Method, System, Terminal and Medium for Salt Field Evaporation Calculation Based on Hybrid Strategy SNS

Abstract

The present invention discloses a method, system, terminal and medium for salt field evaporation calculation based on a hybrid strategy SNS, including: initializing HSNS and objective function parameters; initializing a user group based on an improved Circle chaotic map; calculating the objective function values of the viewpoints held by each user in the user group to obtain the objective function values of each user; randomly selecting a decision model based on the viewpoints held by each user and updating the viewpoints of each user; generating a new user group based on the updated user group and improved lens imaging learning; updating the global optimal positions of the users in the new user group based on a simulated annealing mechanism; comparing whether the difference between the updated optimal position and the previous optimal position meets the set requirements, or whether the number of iterations reaches the maximum value until the conditions are met. The present invention can effectively improve the search efficiency of the algorithm, improve the optimization speed of the algorithm, increase the algorithm efficiency; increase the probability that the algorithm jumps out of the local optimum and finds the global optimum.

Description

Technical Field

[0001] The present invention belongs to the field of evaporation calculation in salt fields, and relates to a salt field evaporation calculation method, system, terminal and medium based on a hybrid strategy SNS. Background Art

[0002] The evaporation model needs to calculate the fresh water evaporation amount with or without photovoltaic panel shading during a period by inputting the geometric parameters of the photovoltaic panel, the location of the salt field, and meteorological data (solar radiation, wind speed, ambient temperature, relative humidity) for a period of time.

[0003] The evaporation model can be numerically expressed as a system of non - linear equations. Currently, the methods for solving non - linear equations can generally be divided into two categories: traditional optimization algorithms and intelligent optimization algorithms.

[0004] Among them, the means of solving non - linear equations by traditional optimization algorithms is usually iteration based on gradient information. For example: Newton iteration method, quasi - Newton iteration method, conjugate gradient method, steepest descent method, etc. The most representative one is the Newton iteration method. However, with the increasing complexity of the equations to be processed nowadays, traditional algorithms have great limitations, such as being very sensitive to the initial value, being prone to falling into local convergence, having high requirements for functions (only applicable to differentiable functions), etc.

[0005] Intelligent optimization algorithm is a population - based optimization algorithm that can search simultaneously from multiple points and has implicit parallelism. Therefore, compared with traditional optimization algorithms, the dependence on the selection of the initial point is significantly reduced. At the same time, intelligent optimization algorithms have the characteristics of self - organization, self - adaptation, and self - learning, and are still applicable to non - differentiable non - linear equations, are not restricted by the problem state, have a wide solution range, and can effectively handle complex problems that are difficult to solve by traditional algorithms.

[0006] However, ordinary intelligent optimization algorithms cannot balance the convergence speed and calculation accuracy when dealing with complex problems. When the accuracy is too high, the convergence speed will slow down or even fail to converge. For example, the whale optimization algorithm and others will not be able to guarantee the solution accuracy when facing complex problems and cannot meet the requirements of the problems. Therefore, there is an urgent need for a method with a fast convergence speed and high calculation accuracy when dealing with complex problems. Summary of the Invention

[0007] The purpose of the present invention is to solve the problems in the prior art, and provide a salt field evaporation calculation method, system, terminal and medium based on a hybrid strategy SNS, which can effectively improve the search efficiency of the algorithm, improve the optimization speed of the algorithm, increase the algorithm efficiency; increase the probability of the algorithm jumping out of the local optimum and finding the global optimum.

[0008] To achieve the above - mentioned purpose, the present invention adopts the following technical solutions:

[0009] Salt field evaporation calculation method based on hybrid strategy SNS, including:

[0010] Step 1: Initialize HSNS and objective function parameters;

[0011] Step 2: Initialize the user group based on the improved Circle chaotic mapping;

[0012] Step 3: Based on the initialized HSNS and objective function parameters, calculate the objective function values of the viewpoints held by each user in the user group, and obtain the objective function values of each user;

[0013] Step 4: Based on the viewpoints held by each user, randomly select a decision model and update the viewpoints of each user;

[0014] Step 5: Judge whether the objective function value corresponding to the updated viewpoint of each user is greater than the objective function value in Step 3; if so, do not update; if not, update;

[0015] Step 6: Generate a new user group based on the updated user group and the improved lens imaging learning;

[0016] Step 7: Based on the simulated annealing mechanism, update the global optimal positions of the users in the new user group;

[0017] Step 8: Compare the difference between the updated optimal position and the previous optimal position, judge whether the difference meets the set requirements, or whether the number of iterations reaches the maximum value. If it meets, output the optimal result; otherwise, repeat Steps 3 to 7 until the conditions are met.

[0018] A further improvement of the present invention lies in:

[0019] HSNS and objective function parameters include: the number of users N of the HSNS algorithm, the maximum number of iterations maxIters, the maximum value UB and the minimum value LB of the user's original viewpoint vector, and the parameters required for objective function calculation;

[0020] The parameters required for objective function calculation include longitude, local time, solar declination, length of the photovoltaic panel, height of the photovoltaic panel from the sea level, spacing between photovoltaic panels, and tilt angle of the photovoltaic panel.

[0021] The improved mathematical model of the Circle chaotic mapping is shown in Formula (1):

[0022]

[0023] Among them, x is the solution and n is the dimension of the solution.

[0024] The objective function formula is shown in Formula (2):

[0025]

[0026] In the formula, T p represents the temperature of the photovoltaic panel, T s represents the water surface temperature, T p , T s is the target solution to be sought, f(T p , T s ) and g(T p , T s ) form a system of equations about T p , T s . is the objective function about T p , T s transformed from the system of equations.

[0027] Step 4 is specifically as follows:

[0028] The decision-making model includes imitation, communication, argument, and innovation;

[0029] The mathematical model of imitation is shown in formula (3):

[0030]

[0031] where X j represents the view vector of the jth user randomly selected, and i≠j; rand(0,1) and rand(-1,1) respectively represent two random vectors within the intervals [0,1] and [-1,1], and the random vectors have the same dimension as the solution vector;

[0032] The mathematical model of communication is shown in formula (4):

[0033]

[0034] where X j and X k both represent the view vectors of randomly selected users, D represents the cognitive difference between users, and sign represents the sign function, which determines the direction of cognitive change;

[0035] The mathematical model of argument is shown in formula (5):

[0036] X i new =X i +rand(0,1)×(M - AF×X i ) (5)

[0037]

[0038] AF = 1 + round(rand)

[0039] Among them, AF is the access factor, and its value is 1 or 2. round(rand) represents rounding the random number in the interval [0, 1]; M represents the summary of viewpoints in the discussion group, and N r is the size of the discussion group, which is a random number in the interval [1, N];

[0040] The innovative mathematical model is shown in formula (6):

[0041]

[0042] Among them, d represents the d-th variable randomly selected in the interval [1, D], D represents the dimension of the variable, and the dimension of the variables in the nonlinear equation system composed of n equations is also n; LB d and UB d represent the minimum value and the maximum value of the d-th variable respectively.

[0043] It also includes: the relationship between the user group and the objective function value: there are N individuals in the user group, each individual has its own viewpoint, the objective function is used to calculate the viewpoint of each user to obtain the objective function value, and each user has its own objective function value.

[0044] Specifically, step 6 is as follows:

[0045] Step 6-1: Perform a mutation operation on the updated user group, and the number of the mutated user group is 2N; the mutation formula is shown in formula (7):

[0046]

[0047] Among them, x′ j represents the value of the j-th dimension after the user undergoes mutation, a and b are the minimum value and the maximum value of the j-th dimension, is the value of the j-th dimension of the current user, t is the current iteration round, T is the maximum iteration round, and k is the scaling factor;

[0048] Step 6-2: Calculate the objective function value for the viewpoint of each user in the mutated user group;

[0049] Step 6-3: Sort the user group according to its objective function value;

[0050] Step 6-4: Select the optimal N users as the new user group to perform step 7.

[0051] Specifically, the simulated annealing mechanism in step 7 is as follows:

[0052] Step 7-1: Select the optimal user in the current iteration, and record its viewpoint vector as X b ;

[0053] Step 7-2: For Xb Perform a random update in Step 4, and denote the new opinion vector as X'. b ;

[0054] Step 7-3: Calculate their objective function values respectively, denoted as and Calculate the increment

[0055] Step 7-4: If then accept X'. b If then calculate If p ≥ rand(0,1), then accept X'. b Otherwise, do not accept X', b and keep X b ;

[0056] Step 7-5: Update the temperature T according to the formula T i+1 = αT i where i is the number of iteration rounds.

[0057] The salt field evaporation calculation system based on the hybrid strategy SNS includes:

[0058] The first initialization module is used to initialize HSNS and the objective function parameters;

[0059] The second initialization module initializes the user group based on the improved Circle chaotic mapping;

[0060] The objective function value acquisition module calculates the objective function values of the opinions held by each user in the user group based on the initialized HSNS and the objective function parameters, and obtains the objective function values of each user;

[0061] The opinion update module randomly selects a decision model based on the opinions held by each user and updates the opinions of each user;

[0062] The first judgment module is used to judge whether the objective function value corresponding to each updated user opinion is greater than the objective function value obtained by the objective function value acquisition module;

[0063] The user group update module generates a new user group based on the updated user group and the improved lens imaging learning;

[0064] The optimal position update module updates the global optimal position of the users in the new user group based on the simulated annealing mechanism;

[0065] A second judgment module, which is used to compare the difference between the updated optimal position and the previous optimal position, determine whether the difference meets the set requirements, or whether the number of iterations reaches the maximum value, until the optimal result is output.

[0066] A terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above method are implemented.

[0067] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0068] Compared with the prior art, the present invention has the following beneficial effects:

[0069] The present invention is based on a social network search algorithm improved by a hybrid strategy, which improves the solution efficiency of complex equations. The population is initialized based on chaotic mapping, making the initialization of the user group more uniform, effectively improving the search efficiency of the algorithm. In each round of iteration, an improved lens imaging learning is used to update the overall user group, and the order of first opposing mutation and then screening elites is adopted, removing bad individuals while retaining elite individuals, improving the optimization speed of the algorithm and increasing the algorithm efficiency. At the same time, a simulated annealing mechanism is adopted to perform a secondary update on the current optimal solution in each round of iteration, increasing the probability that the algorithm jumps out of the local optimum and finds the global optimum. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0071] Figure 1 It is a flowchart of the salt field evaporation calculation method based on the hybrid strategy SNS of the present invention;

[0072] Figure 2 It is a flowchart of the HSNS calculation of the present invention;

[0073] Figure 3 It is a mapping comparison diagram of the original Circle and the improved Circle; (a) is the mapping distribution diagram of the original Circle; (b) is the mapping distribution histogram of the original Circle; (c) is the mapping distribution diagram of the improved Circle; (d) is the mapping distribution histogram of the improved Circle;

[0074] Figure 4It is a schematic diagram for learning lens imaging;

[0075] Figure 5 It is a comparison diagram of the HSNS, SNS, WOA, ABC, PSO, and GWO algorithms under different examples; (a) is the solution comparison diagram of Example 1; (b) is the solution comparison diagram of Example 2; (c) is the solution comparison diagram of Example 3; (d) is the solution comparison diagram of Example 4;

[0076] Figure 6 It is the structural diagram of the salt field evaporation calculation system based on the hybrid strategy SNS of the present invention. Detailed implementation manners

[0077] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, rather than all, of the embodiments of the present invention. Generally, the components of the embodiments of the present invention described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations.

[0078] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0079] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0080] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper", "lower", "horizontal", "inner", etc. are used to indicate the orientation or positional relationship, it is based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship when the product of the present invention is placed habitually. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0081] In addition, if the term "horizontal" appears, it does not mean that the component is required to be absolutely horizontal, but it can be slightly inclined. For example, "horizontal" only means that its direction is more horizontal relative to "vertical", and does not mean that the structure must be completely horizontal, but it can be slightly inclined.

[0082] In the description of the embodiments of the present invention, it should also be noted that unless otherwise clearly specified and limited, if the terms "set", "install", "connected", "connected" are used, they should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0083] The following further describes the present invention in detail with reference to the accompanying drawings:

[0084] See Figure 1 and Figure 2 , the present invention discloses a method for calculating the evaporation of a salt field based on a hybrid strategy SNS, including:

[0085] S101: Initialize the HSNS and the parameters of the objective function.

[0086] The model parameters include: the number of users N of the HSNS algorithm, the maximum number of iterations maxIters, the maximum value UB and the minimum value LB of the original view vector of the users, and the parameters required for calculating the objective function;

[0087] The parameters required for calculating the objective function include longitude, local time, solar declination latitude, length of the photovoltaic panel, height of the photovoltaic panel from the sea level, spacing between the photovoltaic panels, and inclination angle of the photovoltaic panel.

[0088] S102: Initialize the user group based on the improved Circle chaotic map.

[0089] The mathematical model of the improved Circle chaotic map is shown in formula (1):

[0090]

[0091] Among them, x is the solution and n is the dimension of the solution.

[0092] S103: Based on the initialized HSNS and the parameters of the objective function, calculate the objective function value of the view held by each user in the user group, and obtain the objective function value of each user.

[0093] The objective function formula is shown in formula (2):

[0094]

[0095] In the formula, T p represents the temperature of the photovoltaic panel, T s represents the water surface temperature, T p , T s is the target solution to be obtained, f(Tp , T s ), and g(T p , T s ), form an equation system about T p , T s . is the objective function about T transformed from the equation system p , T s .

[0096] S104: Based on the opinions held by each user, randomly select a decision-making model and update the opinions of each user.

[0097] The decision-making models include imitation, communication, argument, and innovation;

[0098] Imitation means that in a social network, people usually learn and imitate the behaviors of other people they follow. The mathematical model of imitation is shown in formula (3):

[0099]

[0100] where X j represents the opinion vector of the randomly selected j-th user, and i ≠ j; rand(0,1) and rand(-1,1) respectively represent two random vectors within the intervals [0,1] and [-1,1], and the random vectors have the same dimension as the solution vector;

[0101] Communication means that in a social network, people can learn from each other through communication, increase their knowledge level, and finally obtain a new worldview, that is, a new user opinion. The mathematical model of communication is shown in formula (4):

[0102]

[0103] where X j and X k both represent the opinion vectors of randomly selected users, D represents the cognitive difference between users, and sign represents the sign function, which determines the direction of cognitive change;

[0104] Argument means that in a social network, users explain their views on things to others and defend their opinions. When arguing, it is usually carried out in groups. The mathematical model of argument is shown in formula (5):

[0105]

[0106] where AF is the access factor, and its value is 1 or 2. round(rand) represents rounding the random number in the interval [0, 1]; M represents the opinion summary in the discussion group, N rThe size of the discussion group is a random number in the interval [1, N];

[0107] Innovation means that in a social network, sometimes users will have a sudden inspiration and understand things more accurately from a more novel perspective. The innovation mathematical model is shown in formula (6):

[0108]

[0109] Among them, d represents the d-th variable randomly selected in the interval [1, D], D represents the dimension of the variable, and the dimension of the variables in the non-linear equation system composed of n equations is also n; LB d and UB d represent the minimum value and the maximum value of the d-th variable respectively.

[0110] S105: Determine whether the objective function value corresponding to each updated user's view is greater than the objective function value in S103; if so, do not update; if not, update.

[0111] S106: Generate a new user group based on the updated user group and the improved lens imaging learning.

[0112] The relationship between the user group and the objective function value: There are N individuals in the user group, each individual has its own view, and the objective function is used to calculate the view of each user to obtain the objective function value, and each user has its own objective function value.

[0113] Specifically, S106 is as follows:

[0114] S106-1: Perform a mutation operation on the updated user group, and the number of the user group after mutation is 2N; the mutation formula is shown in formula (7):

[0115]

[0116] Among them, x′ j represents the value of the j-th dimension after the user undergoes mutation, a and b are the minimum value and the maximum value of the j-th dimension, is the value of the j-th dimension of the current user, t is the current iteration round, T is the maximum iteration round, and k is the scaling factor;

[0117] S106-2: Calculate the objective function value for each user's view in the user group after mutation;

[0118] S106-3: Sort the user group according to its objective function value;

[0119] S106-4: Select the optimal N users as the new user group for S107.

[0120] S107: Update the globally optimal positions of the users in the new user group based on the simulated annealing mechanism.

[0121] S107-1: Select the optimal user in the current iteration, and denote its opinion vector as X b ;

[0122] S107-2: Conduct a random update on X b in Step 4, and denote its new opinion vector as X' b ;

[0123] S107-3: Calculate their objective function values respectively, denoted as and Calculate the increment

[0124] S107-4: If then accept X' b If then calculate If p≥rand(0,1), then accept X' b Otherwise, do not accept X' b and keep X b ;

[0125] S107-5: Update the temperature T according to the formula T i+1 = αT i where i is the number of iteration rounds.

[0126] S108: Compare the difference between the updated optimal position and the previous optimal position, and determine whether the difference meets the set requirements or whether the number of iterations reaches the maximum value. If it meets the requirements, output the optimal result; otherwise, repeat S103 to S107 until the conditions are met.

[0127] For the specific implementation of the present invention, it is called by the customer through the desktop client. Parameters will be passed in during the calling process, and the parameters include longitude, local time, solar declination, length of the photovoltaic panel, height of the photovoltaic panel from the sea level, distance between photovoltaic panels, tilt angle of the photovoltaic panel, wind speed, light intensity, environmental temperature, and relative humidity.

[0128] The client is written in JavaFx, integrated with Spring Boot, and the database is MySQL. The calculated data will be stored in the database. After the evaporation module calculation engine receives the parameters input by the user, it starts to perform calculations, and the calculation results are the temperatures of the photovoltaic panel and the sea surface, and finally the evaporation amount and evaporation rate are determined.

[0129] At the beginning of the HSNS calculation process, that is, when the user group is initialized, the population distribution is prone to uneven distribution due to random initialization. A certain area is too concentrated or dispersed, which will have a great impact on the subsequent search and optimization process, resulting in slow search speed, low efficiency, and even falling into local optimality. To solve the above problems, the Circle chaotic mapping is introduced when the population is initialized, which greatly improves the population distribution. Since the original Circle chaotic mapping is not effective and is prone to clustering in the interval [0.2, 0.4], an improved Circle chaotic mapping is proposed. Its mathematical model is shown in formula (8). Compared with the original Circle mapping, the constant term is removed and the quadratic term of the variable is added as a disturbance. The original Circle mapping distribution and the original Circle mapping distribution histogram are shown in the following figure. Figure 3 (a) and Figure 3 (b) shows; the improved Circle mapping distribution and histogram are shown in Figure 3 (c) and Figure 3 As shown in (d), the improved Circle chaotic map has a more uniform overall distribution and is more suitable for initializing the user group.

[0130]

[0131] In some cases, due to the lack of obvious differences in the overall distribution of the user group, there is a chance that the iteration will linger at a non-optimal solution, which will seriously increase the algorithm's search time and even lead to failure to converge. To solve the above problem, an improved lens imaging learning is used to update the overall user group. The principle of lens imaging learning is as follows: Figure 4 shown.

[0132] Taking one-dimensional space as an example, let the individual be x * , place a lens on the base point O (O is the midpoint of [a, b]), and the reverse point generated by the reverse learning strategy based on the lens imaging principle is x′, then Figure 4 You can get x * The relationship between and x′ is shown in formula (9):

[0133]

[0134] make k is called the scaling factor. By transforming formula (9), we can get the calculation formula of the reverse point, as shown in formula (10):

[0135]

[0136] Specifically, when k = 1, formula (10) is the calculation formula for standard reverse learning, indicating that there is no refraction at this time. k is affected by the properties of the lens itself, and different lenses exhibit different k values. The k value can be regarded as a parameter, whose role is to eliminate the monotonicity of the reverse learning for site calculation. Affected by the update strategy of the leader of the salp swarm algorithm, the update strategy of the k value is defined as shown in formula (11):

[0137]

[0138] In the formula, t is the current iteration round, and T is the maximum iteration round.

[0139] Generally, extending the improved lens imaging learning strategy shown in formula (10) to the D-dimensional space can obtain the expression shown in formula (12):

[0140]

[0141] where x′ j represents the value of the j-th dimension after the user undergoes mutation, a and b are the minimum and maximum values of the j-th dimension, is the value of the j-th dimension of the current user, t is the current iteration round, T is the maximum iteration round, and k is the scaling factor.

[0142] After each round of iteration is completed, all users have undergone an update. At this time, the entire user group is mutated based on formula (12), and the number of the user group changes from N to 2N. At this time, these 2N users are sorted according to the objective function value, and the optimal N of them are selected to form a new user group as the user group for the next iteration. After lens imaging learning, the overall quality of the user group has been greatly improved, which can save a lot of time.

[0143] Sometimes, after the i-th round of iteration, the optimal solution at this time is a local optimal solution, and there is a high probability that it cannot jump out of the range of the local optimal solution in subsequent iterations, resulting in the inability to search for the global optimal solution finally. To solve the above problems, a simulated annealing mechanism is introduced. After each round of iteration, the optimal solution of this round of iteration is updated twice based on simulated annealing, enabling it to accept a worse solution with a certain probability, increasing its chance of jumping out of the local optimum, and thus finding the global optimal solution.

[0144] The improved hybrid strategy social network search algorithm HSNS, the original social network search algorithm SNS, the whale optimization algorithm WOA, the artificial bee colony algorithm ABC, the particle swarm algorithm PSO, and the grey wolf optimization algorithm GWO are used to solve four nonlinear equations respectively. Among them, the dimension of example 4 is 4, the dimensions of the remaining examples are all 20, and the search space of example 3 is [-10, 10] 20 , and the search spaces of examples 1 and 2 are [-2, 2]20 The number of iterations is 1000 for all cases.

[0145] Example 1 considers the non - linear equations:

[0146] f i (x) = x i + sin|x i - 1| = 0, i = 1, 2, 3,..., n

[0147] Its root is x * = (-0.9346, -0.9346,..., -0.9346) T

[0148] Example 2 considers the non - linear equations:

[0149]

[0150] Its root is x * = (1, 1,..., 1) T

[0151] Example 3 considers the non - linear equations:

[0152]

[0153] The components of its root are symmetric, that is, the first dimension is equal to the n - th dimension, and the i - th dimension is equal to the (n - i + 1) - th dimension.

[0154] Example 4 considers the non - linear equations:

[0155]

[0156] Its root is x * = (*, *,.., 0) T , featuring that the last - dimension variable is 0.

[0157] Table 5 - 1 Algorithm running results

[0158]

[0159]

[0160]

[0161] It can be seen from the function convergence curves and experimental running results that the improved social network search algorithm performs excellently in solving non - linear equations. Compared with the original social network search algorithm and other intelligent optimization algorithms, it has certain advantages in optimization accuracy and convergence speed.

[0162] When applying the HSNS algorithm to solve the evaporation module, its running speed and accuracy also perform excellently among a series of optimization algorithms. The present invention innovatively proposes, based on the social network search algorithm, a hybrid strategy that adds chaotic mapping, improved lens imaging learning, simulated annealing mechanism, etc., and proposes the HSNS algorithm. It has been proven that when facing complex nonlinear equations, HSNS can be considered for solution.

[0163] See Figure 6 , the present invention discloses a salt field evaporation calculation system based on a hybrid strategy SNS, including:

[0164] A first initialization module, which is used to initialize the HSNS and target function parameters;

[0165] A second initialization module, which initializes the user group based on the improved Circle chaotic mapping;

[0166] A target function value acquisition module, which calculates the target function values of the viewpoints held by each user in the user group based on the initialized HSNS and target function parameters, and obtains the target function values of each user;

[0167] A viewpoint update module, which randomly selects a decision model based on the viewpoints held by each user and updates the viewpoints of each user;

[0168] A first judgment module, which is used to judge whether the target function value corresponding to each updated user's viewpoint is greater than the target function value obtained by the target function value acquisition module;

[0169] A user group update module, which generates a new user group based on the updated user group and improved lens imaging learning;

[0170] An optimal position update module, which updates the global optimal position of the users in the new user group based on the simulated annealing mechanism;

[0171] A second judgment module, which is used to compare the difference between the updated optimal position and the previous optimal position, judge whether the difference meets the set requirements, or whether the number of iterations reaches the maximum value, until the optimal result is output.

[0172] The terminal device provided by an embodiment of the present invention. The terminal device of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented.

[0173] The computer program can be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention.

[0174] The terminal device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory.

[0175] The processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0176] The memory can be used to store the computer program and / or modules, and the processor realizes various functions of the terminal device by running or executing the computer program and / or modules stored in the memory, and by invoking the data stored in the memory.

[0177] If the modules / units integrated in the terminal device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0178] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for calculating salt field evaporation based on a hybrid strategy SNS, characterized in that, Including: Step 1: Initialize the HSNS and objective function parameters; the HSNS and objective function parameters include: the number of users N of the HSNS algorithm, the maximum number of iterations maxIters, the maximum value UB and minimum value LB of the original view vectors of the users, and the parameters required for calculating the objective function; The parameters required for calculating the objective function include longitude, local time, solar declination latitude, length of the photovoltaic panel, height of the photovoltaic panel from sea level, spacing between photovoltaic panels, and tilt angle of the photovoltaic panel; Step 2: Initialize the user group based on the improved Circle chaotic mapping; the mathematical model of the improved Circle chaotic mapping is shown in formula (1): Where x is the solution and n is the dimension of the solution; The objective function formula is shown in formula (2): Where, T p represents the temperature of the photovoltaic panel, T s represents the water surface temperature, T p , T s is the target solution to be obtained, f(T p , T s ) and g(T p , T s ) form a system of equations regarding T p , T s , is the objective function regarding T p , T s transformed from the system of equations; Step 3: Based on the initialized HSNS and objective function parameters, calculate the objective function values of the views held by each user in the user group, and obtain the objective function values of each user; Step 4: Based on the views held by each user, randomly select a decision model to update the views of each user; specifically: The decision models include imitation, communication, argument, and innovation; The mathematical model of imitation is shown in formula (3): where, X j represents the opinion vector of the j-th randomly selected user, and i≠j; rand(0,1) and rand(-1,1) respectively represent two random vectors located in the intervals [0,1] and [-1,1], and the random vectors have the same dimension as the solution vector; The mathematical model of communication is shown in formula (4): Among them, X j and X k both represent randomly selected user opinion vectors, D represents the cognitive difference between users, and sign represents the sign function that determines the direction of cognitive change; The mathematical model of argument is shown in formula (5): Among them, AF is the admission factor, whose value is 1 or 2, round(rand) means rounding the random number in the interval [0, 1]; M means the summary of the opinions in the discussion group, N r is the size of the discussion group, which is a random number in the interval [1,N]; The mathematical model of innovation is shown in formula (6): Among them, d represents the d-th variable randomly selected within the interval [1, D], D represents the dimension of the variable, and the dimension of the variables in the non-linear equation system composed of n equations is also n; LB d and UB d represent the minimum value and the maximum value of the d-th variable respectively; Step 5: Determine whether the objective function value corresponding to each updated user view is greater than the objective function value in Step 3; if so, do not update; if not, update; Step 6: Generate a new user group based on the updated user group and the improved lens imaging learning; Step 7: Based on the simulated annealing mechanism, update the global optimal positions of the users in the new user group; Step 8: Compare the difference between the updated optimal position and the previous optimal position, and determine whether the difference meets the set requirements, or whether the number of iterations reaches the maximum value. If it meets the conditions, output the optimal result; otherwise, repeat Steps 3 to 7 until the conditions are met.

2. The method for calculating the evaporation of a salt field based on a hybrid strategy SNS according to claim 1, wherein, Also including: The relationship between the user group and the objective function value: There are N individuals in the user group, each individual has its own view, and the objective function is used to calculate the view of each user to obtain the objective function value, and each user has its own objective function value; The specific content of Step 6 is: Step 6-1: Perform a mutation operation on the updated user group, and the number of the mutated user group is 2N; the mutation formula is shown in formula (7): where x j ′ represents the value of the j-th dimension after the user's mutation, and a and b are the minimum and maximum values of the j-th dimension, is the value of the j-th dimension of the current user, t is the current iteration round, T is the maximum iteration round, and k is the scaling factor; Step 6-2: Calculate the objective function values of the views of each user in the mutated user group; Step 6-3: Sort the user group according to its objective function value; Step 6-4: Select the optimal N users as the new user group to perform Step 7.

3. The method for calculating the evaporation of a salt field based on a hybrid strategy SNS according to claim 1, characterized in that, The simulated annealing mechanism in Step 7 is specifically: Step 7-1: Select the optimal user in the current iteration, and denote its view vector as X b ; Step 7-2: Perform a random update on X b once as in Step 4, and denote its new view vector as X' b ; Step 7-3: Calculate their objective function values respectively, denoted as and Calculate the increment Step 7-4: If then accept X′ b , if then calculate If p≥rand(0,1), then accept X′ b , otherwise do not accept X′ b , and keep X b ; Step 7-5: According to the formula T i+1 =ɑT i update the temperature T, where i is the number of iteration rounds.

4. A salt field evaporation calculation system based on a hybrid strategy SNS, characterized in that, Based on the salt field evaporation calculation method based on the hybrid strategy SNS according to any one of claims 1-3, including: The first initialization module is used to initialize the HSNS and objective function parameters; The second initialization module initializes the user group based on the improved Circle chaotic mapping; Objective function value acquisition module, which calculates the objective function values of the opinions held by each user in the user group based on the initialized HSNS and objective function parameters, and obtains the objective function values of each user; Opinion update module, which randomly selects a decision model based on the opinions held by each user and updates the opinions of each user; First judgment module, which is used to judge whether the objective function value corresponding to the updated opinion of each user is greater than the objective function value obtained by the objective function value acquisition module; User group update module, which generates a new user group based on the updated user group and improved lens imaging learning; Optimal position update module, which updates the global optimal positions of the users in the new user group based on the simulated annealing mechanism; Second judgment module, which is used to compare the difference between the updated optimal position and the previous optimal position, judge whether the difference meets the set requirements, or whether the number of iterations reaches the maximum value until the optimal result is output.

5. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1-3.

Images