Antenna parameter optimization method and system, storage medium and equipment

Abstract

The invention belongs to the technical field of wireless communication, and provides an antenna parameter optimization method and system, a storage medium and equipment. The method comprises the steps that discretization processing is carried out on antenna parameters to be optimized to generate a solution space, the solution space is coded, an initial population containing multiple sets of antenna parameters is generated, and each set of parameters corresponds to an individual; calculating the fitness of each individual through an objective function; selecting parent individuals by adopting a proportional selection strategy; pairing the parent individuals according to a preset crossover probability, and generating new individuals through single-point crossover; carrying out basic position variation on the individuals according to a preset variation probability; performing iteration termination judgment according to a preset termination condition: if the termination condition is met, outputting a current individual as an optimal antenna parameter combination; otherwise, returning to the step 2 until a termination condition is met. According to the antenna parameter optimization method, the genetic algorithm is utilized, and the antenna parameter optimization efficiency is improved by simulating natural selection and genetic mechanisms.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of wireless communication, and particularly relates to an antenna parameter optimization method and system, a storage medium and equipment. BACKGROUND

[0002] In the construction of a mobile communication network, the azimuth angle, downtilt angle and height of an antenna have a decisive influence on the network coverage performance. Reasonable configuration of these parameters can significantly improve the coverage rate of the reference signal received power (RSRP) in the target area, thereby optimizing the user experience and network quality. However, in the prior art, the adjustment of the antenna parameters mainly relies on the experience of an engineer: after setting the initial parameters manually, the parameters need to be corrected repeatedly in combination with road test data to gradually approach the optimal configuration.

[0003] The defects of this method are obvious: (1) manual adjustment relies on subjective experience and lacks the support of a systematic mathematical model, resulting in a blind and inefficient optimization process. (2) Multiple road tests and parameter corrections are required to achieve the desired effect, especially in complex wireless environments, which results in a long adjustment period and high cost. (3) Manual adjustment is difficult to fully explore the solution space and is prone to fall into a local optimal solution, which cannot guarantee a globally optimal configuration.

[0004] In the prior art, although some individual studies have attempted to introduce automatic algorithms (such as the gradient descent method and random search), these methods still have the problems of slow convergence speed and high computational complexity when facing high-dimensional and discrete solution spaces. For example, although the exhaustive method can traverse all possible parameter combinations, its exponential complexity makes it difficult to be practically applied in engineering. SUMMARY

[0005] In view of the deficiencies in the prior art, the application provides an antenna parameter optimization method and system, a storage medium and equipment, which utilize a genetic algorithm to simulate natural selection and genetic mechanisms, can efficiently search for a globally optimal solution in a complex solution space, encode the antenna parameters as population individuals, and iteratively optimize them using genetic operations such as selection, crossover and mutation, so as to quickly converge to an optimal parameter combination, significantly improve the calculation efficiency and accuracy of the RSRP coverage rate, and thereby improve the efficiency of antenna parameter optimization.

[0006] The application is implemented by the following technical solutions: Step one: discretize the antenna parameters to be optimized to generate a solution space, encode the solution space, and generate an initial population containing multiple sets of antenna parameters, each set of parameters corresponding to an individual; Step two: calculate the fitness of each individual through a target function, the target function being the ratio of the area in which the reference signal received power (RSRP) exceeds a predetermined threshold to the total area in the planning area; Step three, a proportional selection strategy is adopted to calculate the probability of each individual being selected based on the fitness, and parent individuals are selected; Step four, parent individuals are paired based on a preset crossover probability, and new individuals are generated through single-point crossover; Step five, basic bit mutation is performed on the individuals based on a preset mutation probability; Step six, iterative termination judgment is performed according to a preset termination condition: if the termination condition is met, the current individual is output as the optimal antenna parameter combination; otherwise, step two is returned until the termination condition is met.

[0007] Optionally, The antenna parameters include a directional angle, a downtilt angle and a hanging height parameter of the antenna. The encoding mode of the solution space is binary encoding, and each group of parameters is composed of discrete values of the directional angle, the downtilt angle and the hanging height.

[0008] Optionally, The individual selection probability formula of the proportional selection strategy is: , wherein, is the fitness value of the individual, is the population size.

[0009] Optionally, The new individual generated through single-point crossover includes: Randomly selecting an encoding bit of the parent individual, and exchanging the substring after the bit to generate a new individual.

[0010] Optionally, The basic bit mutation is to randomly select an encoding bit of the individual, and flip the binary value according to a preset rule.

[0011] Optionally, The preset termination condition includes: the number of iterations reaches a set threshold; and / or, the target function value converges to a stable range; and / or, the improvement amplitude of the fitness value is less than a preset tolerance.

[0012] Optionally, The optimal antenna parameter combination is used to adjust the deployment parameters of the directional antenna, including the directional angle, the downtilt angle and the hanging height.

[0013] The application also provides an antenna parameter optimization system for implementing the method described above, and the system includes: An initialization module is configured to discretize the antenna parameters to be optimized to generate a solution space, encode the solution space, and generate an initial population containing multiple groups of antenna parameters, each group of parameters corresponding to an individual; ​The fitness calculation module is configured to calculate the fitness of each individual by a target function, which is a ratio of an area in which a reference signal received power (RSRP) exceeds a preset threshold to a total area in the planning area. The selection operation module is configured to calculate a probability of selection of each individual based on the fitness by using a proportional selection strategy, and select the parent individual. The crossover operation module is configured to pair the parent individual at a preset crossover probability, and generate a new individual by single-point crossover. The mutation operation module is configured to perform basic bit mutation on the individual at a preset mutation probability. The iteration termination module is configured to perform iteration termination judgment according to a preset termination condition, and output the current individual as an optimal antenna parameter combination if the termination condition is met, or return to step two until the termination condition is met.

[0014] The application further provides a computer-readable storage medium storing one or more programs, which, when executed, can implement the aforementioned antenna parameter optimization method.

[0015] The application further provides a device including a processor, a communication interface, a computer-readable storage medium and a communication bus; wherein the processor, the communication interface and the computer-readable storage medium communicate with each other through the communication bus. The processor is configured to execute the program stored in the computer-readable storage medium.

[0016] Compared with the prior art, the application has the following advantages: 1. The antenna parameter optimization method provided by the application can efficiently search for a global optimal solution in a complex solution space by simulating natural selection and genetic mechanisms according to a genetic algorithm, quickly converge to an optimal parameter combination by encoding the antenna parameters into population individuals and iteratively optimizing by using genetic operations such as selection, crossover and mutation, and improve the calculation efficiency and accuracy of RSRP coverage, thereby effectively improving the optimization efficiency.

[0017] 2. The solution space is encoded by using a binary coding method, a diversified population is generated by using crossover and mutation operations, the diversity of solutions is increased to improve the search ability, the algorithm is helped to more effectively explore the solution space, and the algorithm is prevented from falling into a local optimum, the management and calculation of parameters can be simplified, and the execution efficiency and effect of the genetic algorithm are improved.

[0018] 3. The target function is a ratio of an area in which a reference signal received power (RSRP) exceeds a preset threshold to a total area in the planning area, the network coverage performance can be effectively quantified and evaluated, and the signal quality in the coverage area is ensured in optimization.

[0019] Other features and advantages of the present application will be set forth in the description that follows, and in part will be apparent from the description, or can be learned by practice of the application. The purposes and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0021] Figure 1 A flowchart of an antenna parameter optimization method is shown; Figure 2 A structural schematic block diagram of an antenna parameter optimization system is shown; Figure 3 An RSRP coverage target diagram of an embodiment of the present application is shown; Figure 4 An algorithm performance simulation diagram of an embodiment of the present application is shown; Figure 5 A structural schematic diagram of an apparatus of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] In order to make the purposes, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0023] Referring to the drawings, Figure 1 the method of the present application comprises: Step one, discretize the antenna parameters to be optimized to generate a solution space, encode the solution space, and generate an initial population containing multiple sets of antenna parameters, each set of parameters corresponding to an individual; The antenna parameters include: the direction angle, the downtilt angle and the hanging height parameters of the antenna. The encoding mode of the solution space is binary encoding, and each set of parameters is composed of the discrete values of the direction angle, the downtilt angle and the hanging height.

[0024] Step two, calculate the fitness of each individual by a target function, the target function is the ratio of the area where the reference signal received power (RSRP) exceeds a preset threshold to the total area in the planning area; Step three, adopt a proportional selection strategy to calculate the probability of each individual being selected based on the fitness, and select the parent individuals; The individual selection probability formula of the proportional selection strategy is as follows: , Wherein, is the fitness value of the individual, is the population size.

[0025] Step four, pair the parent individuals with a preset crossover probability, and generate new individuals through single-point crossover; The generation of new individuals through single-point crossover includes the following steps: Randomly select the coding site of the parent individual, and exchange the substring after the site to generate a new individual.

[0026] Step five, perform basic bit mutation on the individual with a preset mutation probability; The basic bit mutation is to randomly select a coding site of the individual, and flip its binary value according to a preset rule.

[0027] Step six, according to the preset termination condition, perform iteration termination judgment: if the termination condition is met, output the current individual as the optimal antenna parameter combination; otherwise, return to step two until the termination condition is met.

[0028] The preset termination condition includes: the number of iterations reaches a set threshold; and / or, the target function value converges to a stable range; and / or, the improvement amplitude of the fitness value is less than a preset tolerance; The optimal antenna parameter combination is used to adjust the deployment parameters of the directional antenna, including the direction angle, the downtilt angle and the hanging height.

[0029] Specifically, The application provides an antenna parameter optimization method based on a genetic algorithm. As a bionic optimization algorithm, the genetic algorithm can efficiently search for a global optimal solution in a complex solution space by simulating natural selection and genetic mechanisms. The antenna parameter optimization method in the application embodiment can quickly converge to an optimal parameter combination by encoding the antenna parameters as population individuals and iteratively optimizing them using genetic operations such as selection, crossover and mutation, thereby significantly improving the calculation efficiency and accuracy of the RSRP coverage rate.

[0030] The application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0031] ​The antenna parameter optimization method in the embodiment comprises: Step one, initialization: discretize the antenna parameters to be optimized to generate a solution space, encode the solution space, and generate an initial population containing multiple groups of antenna parameters, each group of parameters corresponding to an individual.

[0032] The antenna parameters include the direction angle, downtilt angle, and hanging height of the antenna. The encoding method of the solution space is binary encoding, and each group of parameters is composed of the discrete values of the direction angle, downtilt angle, and hanging height.

[0033] In the embodiment, the direction angle, downtilt angle, and hanging height of the antenna to be optimized are obtained, the antenna parameters are discretized to generate a solution space, the solution space is encoded, and M groups of parameters are randomly generated, each group of parameters containing a direction angle, a downtilt angle, and a hanging height. Each group of parameters corresponds to an individual, and each group of parameters is encoded into a binary string (i.e., each individual contains the binary encoding of multiple parameter combinations). These individuals form an initial population, which serves as the search base point for the subsequent optimization algorithm.

[0034] Step two, calculate the fitness: calculate the fitness value of each individual based on the objective function, the objective function being the ratio of the area in the planning area where the reference signal received power (RSRP) exceeds a predetermined threshold to the total area, and the fitness of the individual is obtained.

[0035] In the embodiment, the ratio of the area in the planning area where the reference signal received power (RSRP) exceeds a predetermined threshold to the total area is calculated through the objective function. Higher RSRP means better signal reception quality. For each individual, the RSRP distribution in the planning area is calculated. By calculating the ratio of the area where the RSRP exceeds the predetermined threshold to the total area, the fitness of the individual is obtained, i.e., the signal coverage effect under the given parameter setting. The larger the fitness value, the better the optimization effect.

[0036] Step three, selection operation: adopt a proportional selection strategy, calculate the probability of an individual being selected based on the fitness, and select the parent individuals.

[0037] According to the fitness value, a proportional selection strategy is adopted to determine the probability of an individual being selected, and individuals with high fitness are selected as parents.

[0038] The individual selection probability formula of the proportional selection strategy is: , wherein, is the fitness value of the individual, is the population size.

[0039] ​According to the proportional selection strategy, the probability of selection of an individual is proportional to its fitness value. That is, the higher the fitness value, the greater the probability of selection of the individual. The individuals selected by the proportional selection strategy form the parents, providing a basis for the generation of the next generation. The proportional selection strategy can ensure that individuals with higher fitness values are more likely to pass on their excellent characteristics to the next generation, thereby gradually optimizing the population.

[0040] Step four, crossover operation: pairing the parent individuals according to a preset crossover probability, and generating new individuals through single-point crossover.

[0041] Generating new individuals through single-point crossover includes randomly selecting the coding bit positions of the paired parent individuals, and exchanging the substrings after the bit positions to generate new individuals.

[0042] According to the preset crossover probability, individuals are randomly selected from the current parent individuals for pairing. A crossover point is randomly generated for each pair of parent individuals through single-point crossover, and new individuals are generated by exchanging pairing at the crossover point.

[0043] Step five, mutation operation: performing basic bit mutation on the individuals according to a preset mutation probability.

[0044] Basic bit mutation is to randomly select the coding bit positions of the individuals and flip their binary values according to a preset rule.

[0045] The preset rule includes setting a fixed probability value for the mutation operation, generally between 0.01 and 0.1. For example, the mutation probability can be set to 0.05, which means that about 5% of the individual parameters in the population will be mutated. In the later optimization stage, the probability can be adjusted adaptively according to the evolution number or the fitness of the individuals.

[0046] According to the preset mutation probability, a corresponding number of individuals are randomly selected for parameter fine-tuning, thereby maintaining the diversity of the population.

[0047] Step six, iteration termination judgment: according to the preset termination condition, the iteration termination judgment is performed: if the preset termination condition is met, the current individual is output as the optimal antenna parameter combination; otherwise, return to step two until the termination condition is met.

[0048] The preset termination condition includes at least one of the following: the number of iterations reaches a set threshold, the objective function value converges to a stable range, and the improvement amplitude of the fitness value is less than a preset tolerance.

[0049] The termination condition can be set to an improvement amplitude threshold or an iteration number according to the need. When the termination condition is met, the optimal antenna parameter combination is output.

[0050] The method of the present application will be described below in conjunction with specific embodiments.

[0051] Assumption: In a mobile communication network optimization project in a dense business district, the direction angle, downtilt angle and hanging height of multiple directional antennas in the region need to be optimized to improve the coverage rate of the reference signal received power (RSRP) in the coverage area. The target area is a commercial complex with a building height of 3 meters, containing a complex and variable wireless environment (such as high-rise shielding, signal attenuation caused by dense flow, etc.). The RSRP coverage target diagram (i.e. antenna deployment position) of the embodiment of the present application is shown in Figure 2 The antenna type is a directional antenna, and the hanging height value range is 5 meters to 20 meters.

[0052] The specific implementation steps of using the method of the embodiment of the present application are as follows: Step one, parameter initialization: Discretize the direction angle (0°-360°), downtilt angle (0°-15°) and hanging height (5 meters-20 meters) of the antenna into 10 equally spaced value points respectively, forming a solution space containing 1000 parameter combinations. Randomly generate an initial population containing 50 parameter combinations (i.e. population size = 50), and each parameter combination corresponds to an individual.

[0053] Step two, fitness calculation: Use the network planning simulation tool Atoll to import the building plan and wireless environment data of the target area. For each individual (i.e. parameter combination), simulate and calculate its corresponding RSRP distribution.

[0054] The objective function is defined as: , The fitness value is directly taken as the objective function value , and the higher the fitness, the better the coverage effect of the parameter combination.

[0055] Step three, selection operation: Adopt roulette wheel selection strategy, and the probability of being selected as parent is higher for individuals with higher fitness. For example, if the fitness of an individual is 0.68 (i.e. 68% coverage rate), its selection probability is: , Through this strategy, 30 high-fitness individuals are selected as parents.

[0056] Step four, crossover operation: Set the crossover probability to 0.8, and randomly pair the selected parent individuals. Adopt single-point crossover method: randomly select a position in the parameter encoding (such as direction angle encoding site), exchange the sub-codes of the paired individuals after the position, and generate new individuals. For example, after the crossover of parent A (direction angle 30°, downtilt angle 5°, hanging height 12 meters) and parent B (direction angle 45°, downtilt angle 8°, hanging height 15 meters), a child (direction angle 45°, downtilt angle 5°, hanging height 12 meters) may be generated.

[0057] Step five, mutation operation: The mutation probability is set to 0.05, and 5% of the individuals are randomly selected for parameter fine-tuning. For example, the original hanging height of an individual is 10 meters, and after mutation, it may be adjusted to 11 meters; or the direction angle is randomly adjusted from 40° to 35°.

[0058] Step six, iteration termination judgment: The termination condition is set as: the target function value is continuously improved by less than 1% for 3 iterations, or the iteration number reaches 20. In this embodiment, after 12 iterations, the target function value converges to 0.72 (i.e. 72% RSRP coverage rate), and the optimal parameters are direction angle 40°, downtilt angle 7°, and hanging height 17 meters, which meet the termination condition.

[0059] Optimization effect comparison: (1) Traditional experience adjustment: engineers need to perform at least 5 road tests and parameter correction, which takes about 2 weeks, and the final RSRP coverage rate is 65%.

[0060] (2) Method of the present application: as shown in Figure 3 , through the simulation tool and genetic algorithm, only 12 iterations (4 hours) are needed, and the RSRP coverage rate is improved to 72%, without human intervention.

[0061] Result verification: The optimized parameters are deployed to the target area, and through road testing, the coverage area of RSRP≥-110dBm accounts for 70.5%, with an error of less than 2% compared with the simulation result, verifying the effectiveness and engineering practicability of the present application.

[0062] In summary, the method for optimizing antenna parameters of the present application realizes efficient optimization of antenna parameters by combining genetic algorithm and simulation tools. Compared with the traditional method of relying on manual experience for road testing and parameter correction, the present application significantly improves the optimization efficiency and accuracy. In practical application, this method not only shortens the optimization period and reduces the cost, but also ensures the overall improvement of signal quality in the mobile communication network coverage area. Therefore, the present application is of great significance for efficient deployment and optimization of mobile communication networks, and provides strong support for the further development of wireless communication technology.

[0063] Referring to the accompanying Figure 4 , the structure of an antenna parameter optimization system for implementing the above method is shown, which includes an initialization module, a fitness calculation module, a selection operation module, a crossover operation module, a mutation operation module, and an iteration termination module.

[0064] The initialization module is configured to discretize the antenna parameters to be optimized to generate a solution space, encode the solution space, and generate an initial population containing multiple groups of antenna parameters, each group of parameters corresponding to an individual. The fitness calculation module is configured to calculate the fitness of each individual by using a target function, the target function being a ratio of an area in which a reference signal received power (RSRP) exceeds a preset threshold to a total area in a planning region. The selection operation module is configured to calculate a probability of each individual being selected based on the fitness by using a proportional selection strategy, and select parent individuals. The crossover operation module is configured to pair the parent individuals at a preset crossover probability, and generate new individuals by using single-point crossover. The mutation operation module is configured to perform basic bit mutation on the individuals at a preset mutation probability. The iteration termination module is configured to perform iteration termination judgment according to a preset termination condition, and output a current individual as an optimal antenna parameter combination if the termination condition is met, or return to step 2 until the termination condition is met.

[0065] In addition, the embodiment of the application further provides an antenna parameter optimization device, which comprises: The initialization module is configured to discretize the antenna parameters to be optimized to generate a solution space, encode the solution space, and generate an initial population containing multiple groups of antenna parameters, each group of parameters corresponding to an individual. The fitness calculation module is configured to calculate the fitness of each individual by using a target function, the target function being a ratio of an area in which a reference signal received power (RSRP) exceeds a preset threshold to a total area in a planning region. The selection operation module is configured to calculate a probability of each individual being selected based on the fitness by using a proportional selection strategy, and select parent individuals. The crossover operation module is configured to pair the parent individuals at a preset crossover probability, and generate new individuals by using single-point crossover. The mutation operation module is configured to perform basic bit mutation on the individuals at a preset mutation probability. The iteration termination module is configured to perform iteration termination judgment according to a preset termination condition, and output a current individual as an optimal antenna parameter combination if the termination condition is met, or return to step 2 until the termination condition is met.

[0066] Based on the same application concept, the application further provides a computer readable storage medium, which stores one or more programs, and when the one or more programs are executed, the aforementioned antenna parameter optimization method can be implemented.

[0067] As Figure 5As shown, the embodiments of the present application further provide a device comprising a processor, a communication interface, a memory and a communication bus. The processor, the communication interface and the memory communicate with each other through the communication bus.

[0068] The memory is a computer readable storage medium, configured to store one or more programs.

[0069] The processor is configured to execute the program stored in the computer readable storage medium.

[0070] The computer readable storage medium can be included in the device / apparatus described in the above embodiments; or can exist separately and not be assembled into the device / apparatus.

[0071] Although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of antenna parameter optimization, characterized by, The method comprises the steps of: Step 1: discretizing the antenna parameters to be optimized to generate a solution space, encoding the solution space to generate an initial population comprising a plurality of groups of antenna parameters, each group of parameters corresponding to an individual; Step 2: calculating the fitness of each individual through a target function, the target function being the ratio of the area in the planning area where the reference signal received power (RSRP) exceeds a preset threshold to the total area; Step 3: using a proportional selection strategy to calculate the probability of each individual being selected based on the fitness, and selecting parent individuals; Step 4: pairing the parent individuals at a preset crossover probability, and generating new individuals through single-point crossover; Step 5: performing basic bit mutation on the individuals at a preset mutation probability; Step 6: performing iteration termination judgment according to a preset termination condition: if the termination condition is met, outputting the current individual as the optimal antenna parameter combination; otherwise, returning to Step 2 until the termination condition is met.

2. The method of claim 1, wherein the antenna parameters comprise a directional angle, a downtilt angle, and a hanging height parameter of the antenna; and the encoding mode of the solution space is binary encoding, and each group of parameters is composed of discrete values of the directional angle, the downtilt angle, and the hanging height.

3. The method of claim 1, wherein the individual selection probability formula of the proportional selection strategy is: wherein P is the selection probability of an individual, f is the fitness of the individual, and F is the average fitness of all individuals. The method of claim 4, wherein the generating new individuals through single-point crossover comprises: randomly selecting a coding bit of the parent individual, and exchanging the substring after the bit to generate a new individual.

5. The method of claim 4, wherein the basic bit mutation is randomly selecting a coding bit of an individual, and flipping the binary value thereof according to a preset rule.

6. The method of claim 1-5, wherein the preset termination condition comprises: the number of iterations reaching a set threshold; and / or, the target function value converging to a stable range; and / or, the improvement amplitude of the fitness value being less than a preset tolerance.

7. The method of any one of claims 1-5, wherein the optimal antenna parameter combination is used to adjust the deployment parameters of the directional antenna, including the directional angle, the downtilt angle, and the hanging height. ， in, For individuals fitness value, Population size.

4. The method of claim 2, wherein, The system comprises: an initialization module configured to discretize the antenna parameters to be optimized to generate a solution space, encode the solution space to generate an initial population comprising a plurality of groups of antenna parameters, each group of parameters corresponding to an individual; a fitness calculation module configured to calculate the fitness of each individual through a target function, the target function being the ratio of the area in the planning area where the reference signal received power (RSRP) exceeds a preset threshold to the total area; a selection operation module configured to use a proportional selection strategy to calculate the probability of each individual being selected based on the fitness, and select parent individuals; a crossover operation module configured to pair the parent individuals at a preset crossover probability, and generate new individuals through single-point crossover; a mutation operation module configured to perform basic bit mutation on the individuals at a preset mutation probability; an iteration termination module configured to perform iteration termination judgment according to a preset termination condition: if the termination condition is met, output the current individual as the optimal antenna parameter combination; otherwise, return to Step 2 until the termination condition is met. ​ 8. An antenna parameter optimization system, characterized by, ​ ​ ​ ​ ​ ​ ​ 9. A computer readable storage medium storing one or more programs, which when executed by a computer, implement the method of any one of claims 1-7.

9. A computer readable storage medium storing one or more programs, which when executed by a computer, implement the method of any one of claims 1-7.

10. An electronic device comprising a processor, a communication interface, the computer readable storage medium of claim 10 and a communication bus; wherein, The processor, the communication interface, and the computer readable storage medium are in electrical communication with each other via a communication bus; and The processor is configured to execute the programs stored in the computer readable storage medium.

Images