Electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization

Abstract

The application provides a kind of electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization, comprising the following steps: selecting sensing resource scheduling optimization target, the sensing resource scheduling optimization target includes: sensing resource load and task completion effect;Analysis sensing resource scheduling optimization target, establish multi-objective optimization sensing resource scheduling model;Using the genetic algorithm based on fitness optimization designed according to the characteristics of spectrum monitoring task completion effect, find the optimal sensing resource selection scheme under the conditions of meeting sensing task requirements.In the case of meeting the requirements of spectrum monitoring area coverage, as far as possible to optimize the utilization efficiency of electromagnetic sensing resource, the multi-objective optimization model proposed can be compatible with the cooperative scheduling requirements of other sensing tasks and be easy to extend, and the time-consuming link in the scheduling process is improved to optimize the convergence efficiency of algorithm.Implementation of sensing resource scheduling automation and improve the utilization rate of sensing resource.

Description

Technical Field

[0001] This invention relates to the field of electromagnetic sensing technology, and more specifically, to an electromagnetic sensor resource scheduling method for optimizing spectrum monitoring area coverage. Background Technology

[0002] Currently, the scheduling of electromagnetic sensor resources for spectrum monitoring coverage is mostly done manually, which suffers from problems such as the inability to automate the process, high professional requirements, and low resource utilization. Specifically, existing technologies mainly face the following challenges:

[0003] (1) The process cannot be automated: On the one hand, existing heterogeneous electromagnetic sensors have differences in interface standards and communication protocols, which makes it difficult to meet the basic conditions for automated scheduling between sensor devices. On the other hand, there are various types of scheduling objectives to be optimized, such as minimizing the load on sensing resources, maximizing the coverage of the monitoring area, and minimizing the cross coverage rate. It is difficult to take into account the automated scheduling of multiple optimization objectives.

[0004] (2) High professional requirements: The manual scheduling method requires operators to have a deep understanding of the functional indicators, performance indicators, working modes, task characteristics, etc. of various electromagnetic sensors. It not only requires high professional quality of operators, but also results in different scheduling results due to different operators.

[0005] (3) Low resource utilization: Due to the use of manual methods to decompose and allocate tasks for sensing resources, the switching cost of sensing tasks between different sensing resources is high. Inevitably, there is a problem of trading space for time, which means that the switching cost of sensing resources and the cost of human resources consumption are prioritized, thus restricting the efficiency of sensing resource utilization. Summary of the Invention

[0006] The present invention aims to at least solve one of the technical problems in the prior art, namely, the inability to automate the scheduling process of electromagnetic sensor resources for spectrum monitoring coverage, the high professional requirements, and the low resource utilization rate.

[0007] To address the aforementioned problems, this invention introduces a genetic algorithm based on fitness optimization to maximize the sharing of heterogeneous resources and improve the utilization rate of sensing resources. It focuses on iterative optimization of resource combination selection from two aspects: resource load and task achievement effect, and provides an electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization.

[0008] This invention provides an electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization, comprising the following steps:

[0009] S1. Select the target for optimizing the scheduling of sensing resources, which includes: sensing resource load and task completion effect;

[0010] S2. Analyze the optimization objectives of sensing resource scheduling and establish a multi-objective optimization sensing resource scheduling model;

[0011] S3. Using a fitness-optimized genetic algorithm designed based on the characteristics of the spectrum monitoring task completion effect, find the optimal sensing resource selection scheme that meets the requirements of the sensing task.

[0012] The electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization according to the above technical solution of the present invention may further have the following additional technical features:

[0013] In the above technical solution, the perceived resource load in S1 is represented as:

[0014] minW T = min( ) ;

[0015] in, W T Indicates the total load of perceived resources; Let n be the load of the k-th sensing resource, and there are n sensing resources in total.

[0016] In the above technical solution, the task completion effect in S1 is reflected in achieving the maximum single coverage rate of the target area in the spatiotemporal frequency dimension. That is, the task completion effect is measured by the ratio of the monitored area to the target area, and the resource scheduling effect is verified by establishing corresponding optimization models and algorithms. It can be represented as:

[0017] ;

[0018] in, Indicates the first The area that a single sensing resource can cover; Indicates the first The area of ​​the monitoring zone for each resource; Used to calculate the area of ​​the total covered region; Used to calculate the area of ​​the overlapping region between two regions; This indicates the coverage rate of the target monitoring area covered by the scheduled resources, satisfying... , Indicates complete coverage. This indicates that the target area cannot be monitored.

[0019] In the above technical solution, S2 includes the following steps:

[0020] S21. Decompose the sensing task into several jobs and count the number of sensing resources available for scheduling;

[0021] S22. Map several sensing resources to several tasks, and define a mapping matrix. The first in the matrix Line number The elements of a column are represented as , The value represents the first Is the resource allocated to the first...? One assignment;

[0022] S23. Establish a function to constrain the quantity of perceived resources. ;

[0023] S24. Establish a function to constrain the performance of the task. ;

[0024] S25. Based on S23 and S24, establish a multi-objective optimization sensing resource scheduling model.

[0025] In the above technical solution, the mapping matrix in S22 The job exclusivity constraint and resource independence constraint should be satisfied;

[0026] The job exclusivity constraint means that each job can only select one sensing resource;

[0027] The resource independence constraint means that a perceived resource can be allocated to at most one job.

[0028] In the above technical solution, the function in S23 constrains the number of sensing resources. for:

[0029] ;

[0030] Where n represents the number of sensing resources available for scheduling; m represents the current number of sensing resources available for scheduling. The first perception task, in which the second... Each perception task can be broken down into... For each task, then for all current perceptual tasks, a total of [number] tasks can be decomposed into [number]. One assignment.

[0031] In the above technical solution, the function in S24 constrains the task completion effect. for:

[0032] ;

[0033] in, To measure the first A function that determines the completion status of each assignment; These are weighting coefficients, used to represent the weighting coefficients of the first... The importance of each assignment.

[0034] In the above technical solution, the multi-objective optimization sensing resource scheduling model in S25, and the objective function It can be represented as:

[0035] ;

[0036] in, and Hyperparameters that are not less than 0 are used to adjust... and The proportion it accounts for in the objective function.

[0037] In the above technical solution, the fitness-based genetic algorithm in S3 includes algorithm initialization and problem solving;

[0038] The algorithm initialization includes:

[0039] Individual encoding uses a real-number encoding mechanism to describe the solution space in multi-objective optimization problems;

[0040] Establish a fitness function, using the objective function of the multi-objective optimization perception resource scheduling model as the fitness function;

[0041] An initial population is generated. For each schedulable sensor resource, a feasible set is generated. The elements in the set are the supported job numbers. For each individual gene, a value is randomly selected from the feasible set of its corresponding sensor resource and assigned to it, thereby forming a single individual in the initial population, and the initial population for the algorithm to solve is obtained.

[0042] The problem-solving process includes:

[0043] Individual fitness calculation involves decoding each individual in the population to obtain feasible solutions, establishing a unique mapping between task completion performance and individual fitness, and using feasible solutions to calculate individual fitness.

[0044] Select and retain individuals with high fitness.

[0045] Crossover is used to correct crossover results where the value of an individual gene does not exist in the feasible set of the perceptual resources corresponding to that gene. Values ​​are randomly selected from the feasible set of perceptual resources corresponding to the gene to cover the erroneous values.

[0046] Gene mutation is achieved by randomly selecting values ​​from the feasible set of sensory resources corresponding to the gene.

[0047] In any of the above technical solutions, the electromagnetic sensor has a standardized scheduling interface, which can support overall scheduling.

[0048] In summary, due to the adoption of the above-mentioned technical features, the beneficial effects of the present invention are:

[0049] This invention provides a fitness-optimized genetic algorithm for scheduling sensing resources. It optimizes the utilization efficiency of electromagnetic sensing resources while meeting the coverage requirements of the spectrum monitoring area. The proposed multi-objective optimization model is compatible with the collaborative scheduling requirements of other sensing tasks and is easily extensible. Improvements and optimizations are made to the time-consuming steps in the scheduling process to enhance the algorithm's convergence efficiency. Its effects are mainly reflected in the following two aspects:

[0050] Automated scheduling of sensing resources: By designing a multi-objective optimization model, the performance of spectrum monitoring tasks is normalized. This model has openness and compatibility for other sensing tasks. It breaks down the barriers of traditional sensing devices in terms of form, deployment and function, makes full use of various sensor resources, realizes automatic association mapping between sensing tasks and sensing resources, reduces the dependence on professional personnel, and optimizes and improves the operation capability of spectrum sensor resources.

[0051] Improve the utilization rate of sensing resources: By adopting the GFOGA resource scheduling algorithm, the mapping relationship between the effect value of task completion and the individual is cached. Compared with the traditional genetic algorithm, it can converge to the global optimum faster, reduce the switching cost of sensing tasks between different sensing resources, improve the utilization efficiency of sensing resources, and support the efficient collaboration between electromagnetic sensors.

[0052] Additional aspects and advantages of the invention will become apparent in the following description or may be learned by practice of the invention. Attached Figure Description

[0053] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0054] Figure 1 This is a flowchart of an electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization according to an embodiment of the present invention;

[0055] Figure 2 This is a flowchart of a genetic algorithm based on fitness optimization (GFOGA) in an electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization according to an embodiment of the present invention.

[0056] Figure 3 This is a schematic diagram of a feasible decoding method for electromagnetic sensor resource scheduling oriented towards spectrum monitoring area coverage optimization according to an embodiment of the present invention.

[0057] Figure 4 This is a comparison chart of the spectrum sensor resource scheduling effects under full coverage in an electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization according to an embodiment of the present invention;

[0058] Figure 5 This is a comparison chart of the spectrum sensor resource scheduling effects under partial coverage conditions in an electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization according to an embodiment of the present invention. Detailed Implementation

[0059] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0060] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0061] The following reference Figures 1 to 5 This invention describes an electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization, provided by some embodiments of the present invention.

[0062] Some embodiments of this application provide an electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization.

[0063] like Figures 1 to 5 As shown, the first embodiment of the present invention proposes an electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization. The electromagnetic sensors have a standardized scheduling interface and can support overall scheduling. The method includes the following steps:

[0064] S1. Select the target for optimizing the scheduling of sensing resources, which includes: sensing resource load and task completion effect;

[0065] The perceived resource load index system reflects the utilization level of each resource. In S1, the perceived resource load is expressed as:

[0066] minW T = min( ) ;

[0067] in, W T Indicates the total load of perceived resources; Let n be the load of the k-th sensing resource, and there are n sensing resources in total.

[0068] The effectiveness of task completion is related to the task type. For frequency monitoring tasks, the effectiveness in S1 is reflected in achieving the maximum single-layer coverage rate of the spatiotemporal frequency dimension of the target area. This is measured by the ratio of the monitored area to the target area. The effectiveness of resource scheduling is verified by establishing corresponding optimization models and algorithms. If the... If the task is a frequency monitoring task, then It can be represented as:

[0069] ;

[0070] in, Indicates the first The area that a single sensing resource can cover; Indicates the first The area of ​​the monitoring zone for each resource; Used to calculate the area of ​​the total covered region; Used to calculate the area of ​​the overlapping region between two regions; This indicates the coverage rate of the target monitoring area covered by the scheduled resources, satisfying... , Indicates complete coverage. This indicates that the target area cannot be monitored.

[0071] S2. Analyze the optimization objectives of sensing resource scheduling and establish a multi-objective optimization sensing resource scheduling model;

[0072] S2 includes the following steps:

[0073] S21. Decompose the sensing task into several jobs and count the number of sensing resources available for scheduling;

[0074] Suppose there are currently The first perception task, in which the second... Each perception task can be broken down into... For each task, then for all current perceptual tasks, a total of [number] tasks can be decomposed into [number]. There are [number] assignments. If there are currently [number] assignments... If there are several available sensing resources, then under the condition of maximizing utilization, [the following will be implemented / implemented]. Each sensing resource is mapped to The scheduling process involves solving specific tasks. This embodiment obtains the scheduling results by establishing a multi-objective optimization model.

[0075] S22. Map several sensing resources to several tasks, and define a mapping matrix. The first in the matrix Line number The elements of a column are represented as , The value represents the first Is the resource allocated to the first...? One assignment;

[0076] Multi-objective optimization models need to solve for the mapping between resources and jobs, and different jobs for different tasks are represented in the matrix. Arranged in order, that is The first line to the second line The first line is used to represent the job of the first task. The Arriving The row is used to represent the first row. The assignment for each task.

[0077] Mapping matrix in S22 The job exclusivity constraint and resource independence constraint should be satisfied;

[0078] The job exclusivity constraint means that each job can only select one sensing resource;

[0079] The resource independence constraint means that a perceived resource can be allocated to at most one job.

[0080] That is, the mapping matrix The following conditions must be met:

[0081] ;

[0082] when At that time, it indicates that the first The resource is allocated to the first One assignment; when When, it indicates the first The resource will not be allocated to the first one. One assignment. Map the matrix. As a decision variable in a multi-objective optimization model.

[0083] S23. Establish a function to constrain the quantity of perceived resources. , Used to constrain the quantity of resources during resource scheduling;

[0084] Function for constraining the quantity of perceived resources in S23 for:

[0085] ;

[0086] Where n represents the number of sensing resources available for scheduling; m represents the current number of sensing resources available for scheduling. The first perception task, in which the second... Each perception task can be broken down into... For each task, then for all current perceptual tasks, a total of [number] tasks can be decomposed into [number]. One assignment.

[0087] S24. Establish a function to constrain the performance of the task. ;

[0088] Functions in S24 that constrain task completion effects It consists of functions that describe the results of multiple tasks, specifically:

[0089] ;

[0090] in, To measure the first A function that determines the completion status of an assignment. The form is related to the objective of the task; These are weighting coefficients, used to represent the weighting coefficients of the first... The importance of each assignment.

[0091] S25. Based on S23 and S24, establish a multi-objective optimization sensing resource scheduling model.

[0092] In the above technical solution, the multi-objective optimization sensing resource scheduling model in S25, and the objective function It can be represented as:

[0093] ;

[0094] in, and Hyperparameters that are not less than 0 are used to adjust... and The proportion it accounts for in the objective function.

[0095] S3. Using a fitness-optimized genetic algorithm designed based on the characteristics of the spectrum monitoring task completion effect, find the optimal sensing resource selection scheme that meets the requirements of the sensing task.

[0096] Since the completion of spectrum monitoring tasks involves diverse, repetitive, and complex calculations at the operational level, this embodiment adopts a genetic algorithm based on fitness optimization (GFOGA). The genetic algorithm is designed to be adapted to the characteristics of the completion of spectrum monitoring tasks. By establishing a mapping between the task completion effect value and the individual, the speed of individual improvement is accelerated, and the fitness of the individual is optimized.

[0097] The fitness-based genetic algorithm in S3 includes algorithm initialization and problem solving; the algorithm flow is as follows: Figure 2 As shown;

[0098] The algorithm initialization includes:

[0099] Individual encoding uses a real-number encoding mechanism to describe the solution space in multi-objective optimization problems;

[0100] In scheduling problems involving multiple tasks, traditional binary-encoded vectors are insufficient for describing the solution space. Therefore, this embodiment uses a real-number encoding mechanism to describe the solution space in multi-objective optimization problems. Defining a vector... , its first The elements are , , representing the first Each sensing resource is allocated to One assignment. When At that time, it represents the first Individual sensing resources are not allocated. Figure 3 The encoding results of a feasible solution for a given solution are shown for 6 sensing resources and 3 tasks. Figure 3 This indicates that the first job will call resources 2 and 5, the second job will call resources 1 and 4, the third job will call resource 3, and resource 6 will not be called by any job.

[0101] Establish a fitness function, using the objective function of the multi-objective optimization perception resource scheduling model as the fitness function;

[0102] Genetic algorithms use a fitness function to evaluate the quality of each individual in the population. The higher the fitness function value of an individual, the better the individual is and the closer it is to the optimal solution.

[0103] Since the solution space in this embodiment is an integer space, when the number of resources to be scheduled changes, It will change significantly and will combine Reflecting changes in the objective function Therefore, this project directly uses the objective function as the fitness function, which is:

[0104] ;

[0105] in, This is the fitness function.

[0106] An initial population is generated. For each schedulable sensor resource, a feasible set is generated. The elements in the set are the supported job numbers. For each individual gene, a value is randomly selected from the feasible set of its corresponding sensor resource and assigned to it, thereby forming a single individual in the initial population, and the initial population for the algorithm to solve is obtained.

[0107] Different resources can support different tasks, mainly because different sensing resources have different capability ranges, resulting in different tasks they can support. For example, sensing resource 1 is a spectrum monitoring resource, and sensing resource 2 is a spectrum reconnaissance resource; their functions are different. In this embodiment, a feasible set is generated for each schedulable sensing resource, and the elements in the set are the supported task numbers. For example, the first... A feasible set of sensing resources is , For the supported first The assignment number.

[0108] For each individual gene, a value is randomly selected from the feasible set of corresponding perceptual resources and assigned to it, thus forming a single individual in the initial population. This process is repeated to obtain the initial population obtained by the algorithm.

[0109] The problem-solving process includes:

[0110] Individual fitness calculation involves decoding each individual in the population to obtain feasible solutions, establishing a unique mapping between task completion performance and individual fitness, and using feasible solutions to calculate individual fitness.

[0111] In this embodiment, the algorithm stops when the number of iterations exceeds 1000 or the maximum individual fitness remains unchanged for more than 10 iterations. In genetic algorithms, the task completion effect function is calculated with each individual fitness calculation, and repeatedly calculating this for the same individual consumes a significant amount of time. Therefore, it is necessary to optimize individual fitness by establishing a unique mapping between the task completion effect value and the individual, thereby accelerating the algorithm's computation process and reducing time complexity.

[0112] Select and retain individuals with high fitness.

[0113] This invention employs the selection operation of a traditional genetic algorithm to retain individuals with high fitness.

[0114] Regarding the selection of hyperparameters and Used to adjust the weight of the amount of sensing resources and the task completion effect in multi-objective optimization. The larger the value, the higher the requirement for the amount of perceptual resources; conversely, the higher the requirement for the effectiveness of task completion. When At that time, all sensing resources can be allocated to improve task completion. And when... At this point, optimizing the model becomes meaningless because the constraint of task completion effectiveness is lost, and the perceived resources will lose their scheduling purpose. In the actual use of the model, and The value can be flexibly adjusted according to the resource scheduling objectives, or it can be determined by using the analytic hierarchy process (AHP) algorithm combined with expert experience.

[0115] Hyperparameters Used to indicate the importance of an assignment, i.e. The larger the value, the higher the priority the task should be in scheduling. In practical use, This corresponds to the priority of tasks / assignments; the higher the priority, the better. The larger the value, the better. When all When all are the same, it means that all jobs are at the same priority.

[0116] Crossover: In this embodiment, the crossover operation of the traditional genetic algorithm is used.

[0117] However, since the value of an individual gene may not exist in the feasible set of the sensory resources corresponding to that gene after crossover, this embodiment corrects such crossover results by randomly selecting values ​​from the feasible set of sensory resources corresponding to the gene to cover the erroneous values.

[0118] Gene mutation is achieved by randomly selecting values ​​from the feasible set of sensory resources corresponding to the gene.

[0119] The second embodiment of this invention proposes an electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization, and based on the first embodiment, as follows: Figures 1 to 5 As shown, the resource scheduling technique based on fitness-optimized genetic algorithms was implemented. By establishing a corresponding optimization model and verifying the resource scheduling effect, resource optimization allocation for spectrum monitoring area coverage was achieved. The resource scheduling results for a frequency monitoring operation are shown in the table below:

[0120] Relationship between target area coverage and the number of sensor resources

[0121]

[0122] For full coverage scenarios, while maintaining full coverage of the target area, the method proposed in this embodiment can reduce the number of scheduled spectrum sensors from 13 to 7. Simulation results are as follows: Figure 4 As shown; for local coverage scenarios, while maintaining a 94% coverage rate, the method proposed in this embodiment can reduce the number of scheduled spectrum sensors from 6 to 3. The simulation results are as follows. Figure 5 As shown.

[0123] In this specification, the illustrative expressions of the terms used do not necessarily refer to the same embodiments or examples. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0124] Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention shall be included within the scope of protection of this invention.

Claims

1. A method for scheduling electromagnetic sensor resources for coverage optimization in a spectrum monitoring area, characterized in that, Includes the following steps: S1. Select the target for optimizing the scheduling of sensing resources, which includes: sensing resource load and task completion effect; S2. Analyze the optimization objectives of sensing resource scheduling and establish a multi-objective optimization sensing resource scheduling model; S3. Using a fitness-optimized genetic algorithm designed based on the characteristics of the spectrum monitoring task completion effect, find the optimal sensing resource selection scheme that meets the requirements of the sensing task. In S1, the task completion effect is reflected in achieving the maximum single-layer coverage rate of the target area in the spatiotemporal frequency dimension. This is measured by the ratio of the monitored area to the target area, and the resource scheduling effect is verified by establishing corresponding optimization models and algorithms. It can be represented as: ； in, Indicates the first The area that a sensing resource can cover, where n represents the number of sensing resources available for scheduling; Indicates the first The area of ​​the monitoring zone for each resource; Used to calculate the area of ​​the total covered region; Used to calculate the area of ​​the overlapping region between two regions; This indicates the coverage rate of the target monitoring area covered by the scheduled resources, satisfying... , Indicates complete coverage. This indicates that the target area cannot be monitored; S2 includes the following steps: S21. Decompose the sensing task into several jobs and count the number of sensing resources available for scheduling; S22. Map several sensing resources to several tasks, and define a mapping matrix. The first in the matrix Line number The elements of a column are represented as , The value represents the first Is the resource allocated to the first...? One assignment; S23. Establish a function to constrain the quantity of perceived resources. ; S24. Establish a function to constrain the performance of the task. ; S25. Based on S23 and S24, establish a multi-objective optimization sensing resource scheduling model.

2. The electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization according to claim 1, characterized in that, In S1, the perceived resource load is represented as: minW T = min( ) ； in, W T Indicates the total load of perceived resources; Let n be the load of the k-th sensing resource, and there are n sensing resources in total.

3. The electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization according to claim 1, characterized in that, Mapping matrix in S22 The job exclusivity constraint and resource independence constraint should be satisfied; The job exclusivity constraint means that each job can only select one sensing resource; The resource independence constraint means that a perceived resource can be allocated to at most one job.

4. The electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization according to claim 1, characterized in that, Function for constraining the quantity of perceived resources in S23 for: ； Where n represents the number of sensing resources available for scheduling; m represents the current number of sensing resources available for scheduling. The first perception task, in which the second... Each perception task can be broken down into... For each task, then for all current perceptual tasks, a total of [number] tasks can be decomposed into [number]. One assignment.

5. The electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization according to claim 1, characterized in that, Functions in S24 that constrain task completion effects for: ； in, To measure the first A function that determines the completion status of each assignment; These are weighting coefficients, used to represent the weighting coefficients of the first... The importance of each assignment.

6. The electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization according to claim 1, characterized in that, A multi-objective optimization-based perception resource scheduling model in S25, and its objective function. It can be represented as: ； in, and Hyperparameters that are not less than 0 are used to adjust... and The proportion it accounts for in the objective function.

7. The electromagnetic sensor resource scheduling method for spectrum monitoring area coverage optimization according to claim 1, characterized in that, The fitness-based genetic algorithm in S3 includes algorithm initialization and problem solving; The algorithm initialization includes: Individual encoding uses a real-number encoding mechanism to describe the solution space in multi-objective optimization problems; Establish a fitness function, using the objective function of the multi-objective optimization perception resource scheduling model as the fitness function; An initial population is generated. For each schedulable sensor resource, a feasible set is generated. The elements in the set are the supported job numbers. For each individual gene, a value is randomly selected from the feasible set of its corresponding sensor resource and assigned to it, thereby forming a single individual in the initial population, and the initial population for the algorithm to solve is obtained. The problem-solving process includes: Individual fitness calculation involves decoding each individual in the population to obtain feasible solutions, establishing a unique mapping between task completion performance and individual fitness, and using feasible solutions to calculate individual fitness. Select and retain individuals with high fitness. Crossover is used to correct crossover results where the value of an individual gene does not exist in the feasible set of the perceptual resources corresponding to that gene. Values ​​are randomly selected from the feasible set of perceptual resources corresponding to the gene to cover the erroneous values. Gene mutation is achieved by randomly selecting values ​​from the feasible set of sensory resources corresponding to the gene.

8. A method for scheduling electromagnetic sensor resources for coverage optimization in a spectrum monitoring area according to any one of claims 1 to 7, characterized in that, The electromagnetic sensor has a standardized scheduling interface, which can support overall scheduling.

Images