A node position optimization method and device based on an ant colony optimization algorithm

Abstract

The application belongs to the technical field of wireless communication, and specifically discloses a node position optimization method and device based on an ant colony optimization algorithm, which comprises the following steps: setting ant colony optimization algorithm parameters, randomly generating an initial solution, and extending to generate a plurality of ants, wherein each ant respectively represents a different three-dimensional node layout vector; repeatedly performing an iteration process until a preset iteration number is reached; taking the three-dimensional node layout scheme corresponding to the optimal solution after iteration as an optimal node layout scheme, and optimizing the node position based on the optimal node layout scheme; the iteration process comprises the following steps: calculating the fitness of all current ants respectively; comparing the fitness of the ant with the lowest fitness with the original optimal solution, and taking the ant with lower fitness as the current optimal solution; calculating the pheromone intensity based on the fitness of all ants respectively to obtain pheromone distribution; updating the ant position based on the pheromone distribution and performing boundary constraint processing on the new ant position.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of wireless communication, and more particularly relates to a node position optimization method and device based on an ant colony optimization algorithm. BACKGROUND

[0002] In modern wireless communication systems (such as 5G / 6G communication, massive MIMO technology, etc.), the beamforming precision and sidelobe suppression capability of an antenna array have a decisive influence on the system capacity, anti-interference performance and coverage quality. Traditional antenna array optimization methods mainly rely on classical linear programming, convex optimization or iterative search algorithms to achieve predetermined beamforming goals by designing weight vectors or geometric configurations. However, the optimization of the geometric configuration of an antenna array is essentially a high-dimensional, nonlinear and non-convex combinatorial optimization problem, and the traditional methods have the problem of low computational efficiency when dealing with multiple objectives (such as maximum main lobe gain, sidelobe power suppression, beam pointing precision) and complex constraints (such as inter-element spacing restrictions, three-dimensional space layout). SUMMARY

[0003] In view of the defects of the prior art, the purpose of the present application is to provide a node position optimization method and device based on an ant colony optimization algorithm, aiming to solve the problem of low computational efficiency of existing optimization methods.

[0004] To achieve the above-mentioned purpose, in a first aspect, the present application provides a node position optimization method based on an ant colony optimization algorithm, comprising:

[0005] setting ant colony optimization algorithm parameters, randomly generating an initial solution, and expanding to generate a plurality of ants, wherein each ant respectively represents a different three-dimensional node layout vector;

[0006] repeating the iteration process until a preset number of iterations is reached;

[0007] taking the three-dimensional node layout scheme corresponding to the optimal solution after iteration as the optimal node layout scheme, and optimizing the node position based on the optimal node layout scheme;

[0008] The iteration process comprises:

[0009] calculating the fitness of all current ants respectively, comparing the fitness of the ant with the lowest fitness with the original optimal solution, and taking the ant with lower fitness as the current optimal solution;

[0010] calculating the pheromone intensity based on the fitness of all ants respectively, and obtaining the pheromone distribution;

[0011] updating the ant position based on the pheromone distribution, and performing boundary constraint processing on the new ant position.

[0012] The application adopts an ant colony optimization algorithm to search and optimize three-dimensional coordinates of array nodes, generates an ant colony population in a continuous space adaptively, the algorithm can widely search a search domain in a three-dimensional space, effectively avoids falling into a local optimal solution, cooperatively optimizes main lobe gain and side lobe suppression through a multi-objective fitness function, realizes maximization of main lobe gain and multi-beam generation, significantly improves beam pointing accuracy and coverage range, enhances anti-interference capability, and the algorithm steps are clear, the parameters are set explicitly, without complex mathematical modeling, the population is accelerated to concentrate in an optimal area through a pheromone guiding mechanism, can quickly converge to a stable optimal or approximate optimal solution area, and improves calculation efficiency.

[0013] According to the node position optimization method based on the ant colony optimization algorithm provided by the application, the fitness of all ants is calculated respectively, including:

[0014] The main and side beam direction gain is calculated based on the main and side beam direction parameters in the three-dimensional node layout vector.

[0015] The fitness is calculated based on the main and side beam direction gain and the preset weight.

[0016] The application extracts the main and side beam direction parameters to calculate the main and side beam direction gain, and then calculates the fitness, cooperatively optimizes the main lobe gain and the side lobe suppression, realizes maximization of the main lobe gain and multi-beam generation, significantly improves the beam pointing accuracy and the coverage range, and enhances the anti-interference capability.

[0017] According to the node position optimization method based on the ant colony optimization algorithm provided by the application, the main and side beam direction gain is calculated based on the node quantity, the side beam quantity, the main beam direction angle, the side beam direction angle set, the three-dimensional coordinates of each node and the wavelength in the three-dimensional node layout vector, including:

[0018] The main and side beam direction array factor is calculated based on the main and side beam direction parameters in the three-dimensional node layout vector.

[0019] The main and side beam direction gain is calculated based on the main and side beam direction array factor.

[0020] The application calculates the array factor based on the theory of phased array antenna, takes the first iteration result as a benchmark value, constructs a normalized weighted fitness function, converts the problem of maximizing the main and side beam gain into the optimization of minimizing the fitness through a default weight, and realizes multi-objective cooperative evaluation.

[0021] According to the node position optimization method based on the ant colony optimization algorithm provided by the application, the fitness is calculated based on the main and side beam direction gain and the preset weight, including:

[0022] The fitness is calculated through the formula , wherein, This is the normalized main beam directional gain. This is the arithmetic mean of the normalized gain of all sub-beam directions. , To preset weights, For fitness.

[0023] According to the node position optimization method based on ant colony optimization algorithm provided in this application, the step of calculating pheromone intensity based on the fitness of each ant to obtain pheromone distribution includes:

[0024] Through formula Calculate the first The pheromone intensity of individual ants, among which, For the first The fitness of ants The fitness value is the average fitness of all ants at present. For the number of ants, For the first The fitness of ants For the first The intensity of pheromones in a single ant.

[0025] According to the node position optimization method based on ant colony optimization algorithm provided in this application, the boundary constraint processing of the new ant position includes:

[0026] If the new ant's location coordinates are higher than the preset upper limit, the location coordinates are corrected to the preset upper limit. If the new ant's location coordinates are lower than the preset lower limit, the location coordinates are corrected to the preset lower limit.

[0027] Secondly, this application provides a node position optimization device based on an ant colony optimization algorithm, comprising:

[0028] The generation module is used to set the parameters of the ant colony optimization algorithm, randomly generate an initial solution, and expand to generate multiple ants, where each ant represents a different three-dimensional node layout vector.

[0029] The iteration module is used to repeatedly execute the iteration process until the preset number of iterations is reached.

[0030] The optimization module is used to take the 3D node layout scheme corresponding to the optimal solution after iteration as the optimal node layout scheme, and optimize the node position based on the optimal node layout scheme.

[0031] The iterative process includes:

[0032] Calculate the fitness of each ant, compare the fitness of the ant with the original optimal solution, and take the ant with the lower fitness as the current optimal solution;

[0033] Based on the pheromone intensity corresponding to the fitness of each ant, the pheromone distribution is obtained;

[0034] The ant position is updated based on the pheromone distribution, and the new ant position is subjected to boundary constraint processing.

[0035] In a third aspect, the present application provides an electronic device, comprising: at least one memory for storing a program; at least one processor for executing the program stored in the memory, and when the program stored in the memory is executed, the processor is configured to execute the node position optimization method based on the ant colony optimization algorithm described in the first aspect or any possible implementation manner of the first aspect.

[0036] In a fourth aspect, the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and when the computer program runs on the processor, the processor executes the node position optimization method based on the ant colony optimization algorithm described in the first aspect or any possible implementation manner of the first aspect.

[0037] In a fifth aspect, the present application provides a computer program product, and when the computer program product runs on the processor, the processor executes the node position optimization method based on the ant colony optimization algorithm described in the first aspect or any possible implementation manner of the first aspect.

[0038] It can be understood that the beneficial effects of the above-mentioned second aspect to fifth aspect can be referred to the related description in the first aspect, and will not be repeated here.

[0039] Overall, compared with the prior art, the above technical solutions conceived by the present application have the following beneficial effects:

[0040] The ant colony optimization algorithm is adopted to search and optimize the three-dimensional coordinates of the array nodes, the ant population is adaptively generated in the continuous space, the algorithm can widely search the search domain in the three-dimensional space, effectively avoids falling into the local optimal solution, the main lobe gain and the side lobe suppression are cooperatively optimized through the multi-objective fitness function, the main lobe gain maximization and the multi-beam generation are realized, the beam pointing precision and the coverage range are significantly improved, the anti-interference ability is enhanced, the algorithm steps are clear, the parameter setting is clear, the complex mathematical modeling is not needed, the population is accelerated to the optimal area through the pheromone guiding mechanism, the stable optimal or approximate optimal solution area can be quickly converged, and the calculation efficiency is improved. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0042] Figure 1 is a flowchart of the node position optimization method based on the ant colony optimization algorithm provided by the embodiments of the present application.

[0043] Figure 2 is a schematic diagram of the optimal fitness convergence curve provided by the embodiments of the present application.

[0044] Figure 3 is a schematic diagram of the fitness range convergence curve provided by the embodiments of the present application.

[0045] Figure 4 is a single ant trajectory diagram provided by the embodiments of the present application.

[0046] Figure 5 is a schematic diagram of the three-dimensional node distribution before and after optimization provided by the embodiments of the present application.

[0047] Figure 6 is a three-dimensional multi-beam diagram provided by the embodiments of the present application.

[0048] Figure 7 is a schematic diagram of the fitness calculation flow provided by the embodiments of the present application.

[0049] Figure 8 is a structural schematic diagram of the node position optimization device based on the ant colony optimization algorithm provided by the embodiments of the present application.

[0050] Figure 9 is a structural schematic diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the present application more clear, the following will further describe the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0052] The term "and / or" in this paper is a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. The symbol " / " in this paper represents the relationship of or in the associated objects, for example, A / B represents A or B.

[0053] In the embodiments of the present application, the word "exemplary" or "for example" is used to mean serving as an example, instance, or illustration, and not necessarily to imply any preference or superiority. In other words, the use of the word "exemplary" or "for example" is intended to present concepts in a concrete manner.

[0054] In the description of the embodiments of the present application, the meaning of "plurality" is two or more, for example, a plurality of processing units means two or more processing units, and the like; a plurality of elements means two or more elements, and the like, unless otherwise specified.

[0055] The present application is applicable to wireless sensor network, unmanned aerial vehicle communication, phased array radar and the like, and improves the pointing accuracy, coverage range and anti-interference capability of multi-beam by optimizing node layout.

[0056] Next, combined with Figures 1-7 The node position optimization method based on the ant colony optimization algorithm provided in the embodiments of the present application is introduced.

[0057] Figure 1 is a flowchart of the node position optimization method based on the ant colony optimization algorithm provided in the embodiments of the present application, as Figure 1 shown, the method comprises the following steps:

[0058] Step 100, setting the ant colony optimization algorithm parameters, randomly generating an initial solution, and expanding to generate a plurality of ants, wherein each ant respectively represents a different three-dimensional node layout vector;

[0059] First, initialize the ant colony algorithm parameters and generate a population, specifically, set the ant colony size , pheromone evaporation rate, pheromone weight and heuristic information weight, randomly generate an initial solution, and expand to generate ants.

[0060] Optionally, the node coordinate optimization variable range can be determined, the node coordinate feasible region is defined, and a three-dimensional space scene is supported to meet the boundary constraint.

[0061] In an embodiment of the present application, the ant colony size is set to 200, the pheromone evaporation rate is set to 0.3, which is used to simulate the characteristic that the pheromone volatilizes with time in nature, to control the "decay rate" of the pheromone, the pheromone weight is set to 1, which is used to control the influence degree of the pheromone concentration on the path selection of the ants, and the heuristic weight =5, for controlling the degree of influence of heuristic information on ant path selection, defining the feasible region of node coordinates, supporting three-dimensional space scenes to meet boundary constraints; the initial population is generated by randomly generating initial solutions extended generation, including ants, wherein each ant respectively represents a different three-dimensional node layout vector, and each vector corresponds to a three-dimensional node layout scheme.

[0062] Optionally, the ant population position can be initialized by the following formula:

[0063]

[0064] wherein is the initial solution, is the repeated matrix function, is the random number generation function, and are the upper and lower bounds of the coordinates, and N is the number of nodes.

[0065] Step 110, repeatedly performing the iteration process until a preset number of iterations is reached;

[0066] The iteration process includes:

[0067] Calculate the fitness of all ants respectively, compare the fitness of the ant with the lowest fitness with the original optimal solution, and take the ant with lower fitness as the current optimal solution;

[0068] Based on the fitness of all ants respectively, calculate the pheromone intensity and obtain the pheromone distribution;

[0069] Update the ant position based on the pheromone distribution, and perform boundary constraint processing on the new ant position.

[0070] Optionally, the pheromone update mechanism uses an exponential normalization method to calculate the pheromone intensity, highlighting the guiding role of high-quality solutions, and through the reinforcement of pheromone retention and propagation of high-quality solutions, the directional exploration of the dominant area in the solution space is realized.

[0071] Optionally, the roulette algorithm can be used to select the guide solution, so that the selection probability of the top 20% of high-quality solutions is improved by more than 40%.

[0072] Optionally, the step size can be designed to linearly decay with the number of iterations, taking into account global search and local fine adjustment. The new solution is generated by linear combination of the guide solution, the global optimal solution and Gaussian noise, and the legality of the coordinates is guaranteed by the truncation method. The step size linear decay strategy is designed as follows:

[0073]

[0074] wherein to constrain the upper and lower boundaries, the number of iterations for algorithm execution, the total number of iterations, the initial step size is 10% of the boundary of the feasible region, and the final approach is 0, balancing global search and local optimization. A new solution is generated as follows:

[0075]

[0076] Ensure that all node positions are always within the preset feasible region .

[0077] Optionally, the maximum number of iterations can be set according to requirements, based on the closed-loop iteration framework of "fitness evaluation → pheromone update → solution generation", the core process is executed in a loop until the preset maximum number of iterations is reached, driving the solution space to gradually converge; Finally, output the optimal node coordinate set available for engineering, and the key parameters such as the main lobe gain and sidelobe suppression ratio of the corresponding multi-beam pattern, complete the engineering verification of the optimization result.

[0078] Optionally, the smaller the fitness value, the better the performance of the solution.

[0079] Figure 2 is the optimal fitness convergence curve provided by the embodiments of the present application, as Figure 2 shown, the horizontal axis represents the number of iterations, and the vertical axis represents the optimal fitness value so far in each generation (the lower the objective function value, the better the solution), the optimal fitness of the kth iteration is: wherein, is the solution vector of the ith ant in the kth iteration, is the fitness function, the curve rapidly decreases in the early iterations, indicating that the algorithm can quickly find a better solution; then it enters a stable stage, the optimal fitness value tends to be flat, and there is almost no improvement, indicating that the algorithm has converged to a stable optimal or near-optimal solution region.

[0080] Figure 3 is the fitness range convergence curve provided by the embodiments of the present application, as Figure 3 shown, the fitness range convergence curve shows the fitness range change of all ant solutions in the current generation in the iteration process, reflecting the evolution of population diversity, the horizontal axis is also the number of iterations, and the vertical axis represents the fitness range of all ant solutions in the current generation, the fitness range of the kth iteration is: , is the solution vector of the ith ant in the kth iteration, To adapt to the fitness function, the curve reflects the trend of population diversity with iterations: the initial difference is large, indicating that the ant colony traverses a wide range of search space; as the iteration proceeds, the difference generally decreases and tends to a small value, indicating that the population gradually concentrates in the global optimal or near-optimal region, the population diversity decreases, further proving the convergence of the algorithm.

[0081] Figure 4 is a single ant trajectory diagram provided by an embodiment of the present application, as shown in Figure 4 , taking the x-coordinate of node 1 as the x-axis, the y-coordinate of node 1 as the y-axis, and the z-coordinate of node 1 as the z-axis, the three-dimensional search trajectory of the first node of ant No. 1, the starting point position, the pheromone hotspot area and the information concentration distribution are displayed. The right vertical axis is the information concentration value. The black trajectory diverges from the starting point (green dot) and gradually converges to the pheromone enrichment area (dark color) where the end point (red dot) is located.

[0082] Figure 5 is a three-dimensional node distribution diagram before and after optimization provided by an embodiment of the present application, as shown in Figure 5 , the x-axis, y-axis and z-axis are all wavelengths, and the distribution difference of the initial position and the optimized position of the node in the three-dimensional space is compared and displayed. The figure is marked as "initial position" and "optimized position".

[0083] Step 120, taking the three-dimensional node layout scheme corresponding to the optimal solution after iteration as the optimal node layout scheme, and optimizing the node position based on the optimal node layout scheme.

[0084] The steps of fitness evaluation, pheromone update and solution generation are executed in a loop until the maximum number of iterations is reached, and finally the optimal node layout scheme and the corresponding high-precision multi-beam pattern are output, and the node position is optimized based on the optimal node layout scheme.

[0085] Optionally, the optimal node layout scheme is converted into quantifiable multi-beam performance indicators, and a mathematical mapping relationship of the optimization target is established. The three-dimensional coordinate set , the main beam pointing direction, the sub-beam direction set and the working wavelength are extracted from the node position vector, and a mathematical model of the array factor is constructed based on the theory of phased array antenna.

[0086] Figure 6 is a three-dimensional multi-beam diagram provided by an embodiment of the present application, and the three-dimensional beam direction diagram corresponding to the optimized node configuration is as shown in Figure 6 , wherein the azimuth angle of the x-axis is 0, the azimuth angle of the y-axis is , and the elevation angle of the z-axis isWith a gain of 0, the formation of multiple high-gain main lobes can be clearly observed. For example, the gain of the main beam (red star) is 48.3dB, the gain of the beam with the largest gain outside the index of the main side lobe (purple star) is 44.9dB, and the gain of several sub-beams (black star) is 42.9dB and 46.7dB. The sidelobe suppression is obvious and meets the multi-beam performance index.

[0087] In the above scheme, parameter initialization ensures the basis for global exploration optimization, multi-objective fitness function establishes the mapping relationship between node layout and beam performance, pheromone guidance strategy improves search efficiency and accuracy, and iterative process drives the solution space to converge toward the optimal region, together achieving efficient optimization of node position.

[0088] The node position optimization method based on ant colony optimization algorithm provided in this application uses ant colony optimization algorithm to search and optimize the three-dimensional coordinates of array nodes. By adaptively generating ant colonies in continuous space, the algorithm can extensively traverse the search domain in three-dimensional space, effectively avoiding getting trapped in local optima. Through multi-objective fitness function collaborative optimization of main lobe gain and sidelobe suppression, the algorithm maximizes main lobe gain and generates multiple beams, significantly improving beam pointing accuracy and coverage, enhancing anti-interference ability. Moreover, the algorithm steps are clear, the parameter settings are well-defined, and no complex mathematical modeling is required. The pheromone guidance mechanism accelerates the concentration of the population towards the optimal region, and it can quickly converge to a stable optimal or near-optimal solution region, improving computational efficiency.

[0089] In some embodiments, calculating the fitness of each ant in step 110 includes:

[0090] Step 1101: Calculate the main and secondary beam direction gain based on the main and secondary beam direction parameters in the three-dimensional node layout vector;

[0091] Step 1102: Calculate the fitness based on the directional gain of the main and sub-beams and the preset weights.

[0092] Optionally, the main and sub-beam directional parameters may include the number of nodes, the number of sub-beams, the main beam directional angle, the set of sub-beam directional angles, the three-dimensional coordinates of each node, and the wavelength.

[0093] Figure 7 This is a schematic diagram of the fitness calculation process provided in the embodiments of this application, such as... Figure 7 As shown, the fitness calculation first extracts the main and sub-beam directional parameters, including the three-dimensional coordinates of each node, the main beam directional angle, the set of sub-beam directional angles, and the wavelength. Then, the main and sub-beam directional gains are calculated separately. To eliminate the dimensional differences between different iterations, the main and sub-beam gains of the initial array are used as normalization factors. Finally, the main and sub-beams are set to have equal weights, and the normalized main and sub-beam gains are weighted, summed, and the negative value is taken as the final fitness value.

[0094] In some embodiments, step 1101 specifically comprises:

[0095] Step 11011 calculates the main and auxiliary beam direction array factor based on the main and auxiliary beam direction parameters in the three-dimensional node layout vector;

[0096] Step 11012 calculates the main and auxiliary beam direction gain based on the main and auxiliary beam direction array factor.

[0097] Based on the phased array antenna theory, the array factor is calculated, the first iteration result is taken as the benchmark value, a normalized weighted fitness function is constructed, the problem of maximizing the main and auxiliary beam gain is converted into the optimization of minimizing the fitness through the default weight, and multi-objective collaborative evaluation is realized.

[0098] Specifically, the array factor is calculated by the formula , wherein, is the number of nodes, is the wavelength, is the three-dimensional coordinate of the i-th node, is the imaginary unit, , , , , is the elevation angle of the main beam direction, is the azimuth angle of the main beam direction, is the elevation angle of the corresponding auxiliary beam, is the azimuth angle of the corresponding auxiliary beam.

[0099] The main and auxiliary beam direction gain is calculated by the formula , wherein, is the array factor, is the main and auxiliary beam direction gain.

[0100] As shown in Figure 7 , after extracting the main and auxiliary beam direction parameters, the main and auxiliary beam direction array factor is calculated, the loop calculation is performed for each auxiliary beam direction, and then the main and auxiliary beam direction gain is calculated based on the array factor.

[0101] In some embodiments, step 1102 specifically comprises:

[0102] The fitness is calculated by the formula , wherein, is the normalized main beam direction gain, is the arithmetic mean of the normalized main beam direction gain, , is the preset weight, is the fitness.

[0103] As shown in Figure 7After calculating the main and auxiliary beam direction gains, the formula is used to calculate the fitness, and the maximum problem is converted into a minimum problem by a negative sign, and the smaller the fitness value is, the better the performance is.

[0104] In some embodiments, the pheromone intensity based on the fitness of each ant in step 110 is calculated, and the pheromone distribution is obtained, including:

[0105] The formula is used to calculate the pheromone intensity of the i th ant, where is the fitness of the i th ant, is the average fitness of all ants, is the number of ants, is the fitness of the i th ant, is the pheromone intensity of the i th ant. is the fitness of the i th ant, is the pheromone intensity of the i th ant.

[0106] The pheromone update step adopts a fixed evaporation rate mechanism, and the pheromone evaporation rate p is a preset constant, the pheromone intensity is generated by exponential transformation of the fitness function, and dynamic allocation of the pheromone intensity is realized by normalization processing.

[0107] In some embodiments, the boundary constraint processing of the new ant position in step 110 includes:

[0108] If the new ant position coordinate is higher than the preset upper limit value, the position coordinate is corrected to the preset upper limit value, and if the new ant position coordinate is lower than the preset lower limit value, the position coordinate is corrected to the preset lower limit value.

[0109] The boundary constraint processing adopts a truncation method: if the generated node coordinate exceeds the upper limit , the upper limit value is forcibly corrected: ; if it is lower than the lower limit , the lower limit value is forcibly corrected: , and the specific implementation is matrix operation:

[0110]

[0111] to ensure that all node positions are always within the preset feasible region .

[0112] Figure 8 is a structural schematic diagram of a node position optimization device based on an ant colony optimization algorithm provided by the embodiments of the present application, as shown in the figure, the device 800 includes: Figure 8

[0113] ​​​The generation module 810 is used to set the ant colony optimization algorithm parameters, randomly generate an initial solution, and expand to generate multiple ants, where each ant represents a different three-dimensional node layout vector.

[0114] The iteration module 820 is used to repeatedly execute the iteration process until the preset number of iterations is reached;

[0115] The optimization module 830 is used to take the 3D node layout scheme corresponding to the optimal solution after iteration as the optimal node layout scheme, and optimize the node position based on the optimal node layout scheme.

[0116] The iterative process includes:

[0117] Calculate the fitness of each ant, compare the fitness of the ant with the original optimal solution, and take the ant with the lower fitness as the current optimal solution;

[0118] The pheromone intensity is calculated based on the fitness of each ant to obtain the pheromone distribution.

[0119] The ant positions are updated based on pheromone distribution, and boundary constraints are applied to the new ant positions.

[0120] Based on the methods in the above embodiments, Figure 9 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 9 As shown in the illustration, this application provides an electronic device that may include a processor 910, a communication interface 920, a memory 930, and a communication bus 940. The processor 910, communication interface 920, and memory 930 communicate with each other via the communication bus 940. The processor 910 can call logical instructions stored in the memory 930 to execute the node location optimization method based on the ant colony optimization algorithm described in the above embodiment.

[0121] Furthermore, the logical instructions in the aforementioned memory 930 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the node position optimization method based on the ant colony optimization algorithm described in the various embodiments of this application.

[0122] Based on the method in the above embodiment, the embodiment of the application provides a computer readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the node position optimization method based on the ant colony optimization algorithm in the above embodiment.

[0123] Based on the method in the above embodiment, the embodiment of the application provides a computer program product, which makes the processor execute the node position optimization method based on the ant colony optimization algorithm in the above embodiment when the computer program product runs on the processor.

[0124] It can be understood that the processor in the embodiment of the application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor can be a microprocessor or any conventional processor.

[0125] The method steps in the embodiment of the application can be implemented in the form of hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in a random access memory (RAM), a flash memory, a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically EPROM (EEPROM), a register, a hard disk, a mobile hard disk, a CD-ROM or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor, so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC.

[0126] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in or transmitted by a computer readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through a wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media sets. The available media can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0127] It can be understood that various numerical numbers involved in the embodiments of the present application are only distinguished for convenience of description, and are not used to limit the scope of the embodiments of the present application.

[0128] Those skilled in the art easily understand that the above only describes the preferred embodiments of the present application and is not used to limit the present application. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A node position optimization method based on ant colony optimization algorithm, characterized in that, include: Set the ant colony optimization algorithm parameters, randomly generate an initial solution, and expand to generate multiple ants, where each ant represents a different three-dimensional node layout vector; Repeat the iterative process until the preset number of iterations is reached; The 3D node layout scheme corresponding to the optimal solution after iteration is taken as the optimal node layout scheme, and the node positions are optimized based on the optimal node layout scheme. The iterative process includes: Calculate the fitness of each ant, compare the fitness of the ant with the original optimal solution, and take the ant with the lower fitness as the current optimal solution; The pheromone intensity is calculated based on the fitness of each ant to obtain the pheromone distribution. The ant positions are updated based on pheromone distribution, and boundary constraints are applied to the new ant positions. The calculation of the fitness of each ant includes: Calculate the main and secondary beam directional gain based on the main and secondary beam directional parameters in the three-dimensional node layout vector; The fitness is calculated based on the directional gain of the main and sub-beams and preset weights. The fitness calculation based on the directional gain of the main and sub-beams and preset weights includes: Through formula Calculate fitness, where, This is the normalized main beam directional gain. This is the arithmetic mean of the normalized gain of all sub-beam directions. , To preset weights, For fitness; The step of calculating pheromone intensity based on the fitness of each ant to obtain pheromone distribution includes: Through formula Calculate the first The pheromone intensity of individual ants, among which, For the first The fitness of ants The fitness value is the average fitness of all ants at present. The number of ants. For the first The fitness of ants For the first The intensity of pheromones in a single ant.

2. The node position optimization method based on ant colony optimization algorithm according to claim 1, characterized in that, The calculation of the main and secondary beam directional gain based on the main and secondary beam directional parameters in the three-dimensional node layout vector includes: Calculate the main and secondary beam direction array factor based on the main and secondary beam direction parameters in the three-dimensional node layout vector; The directional gain of the main and sub-beams is calculated based on the main and sub-beam directional array factors.

3. The node position optimization method based on ant colony optimization algorithm according to claim 1, characterized in that, The boundary constraint processing for the new ant position includes: If the new ant's location coordinates are higher than the preset upper limit, the location coordinates are corrected to the preset upper limit. If the new ant's location coordinates are lower than the preset lower limit, the location coordinates are corrected to the preset lower limit.

4. A node position optimization device based on ant colony optimization algorithm, characterized in that, include: The generation module is used to set the parameters of the ant colony optimization algorithm, randomly generate an initial solution, and expand to generate multiple ants, where each ant represents a different three-dimensional node layout vector. The iteration module is used to repeatedly execute the iteration process until the preset number of iterations is reached. The optimization module is used to take the 3D node layout scheme corresponding to the optimal solution after iteration as the optimal node layout scheme, and optimize the node position based on the optimal node layout scheme. The iterative process includes: Calculate the fitness of each ant, compare the fitness of the ant with the original optimal solution, and take the ant with the lower fitness as the current optimal solution; The pheromone intensity is calculated based on the fitness of each ant to obtain the pheromone distribution. The ant positions are updated based on pheromone distribution, and boundary constraints are applied to the new ant positions. The calculation of the fitness of each ant includes: Calculate the main and secondary beam directional gain based on the main and secondary beam directional parameters in the three-dimensional node layout vector; The fitness is calculated based on the directional gain of the main and sub-beams and preset weights. The fitness calculation based on the directional gain of the main and sub-beams and preset weights includes: Through formula Calculate fitness, where, This is the normalized main beam directional gain. This is the arithmetic mean of the normalized gain of all sub-beam directions. , To preset weights, For fitness; The step of calculating pheromone intensity based on the fitness of each ant to obtain pheromone distribution includes: Through formula Calculate the first The pheromone intensity of individual ants, among which, For the first The fitness of ants The fitness value is the average fitness of all ants at present. The number of ants. For the first The fitness of ants For the first The intensity of pheromones in a single ant.

5. An electronic device, characterized in that, include: At least one memory for storing computer programs; At least one processor is configured to execute a program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to execute the node position optimization method based on the ant colony optimization algorithm as described in any one of claims 1-3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is run on the processor, the processor performs the node location optimization method based on the ant colony optimization algorithm as described in any one of claims 1-3.

7. A computer program product, characterized in that, When the computer program product is run on a processor, the processor performs the node location optimization method based on the ant colony optimization algorithm as described in any one of claims 1-3.

Images