Cable connection methods and equipment for photovoltaic power stations

Abstract

The present invention discloses a cable connection method and device for a photovoltaic power station, belonging to the technical field of photovoltaic power generation. The method comprises the following steps: arranging and combining photovoltaic modules and inverters of a photovoltaic power station to obtain a string set, and dividing the string set to obtain multiple complement sequences; inputting the positions of the photovoltaic modules in the complement sequence into a preset meta-model, solving the target solution of the complement sequence with a preset objective function; determining the cable distance from the photovoltaic modules in the string set to the inverter among all target solutions, and performing cable connection of the photovoltaic power station using the cable connection sequence with the shortest cable distance. Reinforcement learning is used to obtain a fast, efficient, and more universal string arrangement for any power station, thereby avoiding the problem of non-shortest distance from photovoltaic modules to inverters and non-lowest cable costs due to manual string arrangement, as well as the problem of jumpers within the string line.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and in particular to a cable connection method and equipment for a photovoltaic power station. Background Art

[0002] Currently, the stringing of components in photovoltaic power stations is often done manually, which often results in the distance from the photovoltaic components to the inverter not being the shortest, the cable cost not being the lowest, and there being problems with jumpers inside the stringing. Summary of the Invention

[0003] The main purpose of the present invention is to provide a cable connection method for a photovoltaic power station, aiming to solve the technical problems in the prior art of unreasonable string connection methods resulting in long string connection distances and high costs.

[0004] To achieve the above object, the present invention provides a cable connection method for a photovoltaic power station, the cable connection method for a photovoltaic power station comprising:

[0005] Arrange and combine photovoltaic modules and inverters of the photovoltaic power station to obtain a string set, and divide the string set to obtain a plurality of complement sequences;

[0006] Inputting the positions of the photovoltaic modules in the complement sequence into a preset meta-model, and solving the complement sequence with a preset objective function to obtain a target solution;

[0007] Among all the target solutions, the cable distances from the photovoltaic components in the string set to the inverter are determined, and the photovoltaic power station cables are connected using a cable connection sequence with the shortest cable distance.

[0008] Optionally, the step of arranging and combining photovoltaic modules and inverters of the photovoltaic power station to obtain a string set includes:

[0009] Obtaining a first number of photovoltaic modules, a second number of inverters, and a third number of photovoltaic modules in a string in a photovoltaic power station;

[0010] A string set is obtained by performing permutations and combinations according to the first quantity, the second quantity and / or the third quantity.

[0011] Optionally, the step of obtaining a string set by performing permutations and combinations according to the first quantity, the second quantity and / or the third quantity includes:

[0012] If the third number of each string is the same, then the internal arrangement and combination of each photovoltaic module in the string is performed;

[0013] If the third quantities of the strings are different, external arrangement and combination of the strings are performed, and then internal arrangement and combination of the photovoltaic modules in the strings are performed.

[0014] Optionally, the step of obtaining a string set by permuting and combining the first quantity, the second quantity and / or the third quantity further includes:

[0015] If it is a single inverter, a string set is obtained by performing permutations and combinations according to the first quantity and the second quantity;

[0016] If there are multiple inverters, a string set is obtained by permuting and combining the first quantity, the second quantity, and the third quantity.

[0017] Optionally, before the step of dividing the group string set to obtain a plurality of complement sequences, the step further includes:

[0018] A first position of a photovoltaic component in a photovoltaic power station is obtained, and a first distance weight set from any photovoltaic component to other photovoltaic components is determined based on the first position.

[0019] Optionally, the step of dividing the group string set to obtain a plurality of complement sequences includes:

[0020] The group string set is divided according to the first distance weight set to obtain a plurality of complement sequences.

[0021] Optionally, before the step of solving the target solution of the complement sequence using a preset objective function, the method further includes:

[0022] A second position of an inverter in the photovoltaic power station is obtained, and a second distance weight set from any photovoltaic component to the inverter is determined according to the second position.

[0023] Optionally, the step of obtaining a target solution of the complement sequence by solving a preset objective function includes:

[0024] According to the objective function of minimizing the jumper length between strings in the string set and minimizing the second distance weight set, the target solution of the current complement sequence is obtained.

[0025] Optionally, before the step of inputting the positions of the photovoltaic components in the complement sequence into a preset meta-model, the method further includes:

[0026] A preset meta-model based on a pointer network is trained according to the positions of the photovoltaic components in the complement sequence.

[0027] Optionally, the step of determining the cable distances from the photovoltaic components in the string set to the inverter among all the target solutions, and performing cable connection of the photovoltaic power station using a cable connection sequence with the shortest cable distance includes:

[0028] Merging the target solutions of all the complement sequences to obtain an optimal string set;

[0029] A cable connection sequence with a minimum distance to the inverter is solved in the optimal string set, and the cable connection sequence with the minimum distance is used as the final solution of the string set, that is, the optimal cable connection sequence of the photovoltaic power station.

[0030] In addition, to achieve the above-mentioned purpose, the present invention also provides a cable connection optimization device for a photovoltaic power station, and the cable connection optimization device for a photovoltaic power station includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor. When the computer program is executed by the processor, the steps of the cable connection method for the photovoltaic power station as described above are implemented.

[0031] An embodiment of the present invention proposes a cable connection method and device for a photovoltaic power station. The method is as follows: photovoltaic components and inverters of the photovoltaic power station are arranged and combined to obtain a string set, and the string set is divided to obtain multiple complement sequences; the positions of the photovoltaic components in the complement sequence are input into a preset meta-model, and a target solution of the complement sequence is obtained by solving a preset objective function; among all the target solutions, the cable distance from the photovoltaic components in the string set to the inverter is determined, and the cables of the photovoltaic power station are connected using the cable connection sequence with the smallest cable distance.

[0032] In this embodiment, a method is provided for discretizing possible inverter position points based on the known number of allocated inverters and the number of inverter strings connected in series and parallel, and then performing optimal division of string lines for the discretized lower wall point positions, and performing statistical calculations on the distances and number of jumpers after the string line divisions, and obtaining the cable under the inverter position with the shortest distance in the minimum value set as the final result after optimization.

[0033] Reinforcement learning can be used to obtain a faster, more efficient, and more universal string and cable arrangement for any power station, thus avoiding the problem of manual string and cable arrangement resulting in non-shortest distance from PV panels to inverters, non-lowest cable costs, and jumper wires within the string cables. A reasonable string and cable arrangement method can be used to save cable costs and manpower, thereby achieving higher economic value. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the structure of the operating equipment of the hardware operating environment involved in the embodiment of the present invention;

[0035] Figure 2 This is a flow chart of an embodiment of a cable connection method for a photovoltaic power station according to the present invention;

[0036] Figure 3 A schematic diagram of a policy gradient optimization training based on a pointer network according to an embodiment of a cable connection method for a photovoltaic power station of the present invention.

[0037] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0038] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0039] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of the operating equipment of the hardware operating environment involved in the embodiment of the present invention.

[0040] like Figure 1 As shown, the operating device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may optionally include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0041] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the operating device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0042] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module and a computer program.

[0043] exist Figure 1In the operating device shown, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the operating device of the present invention can be set in the operating device, and the operating device calls the computer program stored in the memory 1005 through the processor 1001 and performs the following operations:

[0044] Arrange and combine photovoltaic modules and inverters of the photovoltaic power station to obtain a string set, and divide the string set to obtain a plurality of complement sequences;

[0045] Inputting the positions of the photovoltaic modules in the complement sequence into a preset meta-model, and solving the complement sequence with a preset objective function to obtain a target solution;

[0046] Among all the target solutions, the cable distances from the photovoltaic components in the string set to the inverter are determined, and the photovoltaic power station cables are connected using a cable connection sequence with the shortest cable distance.

[0047] Furthermore, the processor 1001 may call a computer program stored in the memory 1005 and perform the following operations:

[0048] The step of arranging and combining photovoltaic modules and inverters of the photovoltaic power station to obtain a string set includes:

[0049] Obtaining a first number of photovoltaic modules, a second number of inverters, and a third number of photovoltaic modules in a string in a photovoltaic power station;

[0050] A string set is obtained by performing permutations and combinations according to the first quantity, the second quantity and / or the third quantity.

[0051] Furthermore, the processor 1001 may call a computer program stored in the memory 1005 and perform the following operations:

[0052] The step of obtaining a string set by permuting and combining the first quantity, the second quantity, and / or the third quantity includes:

[0053] If the third number of each string is the same, then the internal arrangement and combination of each photovoltaic module in the string is performed;

[0054] If the third quantities of the strings are different, external arrangement and combination of the strings are performed, and then internal arrangement and combination of the photovoltaic modules in the strings are performed.

[0055] Furthermore, the processor 1001 may call a computer program stored in the memory 1005 and perform the following operations:

[0056] The step of obtaining a string set by permuting and combining the first quantity, the second quantity and / or the third quantity further includes:

[0057] If it is a single inverter, a string set is obtained by performing permutations and combinations according to the first quantity and the second quantity;

[0058] If there are multiple inverters, a string set is obtained by permuting and combining the first quantity, the second quantity, and the third quantity.

[0059] Furthermore, the processor 1001 may call a computer program stored in the memory 1005 and perform the following operations:

[0060] Before the step of dividing the group string set to obtain a plurality of complement sequences, the method further includes:

[0061] A first position of a photovoltaic component in a photovoltaic power station is obtained, and a first distance weight set from any photovoltaic component to other photovoltaic components is determined based on the first position.

[0062] Furthermore, the processor 1001 may call a computer program stored in the memory 1005 and perform the following operations:

[0063] The step of dividing the group string set to obtain a plurality of complement sequences includes:

[0064] The group string set is divided according to the first distance weight set to obtain a plurality of complement sequences.

[0065] Furthermore, the processor 1001 may call a computer program stored in the memory 1005 and perform the following operations:

[0066] Before the step of solving the target solution of the complement sequence by using the preset objective function, the method further includes:

[0067] A second position of an inverter in the photovoltaic power station is obtained, and a second distance weight set from any photovoltaic component to the inverter is determined according to the second position.

[0068] Furthermore, the processor 1001 may call a computer program stored in the memory 1005 and perform the following operations:

[0069] The step of solving the target solution of the complement sequence by using the preset objective function includes:

[0070] According to the objective function of minimizing the jumper length between strings in the string set and minimizing the second distance weight set, the target solution of the current complement sequence is obtained.

[0071] Furthermore, the processor 1001 may call a computer program stored in the memory 1005 and perform the following operations:

[0072] Before the step of inputting the positions of the photovoltaic components in the complement sequence into the preset meta-model, the method further includes:

[0073] A preset meta-model based on a pointer network is trained according to the positions of the photovoltaic components in the complement sequence.

[0074] Furthermore, the processor 1001 may call a computer program stored in the memory 1005 and perform the following operations:

[0075] The step of determining the cable distances between the photovoltaic components in the string set and the inverter among all the target solutions, and performing cable connection of the photovoltaic power station using a cable connection sequence with the shortest cable distance, includes:

[0076] Merging the target solutions of all the complement sequences to obtain an optimal string set;

[0077] A cable connection sequence with a minimum distance to the inverter is solved in the optimal string set, and the cable connection sequence with the minimum distance is used as the final solution of the string set, that is, the optimal cable connection sequence of the photovoltaic power station.

[0078] The embodiment of the present invention provides a method for connecting cables in a photovoltaic power station. Figure 2 , Figure 2 The figure is a flow chart of an embodiment of a cable connection method for a photovoltaic power station according to the present invention.

[0079] In this embodiment, the cable connection method of the photovoltaic power station includes:

[0080] Step S10: arranging and combining photovoltaic modules and inverters of the photovoltaic power station to obtain a string set, and dividing the string set to obtain a plurality of complement sequences.

[0081] Step S20: inputting the positions of the photovoltaic modules in the complement sequence into a preset meta-model, and solving the complement sequence with a preset objective function to obtain a target solution.

[0082] Step S30: determining the cable distances from the photovoltaic components in the string set to the inverter in all the target solutions, and performing cable connection of the photovoltaic power station using a cable connection sequence with the shortest cable distance.

[0083] Assume that a photovoltaic power station requires a total of N = 200 modules with a power generation capacity of W = 450W. It also requires one inverter of model W1 = 50kW and one inverter of model W2 = 40kW. The 50kW inverter is assigned 100 modules, and the 40kW inverter is also assigned 100 modules. The location coordinates of the inverters are known, P. The resulting set of strings is: N = N1 + N2. Assume that N1 = [n11 = 20, n12 = 20, n13 = 20, n14 = 20, n15 = 20],

[0084] N2=[n21=20, n22=20, n23=20, n24=20, n25=20].

[0085] Partitioning the two string sets N1 and N2 yields multiple complement sequences. If there is only one inverter, assume Nj = [nj1, nj2, nj3, nj4, nj5], selecting N(j1) components from Nj. The second partitioning involves selecting N(j2) components from NN(j1), and so on. The final complement sequence is to select N(jm) components from NN(j1)-N(j2)…-N(jm-1).

[0086] A preset meta-model is trained using policy gradient optimization learning based on a pointer network. This preset meta-model can be applied to any of the above-mentioned complement sequences of N(i), thereby solving the target solution of the multi-objective problem (N1, N2) in the complement sequence using the preset objective function.

[0087] If multiple inverters are used, the target solution is divided into multiple strings according to Nj = [nj1, nj2, nj3, nj4, nj5], and the minimum value is selected as the final target solution. If a single inverter is used, the solution with the lowest sum of all cable costs among the target solutions is selected as the final target solution. That is, among all target solutions, the cable distance from the PV modules in the string set to the inverter is determined, and the cable connection sequence with the minimum cable distance is regarded as the optimal cable connection sequence for the PV power station cable connection.

[0088] In this embodiment, the photovoltaic components and inverters of the photovoltaic power station are arranged and combined to obtain a string set, and the string set is divided to obtain a plurality of complement sequences; the positions of the photovoltaic components in the complement sequence are input into a preset meta-model, and a target solution of the complement sequence is obtained by solving a preset objective function; among all the target solutions, the cable distance from the photovoltaic components in the string set to the inverter is determined, and the photovoltaic power station cables are connected using the cable connection sequence with the smallest cable distance.

[0089] In this embodiment, a method is provided for discretizing possible inverter position points based on the known number of allocated inverters and the number of inverter strings connected in series and parallel, and then performing optimal division of string lines for the discretized lower wall point positions, and performing statistical calculations on the distances and number of jumpers after the string line divisions, and obtaining the cable under the inverter position with the shortest distance in the minimum value set as the final result after optimization.

[0090] Reinforcement learning can be used to obtain a faster, more efficient, and more universal string and cable arrangement for any power station, thus avoiding the problem of manual string and cable arrangement resulting in non-shortest distance from PV panels to inverters, non-lowest cable costs, and jumper wires within the string cables. A reasonable string and cable arrangement method can be used to save cable costs and manpower, thereby achieving higher economic value.

[0091] Optionally, the step of arranging and combining photovoltaic modules and inverters of the photovoltaic power station to obtain a string set includes:

[0092] Obtaining a first number of photovoltaic modules, a second number of inverters, and a third number of photovoltaic modules in a string in a photovoltaic power station;

[0093] A string set is obtained by performing permutations and combinations according to the first quantity, the second quantity and / or the third quantity.

[0094] Optionally, the step of obtaining a string set by performing permutations and combinations according to the first quantity, the second quantity and / or the third quantity includes:

[0095] If the third number of each string is the same, then the internal arrangement and combination of each photovoltaic module in the string is performed;

[0096] If the third quantities of the strings are different, external arrangement and combination of the strings are performed, and then internal arrangement and combination of the photovoltaic modules in the strings are performed.

[0097] Optionally, the step of obtaining a string set by permuting and combining the first quantity, the second quantity and / or the third quantity further includes:

[0098] If it is a single inverter, a string set is obtained by performing permutations and combinations according to the first quantity and the second quantity;

[0099] If there are multiple inverters, a string set is obtained by permuting and combining the first quantity, the second quantity, and the third quantity.

[0100] In this embodiment, assuming the assigned module model W is known, the power plant requires a total of N = N(i) + N(j) modules. The recommended inverters are W(i) and W(j). The module resources allocated to W(i) are N(i), and the module strings are divided into N(i) = [N(i1), N(i2), ..., N(im)]. The module resources allocated to W(j) are N(j), and the module strings are divided into N(j) = [N(j1), N(j2), ..., N(j1)]. Therefore, the total number of combined strings is N' = [N(i1), N(i2), ..., N(im), N(j1), N(j2), ..., N(j1)]. The fixed position coordinates of the two inverters are P1(x1, y1) and P2(x2, y2).

[0101] If the number of components in each string is the same, the permutations and combinations of the components within each string are performed. If the number of components in each string is different, the string positions are first permuted, and then the components within each string are permuted. If the number of components in each string is different, the strings are first permuted and combined; if they are the same, the components within the strings are permuted and combined.

[0102] Since the number of strings in N' may be the same or different, we can arrange and combine them according to the number of strings, and obtain multiple different sequences from any component and any number of strings. For a single inverter, N^ = [N(j1), N(j2), ..., N(jl)]. For multiple inverters, N^ = N(1) + ... + N(i), where N(i) = [N(i1), N(i2), ..., N(im)].

[0103] Optionally, before the step of dividing the group string set to obtain a plurality of complement sequences, the step further includes:

[0104] A first position of a photovoltaic component in a photovoltaic power station is obtained, and a first distance weight set from any photovoltaic component to other photovoltaic components is determined based on the first position.

[0105] Optionally, the step of dividing the group string set to obtain a plurality of complement sequences includes:

[0106] The group string set is divided according to the first distance weight set to obtain a plurality of complement sequences.

[0107] Optionally, before the step of solving the target solution of the complement sequence using a preset objective function, the method further includes:

[0108] A second position of an inverter in the photovoltaic power station is obtained, and a second distance weight set from any photovoltaic component to the inverter is determined according to the second position.

[0109] Optionally, the step of obtaining a target solution of the complement sequence by solving a preset objective function includes:

[0110] According to the objective function of minimizing the jumper length between strings in the string set and minimizing the second distance weight set, the target solution of the current complement sequence is obtained.

[0111] In this embodiment, assuming that the coordinate positions of N photovoltaic modules are known, first, for each of the N photovoltaic modules, a distance weight set L1 from any photovoltaic module to the remaining photovoltaic modules is obtained. Then, based on the fixed inverter position, a distance weight set L2 from all photovoltaic modules to the inverter position is calculated.

[0112] Next, different complement sequences are created based on the distance weight set L1 between PV modules and the string set. Assuming one of the string sets is N^ = [N(j1), N(j2), ..., N(j1), N(i1), N(i2), ... N(im)], then the first complement sequence is created by selecting N(j1) PV modules from N^ according to L1. The second complement sequence is created by selecting N(j2) PV modules from NN(j1) according to the same L1 principle. And so on. The final complement sequence is created by selecting N(im) PV modules from NN(j1) - N(j2) ... - N(im-1).

[0113] Then, refer to Figure 3 , Figure 3 This diagram illustrates the policy gradient optimization training based on a pointer network for one embodiment of a cable connection method for a photovoltaic power station. Assuming all photovoltaic modules in N(j1) are input as q1, q2, q3, …, qN(j1), the optimized solution is qN, q5, …, q1. Similarly, the remaining complement sequences will also yield the target solution. Finally, these target solutions are combined to form the optimal string set.

[0114] Optionally, before the step of inputting the positions of the photovoltaic components in the complement sequence into a preset meta-model, the method further includes:

[0115] A preset meta-model based on a pointer network is trained according to the positions of the photovoltaic components in the complement sequence.

[0116] A preset meta-model is trained using policy gradient optimization learning based on a pointer network. This preset meta-model can be applied to the string sequence of the positions of photovoltaic modules in any of the above-mentioned complement sequences of N(j1), thereby obtaining the target solution to the multi-objective problem. That is, the shortest jumper between strings and the L2 principle are used as the objective function. Based on the shortest jumper between each string in the string set and the minimum second distance weight set as the objective function, the target solution of the current complement sequence is obtained.

[0117] Optionally, the step of determining the cable distances from the photovoltaic components in the string set to the inverter among all the target solutions, and performing cable connection of the photovoltaic power station using a cable connection sequence with the shortest cable distance includes:

[0118] Merging the target solutions of all the complement sequences to obtain an optimal string set;

[0119] A cable connection sequence with a minimum distance to the inverter is solved in the optimal string set, and the cable connection sequence with the minimum distance is used as the final solution of the string set, that is, the optimal cable connection sequence of the photovoltaic power station.

[0120] If it is a single inverter, then all merged target solutions are screened, and the solution with the shortest distance to the inverter among the target solutions is obtained as the final solution and the optimal cable connection sequence for the PV power station.

[0121] If there are multiple inverters,

[0122] The sequence of N^=N(1)+…+N(i), N(i)=[N(i1),N(i2),..N(im)] is divided into multiple groups in a fine-grained manner. The minimum solution is obtained from the result set according to the L2 principle as the target solution of the current inverter N(i). At the same time, all the merged target solutions are screened, and the solution with the minimum distance to the inverter among the target solutions is obtained as the final solution and the optimal cable connection sequence for the photovoltaic power station.

[0123] In summary, this embodiment provides a cable connection method for a photovoltaic power station, which includes the following steps:

[0124] Obtaining a first position of a photovoltaic component and a second position of an inverter in a photovoltaic power station;

[0125] Determine a first distance weight set from any photovoltaic component to other photovoltaic components and a second distance weight set from any photovoltaic component to an inverter according to the first position and the second position;

[0126] Obtaining a first number of photovoltaic modules and a second number of inverters in a photovoltaic power station;

[0127] Performing permutations and combinations according to the first quantity and the second quantity to obtain a string set;

[0128] Divide the group string set according to the first distance weight set to obtain a plurality of complement sequences;

[0129] Inputting the positions of the photovoltaic modules in the complement sequence into a preset meta-model, taking the shortest jumper between strings and the minimum second distance weight set as the objective function, and obtaining the target solution of the current complement sequence;

[0130] Merging the target solutions of all the complement sequences to obtain an optimal string set;

[0131] A cable connection sequence with a minimum distance to the inverter is solved in the optimal string set, and the cable connection sequence with the minimum distance is used as the final solution of the string set, that is, the optimal cable connection sequence of the photovoltaic power station.

[0132] In addition, an embodiment of the present invention also provides a cable connection optimization device for a photovoltaic power station, wherein the cable connection optimization device for a photovoltaic power station includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor. When the computer program is executed by the processor, the steps of the cable connection method for the photovoltaic power station as described above are implemented.

[0133] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0134] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0135] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0136] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A cable connection method for a photovoltaic power station, characterized in that: The cable connection method of the photovoltaic power station comprises the following steps: Arrange and combine photovoltaic modules and inverters of a photovoltaic power station to obtain a string set, wherein the inverter is in a fixed position, obtain a first position of the photovoltaic modules in the photovoltaic power station, determine a first distance weight set from any photovoltaic module to other photovoltaic modules based on the first position, and divide the string set based on the first distance weight set to obtain multiple complement sequences; Inputting the positions of the photovoltaic components in the complement sequence into a preset meta-model, and solving the preset objective function to obtain a target solution for the complement sequence, wherein a second position of the inverter in the photovoltaic power station is obtained, and a second distance weight set from any photovoltaic component to the inverter is determined based on the second position; and obtaining the target solution for the current complement sequence based on the objective function of minimizing the jumper wire between each string in the string set and minimizing the second distance weight set; Among all the target solutions, the cable distances from the photovoltaic components in the string set to the inverter are determined, and the photovoltaic power station cables are connected using a cable connection sequence with the shortest cable distance.

2. The cable connection method for a photovoltaic power station according to claim 1, wherein: The step of arranging and combining photovoltaic modules and inverters of the photovoltaic power station to obtain a string set includes: Obtaining a first number of photovoltaic modules, a second number of inverters, and a third number of photovoltaic modules in a string in a photovoltaic power station; A string set is obtained by performing permutations and combinations according to the first quantity, the second quantity and / or the third quantity.

3. The cable connection method for a photovoltaic power station according to claim 2, wherein: The step of obtaining a string set by permuting and combining the first quantity, the second quantity, and / or the third quantity includes: If the third number of each string is the same, then the internal arrangement and combination of each photovoltaic module in the string is performed; If the third quantities of the strings are different, external arrangement and combination of the strings are performed, and then internal arrangement and combination of the photovoltaic modules in the strings are performed.

4. The cable connection method for a photovoltaic power station according to claim 3, wherein: The step of obtaining a string set by permuting and combining the first quantity, the second quantity and / or the third quantity further includes: If it is a single inverter, a string set is obtained by performing permutations and combinations according to the first quantity and the second quantity; If there are multiple inverters, a string set is obtained by permuting and combining the first quantity, the second quantity, and the third quantity.

5. The cable connection method for a photovoltaic power station according to claim 1, wherein: Before the step of inputting the positions of the photovoltaic components in the complement sequence into the preset meta-model, the method further includes: A preset meta-model based on a pointer network is trained according to the positions of the photovoltaic components in the complement sequence.

6. The cable connection method for a photovoltaic power station according to claim 1, wherein: The step of determining the cable distances between the photovoltaic components in the string set and the inverter among all the target solutions, and performing cable connection of the photovoltaic power station using a cable connection sequence with the shortest cable distance, includes: Merging the target solutions of all the complement sequences to obtain an optimal string set; A cable connection sequence with a minimum distance to the inverter is solved in the optimal string set, and the cable connection sequence with the minimum distance is used as the final solution of the string set, that is, the optimal cable connection sequence of the photovoltaic power station.

7. A cable connection optimization device for a photovoltaic power station, characterized in that: The cable connection optimization device for a photovoltaic power station includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the cable connection method for a photovoltaic power station according to any one of claims 1 to 6.

Images