaning and maintenance cost factor.

[0052] The optimal cleaning period obtaining module is configured to obtain the optimal cleaning period by solving the target model by using the lightning algorithm.

[0053] In a third aspect, a computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the lightning algorithm-based photovoltaic module cleaning period optimization method when executing the computer program.

[0054] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium including a computer program, and the computer program implements the steps of the lightning algorithm-based photovoltaic module cleaning period optimization method when executed by a processor.

[0055] Compared with the prior art, the present application has the following technical effects:

[0056] The present application comprehensively considers the influence of rainfall, installation height and installation angle on the cleaning period of the photovoltaic module, combines the power generation loss in the cleaning period and the economic influence of cleaning and maintenance cost on the cleaning of the photovoltaic module, establishes a total cleaning economic benefit target, and obtains the optimal cleaning benefit method by using the lightning algorithm, so that the cleaning period of the photovoltaic module can be more comprehensively obtained.

[0057] The present application realizes the construction of the influence factor of the optimized photovoltaic module cleaning period from different angles, optimizes comprehensively, uses the lightning algorithm to comprehensively construct the five influence factors, obtains the target function (total cleaning economic benefit), and can optimize the more accurate photovoltaic module cleaning period, which has an effective guiding effect on engineering practice. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1 A lightning algorithm-based photovoltaic module cleaning period optimization research method flowchart. DETAILED DESCRIPTION

[0059] The present application is further described below in combination with the drawings:

[0060] Lightning algorithm-based photovoltaic module cleaning period optimization method and related device

[0061] (1) Construction of component dirt influence factor: rain cleaning factor, installation height cleaning factor and installation angle cleaning factor are established from the aspects of rainfall, installation height and installation angle.

[0062] A rain day cleaning factor D is constructed from rainfall to evaluate the effect of rainfall on the dust accumulation of a photovoltaic module. Rainfall has a cleaning effect on a photovoltaic module, and a decrease in rainfall will increase the dust accumulation of a photovoltaic module and the economic loss of power generation. A rain day cleaning factor D is defined to represent the degree of influence of rainfall on the economic loss of power generation, and is determined according to the following formula:

[0063]

[0064] where d1 is the number of non-rainy days in a season, and d is the total number of days in a season.

[0065] An installation height cleaning factor G is constructed from the installation height to evaluate the effect of the installation height on the dust accumulation of a photovoltaic module. The installation height also affects the degree of dust accumulation of a photovoltaic module. An installation height cleaning factor G is defined by the ratio of the dust accumulation density of the installation height to the dust accumulation density of the standard installation height, to represent the influence of the installation height on the economic loss of power generation, and is determined according to the following formula:

[0066]

[0067] where y x (h1) is the dust accumulation density of a photovoltaic module affected by different installation heights h1, with a unit of gm 2 ; y x (h) is the dust accumulation density of a photovoltaic module affected by a standard installation height h in a season, with a unit of gm 2 .

[0068] An installation angle cleaning factor Q is constructed from the installation angle to evaluate the effect of the installation angle on the dust accumulation of a photovoltaic module. As the installation angle increases, the dust accumulation density of a photovoltaic module decreases, and the economic loss of power generation decreases. An installation angle cleaning factor Q is defined by the ratio of the dust accumulation density of the installation angle to the dust accumulation density of the standard installation angle, to represent the influence of the installation angle on the economic loss of power generation, and is determined according to the following formula:

[0069]

[0070] where q x (θ1) is the dust accumulation density of a photovoltaic module affected by different installation angles θ1, with a unit of gm 2 ; q x (θ) is the dust accumulation density of a photovoltaic module affected by a standard installation angle θ in a season, with a unit of gm 2 .

[0071] (2) Construction of the power generation loss and cleaning and maintenance cost factor in the cleaning period:

[0072] The power loss mainly considers the electricity price, daily effective operation time, power station installed capacity and ash deposition. The daily average power loss cost in the cleaning period is

[0073] F = P η x Y J (4)

[0074] Where P is the installed capacity of photovoltaic module, unit: kW. η x is the opportunity density of a certain season, Y is the daily effective operation time of photovoltaic module, unit: h, J is the local electricity price, unit: yuan / kWh.

[0075] The cleaning and maintenance cost is collected according to the area of module, so the cleaning and maintenance factor is

[0076] W = S C (5)

[0077] Where W is the single cleaning and maintenance cost of photovoltaic module, unit: yuan; S is the area of photovoltaic module, unit: m2; C is the cleaning cost per unit area, unit: yuan / m2.

[0078] (3) Establishment of total target model

[0079] Considering the module dirty influence factor and the economic reasons in the cleaning period, the total cleaning economic benefit of photovoltaic module is calculated as follows:

[0080]

[0081] Where M is the module power generation benefit after cleaning, D is the rainy day cleaning factor; G is the installation height cleaning factor; Q is the installation inclination cleaning factor; F is the daily average power loss cost in a certain season; N is the cleaning frequency, the ratio of operation time in a certain season to cleaning period, unit: times, t x is the operation time of system in a certain season, unit: day; T is the optimal cleaning period.

[0082] The constraint condition is that the power cleaning benefit is greater than the comprehensive maintenance cost of photovoltaic system, and the power cleaning benefit is greater than 0:

[0083]

[0084] (4) Model solution

[0085] The optimal cleaning cycle model is solved by using lightning algorithm. The lightning algorithm is derived from the lightning phenomenon between the cloud layer and the bottom. The initial population of the algorithm is the electric charges with different positions, which can be randomly assigned in the bounded interval, as shown in equation (8). Among these randomly assigned electric charges, the n optimal electric charges are selected as the stepped leaders, and the n stepped leaders and the rest of the electric charges are evenly distributed into n lightning channels. This process corresponds to the physical process of cloud ionization.

[0086] I = I min + r(I max - I min ) (8)

[0087] where I max , I min are the maximum and minimum values of the electric charges, and r is a random number between 0 and 1.

[0088] After randomly initializing a group of electric charges, the optimal solution is found through iteration.

[0089] First, after initialization, all electric charges move towards the ground along the channel they are in. Each electric charge updates its own charge value in the direction of the stepped leader, as shown in equations (9) and (10). If the updated electric charge is better than the stepped leader, the stepped leader is replaced by the current individual; otherwise, the original stepped leader is retained.

[0090] J ij (t) = w · J ij (t - 1) + C1 · r · [X i (t - 1) - X ij (t) (9)

[0091] X ij (t) = X ij (t - 1) + J ij (t) (10)

[0092] where w is the inertia weight of the downward movement of the electric charge, which can ensure that the electric charge moves downward in the direction of the stepped leader in the lightning channel. Jij represents the jump value of electric charge j in channel i, Xi represents the stepped leader of channel i, and Xij represents the value of electric charge j in channel i.

[0093] Then, the distance d between the optimal electric charge and the worst electric charge in all channels is measured as the decision parameter for the electric charge jump process.

[0094] d i = X i (t) - X iw (t) (11)

[0095] where X iw(t) represents the worst charge in channel i.

[0096] Before the charge jumps, the step leader will absorb and assimilate all the charges in the channel, that is, all the charges are equal to the step leader. Finally, the charge jump process is carried out, and the direction of the charge jump is not the same in order to diversify the population. After the charge value is updated, if the charge is better than the step leader, it is replaced, otherwise, the original value is retained. Thus, a complete optimization process is completed. In order to solve the optimal value, the above process is repeated until the set iteration number or error precision is reached.

[0097] X ij (t) = X i (t) (12)

[0098] X ij (t) = X ij (t) + r·d i ·(13)

[0099] Wherein, α represents the lightning speed.

[0100] In still another embodiment of the present application, a photovoltaic module cleaning cycle optimization system based on lightning algorithm is provided, which can be used to implement the photovoltaic module cleaning cycle optimization method based on lightning algorithm. Specifically, the system comprises:

[0101] A photovoltaic module cleaning obtaining module is configured to establish a rainy day cleaning factor, an installation height cleaning factor and an installation angle cleaning factor based on rainfall, photovoltaic module installation height and photovoltaic module installation angle.

[0102] A power generation loss and cleaning maintenance cost factor obtaining module is configured to obtain the power generation loss and cleaning maintenance cost factor within the cleaning cycle according to the electricity price, daily effective operation time, power station installed capacity and dust accumulation condition.

[0103] A target model establishing module is configured to establish a target model with the total cleaning economic benefit of the photovoltaic module as the target according to the rainy day cleaning factor, the installation height cleaning factor, the installation angle cleaning factor, the power generation loss and the cleaning maintenance cost factor within the cleaning cycle.

[0104] An optimal cleaning cycle obtaining module is configured to obtain the optimal cleaning cycle by using the lightning algorithm to solve the target model.

[0105] The division of the modules in the embodiments of the present application is illustrative, and is only a logical function division. In actual implementation, another division mode can be used. In addition, the function modules in each embodiment of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software function module.

[0106] In another embodiment of the present application, a computer device is provided, which comprises a processor and a memory, the memory is configured to store a computer program, the computer program comprises program instructions, and the processor is configured to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, and are suitable for implementing one or more instructions, and are particularly suitable for loading and executing one or more instructions in the computer storage medium to implement a corresponding method flow or a corresponding function; the processor in the embodiments of the present application can be used for the operation of the photovoltaic module cleaning cycle optimization method based on the lightning algorithm.

[0107] In another embodiment of the present application, the present application further provides a storage medium, specifically a computer readable storage medium (Memory), which is a memory device in a computer device, and is configured to store programs and data. It can be understood that the computer readable storage medium herein can include an internal storage medium in the computer device, and of course can also include an extended storage medium supported by the computer device. The computer readable storage medium provides a storage space, and the storage space stores an operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and the instructions can be one or more computer programs (including program codes). It should be noted that the computer readable storage medium herein can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory. One or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the photovoltaic module cleaning cycle optimization method based on the lightning algorithm in the above embodiments.

[0108] Those skilled in the art will appreciate that embodiments of the application can be devised for a method, a system, or a computer program product. Accordingly, the present application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0109] The present application is described in reference to the flowchart and / or block diagrams of the method, apparatus (system) and computer program product according to embodiments of the application. It will be understood that each block of the flowchart and / or block diagrams, and combinations of blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing device or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0110] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0112] Finally, it should be noted that the above-mentioned embodiments are merely intended for describing the technical solutions of the present application, but not for limiting it. Although the present application is described in detail with reference to the above embodiments, those skilled in the field should understand that the specific embodiments of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and any modification or equivalent replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. A method for optimizing the cleaning cycle of a photovoltaic module based on the lightning algorithm, characterized in that, The method comprises the following steps: establishing a rain cleaning factor, an installation height cleaning factor and an installation angle cleaning factor based on rainfall, installation height of the photovoltaic module and installation angle of the photovoltaic module; obtaining a power generation loss in the cleaning period and a cleaning and maintenance cost factor according to electricity price, daily effective operation time, installed capacity of the power station and soot accumulation; establishing a target model with the total cleaning economic benefit of the photovoltaic module as a target according to the rain cleaning factor, the installation height cleaning factor, the installation angle cleaning factor, the power generation loss in the cleaning period and the cleaning and maintenance cost factor; solving the target model by using a lightning algorithm to obtain an optimal cleaning period; solving the optimal cleaning period model by using the lightning algorithm is specifically as follows: taking the step leader in the lightning algorithm as the total cleaning economic benefit of the photovoltaic module, the total cleaning economic benefit of the photovoltaic module is obtained by using the lightning algorithm: the initial population of the lightning algorithm is a set of charges with different positions, and the charges are randomly assigned in a bounded interval; in the randomly assigned charges, n optimal charges are selected as step leaders, and the n step leaders and the remaining charges are evenly distributed in n lightning channels; this process corresponds to the physical process of cloud ionization; wherein and are the maximum and minimum values in the charge individuals, r is a random value between 0 and 1. after a group of charges are randomly initialized, the optimal solution is found through iteration; first, all the charges after initialization move along the channel to the ground, and each charge updates its charge value in the direction of the step leader; if the updated charge is better than the step leader, the step leader is replaced by the current individual as the total cleaning economic benefit of the photovoltaic module, otherwise, the original step leader is retained as the current total cleaning economic benefit of the photovoltaic module; wherein is the inertial weight of the charge downshift motion; is the channel is the value of the charge is the jump value of the charge is the channel is the step leader of the channel is the value of the charge is the value of the charge is the value of the charge then, the distance d between the optimal charge and the worst charge in all channels is measured as a decision parameter for the charge jumping process; wherein, represents the worst charge in channel i; before the charge jumps, the step leader will absorb and assimilate all the charges in the channel, that is, all the charges are equal to the step leader; finally, the charge jumping process, the direction of the charge jump is not the same, after the charge value is updated, if there is a charge better than the step leader, it is replaced, otherwise, the original value is retained; thus, a complete optimization process is completed; the optimal value is solved as the total cleaning economic benefit of the photovoltaic module, and the above process is repeated until the set number of iterations or the error precision is reached; wherein represents the speed of the lightning strike; the total cleaning economic benefit of the photovoltaic module is solved, and the cleaning period of the photovoltaic module is obtained.

2. The lightning algorithm based photovoltaic module cleaning cycle optimization method of claim 1, wherein, From rainfall to construct evaluation rainfall to photovoltaic module dust amount rain day cleaning factor , rain day cleaning factor In detail as follows: wherein, is the number of non-rainy days in a season, is the total number of days in a season.

3. The lightning algorithm based photovoltaic module cleaning cycle optimization method of claim 1, wherein, Installation height cleaning factor for dust accumulation on photovoltaic modules from installation height to build-up height As follows: wherein for different installation heights soiling density affecting the photovoltaic module; for a certain season installation height is the standard height soiling density of the photovoltaic module.

4. The lightning algorithm based photovoltaic module cleaning cycle optimization method of claim 1, wherein, An installation inclination cleaning factor of a dust accumulation amount of a photovoltaic module from an installation inclination angle of an evaluation angle As follows: wherein for different installation tilt angles dirt accumulation density affecting the photovoltaic module; for installation tilt angles of certain seasons dirt accumulation density affecting the photovoltaic module.

5. The lightning algorithm based photovoltaic module cleaning cycle optimization method of claim 1, wherein, The power generation loss in the cleaning period and the cleaning and maintenance cost factor are constructed as follows: According to the electricity price, the daily effective operation time, the installed capacity of the power station and the soot accumulation, the daily average power generation loss cost in the cleaning period is: wherein, is the installed capacity of the photovoltaic assembly; is the soiling density of a certain season, is the daily effective operating time of the photovoltaic assembly, is the local electricity price; The cleaning and maintenance cost is collected according to the area of the module, so the cleaning and maintenance factor is: wherein, is the cost of a single cleaning maintenance for a photovoltaic module; is the area of the photovoltaic module; is the cost of cleaning per unit area.

6. The lightning algorithm based photovoltaic module cleaning cycle optimization method of claim 1, wherein, The total cleaning economic benefit of the photovoltaic module is calculated as follows: wherein, is a post-wash assembly power generation benefit, is a rain day wash factor; is a mounting height wash factor; is a mounting tilt wash factor; is a certain season average daily power generation loss cost; is a wash frequency, is a system certain season run time; is an optimal wash period; The constraint condition starts from the power generation cleaning benefit, the power generation cleaning benefit is greater than the comprehensive maintenance cost of the photovoltaic system, and the power generation cleaning benefit is greater than 0: 。 7. A system for optimizing the cleaning cycle of a photovoltaic module based on the lightning algorithm, characterized by, It comprises: a photovoltaic module cleaning obtaining module, configured to establish a rain cleaning factor, an installation height cleaning factor and an installation angle cleaning factor based on rainfall, installation height of the photovoltaic module and installation angle of the photovoltaic module; The power generation loss and cleaning maintenance cost factor obtaining module is configured to obtain the power generation loss and cleaning maintenance cost factor in the cleaning period according to the electricity price, the daily effective operation time, the power station installed capacity and the soot accumulation condition; The target model establishing module is configured to establish a target model with the total cleaning economic benefit of the photovoltaic module as a target according to the rain day cleaning factor, the installation height cleaning factor, the installation inclination cleaning factor, the power generation loss and cleaning maintenance cost factor in the cleaning period; The optimal cleaning period obtaining module is configured to obtain the optimal cleaning period by solving the target model by using the lightning algorithm. The lightning algorithm is used to solve the optimal cleaning period model, and the total cleaning economic benefit of the photovoltaic module is obtained by using the step leader in the lightning algorithm as the total cleaning economic benefit of the photovoltaic module: The initial population of the lightning algorithm is a set of charges with different positions, which are randomly assigned in a bounded interval; among the randomly assigned charges, n optimal charges are selected as the step leaders, and the n step leaders and the remaining charges are evenly distributed in n lightning channels; this process corresponds to the physical process of cloud ionization; After a group of charges are randomly initialized, the optimal solution is found by iteration; first, all the charges after initialization move along the channel to the ground, and each charge updates its charge value in the direction of the step leader; if the updated charge is better than the step leader, the step leader is replaced by the current individual as the total cleaning economic benefit of the photovoltaic module, otherwise, the original step leader is retained as the current total cleaning economic benefit of the photovoltaic module; wherein and are the maximum and minimum values in the charge individuals, r is a random value between 0 and 1. Then, the distance d between the optimal charge and the worst charge in all channels is measured as the decision parameter of the charge jumping process; wherein is the inertial weight of the charge downshift motion; is the channel of the charge jump value, is the channel of the ladder leader, is the channel of the charge value; Before the charge jumps, the step leader will absorb and assimilate all the charges in the channel, that is, all the charges are equal to the step leader; finally, the charge jumping process, the direction of the charge jump is not the same, after the charge value is updated, if there is a charge better than the step leader, it is replaced, otherwise, the original value is retained; thus, a complete optimization process is completed; the optimal value is solved as the total cleaning economic benefit of the photovoltaic module, and the above process is repeated until the set iteration number or error precision is reached; wherein, represents the worst charge in channel i; The total cleaning economic benefit of the photovoltaic module is solved, and the cleaning period of the photovoltaic module is obtained. wherein represents the speed of the lightning strike; The processor executes the computer program to realize the steps of the lightning algorithm-based photovoltaic module cleaning period optimization method according to any one of claims 1 to 6.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The computer program is executed by the processor to realize the steps of the lightning algorithm-based photovoltaic module cleaning period optimization method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. ​

Images