An electromagnetic suppression zone collaborative suppression power optimization method, system, device and medium based on a genetic algorithm

Abstract

A genetic algorithm-based electromagnetic suppression area cooperative suppression power optimization method, system, device and medium, the method comprising: electromagnetic suppression area task analysis and scene model initialization; according to the electromagnetic suppression area suppression task, the cooperative suppression power optimization problem is modeled, and the power optimization model based on the genetic algorithm is obtained; the parameters in the power optimization model based on the genetic algorithm are initialized and set, the initialized power optimization model based on the genetic algorithm is obtained, and the initialized power optimization model based on the genetic algorithm is solved; the system, the device and the medium are used to realize the method; the present application considers the cooperative relationship between the suppression equipment and the interference problem of the normal signal in the environment, and solves the optimization problem constructed by the genetic algorithm, which can suppress abnormal signals while reducing the interference to normal signals, has the advantages of high interference efficiency, small injury and fast response speed.

Description

Technical Field

[0001] This invention belongs to the field of radio interference technology, specifically relating to a method, system, device, and medium for optimizing the power of electromagnetic suppression in a region based on a genetic algorithm. Background Technology

[0002] Ensuring electromagnetic environment safety during major events is a crucial and challenging issue. If the transmitted power within the controlled frequency band is too low, it's difficult to effectively suppress conventional signals; conversely, if the suppression power is too high, the suppression range and out-of-band emissions increase, potentially impacting whitelisted devices operating normally outside the controlled frequency band or adjacent controlled areas. This issue inherently presents a contradiction in electromagnetic safety management: it requires using electromagnetic suppression equipment to effectively suppress controlled radio stations (controlled stations) within key areas, rendering them inoperable, while simultaneously minimizing the harmful interference to uncontrolled stations caused by excessive suppression power.

[0003] In traditional security operations for major events, communication is often blocked by radiating continuous high-power omnidirectional radio frequency signals, which can effectively suppress targets using specific frequencies. However, electromagnetic suppression equipment has excessive radiated power and lacks dynamic adjustment capabilities, which inevitably leads to large-scale accidental damage or serious harmful interference.

[0004] The patent application document with publication number CN115987408A discloses a "Wireless Signal Detection and Interference Control System and Method". It detects abnormal signals in the environment through a wireless detection device and interferes with the abnormal signals in the environment by transmitting high-intensity signals through an jammer associated with the detection device. However, it does not consider the interference of the interference signal to the normal signals in the environment or the cooperative work between various jammers, resulting in low interference efficiency and large false alarms. Summary of the Invention

[0005] To overcome the shortcomings of the prior art, the present invention aims to provide a method, system, device, and medium for optimizing the power of electromagnetic suppression region collaborative suppression based on a genetic algorithm. By considering the collaborative relationship between suppression devices and the interference with normal signals in the environment, and by using a genetic algorithm to solve the constructed optimization problem, the power optimization of electromagnetic suppression region collaborative suppression is achieved using a genetic algorithm. This can reduce interference with normal signals while suppressing abnormal signals, and has the advantages of high interference efficiency, low false alarm rate, and fast response speed.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0007] A method for optimizing the collaborative suppression power of electromagnetic suppression regions based on genetic algorithms includes the following steps:

[0008] Step 1: Electromagnetic suppression area task analysis and scene model initialization;

[0009] Step 2: Based on the electromagnetic suppression area suppression task in Step 1, model the collaborative suppression power optimization problem to obtain a power optimization model based on a genetic algorithm.

[0010] Step 3: Initialize the parameters in the power optimization model based on the genetic algorithm obtained in Step 2 to obtain the initialized power optimization model based on the genetic algorithm.

[0011] Step 4: Solve the power optimization model based on the genetic algorithm after initialization in Step 3.

[0012] The specific method for step 1 is as follows:

[0013] Identify the specific frequency bands and target devices to be suppressed within the electromagnetic suppression area, as well as the required suppression intensity at each typical suppression point and target device calculated using the interference-to-noise ratio protection criterion;

[0014] For the suppression scenario, the suppression equipment, typical suppression points, whitelisted equipment, and control stations are identified, along with the corresponding suppression intensity requirements. The suppression equipment is represented by a collection... This indicates that suppressing typical points uses sets. This indicates that whitelisted devices use a collection It indicates that the control station uses a collection This indicates that N1, N2, N3, and N4 represent the number of suppression devices, typical suppression points, whitelisted devices, and control stations, respectively.

[0015] The specific method for step 2 is as follows:

[0016] The power of each suppression device is used as the optimization variable, the suppression intensity of each typical suppression point, whitelisted device and control station is used as the constraint condition, and the mean square error between the actual suppression intensity and the required suppression intensity at each typical suppression point is used as the optimization objective to construct a collaborative suppression power optimization problem.

[0017] Step 2.1: Calculate the losses from each pressing device to the typical pressing point, whitelisted devices, and control station:

[0018] Assuming the pressing device s i The antenna gain ∈S is Suppressing typical point t j The antenna gain of receiver ∈T is Then the pressing equipment s i To suppress typical point t j The losses at the location are as follows:

[0019]

[0020] in, Indicates the pressing device s i To suppress typical point t j Transmission path loss at that location Indicates the distance between the two; This represents the frequency suppression factor between the two. It is the difference in operating frequencies between the two, and its calculation method is as follows:

[0021]

[0022] in, To suppress the power spectral density (W / kHz) of the device signal, To suppress the frequency response of the receiver's filter at typical points;

[0023] Similarly, the pressing equipment s i To whitelisted devices w m The losses at the location are as follows:

[0024]

[0025] in, Indicates the pressing device s i To whitelisted devices w m The distance; This represents the frequency suppression factor between the two. It is the difference in operating frequency between the two;

[0026] Pressing equipment i To control station c n The losses at the location are as follows:

[0027]

[0028] in, Indicates the pressing device s i To control station c n The distance; This represents the frequency suppression factor between the two. It is the difference in operating frequency between the two;

[0029] Step 2.2, based on the loss calculated in Step 2.1, construct an optimization problem for the suppression scenario:

[0030] The operating power of each pressing device The constraints of the optimization problem are constructed around suppressing typical points, whitelisted devices, and control stations, and are set as optimization variables.

[0031] Pressing equipmenti To suppress typical point t j The pressure intensity at that point is:

[0032]

[0033] in, The units are all dBm or dBw;

[0034] All pressing equipment at typical pressing point t j The sum of the suppression intensities at each point yields the typical suppression point t. j The pressure intensity at that point is:

[0035]

[0036] in, The units are all mW or W;

[0037] Assuming suppression of typical point t j The suppression requirement at the location is The following constraints must be met:

[0038]

[0039] All typical suppression points must meet the suppression requirements. Therefore, the following constraints are constructed for the typical suppression points:

[0040]

[0041] Similarly, the constraints for constructing whitelisted devices and control stations can be obtained as follows:

[0042]

[0043]

[0044] in, These represent all compression devices in the whitelist device w. m and control station c n The cumulative suppression intensity, These represent whitelisted devices w m Maximum allowable suppression intensity and control station c n The required compression strength;

[0045] Minimizing the mean square error between the actual suppression intensity and the suppression requirement at typical suppression points is taken as the optimization objective of the optimization problem, as follows:

[0046]

[0047] In summary, the power optimization model based on the genetic algorithm is as follows:

[0048]

[0049] st

[0050]

[0051]

[0052]

[0053] Where N2 represents the number of typical suppression points.

[0054] The specific method for step 3 is as follows:

[0055] Based on the key area suppression task, the initial settings for power optimization based on genetic algorithm are: number of evolutions, population size, crossover probability, mutation probability and encoding form, and the fitness function of individual populations is designed.

[0056] Step 3.1, Encoding and generating the initial population: Real number encoding is used, and the length of each individual is N1, which is the number of pressing devices. A certain number of individuals are randomly generated within the working power range of the pressing devices as the initial population.

[0057] Step 3.2: Design the fitness function for individuals in the population. If all constraints are satisfied, the fitness is the objective function value; if the constraints are violated, a penalty function method is used to calculate the fitness of the individual, as described below:

[0058]

[0059] ·

[0060] ·

[0061] ·

[0062] Where M1 is the penalty function coefficient corresponding to the constraint conditions of suppressing typical points and control stations; M2 is the penalty function coefficient corresponding to the constraint conditions of whitelisted devices, and M1≥M2;

[0063] Step 3.3: Select various genetic operators, using roulette wheel as the selection operator, setting the crossover operator to single-point crossover, and selecting real number mutation as the mutation operator.

[0064] The specific method for step 4 is as follows:

[0065] Step 4.1, Iterative Update: According to the evolutionary principle of survival of the fittest, the population evolves through operations such as selection, recombination and mutation, and continuously improves the population's fitness.

[0066] Step 4.2, Scheme Evaluation: When the population has evolved to the set number of evolutions, evaluate the effectiveness of the cooperative suppression power scheme corresponding to the current best individual;

[0067] Step 4.3, Iteration Stop: If the scheme evaluation is successful, the iteration stops; otherwise, adjustments are made according to the evaluation results, and the iteration process continues.

[0068] The specific method for step 4.1 is as follows:

[0069] Step 4.1.1: Calculate the fitness of each individual, use the fitness function to calculate the fitness of individuals in the population, and evaluate the quality of individuals in the population.

[0070] Step 4.1.2, Selection operation: Eliminate individuals with high fitness values ​​calculated in step 4.1.1, and retain individuals with low fitness values ​​for evolutionary operations;

[0071] Step 4.1.3, Crossover operation: Randomly select two different individuals from the population retained in step 4.1.2 to perform crossover operation and generate a new population;

[0072] Step 4.1.4, Mutation Operation: In the newly generated population in step 4.1.3, individuals mutate with a certain probability to maintain the algorithm's exploratory ability;

[0073] Step 4.1.5: Determine if the termination condition is met: If the number of generations reaches the set maximum number of generations, stop the iteration and select the best individual as the optimal solution; otherwise, go to step 4.1.1 to continue the iteration.

[0074] The specific method for step 4.2 is as follows:

[0075] Evaluate the current optimal solution: convert the optimal solution of the genetic algorithm into the working power of each suppression device, and calculate the actual suppression intensity at typical suppression points, whitelisted devices, and control stations;

[0076] The specific method for step 4.3 is as follows:

[0077] Algorithm termination criteria: If the suppression intensity at the typical suppression points and control stations in the evaluation scheme does not meet the requirements, suppression equipment needs to be added, and then proceed to step 2.1; if the suppression intensity of the whitelisted equipment in the evaluation scheme does not meet the requirements, the maximum allowable suppression intensity of the whitelisted equipment with the greatest violation is increased to the current suppression intensity at that whitelisted equipment, and then proceed to step 4.1.1 to continue the iteration process; if the scheme evaluation is successful, the iteration stops, and the operating power of each suppression equipment is output.

[0078] This invention also provides a system for optimizing the power of electromagnetic suppression in a region based on a genetic algorithm, comprising:

[0079] Task parsing and initialization module: used to implement task parsing and scene model initialization in the electromagnetic suppression area;

[0080] Power optimization model construction module: used to model the power optimization problem of collaborative suppression based on the electromagnetic suppression region suppression task, and obtain a power optimization model based on genetic algorithm;

[0081] Power optimization model initialization module: used to initialize the parameters in the genetic algorithm-based power optimization model, and obtain the initialized genetic algorithm-based power optimization model;

[0082] Power optimization model solution module: Used to solve the initialized power optimization model based on genetic algorithm.

[0083] This invention also provides a device for optimizing the collaborative suppression power of electromagnetic suppression regions based on a genetic algorithm, comprising:

[0084] Memory: A computer program that stores the above-mentioned method for optimizing the collaborative suppression power of electromagnetic suppression regions based on genetic algorithms, and is a computer-readable device;

[0085] Processor: Used to implement the aforementioned method for optimizing electromagnetic suppression regional collaborative suppression power based on genetic algorithm when executing the computer program.

[0086] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the aforementioned method for optimizing the collaborative suppression power of electromagnetic suppression regions based on a genetic algorithm.

[0087] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0088] 1. Existing technologies only consider abnormal signals (control stations) and frequency bands where abnormal signals may exist (typical suppression points), without considering the potential interference to normal signals. In contrast, this invention addresses the issue of accidental damage to whitelisted devices. A signal strength threshold is set; if the actual interference signal strength at the whitelist location is lower than this threshold, it is considered not to cause interference, and the normal signal can still function normally. Because this invention considers the interference of interfering signals to normal signals in the scene, it can significantly reduce the impact of accidental damage to normal signals, resulting in a suppression effect with minimal accidental damage.

[0089] 2. By optimizing the working power of each pressing device in the scene, this invention enables all pressing devices to work in the best cooperative state, resulting in a pressing effect with high interference efficiency.

[0090] 3. This invention uses a genetic algorithm in heuristic algorithms to solve optimization problems in a scenario, which can quickly find the optimal coordination relationship of the power of each suppression device in the current scenario, and has the advantage of fast response speed.

[0091] In summary, this invention, by considering the collaborative relationship between suppression devices and the interference with normal signals in the environment, and by using a genetic algorithm to solve the constructed optimization problem, can reduce interference with normal signals while suppressing abnormal signals. It has the advantages of high interference efficiency, low false alarm rate, and fast response speed. Attached Figure Description

[0092] Figure 1 This is a scene model diagram of the present invention.

[0093] Figure 2 This is a system flowchart of the present invention.

[0094] Figure 3 This is a simulation diagram of the convergence of the genetic algorithm in an embodiment of the present invention.

[0095] Figure 4 This is a simulation diagram of the device power under different numbers of pressing devices in an embodiment of the present invention.

[0096] Figure 5 This is a simulation diagram comparing the effects of an embodiment of the present invention with a fixed transmission power. Detailed Implementation

[0097] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments:

[0098] like Figure 1 As shown, the application scenario established by this invention is 1km × 1km in size, including several suppression devices, typical suppression points, whitelisted devices, and control stations. In this scenario, it is assumed that the transmitting antennas of the suppression devices are all omnidirectional and responsible for the suppression task of the entire scenario area. Based on the location distribution of the suppression devices, a certain number of typical suppression points are selected throughout the scenario area to measure the suppression effect within the entire area. During the suppression of the entire area, the whitelisted devices need to operate normally. This invention needs to minimize the impact on the whitelisted devices by adjusting the power of the suppression devices. The control stations are also the suppression targets in the containment process. This invention needs to ensure that the suppression intensity emitted by the control stations reaches a certain level, rendering them unable to operate normally. This invention assumes that the information of all devices is known, including the power spectral density of the suppression device signals, the frequency response of the receiving filters of the whitelisted devices and the control stations, and their operating frequencies.

[0099] Specifically, a method for optimizing the collaborative suppression power in key regions based on genetic algorithms includes the following steps:

[0100] Step 1: Electromagnetic suppression area task analysis and scene model initialization;

[0101] Identify the specific frequency bands and target devices to be suppressed within the electromagnetic suppression area, as well as the required suppression intensity at each typical suppression point and target device calculated using the interference-to-noise ratio protection criterion;

[0102] For the suppression scenario, the suppression equipment, typical suppression points, whitelisted equipment, and control stations are identified, along with the corresponding suppression intensity requirements. The suppression equipment is represented by a collection... This indicates that suppressing typical points uses sets. This indicates that whitelisted devices use a collection It indicates that the control station uses a collection This indicates that N1, N2, N3, and N4 represent the number of suppression devices, typical suppression points, whitelisted devices, and control stations, respectively.

[0103] like Figure 2 As shown, in step 2, based on the electromagnetic suppression area suppression task in step 1, a collaborative suppression power optimization problem is modeled to obtain a power optimization model based on a genetic algorithm.

[0104] The power of each suppression device is used as the optimization variable, the suppression intensity of each typical suppression point, whitelisted device and control station is used as the constraint condition, and the mean square error between the actual suppression intensity and the required suppression intensity at each typical suppression point is used as the optimization objective to construct a collaborative suppression power optimization problem.

[0105] Step 2.1: Calculate the losses from each pressing device to the typical pressing point, whitelisted devices, and control station:

[0106] Assuming the pressing device s i The antenna gain ∈S is Suppressing typical point t j The antenna gain of receiver ∈T is Then the pressing equipment s i To suppress typical point t j The losses at the location are as follows:

[0107]

[0108] in, Indicates the pressing device s i To suppress typical point t j Transmission path loss at that location Indicates the distance between the two; This represents the frequency suppression factor between the two. It is the difference in operating frequencies between the two, and its calculation method is as follows:

[0109]

[0110] in, To suppress the power spectral density (W / kHz) of the device signal, To suppress the frequency response of the receiver's filter at typical points;

[0111] Similarly, the pressing equipment s i To whitelisted devices w m The losses at the location are as follows:

[0112]

[0113] in, Indicates the pressing device s i To whitelisted devices w m The distance; This represents the frequency suppression factor between the two. It is the difference in operating frequency between the two;

[0114] Pressing equipment i To control station c n The losses at the location are as follows:

[0115]

[0116] in, Indicates the pressing device s i To control station c n The distance; This represents the frequency suppression factor between the two. It is the difference in operating frequency between the two;

[0117] Step 2.2, based on the loss calculated in Step 2.1, construct an optimization problem for the suppression scenario:

[0118] The operating power of each pressing device The power of the suppression equipment is adjusted as the optimization variable to achieve accurate suppression with minimal accidental damage and high efficiency. The constraints of the optimization problem are constructed around three objects: typical suppression points, whitelisted equipment, and control stations.

[0119] Pressing equipment i To suppress typical point t j The pressure intensity at that point is:

[0120]

[0121] in, The units are all dBm or dBw.

[0122] All pressing equipment at typical pressing point t j By accumulating the suppression intensity at each point, the typical suppression point t can be obtained. j The pressure intensity at that point is:

[0123]

[0124] in, The units are all mW or W;

[0125] Assuming suppression of typical point t j The suppression requirement at the location is For this typical point to meet the suppression requirements, the following constraints must hold:

[0126]

[0127] All typical suppression points must meet the suppression requirements. Therefore, the following constraints are constructed for the typical suppression points:

[0128]

[0129] Similarly, the constraints for constructing whitelisted devices and control stations can be obtained as follows:

[0130]

[0131]

[0132] in, These represent all compression devices in the whitelist device w. m and control station c n The cumulative suppression intensity, These represent whitelisted devices w m Maximum allowable suppression intensity and control station c n The required compression strength;

[0133] To achieve precise and efficient containment with minimal collateral damage, this invention uses minimizing the mean square error between the actual containment intensity and the containment requirement at typical containment points as the optimization objective, as follows:

[0134]

[0135] In summary, the power optimization model based on the genetic algorithm is as follows:

[0136]

[0137] st

[0138]

[0139]

[0140]

[0141] Where N2 represents the number of typical suppression points.

[0142] Step 3: Initialize the parameters in the power optimization model based on genetic algorithm obtained in Step 2 to obtain the initialized power optimization model based on genetic algorithm.

[0143] Based on the electromagnetic suppression region suppression task, the initial settings for power optimization based on the genetic algorithm are: number of evolutions, population size, crossover probability, mutation probability, and encoding form. The fitness function of the population individuals is designed.

[0144] Step 3.1, Encoding and generating the initial population: Real number encoding is used, and the length of each individual is N1, which is the number of pressing devices. A certain number of individuals are randomly generated within the working power range of the pressing devices as the initial population.

[0145] Step 3.2: Design the fitness function for individuals in the population. The fitness of an individual is related to the objective function value and the violation of constraints. If all constraints are satisfied, the fitness is the objective function value. If constraints are violated, a penalty function method is used to calculate the fitness of the individual, as described below:

[0146]

[0147] ·

[0148] ·

[0149] ·

[0150] Where M1 is the penalty function coefficient corresponding to the constraint conditions of the typical suppression point and the control station; M2 is the penalty function coefficient corresponding to the constraint conditions of the whitelist device. In this suppression scenario, the present invention must ensure that the requirements are met at the typical suppression point and the control station, and satisfy the normal operation of the whitelist as much as possible. Therefore, in this design, M1 and M2 have the following relationship: M1≥M2.

[0151] Step 3.3: Select various genetic operators, using roulette wheel as the selection operator, setting the crossover operator to single-point crossover, and selecting real number mutation as the mutation operator.

[0152] Step 4: Solve the power optimization model based on the genetic algorithm after initialization in Step 3.

[0153] Step 4.1, Iterative Update: According to the evolutionary principle of survival of the fittest, the population evolves through operations such as selection, recombination and mutation, and continuously improves the population's fitness.

[0154] Step 4.1.1: Calculate the fitness of each individual, use the fitness function to calculate the fitness of individuals in the population, and evaluate the quality of individuals in the population.

[0155] Step 4.1.2, Selection operation: Eliminate individuals with high fitness values ​​calculated in step 4.1.1, and retain individuals with low fitness values ​​for subsequent evolutionary operations;

[0156] Step 4.1.3, Crossover operation: Randomly select two different individuals from the population retained in step 4.1.2 to perform crossover operation and generate a new population;

[0157] Step 4.1.4, Mutation Operation: In the newly generated population in step 4.1.3, individuals mutate with a certain probability to maintain the algorithm's exploratory ability;

[0158] Step 4.1.5: Determine if the termination condition is met: If the number of generations reaches the set maximum number of generations, stop the iteration and select the best individual as the optimal solution; otherwise, go to step 4.1.1 to continue the iteration.

[0159] Step 4.2, Scheme Evaluation: When the population has evolved to the set number of evolutions, evaluate the effectiveness of the cooperative suppression power scheme corresponding to the current best individual;

[0160] Evaluate the current optimal solution: convert the optimal solution of the genetic algorithm into the working power of each suppression device, and calculate the actual suppression intensity at typical suppression points, whitelisted devices, and control stations;

[0161] Step 4.3, Iteration Stop: If the scheme evaluation is successful, the iteration stops; otherwise, adjustments are made according to the evaluation results, and the iteration process continues.

[0162] Algorithm termination criteria: If the suppression intensity at the typical suppression points and control stations in the evaluation scheme does not meet the requirements, suppression equipment needs to be added, and then proceed to step 2.1; if the suppression intensity of the whitelisted equipment in the evaluation scheme does not meet the requirements, the maximum allowable suppression intensity of the whitelisted equipment with the greatest violation is increased to the current suppression intensity at that whitelisted equipment, and then proceed to step 4.1.1 to continue the iteration process; if the scheme evaluation is successful, the iteration stops, and the operating power of each suppression equipment is output.

[0163] Simulation Description

[0164] 1. Simulation conditions:

[0165] The number of typical suppression points N2 = 40, the number of whitelisted devices N3 = 10, the number of control stations N4 = 1, the propagation loss calculation model is the UMi_Street_Canyon model, and the coefficients of the penalty function are M1 = 500 and M2 = 50.

[0166] 2. Simulation content:

[0167] like Figure 3 As shown, when the number of pressing devices is 4 to 6, the genetic algorithm can converge within 10 generations, demonstrating its rapid convergence characteristic. This allows the present invention to quickly adjust the power of the pressing devices in response to sudden situations in the pressing scenario.

[0168] like Figure 4 The diagram illustrates the power consumption of each pressing device under varying numbers of devices. The lower dashed line indicates that the minimum operating power of the pressing device is 30 dBm; the upper dashed line indicates that if all devices operate at the same power, a power setting of 42 dBm is required to meet the pressing requirements in the scenario. Experimental results demonstrate that this invention, through power cooperation among the pressing devices, achieves a lower power consumption in the actual pressing scheme.

[0169] like Figure 5 As shown, the mean square error of the pressing intensity at various typical pressing points varies with the number of pressing devices under two conditions: fixed power and the use of the present invention. Experimental results demonstrate that the present invention can maintain the mean square error of the pressing scheme at a very low level, achieving "precise" electromagnetic pressing.

[0170] This invention also provides a system for optimizing the power of electromagnetic suppression in a region based on a genetic algorithm, comprising:

[0171] Task parsing and initialization module: used to implement task parsing and scene model initialization for the electromagnetic suppression area in step 1;

[0172] Power optimization model construction module: used to realize the collaborative suppression power optimization problem modeling in step 2 based on the electromagnetic suppression area suppression task, and obtain the power optimization model based on genetic algorithm;

[0173] Power optimization model initialization module: used to initialize the parameters in the power optimization model based on genetic algorithm in step 3, and obtain the initialized power optimization model based on genetic algorithm;

[0174] Power optimization model solution module: used to solve the initialized power optimization model based on genetic algorithm in step 4.

[0175] This invention also provides a device for optimizing the collaborative suppression power of electromagnetic suppression regions based on a genetic algorithm, comprising:

[0176] Memory: A computer program that stores the above-mentioned method for optimizing the collaborative suppression power of electromagnetic suppression regions based on genetic algorithms, and is a computer-readable device;

[0177] Processor: Used to implement the aforementioned method for optimizing electromagnetic suppression regional collaborative suppression power based on genetic algorithm when executing the computer program.

[0178] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the aforementioned method for optimizing the collaborative suppression power of electromagnetic suppression regions based on a genetic algorithm.

Claims

1. A method for optimizing the collaborative suppression power of electromagnetic suppression regions based on genetic algorithms, characterized in that: Includes the following steps: Step 1: Electromagnetic suppression area task analysis and scene model initialization; Step 2: Based on the electromagnetic suppression area suppression task in Step 1, model the collaborative suppression power optimization problem to obtain a power optimization model based on a genetic algorithm. The specific method for step 2 is as follows: The power of each suppression device is used as the optimization variable, the suppression intensity of each typical suppression point, whitelisted device and control station is used as the constraint condition, and the mean square error between the actual suppression intensity and the required suppression intensity at each typical suppression point is used as the optimization objective to construct a collaborative suppression power optimization problem. Step 2.1: Calculate the losses from each pressing device to the typical pressing point, whitelisted devices, and control station: Assuming the pressing device s i The antenna gain ∈S is Suppressing typical point t j The antenna gain of receiver ∈T is Then the pressing equipment s i To suppress typical point t j The losses at the location are as follows: in, Indicates the pressing device s i To suppress typical point t j Transmission path loss at that location Indicates the distance between the two; This represents the frequency suppression factor between the two. It is the difference in operating frequencies between the two, and its calculation method is as follows: in, To suppress the power spectral density of the device signal in W / kHz, To suppress the frequency response of the receiver's filter at typical points; Similarly, the pressing equipment s i To whitelisted devices w m The losses at the location are as follows: in, Indicates the pressing device s i To whitelisted devices w m The distance; This represents the frequency suppression factor between the two. It is the difference in operating frequency between the two; Pressing equipment i To control station c n The losses at the location are as follows: in, Indicates the pressing device s i To control station c n The distance; This represents the frequency suppression factor between the two. It is the difference in operating frequency between the two; Step 2.2, based on the loss calculated in Step 2.1, construct an optimization problem for the suppression scenario: The operating power of each pressing device Let s be the optimization variable. i ∈S, the constraints of the optimization problem are constructed around suppressing typical points, whitelisted devices, and control stations; Pressing equipment i To suppress typical point t j The pressure intensity at that point is: in, The units are all dBm or dBw; All pressing equipment at typical pressing point t j The sum of the suppression intensities at each point yields the typical suppression point t. j The pressure intensity at that point is: in, The units are all mW or W; Assuming suppression of typical point t j The suppression requirement at the location is The following constraints must be met: All typical suppression points must meet the suppression requirements. Therefore, the following constraints are constructed for the typical suppression points: Similarly, the constraints for constructing whitelisted devices and control stations can be obtained as follows: in, These represent all compression devices in the whitelist device w. m and control station c n The cumulative suppression intensity, These represent whitelisted devices w m Maximum allowable suppression intensity and control station c n The required compression strength; Minimizing the mean square error between the actual suppression intensity and the suppression requirement at typical suppression points is taken as the optimization objective of the optimization problem, as follows: In summary, the power optimization model based on the genetic algorithm is as follows: st Where N2 is the number of typical suppression points; Step 3: Initialize the parameters in the power optimization model based on genetic algorithm obtained in Step 2 to obtain the initialized power optimization model based on genetic algorithm. Step 4: Solve the power optimization model based on the genetic algorithm after initialization in Step 3.

2. The method for optimizing the collaborative suppression power of electromagnetic suppression regions based on genetic algorithms according to claim 1, characterized in that: The specific method for step 1 is as follows: Identify the specific frequency bands and target devices to be suppressed within the electromagnetic suppression area, as well as the required suppression intensity at each typical suppression point and target device calculated using the interference-to-noise ratio protection criterion; For the suppression scenario, the suppression equipment, typical suppression points, whitelisted equipment, and control stations are identified, along with the corresponding suppression intensity requirements. The suppression equipment is represented by a collection... This indicates that suppressing typical points uses sets. This indicates that whitelisted devices use a collection It indicates that the control station uses a collection This indicates that N1, N2, N3, and N4 represent the number of suppression devices, typical suppression points, whitelisted devices, and control stations, respectively.

3. The method for optimizing the collaborative suppression power of electromagnetic suppression regions based on genetic algorithms according to claim 1, characterized in that: The specific method for step 3 is as follows: Based on the key area suppression task, the initial settings for power optimization based on genetic algorithm are: number of evolutions, population size, crossover probability, mutation probability and encoding form, and the fitness function of individual populations is designed. Step 3.1, Encoding and generating the initial population: Real number encoding is used, and the length of each individual is N1, which is the number of pressing devices. A certain number of individuals are randomly generated within the working power range of the pressing devices as the initial population. Step 3.2: Design the fitness function for individuals in the population. If all constraints are satisfied, the fitness is the objective function value; if the constraints are violated, a penalty function method is used to calculate the fitness of the individual, as described below: Where M1 is the penalty function coefficient corresponding to the constraint conditions of suppressing typical points and control stations; M2 is the penalty function coefficient corresponding to the constraint conditions of whitelisted devices, and M1≥M2; Step 3.3: Select various genetic operators, using roulette wheel as the selection operator, setting the crossover operator to single-point crossover, and selecting real number mutation as the mutation operator.

4. The method for optimizing the collaborative suppression power of electromagnetic suppression regions based on genetic algorithms according to claim 1, characterized in that: The specific method for step 4 is as follows: Step 4.1, Iterative Update: According to the evolutionary principle of survival of the fittest, the population evolves through selection, recombination and mutation, continuously improving the population's fitness; Step 4.2, Scheme Evaluation: When the population has evolved to the set number of evolutions, evaluate the effectiveness of the cooperative suppression power scheme corresponding to the current best individual; Step 4.3, Iteration Stop: If the scheme evaluation is successful, the iteration stops; otherwise, adjustments are made according to the evaluation results, and the iteration process continues.

5. The method for optimizing the collaborative suppression power of electromagnetic suppression regions based on genetic algorithms according to claim 4, characterized in that: The specific method for step 4.1 is as follows: Step 4.1.1: Calculate the fitness of each individual, use the fitness function to calculate the fitness of individuals in the population, and evaluate the quality of individuals in the population. Step 4.1.2, Selection operation: Eliminate individuals with high fitness values ​​calculated in step 4.1.1, and retain individuals with low fitness values ​​for evolutionary operations; Step 4.1.3, Crossover operation: Randomly select two different individuals from the population retained in step 4.1.2 to perform crossover operation and generate a new population; Step 4.1.4, Mutation Operation: In the newly generated population in step 4.1.3, individuals mutate with a certain probability to maintain the algorithm's exploratory ability; Step 4.1.5: Determine if the termination condition is met: If the number of generations reaches the set maximum number of generations, stop the iteration and select the best individual as the optimal solution; otherwise, go to step 4.1.1 to continue the iteration.

6. A method for optimizing the collaborative suppression power of electromagnetic suppression regions based on a genetic algorithm, as described in claim 4 or 5, characterized in that: The specific method for step 4.2 is as follows: Evaluate the current optimal solution: convert the optimal solution of the genetic algorithm into the working power of each suppression device, and calculate the actual suppression intensity at typical suppression points, whitelisted devices, and control stations; The specific method for step 4.3 is as follows: Algorithm termination criteria: If the suppression intensity at the typical suppression points and control stations in the evaluation scheme does not meet the requirements, suppression equipment needs to be added, and then proceed to step 2.1; if the suppression intensity of the whitelisted equipment in the evaluation scheme does not meet the requirements, the maximum allowable suppression intensity of the whitelisted equipment with the greatest violation is increased to the current suppression intensity at that whitelisted equipment, and then proceed to step 4.1.1 to continue the iteration process; if the scheme evaluation is successful, the iteration stops, and the operating power of each suppression equipment is output.

7. A genetic algorithm-based electromagnetic suppression regional collaborative suppression power optimization system based on the method of claim 1, characterized in that: include: Task parsing and initialization module: used to implement task parsing and scene model initialization in the electromagnetic suppression area; Power optimization model construction module: used to model the power optimization problem of collaborative suppression based on the electromagnetic suppression region suppression task, and obtain a power optimization model based on genetic algorithm; Power optimization model initialization module: used to initialize the parameters in the genetic algorithm-based power optimization model, and obtain the initialized genetic algorithm-based power optimization model; Power optimization model solution module: Used to solve the initialized power optimization model based on genetic algorithm.

8. A device for optimizing the collaborative suppression power of electromagnetic suppression regions based on genetic algorithms, characterized in that: include: Memory: A computer program for optimizing the electromagnetic suppression region collaborative suppression power based on a genetic algorithm, as described in any one of claims 1-6, and is a computer-readable device; Processor: Used to implement the electromagnetic suppression region collaborative suppression power optimization method based on genetic algorithm as described in any one of claims 1-6 when executing the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that, when executed by a processor, can implement the electromagnetic suppression region collaborative suppression power optimization method based on a genetic algorithm as described in any one of claims 1-6.

Images