Power distribution network distributed photovoltaic bearing capacity scheme generation method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a power distribution network distributed photovoltaic bearing capacity scheme generation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of randomly generating a plurality of power distribution network distributed photovoltaic bearing capacity schemes based on a preset demand; optimizing the plurality of schemes through a chaotic mapping mechanism to obtain a plurality of initial schemes; iteratively optimizing the plurality of initial photovoltaic bearing capacity schemes based on the optimization constraint and the fitness function; each iteration comprises the steps of determining a target scheme and a target optimization mode of the current iteration, optimizing a plurality of previous schemes according to the target optimization mode, the target scheme and crossover and mutation operations to obtain a plurality of current schemes, and determining fitness values of the plurality of current schemes based on a fitness function; and determining the optimized distributed photovoltaic bearing capacity scheme of the power distribution network according to the fitness values of the plurality of schemes at the last time when the iteration is ended. By adopting the method, the distributed photovoltaic bearing capacity scheme of the power distribution network can be accurately generated.

Description

Technical Field

[0001] This application relates to the technical field of power systems, and in particular, to a method, device, computer device, computer-readable storage medium, and computer program product for generating a distributed photovoltaic carrying capacity scheme for a distribution network. Background Art

[0002] Driven by the "dual carbon" goal, distributed generation technologies represented by distributed photovoltaics have developed rapidly. When the grid-connected capacity of distributed photovoltaics is relatively large, the reverse power feeding to the distribution network brings serious problems to safe operation, especially the problems of node voltage over-limit and reverse overload of distribution transformers have a greater impact. Node voltage over-limit will cause over-voltage breakdown of the equipment of power supply users; reverse overload of distribution transformers is likely to cause overheating and damage of the transformers. At present, the reverse overload of distributed photovoltaic distribution transformers has become the main reason for the damage of distribution transformers, and it is also the biggest potential safety hazard for distributed photovoltaic grid connection. At the same time, the replacement and repair of distribution transformers bring greater economic losses to the distribution network. Therefore, the assessment of the distributed photovoltaic carrying capacity of medium-voltage distribution networks is of great significance for the stability of the node voltage of the distribution network and the safe operation of distribution transformers.

[0003] In recent years, analysis methods combining big data analysis and artificial intelligence technologies have gradually emerged. By using a large amount of distribution network operation data and real-time monitoring information, the impact of distributed photovoltaics on the distribution network can be evaluated more accurately. However, this method still needs to be further improved in terms of data processing difficulty, model generality, etc. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer device, computer-readable storage medium, and computer program product for generating a distributed photovoltaic carrying capacity scheme for a distribution network that can accurately generate a distributed photovoltaic carrying capacity scheme for a distribution network according to grid connection requirements.

[0005] In a first aspect, this application provides a method for generating a distributed photovoltaic carrying capacity scheme for a distribution network, including:

[0006] Based on a preset distributed photovoltaic grid connection requirement, randomly generate a plurality of distributed photovoltaic carrying capacity schemes for the distribution network; optimize the plurality of distributed photovoltaic carrying capacity schemes through a chaotic mapping method to obtain a plurality of initial photovoltaic carrying capacity schemes;

[0007] Establish optimization constraints and fitness functions, and iteratively optimize the multiple initial photovoltaic carrying capacity schemes based on the optimization constraints and the fitness functions; each iteration process includes: determining a target scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes in the previous iteration; determining the target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity schemes obtained in the previous iteration according to the target optimization method and the target scheme to obtain the multiple preliminary optimized photovoltaic carrying capacity schemes for the current iteration, optimizing the multiple preliminary optimized photovoltaic carrying capacity schemes through crossover and mutation operations to obtain the multiple photovoltaic carrying capacity schemes for the current iteration, and determining the fitness values of the multiple photovoltaic carrying capacity schemes for the current iteration based on the fitness function;

[0008] When the number of iterations reaches the first preset number, end the iterative optimization process, and determine the target photovoltaic carrying capacity scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes obtained in the last iteration; use the target photovoltaic carrying capacity scheme as the optimized distribution network distributed photovoltaic carrying capacity scheme.

[0009] In one embodiment, the method of optimizing the multiple photovoltaic carrying capacity schemes through chaos mapping to obtain multiple initial photovoltaic carrying capacity schemes includes:

[0010] Based on a preset control parameter and a preset chaos mapping mechanism, perform iterative operations on the multiple photovoltaic carrying capacity schemes for a second preset number of times, and use the multiple photovoltaic carrying capacity schemes generated in the last iteration as the multiple initial photovoltaic carrying capacity schemes.

[0011] In one embodiment, the method of determining the target optimization method for the current iteration through a preset selection strategy includes:

[0012] Randomly generate a probability value. If the probability value is less than the first preset value, generate a first random vector, and determine a first coefficient vector based on the first random vector and the adaptive weight of the current iteration; if the absolute value of the first coefficient vector is less than the second preset value, select the first preset method as the target optimization method for the current iteration.

[0013] In one embodiment, the method further includes:

[0014] If the absolute value of the first coefficient vector is not less than the second preset value, select the second preset method as the target optimization method for the current iteration; if the probability value is not less than the first preset value, select the third preset method as the target optimization method for the current iteration.

[0015] In one embodiment, the establishment of the optimization constraints includes:

[0016] Determine the power flow constraints of the distribution network, and determine the voltage deviation range, maximum penetration rate, maximum line current, and maximum reverse load rate of each distributed photovoltaic grid-connected node; use the power flow constraints, the voltage deviation range, the maximum penetration rate, the maximum line current, and the maximum reverse load rate as optimization constraints.

[0017] In one embodiment, the establishment of the fitness function includes:

[0018] Based on the preset distributed photovoltaic grid-connected demand, determine the number of distributed photovoltaic grid connections and the network loss of the distribution network; based on the number of distributed photovoltaic grid connections and the network loss, determine the objective function; based on the objective function, determine the fitness function.

[0019] In a second aspect, the present application also provides a device for generating a distributed photovoltaic carrying capacity plan for a distribution network, including:

[0020] An initialization module, configured to randomly generate multiple distributed photovoltaic carrying capacity plans for the distribution network based on the preset distributed photovoltaic grid-connected demand; optimize the multiple distributed photovoltaic carrying capacity plans through the method of chaotic mapping to obtain multiple initial photovoltaic carrying capacity plans;

[0021] An optimization module, configured to establish optimization constraints and a fitness function, and iteratively optimize the multiple initial photovoltaic carrying capacity plans based on the optimization constraints and the fitness function; each iteration process includes: determining a target plan according to the fitness values of the multiple photovoltaic carrying capacity plans in the previous iteration; determining the target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity plans obtained in the previous iteration according to the target optimization method and the target plan to obtain multiple initially optimized photovoltaic carrying capacity plans for the current iteration, optimizing the multiple initially optimized photovoltaic carrying capacity plans through crossover and mutation operations to obtain multiple photovoltaic carrying capacity plans for the current iteration, and determining the fitness values of the multiple photovoltaic carrying capacity plans for the current iteration based on the fitness function;

[0022] A generation module, configured to end the iterative optimization process when the number of iterations reaches a first preset number, and determine the target photovoltaic carrying capacity plan according to the fitness values of the multiple photovoltaic carrying capacity plans obtained in the last iteration; use the target photovoltaic carrying capacity plan as the optimized distributed photovoltaic carrying capacity plan for the distribution network.

[0023] In a third aspect, the present application also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0024] Based on the preset distributed photovoltaic grid connection requirements, randomly generate multiple distributed photovoltaic carrying capacity schemes for the distribution network; optimize the multiple distributed photovoltaic carrying capacity schemes for the distribution network in a chaotic mapping manner to obtain multiple initial photovoltaic carrying capacity schemes;

[0025] Establish optimization constraints and fitness functions, and iteratively optimize the multiple initial photovoltaic carrying capacity schemes based on the optimization constraints and the fitness functions; each iteration process includes: determining a target scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes in the previous iteration; determining the target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity schemes obtained in the previous iteration according to the target optimization method and the target scheme to obtain multiple initially optimized photovoltaic carrying capacity schemes for the current iteration, optimizing the multiple initially optimized photovoltaic carrying capacity schemes through crossover and mutation operations to obtain multiple photovoltaic carrying capacity schemes for the current iteration, and determining the fitness values of the multiple photovoltaic carrying capacity schemes for the current iteration based on the fitness function;

[0026] When the number of iterations reaches the first preset number, end the iterative optimization process, and determine the target photovoltaic carrying capacity scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes obtained in the last iteration; use the target photovoltaic carrying capacity scheme as the optimized distributed photovoltaic carrying capacity scheme for the distribution network.

[0027] Fourthly, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0028] Based on the preset distributed photovoltaic grid connection requirements, randomly generate multiple distributed photovoltaic carrying capacity schemes for the distribution network; optimize the multiple distributed photovoltaic carrying capacity schemes for the distribution network in a chaotic mapping manner to obtain multiple initial photovoltaic carrying capacity schemes;

[0029] Establish optimization constraints and fitness functions, and iteratively optimize the multiple initial photovoltaic carrying capacity schemes based on the optimization constraints and the fitness functions; each iteration process includes: determining a target scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes in the previous iteration; determining the target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity schemes obtained in the previous iteration according to the target optimization method and the target scheme to obtain multiple initially optimized photovoltaic carrying capacity schemes for the current iteration, optimizing the multiple initially optimized photovoltaic carrying capacity schemes through crossover and mutation operations to obtain multiple photovoltaic carrying capacity schemes for the current iteration, and determining the fitness values of the multiple photovoltaic carrying capacity schemes for the current iteration based on the fitness function;

[0030] When the number of iterations reaches the first preset number, end the iterative optimization process, and determine the target photovoltaic carrying capacity plan according to the fitness values of multiple photovoltaic carrying capacity plans obtained in the last iteration; use the target photovoltaic carrying capacity plan as the optimized distributed photovoltaic carrying capacity plan of the distribution network.

[0031] In a fifth aspect, the present application also provides a computer program product, including a computer program, which when executed by a processor implements the following steps:

[0032] Based on the preset distributed photovoltaic grid connection requirements, randomly generate multiple distributed photovoltaic carrying capacity plans for the distribution network; optimize the multiple distributed photovoltaic carrying capacity plans for the distribution network by means of chaotic mapping to obtain multiple initial photovoltaic carrying capacity plans;

[0033] Establish optimization constraints and a fitness function, and iteratively optimize the multiple initial photovoltaic carrying capacity plans based on the optimization constraints and the fitness function; each iteration process includes: determining a target plan according to the fitness values of the multiple photovoltaic carrying capacity plans in the previous iteration; determining the target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity plans obtained in the previous iteration according to the target optimization method and the target plan to obtain multiple preliminarily optimized photovoltaic carrying capacity plans for the current iteration, optimizing the multiple preliminarily optimized photovoltaic carrying capacity plans through crossover and mutation operations to obtain multiple photovoltaic carrying capacity plans for the current iteration, and determining the fitness values of the multiple photovoltaic carrying capacity plans for the current iteration based on the fitness function;

[0034] When the number of iterations reaches the first preset number, end the iterative optimization process, and determine the target photovoltaic carrying capacity plan according to the fitness values of multiple photovoltaic carrying capacity plans obtained in the last iteration; use the target photovoltaic carrying capacity plan as the optimized distributed photovoltaic carrying capacity plan of the distribution network.

[0035] The above method, device, computer equipment, computer-readable storage medium and computer program product for generating a distributed photovoltaic carrying capacity scheme of a distribution network randomly generate multiple distributed photovoltaic carrying capacity schemes of the distribution network based on a preset distributed photovoltaic grid connection requirement; optimize the multiple distributed photovoltaic carrying capacity schemes of the distribution network in a chaotic mapping manner to obtain multiple initial photovoltaic carrying capacity schemes; establish an optimization constraint and a fitness function, and iteratively optimize the multiple initial photovoltaic carrying capacity schemes based on the optimization constraint and the fitness function; each iteration process includes: determining a target scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes in the previous iteration; determining a target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity schemes obtained in the previous iteration according to the target optimization method and the target scheme to obtain multiple initially optimized photovoltaic carrying capacity schemes for the current iteration, optimizing the multiple initially optimized photovoltaic carrying capacity schemes through crossover and mutation operations to obtain multiple photovoltaic carrying capacity schemes for the current iteration, and determining the fitness values of the multiple photovoltaic carrying capacity schemes for the current iteration based on the fitness function; when the number of iterations reaches a first preset number, end the iterative optimization process, and determine a target photovoltaic carrying capacity scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes obtained in the last iteration; use the target photovoltaic carrying capacity scheme as the optimized distributed photovoltaic carrying capacity scheme of the distribution network. Using this method can accurately generate a distributed photovoltaic carrying capacity scheme of the distribution network according to the grid connection requirement. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0037] Figure 1 It is a schematic flowchart of a method for generating a distributed photovoltaic carrying capacity scheme of a distribution network in an embodiment;

[0038] Figure 2 It is a detailed flowchart of a method for generating a distributed photovoltaic carrying capacity scheme of a distribution network in an embodiment;

[0039] Figure 3 It is a structural block diagram of a device for generating a distributed photovoltaic carrying capacity scheme of a distribution network in another embodiment;

[0040] Figure 4 It is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] To make the objectives, technical solutions and advantages of this application more clear and understandable, the following further details this application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely used to explain this application and are not used to limit this application.

[0042] In one embodiment, as Figure 1 shown, a method for generating a distributed photovoltaic carrying capacity scheme for a distribution network is provided. In this embodiment, an example is given where this method is applied to a terminal. It can be understood that this method can also be applied to a server, or to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0043] Step 102, based on a preset distributed photovoltaic grid connection requirement, randomly generate multiple distributed photovoltaic carrying capacity schemes for the distribution network; optimize the multiple distributed photovoltaic carrying capacity schemes through a chaotic mapping method to obtain multiple initial photovoltaic carrying capacity schemes.

[0044] Optionally, the preset distributed photovoltaic grid connection requirement can be single-node distributed photovoltaic grid connection, multi-node distributed photovoltaic grid connection, and full-node distributed photovoltaic grid connection. Subsequently, an improved whale algorithm is selected to optimize the multiple randomly generated photovoltaic carrying capacity schemes, and each photovoltaic carrying capacity scheme is represented as a whale. The chaotic mapping is the Tent chaotic mapping mechanism.

[0045] Exemplarily, based on a preset distributed photovoltaic grid connection requirement, randomly generate multiple photovoltaic carrying capacity schemes. In the improved whale algorithm, each photovoltaic carrying capacity scheme is represented as a whale; optimize the multiple whales through the Tent chaotic mapping mechanism to obtain multiple initial whales.

[0046] Step 104, establish an optimization constraint and a fitness function, and iteratively optimize the multiple initial photovoltaic carrying capacity schemes based on the optimization constraint and the fitness function; each iteration process includes: determining a target scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes in the previous iteration; determining the target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity schemes obtained in the previous iteration according to the target optimization method and the target scheme to obtain multiple preliminarily optimized photovoltaic carrying capacity schemes for the current iteration, optimize the multiple preliminarily optimized photovoltaic carrying capacity schemes through crossover and mutation operations to obtain multiple photovoltaic carrying capacity schemes for the current iteration, and determine the fitness values of the multiple photovoltaic carrying capacity schemes for the current iteration based on the fitness function.

[0047] Among them, the target scheme corresponds to the prey in the improved whale optimization algorithm.

[0048] Optionally, the target optimization method can be the improved shrinking encirclement optimization, the improved random search optimization, or the improved spiral ascent optimization in the improved whale optimization algorithm.

[0049] Exemplarily, optimization constraints and a fitness function are established. Based on the optimization constraints and the fitness function, multiple initial whales are iteratively optimized. Each iteration process includes: taking the whale with the minimum fitness value among the multiple whales in the previous iteration as the prey; selecting, through a preset selection strategy, one of the improved shrinking encirclement optimization, the improved random search optimization, and the improved spiral ascent optimization as the target optimization method for the current iteration, and optimizing the multiple whales obtained in the previous iteration according to the target optimization method and the prey to obtain multiple preliminarily optimized whales in the current iteration, calculating the fitness values of the multiple preliminarily optimized whales, randomly pairing the multiple preliminarily optimized whales in pairs, taking the paired whales as the parent whales, and optimizing each pair of parent whales based on the fitness values of the multiple preliminarily optimized whales and crossover and mutation operations to obtain the multiple whales in the current iteration. The formula for the crossover operation is as follows:

[0050]

[0051] Where and represent the offspring whales generated by the parent whales; and represent two paired parent whales; represents a random number between the intervals [0, 1]. The formula for the mutation operation is as follows:

[0052]

[0053] Where represents the offspring generated by mutation; represents the current individual; represents the fitness of the individual; represents a random real number between the intervals [0, 1]; represents a random number that satisfies a uniform distribution between [lb - ub, ub - lb], where lb represents the lower bound of the interval where the individual is located, and ub represents the upper bound of the interval where the individual is located. Based on the fitness function, the fitness values of the multiple whales in the current iteration are determined.

[0054] Step 106, when the number of iterations reaches the first preset number, end the iterative optimization process, and determine the target photovoltaic carrying capacity plan according to the fitness values of the multiple photovoltaic carrying capacity plans obtained in the last iteration; take the target photovoltaic carrying capacity plan as the optimized distribution network distributed photovoltaic carrying capacity plan.

[0055] Optionally, the first preset number is the total number of iterative optimizations, which can be 500.

[0056] Exemplarily, when the number of iterations reaches 500 times, the iterative optimization process is terminated, and the whale with the lowest fitness value among the multiple whales obtained in the last iteration is used as the target whale; the target whale is used as the optimized whale, that is, the optimized photovoltaic carrying capacity scheme of the distribution network.

[0057] The above method, device, computer device, computer-readable storage medium, and computer program product for generating a photovoltaic carrying capacity scheme of a distribution network randomly generate multiple photovoltaic carrying capacity schemes of the distribution network based on a preset distributed photovoltaic grid connection requirement; optimize the multiple photovoltaic carrying capacity schemes of the distribution network by means of chaotic mapping to obtain multiple initial photovoltaic carrying capacity schemes; establish optimization constraints and a fitness function, and iteratively optimize the multiple initial photovoltaic carrying capacity schemes based on the optimization constraints and the fitness function; each iterative process includes: determining the target optimization method of the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity schemes obtained in the previous iteration according to the target optimization method to obtain multiple preliminary optimized photovoltaic carrying capacity schemes of the current iteration, and optimizing the multiple preliminary optimized photovoltaic carrying capacity schemes through crossover and mutation operations to obtain multiple photovoltaic carrying capacity schemes of the current iteration; when the number of iterations reaches a first preset number, the iterative optimization process is terminated, and the target photovoltaic carrying capacity scheme is determined according to the fitness values of the multiple photovoltaic carrying capacity schemes obtained in the last iteration; the target photovoltaic carrying capacity scheme is used as the optimized photovoltaic carrying capacity scheme of the distribution network. Using this method can accurately generate a photovoltaic carrying capacity scheme of a distribution network according to the grid connection requirement.

[0058] In an exemplary embodiment, the optimizing the multiple photovoltaic carrying capacity schemes by means of chaotic mapping to obtain multiple initial photovoltaic carrying capacity schemes includes:

[0059] Based on a preset control parameter and a preset chaotic mapping mechanism, iteratively optimize the multiple photovoltaic carrying capacity schemes for a second preset number of times, and use the multiple photovoltaic carrying capacity schemes generated in the last iteration as the multiple initial photovoltaic carrying capacity schemes.

[0060] Optionally, the second preset number of times can be 300 times.

[0061] Exemplarily, based on a preset control parameter and the Tent chaotic mapping mechanism, iteratively optimize multiple whales for 300 times, and the formula for iterative optimization is as follows:

[0062]

[0063] where is the whale at the nth iteration, that is, the photovoltaic carrying capacity scheme at the nth iteration; As a control parameter, its value range is between [0, 2]. After optimization, multiple initial whales are obtained, that is, multiple initial photovoltaic carrying capacity schemes.

[0064] In this embodiment, the chaotic mapping mechanism is used to optimize the multiple photovoltaic carrying capacity schemes generated by initialization, which can ensure the uniform distribution of the whale population in the entire solution space and improve the global optimization ability of the algorithm.

[0065] In an exemplary embodiment, determining the target optimization method for the current iteration through a preset selection strategy includes:

[0066] Randomly generate a probability value. If the probability value is less than the first preset value, generate a first random vector, and determine a first coefficient vector based on the first random vector and the adaptive weight of the current iteration; if the absolute value of the first coefficient vector is less than the second preset value, select the first preset method as the target optimization method for the current iteration.

[0067] Optionally, the first preset value can be 0.5, the second preset value can be 1, and the first preset method can be improved shrink and surround optimization.

[0068] Exemplarily, randomly generate a probability value p, where p is a random number in the interval [0, 1]. If the probability value p is less than 0.5, generate a first random vector , and based on the first random vector and the adaptive weight a of the current iteration, determine the first coefficient vector A; if the absolute value of the first coefficient vector is less than 1, select the improved shrink and surround optimization as the target optimization method for the current iteration. The formula for the improved shrink and surround optimization is:

[0069]

[0070] Among them, represents the whale of the previous iteration; represents the prey, is the number of the current iteration; and are the first coefficient vector and the second coefficient vector respectively; represents the adaptive inertia weight; and are the first random vector and the second random vector in the interval [0, 1]. The adaptive inertia weight has the following calculation formula:

[0071]

[0072] Among them, represents the number of the current iteration, and n represents the maximum number of iterations, that is, the first preset number of iterations. Represents a random number between the interval [0.5, 1].

[0073] In this embodiment, by performing improved shrinkage enclosure optimization on multiple photovoltaic bearing capacity schemes, a photovoltaic bearing capacity scheme with a greater bearing capacity can be obtained.

[0074] In an exemplary embodiment, the method further includes:

[0075] If the absolute value of the first coefficient vector is not less than a second preset value, then select the second preset method as the target optimization method for the current iteration; if the probability value is not less than a first preset value, then select the third preset method as the target optimization method for the current iteration.

[0076] Optionally, the second preset method can be improved random search optimization, and the third preset method can be improved spiral ascent optimization.

[0077] Exemplarily, if the absolute value of the first coefficient vector is not less than 1, then select improved random search optimization as the target optimization method for the current iteration; the formula for improved random search optimization is:

[0078]

[0079] where is a randomly selected whale. If the probability value p is not less than 0.5, then select improved spiral ascent optimization as the target optimization method for the current iteration; the formula for improved spiral ascent optimization is:

[0080]

[0081] where b is a constant; l is a random number between the interval [−1, 1]; p is a random number between the interval [0, 1].

[0082] In this embodiment, by performing improved random search optimization or improved spiral ascent optimization on multiple photovoltaic bearing capacity schemes, a photovoltaic bearing capacity scheme with a greater bearing capacity can be obtained.

[0083] In an exemplary embodiment, the establishment of the optimization constraints includes:

[0084] Determine the power flow constraints of the distribution network, determine the voltage deviation intervals, maximum penetration rates, maximum line currents, and maximum reverse load rates of each distributed photovoltaic grid connection node; use the power flow constraints, the voltage deviation intervals, the maximum penetration rates, the maximum line currents, and the maximum reverse load rates as optimization constraints.

[0085] Exemplarily, the power flow constraint formula of the distribution network is:

[0086]

[0087] Among them, and are the active power and reactive power flowing through node i; is the line reactance between node i + 1 and node i; is the line resistance between node i + 1 and node i; represents the active load at node i + 1; represents the reactive load at node i + 1; is the active power output of the distributed PV at node i + 1; is the reactive power output of the distributed PV at node i + 1. The voltage deviation range is:

[0088]

[0089] Among them, and are the voltage deviation rates, is the rated voltage of the node. The maximum penetration rate is:

[0090]

[0091] Among them, is the active power output of the distributed PV; is the active load of the system. The maximum line current limit is:

[0092]

[0093] Among them, is the current of the i-th line. The limit of the reverse load rate is:

[0094]

[0095] Among them, is the reverse load rate of the distribution transformer at node i. The above power flow constraints, voltage deviation range, maximum penetration rate, maximum line current, and maximum reverse load rate together constitute the optimization constraints.

[0096] In this embodiment, by establishing the optimization constraints, it can be ensured that while optimizing the distributed PV grid connection scheme, the system can operate stably.

[0097] In an exemplary embodiment, the establishment of the fitness function includes:

[0098] Based on the preset distributed photovoltaic grid connection requirements, determine the number of distributed photovoltaic grid connections and the network loss of the distribution network; based on the number of distributed photovoltaic grid connections and the network loss, determine the objective function; based on the objective function, determine the fitness function.

[0099] Exemplarily, based on the preset distributed photovoltaic grid connection requirements, determine the number of distributed photovoltaic grid connections and the network loss of the distribution network; based on the number of distributed photovoltaic grid connections and the network loss, determine the objective function; the formula of the objective function is as follows:

[0100]

[0101] Among them, is the number of distributed photovoltaic grid connections in the line, is the active power output of the distributed photovoltaic at node i, is the network loss of the distribution network, The formula of

[0102]

[0103]

[0104] Among them, is the set of system nodes, is the line current between nodes i and j, , are the active and reactive powers transmitted between nodes i and j, is the voltage of node i, is the resistance of line ij. Take the reciprocal of the objective function as the fitness function; the formula of the fitness function is:

[0105]

[0106] In this embodiment, by providing a fitness function, the advantages and disadvantages of each scheme can be accurately evaluated.

[0107] In an exemplary embodiment, as Figure 2 shown, a method for generating a distributed photovoltaic carrying capacity scheme for a distribution network includes: randomly generating a plurality of photovoltaic carrying capacity schemes based on the preset distributed photovoltaic grid connection requirements, and in the improved whale algorithm, each photovoltaic carrying capacity scheme is represented as a whale; based on the preset control parameters and Tent chaos mapping mechanism, perform 300 iterations of optimization on the plurality of whales, and the formula of the iterative optimization is as follows:

[0108]

[0109] Among them, is the whale of the nth iteration, that is, the photovoltaic carrying capacity scheme of the nth iteration; is the control parameter, and its value range is between [0, 2]. After optimization, multiple initial whales are obtained, that is, multiple initial photovoltaic carrying capacity schemes. An optimization constraint is established. The power flow constraint formula of the distribution network is:

[0110]

[0111] where, and are the active power and reactive power flowing through node i; is the line reactance between node i + 1 and node i; is the line resistance between node i + 1 and node i; represents the active load at node i + 1; represents the reactive load at node i + 1; is the active power output of the distributed photovoltaic at node i + 1; is the reactive power output of the distributed photovoltaic at node i + 1. The voltage deviation range is:

[0112]

[0113] where, and are the voltage deviation rates, is the rated voltage of the node. The maximum penetration rate is:

[0114]

[0115] where, is the active power output of the distributed photovoltaic; is the system active load. The maximum line current limit is:

[0116]

[0117] where, is the current of the ith line. The limit of the reverse load rate is:

[0118]

[0119] where, is the reverse load rate of the distribution transformer at node i. The above power flow constraint, voltage deviation range, maximum penetration rate, maximum line current and maximum reverse load rate jointly constitute the optimization constraint. Based on the preset grid connection requirements of the distributed photovoltaic, the number of distributed photovoltaics connected to the grid and the network loss of the distribution network are determined; based on the number of distributed photovoltaics connected to the grid and the network loss, the objective function is determined; the formula of the objective function is as follows:

[0120]

[0121] Among them, is the number of distributed photovoltaic grid connections in the line, is the active power output of the distributed photovoltaic at node i, is the network loss of the distribution network, The formula of

[0122]

[0123]

[0124] Among them, is the set of system nodes, is the line current between nodes i and j, , are the active and reactive powers transmitted between nodes i and j, is the voltage of node i, is the resistance of line ij. Take the reciprocal of the objective function as the fitness function; the formula of the fitness function is:

[0125]

[0126] Based on the optimization constraints and the fitness function, iteratively optimize multiple initial whales; each iteration process includes: taking the whale with the minimum fitness value among the multiple whales in the previous iteration as the prey. Randomly generate a probability value p, where p is a random number in the interval [0, 1]. If the probability value p is less than 0.5, then generate the first random vector , and determine the first coefficient vector A based on the first random vector and the adaptive weight a in the current iteration; if the absolute value of the first coefficient vector is less than 1, then select the improved shrinking encirclement optimization as the target optimization method for the current iteration. The formula of the improved shrinking encirclement optimization is:

[0127]

[0128] Among them, represents the whale in the previous iteration; represents the prey, is the number of the current iteration; and are the first coefficient vector and the second coefficient vector respectively; represents the adaptive inertia weight; and are the first random vector and the second random vector in the interval [0, 1]. The calculation formula of the adaptive inertia weight is as follows:

[0129]

[0130] Among them, represents the number of the current iteration, and n represents the maximum number of iterations, that is, the first preset number of iterations. represents a random number between the interval [0.5, 1]. If the absolute value of the first coefficient vector is not less than 1, then the improved random search optimization is selected as the target optimization method for the current iteration; the formula for the improved random search optimization is:

[0131]

[0132] Among them, is a randomly selected whale. If the probability value p is not less than 0.5, then the improved spiral ascent optimization is selected as the target optimization method for the current iteration; the formula for the improved spiral ascent optimization is:

[0133]

[0134] Among them, b is a constant; l is a random number between the interval [−1, 1]; p is a random number between the interval [0, 1]. According to the target optimization method and the prey, multiple whales obtained from the previous iteration are optimized to obtain multiple preliminary optimized whales for the current iteration, the fitness values of the multiple preliminary optimized whales are calculated, the multiple preliminary optimized whales are randomly paired pairwise, the paired whales are used as the parent whales, and each pair of parent whales is optimized based on the fitness values of the multiple preliminary optimized whales and the crossover and mutation operations to obtain multiple whales for the current iteration. The formula for the crossover operation is as follows:

[0135]

[0136] Among them, and represent the offspring whales generated by the parent whales; and represent two paired parent whales; represents a random number between the interval [0, 1]. The formula for the mutation operation is as follows:

[0137]

[0138] Among them, represents the offspring generated by the mutation; represents the current individual; represents the fitness of this individual; represents a random real number between the interval [0, 1]; Represents a random number that satisfies a uniform distribution within [lb - ub, ub - lb], where lb represents the lower bound of the interval where the individual is located, and ub represents the upper bound of the interval where the individual is located. Based on the fitness function, the fitness values of multiple whales in the current iteration are determined. When the number of iterations reaches 500 times, the iterative optimization process ends, and the whale with the lowest fitness value among the multiple whales obtained in the last iteration is taken as the target whale; the target whale is taken as the optimized whale, that is, the optimized distributed photovoltaic carrying capacity scheme of the distribution network.

[0139] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the indication of the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps does not have a strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages, and these steps or stages do not necessarily have to be executed at the same moment, but can be executed at different moments, and the execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0140] In an exemplary embodiment, as Figure 3 shown, a device for generating a distributed photovoltaic carrying capacity scheme for a distribution network is provided, including: an initialization module 301, an optimization module 302, and a generation module 303, where:

[0141] The initialization module is used to randomly generate multiple distributed photovoltaic carrying capacity schemes for the distribution network based on the preset distributed photovoltaic grid connection requirements; optimize the multiple distributed photovoltaic carrying capacity schemes through the method of chaotic mapping to obtain multiple initial photovoltaic carrying capacity schemes;

[0142] The optimization module is used to establish optimization constraints and a fitness function, and iteratively optimize the multiple initial photovoltaic carrying capacity schemes based on the optimization constraints and the fitness function; each iteration process includes: determining a target scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes in the previous iteration; determining the target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity schemes obtained in the previous iteration according to the target optimization method and the target scheme to obtain multiple initially optimized photovoltaic carrying capacity schemes in the current iteration, optimizing the multiple initially optimized photovoltaic carrying capacity schemes through crossover and mutation operations to obtain multiple photovoltaic carrying capacity schemes in the current iteration, and determining the fitness values of the multiple photovoltaic carrying capacity schemes in the current iteration based on the fitness function;

[0143] A generation module, configured to end the iterative optimization process when the number of iterations reaches a first preset number, and determine a target photovoltaic carrying capacity plan according to the fitness values of multiple photovoltaic carrying capacity plans obtained in the last iteration; and use the target photovoltaic carrying capacity plan as the optimized distributed photovoltaic carrying capacity plan of the distribution network.

[0144] In one embodiment, the initialization module is further configured to:

[0145] Based on a preset control parameter and a preset chaotic mapping mechanism, perform a second preset number of iterations on the multiple photovoltaic carrying capacity plans, and use the multiple photovoltaic carrying capacity plans generated in the last iteration as multiple initial photovoltaic carrying capacity plans.

[0146] In one embodiment, the optimization module is further configured to:

[0147] Randomly generate a probability value. If the probability value is less than a first preset value, generate a first random vector, and determine a first coefficient vector based on the first random vector and the adaptive weight of the current iteration; if the absolute value of the first coefficient vector is less than a second preset value, select a first preset method as the target optimization method for the current iteration.

[0148] In one embodiment, the optimization module is further configured to:

[0149] If the absolute value of the first coefficient vector is not less than the second preset value, select a second preset method as the target optimization method for the current iteration; if the probability value is not less than the first preset value, select a third preset method as the target optimization method for the current iteration.

[0150] In one embodiment, the optimization module is further configured to:

[0151] Determine the power flow constraint of the distribution network, and determine the voltage deviation range, maximum penetration rate, maximum line current, and maximum reverse load rate of each distributed photovoltaic grid connection node; use the power flow constraint, the voltage deviation range, the maximum penetration rate, the maximum line current, and the maximum reverse load rate as optimization constraints.

[0152] In one embodiment, the optimization module is further configured to:

[0153] Based on the preset distributed photovoltaic grid connection demand, determine the number of distributed photovoltaic grid connections and the network loss of the distribution network; based on the number of distributed photovoltaic grid connections and the network loss, determine an objective function; based on the objective function, determine a fitness function.

[0154] Each module in the above-mentioned device for generating a distributed photovoltaic carrying capacity scheme for a distribution network can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or stored in a memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0155] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structural diagram can be as Figure 4 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store a distributed photovoltaic carrying capacity scheme for a distribution network. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for generating a distributed photovoltaic carrying capacity scheme for a distribution network.

[0156] Those skilled in the art can understand that Figure 4 the structure shown in

[0157] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0158] Based on a preset distributed photovoltaic grid connection requirement, randomly generate multiple distributed photovoltaic carrying capacity schemes for a distribution network; in a chaotic mapping manner, optimize the multiple distributed photovoltaic carrying capacity schemes for a distribution network to obtain multiple initial photovoltaic carrying capacity schemes;

[0159] Establish optimization constraints and fitness functions, and iteratively optimize the multiple initial photovoltaic carrying capacity schemes based on the optimization constraints and the fitness functions; each iteration process includes: determining a target scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes in the previous iteration; determining the target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity schemes obtained in the previous iteration according to the target optimization method and the target scheme to obtain the multiple preliminary optimized photovoltaic carrying capacity schemes for the current iteration, optimizing the multiple preliminary optimized photovoltaic carrying capacity schemes through crossover and mutation operations to obtain the multiple photovoltaic carrying capacity schemes for the current iteration, and determining the fitness values of the multiple photovoltaic carrying capacity schemes for the current iteration based on the fitness function;

[0160] When the number of iterations reaches the first preset number, end the iterative optimization process, and determine the target photovoltaic carrying capacity scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes obtained in the last iteration; use the target photovoltaic carrying capacity scheme as the optimized distribution network distributed photovoltaic carrying capacity scheme.

[0161] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0162] Based on the preset control parameters and the preset chaotic mapping mechanism, perform iterative operations on the multiple photovoltaic carrying capacity schemes for the second preset number of times, and use the multiple photovoltaic carrying capacity schemes generated in the last iteration as the multiple initial photovoltaic carrying capacity schemes.

[0163] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0164] Randomly generate a probability value. If the probability value is less than the first preset value, generate a first random vector, and determine a first coefficient vector based on the first random vector and the adaptive weight of the current iteration; if the absolute value of the first coefficient vector is less than the second preset value, select the first preset method as the target optimization method for the current iteration.

[0165] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0166] If the absolute value of the first coefficient vector is not less than the second preset value, select the second preset method as the target optimization method for the current iteration; if the probability value is not less than the first preset value, select the third preset method as the target optimization method for the current iteration.

[0167] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0168] Determine the power flow constraints of the distribution network, and determine the voltage deviation range, maximum penetration rate, maximum line current, and maximum reverse load rate of each distributed photovoltaic grid-connected node; use the power flow constraints, the voltage deviation range, the maximum penetration rate, the maximum line current, and the maximum reverse load rate as optimization constraints.

[0169] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0170] Based on the preset distributed photovoltaic grid-connected requirements, determine the number of distributed photovoltaic grid connections and the network loss of the distribution network; based on the number of distributed photovoltaic grid connections and the network loss, determine the objective function; based on the objective function, determine the fitness function.

[0171] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0172] Based on the preset distributed photovoltaic grid-connected requirements, randomly generate multiple distribution network distributed photovoltaic carrying capacity schemes; optimize the multiple distribution network distributed photovoltaic carrying capacity schemes by means of chaotic mapping to obtain multiple initial photovoltaic carrying capacity schemes;

[0173] Establish optimization constraints and a fitness function, and iteratively optimize the multiple initial photovoltaic carrying capacity schemes based on the optimization constraints and the fitness function; each iteration process includes: determining a target scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes in the previous iteration; determining the target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity schemes obtained in the previous iteration according to the target optimization method and the target scheme to obtain multiple preliminary optimized photovoltaic carrying capacity schemes for the current iteration, optimizing the multiple preliminary optimized photovoltaic carrying capacity schemes through crossover and mutation operations to obtain multiple photovoltaic carrying capacity schemes for the current iteration, and determining the fitness values of the multiple photovoltaic carrying capacity schemes for the current iteration based on the fitness function;

[0174] When the number of iterations reaches the first preset number, end the iterative optimization process, and determine the target photovoltaic carrying capacity scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes obtained in the last iteration; use the target photovoltaic carrying capacity scheme as the optimized distribution network distributed photovoltaic carrying capacity scheme.

[0175] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0176] Based on the preset control parameters and the preset chaotic mapping mechanism, perform iterative operations on the multiple photovoltaic carrying capacity schemes for the second preset number of times, and use the multiple photovoltaic carrying capacity schemes generated in the last iteration as multiple initial photovoltaic carrying capacity schemes.

[0177] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0178] Randomly generate a probability value. If the probability value is less than a first preset value, generate a first random vector, and determine a first coefficient vector based on the first random vector and the adaptive weight of the current iteration; if the absolute value of the first coefficient vector is less than a second preset value, select a first preset method as the target optimization method for the current iteration.

[0179] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0180] If the absolute value of the first coefficient vector is not less than the second preset value, select a second preset method as the target optimization method for the current iteration; if the probability value is not less than the first preset value, select a third preset method as the target optimization method for the current iteration.

[0181] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0182] Determine the power flow constraints of the distribution network, and determine the voltage deviation range, maximum penetration rate, maximum line current, and maximum reverse load rate of each distributed photovoltaic grid-connected node; use the power flow constraints, the voltage deviation range, the maximum penetration rate, the maximum line current, and the maximum reverse load rate as optimization constraints.

[0183] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0184] Based on the preset distributed photovoltaic grid-connected demand, determine the number of distributed photovoltaics connected to the grid and the network loss of the distribution network; based on the number of distributed photovoltaics connected to the grid and the network loss, determine the objective function; based on the objective function, determine the fitness function.

[0185] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0186] Based on the preset distributed photovoltaic grid-connected demand, randomly generate multiple distribution network distributed photovoltaic carrying capacity schemes; optimize the multiple distribution network distributed photovoltaic carrying capacity schemes through the method of chaotic mapping to obtain multiple initial photovoltaic carrying capacity schemes;

[0187] Establish optimization constraints and fitness functions, and iteratively optimize the multiple initial photovoltaic carrying capacity schemes based on the optimization constraints and the fitness functions; Each iteration process includes: determining a target scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes in the previous iteration; determining the target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity schemes obtained in the previous iteration according to the target optimization method and the target scheme to obtain the multiple preliminary optimized photovoltaic carrying capacity schemes in the current iteration, optimizing the multiple preliminary optimized photovoltaic carrying capacity schemes through crossover and mutation operations to obtain the multiple photovoltaic carrying capacity schemes in the current iteration, and determining the fitness values of the multiple photovoltaic carrying capacity schemes in the current iteration based on the fitness function;

[0188] When the number of iterations reaches the first preset number, end the iterative optimization process, and determine the target photovoltaic carrying capacity scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes obtained in the last iteration; Take the target photovoltaic carrying capacity scheme as the optimized distribution network distributed photovoltaic carrying capacity scheme.

[0189] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0190] Based on a preset control parameter and a preset chaotic mapping mechanism, perform iterative operations on the multiple photovoltaic carrying capacity schemes for a second preset number of times, and take the multiple photovoltaic carrying capacity schemes generated in the last iteration as the multiple initial photovoltaic carrying capacity schemes.

[0191] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0192] Randomly generate a probability value. If the probability value is less than the first preset value, generate a first random vector, and determine a first coefficient vector based on the first random vector and the adaptive weight of the current iteration; If the absolute value of the first coefficient vector is less than the second preset value, select the first preset method as the target optimization method for the current iteration.

[0193] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0194] If the absolute value of the first coefficient vector is not less than the second preset value, select the second preset method as the target optimization method for the current iteration; If the probability value is not less than the first preset value, select the third preset method as the target optimization method for the current iteration.

[0195] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0196] Determine the power flow constraints of the distribution network, and determine the voltage deviation range, maximum penetration rate, maximum line current, and maximum reverse load rate of each distributed photovoltaic grid-connected node; use the power flow constraints, the voltage deviation range, the maximum penetration rate, the maximum line current, and the maximum reverse load rate as optimization constraints.

[0197] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0198] Based on the preset distributed photovoltaic grid connection requirements, determine the number of distributed photovoltaic grid connections and the network loss of the distribution network; based on the number of distributed photovoltaic grid connections and the network loss, determine the objective function; based on the objective function, determine the fitness function.

[0199] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, a database, or other media used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include Read-Only Memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, Resistive Random Access Memory (ReRAM), Magnetoresistive Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene memory, etc. Volatile memory can include Random Access Memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, Artificial Intelligence (AI) processors, etc., and are not limited thereto.

[0200] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present application.

[0201] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for generating a distributed photovoltaic carrying capacity scheme for a distribution network, characterized in that The method includes: Based on the preset distributed photovoltaic grid connection requirements, randomly generate multiple distributed photovoltaic carrying capacity schemes for the distribution network; optimize the multiple distributed photovoltaic carrying capacity schemes for the distribution network by means of chaotic mapping to obtain multiple initial photovoltaic carrying capacity schemes; Establish optimization constraints and a fitness function, and iteratively optimize the multiple initial photovoltaic carrying capacity schemes based on the optimization constraints and the fitness function; each iteration process includes: determining a target scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes in the previous iteration; determining the target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity schemes obtained in the previous iteration according to the target optimization method and the target scheme to obtain multiple preliminary optimized photovoltaic carrying capacity schemes for the current iteration, optimizing the multiple preliminary optimized photovoltaic carrying capacity schemes through crossover and mutation operations to obtain multiple photovoltaic carrying capacity schemes for the current iteration, and determining the fitness values of the multiple photovoltaic carrying capacity schemes for the current iteration based on the fitness function; When the number of iterations reaches the first preset number, end the iterative optimization process, and determine the target photovoltaic carrying capacity scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes obtained in the last iteration; use the target photovoltaic carrying capacity scheme as the optimized distributed photovoltaic carrying capacity scheme for the distribution network.

2. The method according to claim 1, wherein The step of optimizing the multiple photovoltaic carrying capacity schemes by means of chaotic mapping to obtain multiple initial photovoltaic carrying capacity schemes includes: Based on the preset control parameters and the preset chaotic mapping mechanism, perform iterative operations on the multiple photovoltaic carrying capacity schemes for the second preset number of times, and use the multiple photovoltaic carrying capacity schemes generated in the last iteration as the multiple initial photovoltaic carrying capacity schemes.

3. The method according to claim 1, wherein The step of determining the target optimization method for the current iteration through a preset selection strategy includes: Randomly generate a probability value. If the probability value is less than the first preset value, generate a first random vector, and determine a first coefficient vector based on the first random vector and the adaptive weight of the current iteration; If the absolute value of the first coefficient vector is less than the second preset value, select the first preset method as the target optimization method for the current iteration.

4. The method according to claim 3, wherein The method further includes: If the absolute value of the first coefficient vector is not less than the second preset value, select the second preset method as the target optimization method for the current iteration; If the probability value is not less than the first preset value, select the third preset method as the target optimization method for the current iteration.

5. The method according to claim 1, characterized in that The establishment of the optimization constraints includes: Determine the power flow constraints of the distribution network, and determine the voltage deviation range, maximum penetration rate, maximum line current, and maximum reverse load rate of each distributed photovoltaic grid connection node; Use the power flow constraints, the voltage deviation range, the maximum penetration rate, the maximum line current, and the maximum reverse load rate as the optimization constraints.

6. The method according to claim 1, wherein The establishment of the fitness function includes: Based on the preset distributed photovoltaic grid connection requirements, determine the number of distributed photovoltaic grid connections and the network loss of the distribution network; Based on the number of distributed photovoltaic grid connections and the network loss, determine the objective function; Based on the objective function, determine the fitness function.

7. A device for generating a distributed photovoltaic carrying capacity scheme for a distribution network, characterized in that, The device includes: An initialization module, configured to randomly generate multiple distribution network distributed photovoltaic carrying capacity schemes based on preset distributed photovoltaic grid connection requirements; optimize the multiple distribution network distributed photovoltaic carrying capacity schemes by means of chaotic mapping to obtain multiple initial photovoltaic carrying capacity schemes; An optimization module, configured to establish optimization constraints and a fitness function, and iteratively optimize the multiple initial photovoltaic carrying capacity schemes based on the optimization constraints and the fitness function; each iteration process includes: determining a target scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes in the previous iteration; determining a target optimization method for the current iteration through a preset selection strategy, and optimizing the multiple photovoltaic carrying capacity schemes obtained in the previous iteration according to the target optimization method and the target scheme to obtain multiple initially optimized photovoltaic carrying capacity schemes for the current iteration, optimizing the multiple initially optimized photovoltaic carrying capacity schemes through crossover and mutation operations to obtain multiple photovoltaic carrying capacity schemes for the current iteration, and determining the fitness values of the multiple photovoltaic carrying capacity schemes for the current iteration based on the fitness function; A generation module, configured to end the iterative optimization process when the number of iterations reaches a first preset number, and determine a target photovoltaic carrying capacity scheme according to the fitness values of the multiple photovoltaic carrying capacity schemes obtained in the last iteration; use the target photovoltaic carrying capacity scheme as the optimized distribution network distributed photovoltaic carrying capacity scheme.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images