Intelligent short-wave communication resource allocation method and system based on strategy revenue

Abstract

The invention provides an intelligent short-wave communication resource allocation method and system based on strategy revenue, and relates to the technical field of network communication, and the method comprises the steps: obtaining communication station, equipment frequency, historical business and electromagnetic environment communication resource data; constructing a hybrid coding chromosome based on the site basic data, decoding the hybrid coding chromosome into a site equipment configuration scheme, and calculating a corresponding frequency use scheme and a path total efficiency evaluation value; establishing a layout cost, regional guarantee efficiency and strategy income model by using equipment frequency, historical business, electromagnetic environment and evaluation value; inputting each set of scheme into the model, calculating the total strategy income, the area coverage rate and the total cost of the scheme, and forming a fitness vector; according to the method, the sum of all components of the fitness vector is maximized as a target, iterative optimization is carried out by adopting a non-dominated sorting genetic algorithm, an optimal station equipment configuration and resource allocation scheme is obtained, and the overall benefit of resource use and decision scientificity are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of network communication technology, in particular to a strategy benefit-based intelligent short-wave communication resource allocation method and system. BACKGROUND

[0002] As a communication guarantee means relying on ionosphere reflection for long-distance transmission, short-wave communication plays a vital role in the fields of military and global maritime distress and safety system. The traditional short-wave communication task resource allocation method highly depends on manual experience. The operator first selects the guarantee site and communication equipment, and then calculates a set of frequency with the best communication quality in combination with the task area.

[0003] This traditional method has significant limitations: when cooperating with a single or multiple communication tasks, it lacks a systematic framework to comprehensively weigh from multiple dimensions such as "site quantity, equipment resources, frequency resources, and communication effect", and cannot quantify and maximize the "overall benefit of resource use". SUMMARY

[0004] To overcome the above-mentioned lack of overall framework to maximize the overall benefit of resources from multiple dimensions under the resources of site quantity, equipment resources, frequency resources, and communication effect, the present application provides a strategy benefit-based intelligent short-wave communication resource allocation method and system.

[0005] To solve the above technical problems, the technical solutions of the present application are as follows: The present application provides a strategy benefit-based intelligent short-wave communication resource allocation method and system, comprising: obtaining communication resource data of short-wave communication, including communication site basic data, equipment frequency feature parameters, historical communication business data, and electromagnetic environment perception data; constructing a plurality of hybrid coding chromosomes based on the communication site basic data; decoding each of the hybrid coding chromosomes into a corresponding site equipment configuration scheme, and calculating a corresponding frequency use scheme and path total efficiency evaluation value for each of the site equipment configuration schemes; establishing a site layout cost model, a regional guarantee efficiency model, and a strategy benefit model based on the equipment frequency feature parameters, the historical communication business data, the electromagnetic environment perception data, and the path total efficiency evaluation value; inputting each of the site equipment configuration schemes and its corresponding frequency use scheme into the site layout cost model, the regional guarantee efficiency model, and the strategy benefit model, respectively, calculating the total strategy benefit, the regional coverage rate, and the total cost of each of the site equipment configuration schemes, and forming an adaptability vector with the total strategy benefit, the regional coverage rate, and the total cost of each set of scheme; The non-dominated sorting genetic algorithm is iteratively optimized with the maximum sum of each component of the fitness vector as the goal, and a corresponding site equipment configuration scheme with the maximum sum of each component of the fitness vector is obtained as the optimal communication resource allocation scheme.

[0006] Preferably, a plurality of hybrid encoding chromosomes are constructed based on the communication site basic data, including: The hybrid encoding chromosome adopts segmented hybrid encoding. Each site occupies a gene in the hybrid encoding chromosome, and each site equipment in each site occupies at least two gene bits in the corresponding gene of the site. The first gene bit indicates whether to enable the type of site equipment, and the second gene bit indicates the antenna pointing angle of the site equipment.

[0007] Preferably, each of the hybrid encoding chromosomes is decoded into a corresponding site equipment configuration scheme, and a corresponding frequency usage scheme and path total performance evaluation value are calculated for each of the site equipment configuration schemes, including: Each of the hybrid encoding chromosomes is decoded into a corresponding specific site equipment configuration scheme. The site equipment configuration scheme is mapped to a time-frequency grid with time as the horizontal axis and frequency as the vertical axis. The frequency usage performance and transfer loss of each grid are calculated. According to the frequency usage performance and transfer loss of each, the Dijkstra algorithm is used to plan the optimal frequency usage path of the time-frequency grid, the optimal frequency usage path is set as the frequency usage scheme, and the path total performance evaluation value of the optimal frequency usage path is calculated.

[0008] Preferably, the frequency usage performance is calculated as follows:

[0009] Wherein, is a subtask usage frequency the frequency usage performance at time t; is a subtask usage frequency propagation loss at time t; is the maximum allowable propagation loss; is an invalid frequency weight parameter; is the transmission power of the jth site jth type of equipment; is the transmission gain of the antenna; is the user terminal antenna gain at the receiving point; is the receiving point coverage determination threshold.

[0010] Preferably, the transition loss is calculated as follows:

[0011] wherein, is the frequency at time point transitions to the frequency at time point ; is the state transition weight parameter; , is the frequency value at different frequency points.

[0012] Preferably, the path total performance evaluation value is calculated as follows:

[0013] wherein, is the path total performance evaluation value, is the total task time period data; is the frequency index selected at the time period; is the use frequency performance of frequency at the time period; is the frequency value actually used at the time period ; is the transition loss from the frequency at the time period to the frequency at the time period , represents the total communication quality of the selected frequency at all time periods during the entire task, represents the total cost generated in the frequency switching process.

[0014] Preferably, the total strategy benefit is calculated as follows: Calculate the single task strategy benefit:

[0015] wherein, is the task priority benefit, is the site cost benefit, is the equipment performance benefit, is the communication effect benefit; Calculate the total strategy benefit: .

[0016] Preferably, the area coverage rate is calculated as follows: Predict the path loss using the pre-trained propagation loss model:

[0017] wherein, , is a transceiver point coordinate, is a loss calculation time, is a usage frequency, is a sunspot number; a path loss is calculated to determine a coverage state of a site; a site is equipped with a first type equipment at a time , a usage frequency is used to calculate a coverage state of a receiving point , and a calculation method is as follows:

[0018] a guarantee area of an acquisition scheme is meshed to obtain a spatial point set ; time is discretized to obtain a time point set ; a region coverage rate is calculated as follows:

[0019] wherein, is a weight of a space-time grid point , is an indicator function, is a required minimum number of simultaneously covered sites, is a time-frequency path performance factor; wherein, the time-frequency path performance factor is calculated as follows:

[0020] wherein, and are weight parameters.

[0021] Preferably, the total cost is calculated as follows:

[0022] wherein, is a total number of selectable sites in the system; is a total number of types of selectable equipment; is a binary decision variable; is a fixed deployment cost of a site ; and is an operation cost of using a first type equipment at a site . ​

[0023] The application also provides an intelligent short-wave communication resource allocation system based on strategy benefits, comprising: A communication resource data acquisition module is configured to acquire communication resource data of short-wave communication, including communication site basic data, equipment frequency use characteristic parameters, historical communication service data and electromagnetic environment sensing data. A hybrid coding chromosome construction module is configured to construct a plurality of hybrid coding chromosomes based on the communication site basic data. A configuration scheme solving module is configured to decode each of the hybrid coding chromosomes into a corresponding site equipment configuration scheme, and calculate a corresponding frequency use scheme and path total efficiency evaluation value for each of the site equipment configuration schemes. A model construction module is configured to establish a site layout cost model, a regional guarantee efficiency model and a strategy benefit model based on the equipment frequency use characteristic parameters, the historical communication service data, the electromagnetic environment sensing data and the path total efficiency evaluation value. A fitness vector composition module is configured to input each of the site equipment configuration schemes and its corresponding frequency use scheme into the site layout cost model, the regional guarantee efficiency model and the strategy benefit model respectively, calculate total strategy benefits, regional coverage rates and total costs of each of the site equipment configuration schemes, and compose the total strategy benefits, the regional coverage rates and the total costs of each set of scheme into a fitness vector. An iterative optimization module is configured to maximize the sum of components of the fitness vector, and obtain a site equipment configuration scheme corresponding to the maximum sum of components of the fitness vector as an optimal communication resource allocation scheme by iterative optimization using a non-dominated sorting genetic algorithm.

[0024] Compared with the prior art, the technical scheme of the application has the following beneficial effects: The application constructs a plurality of site equipment configuration schemes according to communication resources, solves total strategy benefits, regional coverage rates and total costs by using constructed models, composes the total strategy benefits, the regional coverage rates and the total costs into a fitness vector, and optimizes iteration with the maximum of the fitness vector as a target to obtain an optimal communication resource allocation scheme, thereby significantly improving overall benefits of resource use and decision-making scientificity. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 It is a flowchart of an embodiment 1 of an intelligent short-wave communication resource allocation method based on strategy benefits. Figure 2 It is a structural diagram of a hybrid coding chromosome in an embodiment 2. Figure 3 It is a structural diagram of a time-frequency grid in an embodiment 2. Figure 4Flowchart of the hybrid optimization process based on NSGA-II and Dijkstra algorithm in Example 2; Figure 5 Flowchart of the propagation loss model training process in Example 2; Figure 6 BiGRU network structure in Example 2; Figure 7 Single-site guarantee different resource allocation scheme revenue statistics in Example 2; Figure 8 Two-site guarantee different resource allocation scheme revenue statistics in Example 2; Figure 9 Three-site guarantee different resource allocation scheme revenue statistics in Example 2; Figure 10 Center frequency recommended by site day-night frequency mode in Example 2; Figure 11 Center frequency recommended by site day-night frequency mode in Example 2; Figure 12 Structure of an intelligent shortwave communication resource allocation system based on strategy revenue in Example 3. DETAILED DESCRIPTION

[0026] The accompanying drawings are only for illustrative purposes and should not be construed as limiting the patent; In order to better illustrate the present embodiment, some components in the drawings may be omitted, enlarged or reduced, and do not represent the actual size of the product; It is understandable that some well-known structures and their descriptions in the drawings may be omitted for those skilled in the art.

[0027] The technical solutions of the present application will be further described below in conjunction with the drawings and examples.

[0028] Example 1 The present embodiment provides an intelligent shortwave communication resource allocation method based on strategy revenue, as shown in Figure 1 , comprising: Obtaining communication resource data of shortwave communication, including communication site basic data, equipment frequency use characteristic parameters, historical communication service data and electromagnetic environment perception data; Constructing a plurality of hybrid encoding chromosomes based on the communication site basic data; Decoding each of the hybrid encoding chromosomes into a corresponding site equipment configuration scheme, and calculating a corresponding frequency use scheme and path total performance evaluation value for each of the site equipment configuration schemes; establish a site layout cost model, a regional guarantee performance model and a strategy benefit model based on the equipment frequency characteristic parameters, the historical communication service data and the electromagnetic environment sensing data and the path total performance evaluation value; input each of the site equipment configuration schemes and the corresponding frequency use schemes into the site layout cost model, the regional guarantee performance model and the strategy benefit model respectively, calculate the total strategy benefit, the regional coverage rate and the total cost of each of the site equipment configuration schemes, and form a fitness vector of the total strategy benefit, the regional coverage rate and the total cost of each set of scheme; maximize the sum of the components of the fitness vector, and obtain the corresponding site equipment configuration scheme as the optimal communication resource allocation scheme when the sum of the components of the fitness vector is the maximum value by using the non-dominated sorting genetic algorithm for iterative optimization.

[0029] In the specific implementation process, the application first acquires communication resource data of short wave communication, including communication site basic data, equipment frequency characteristic parameters, historical communication service data and electromagnetic environment sensing data; then constructs a plurality of hybrid coding chromosomes based on the communication site basic data; then decodes each of the hybrid coding chromosomes into a corresponding site equipment configuration scheme, and calculates a corresponding frequency use scheme and a path total performance evaluation value for each of the site equipment configuration schemes; establishes a site layout cost model, a regional guarantee performance model and a strategy benefit model based on the equipment frequency characteristic parameters, the historical communication service data and the electromagnetic environment sensing data and the path total performance evaluation value; inputs each of the site equipment configuration schemes and the corresponding frequency use schemes into the site layout cost model, the regional guarantee performance model and the strategy benefit model respectively, calculates the total strategy benefit, the regional coverage rate and the total cost of each of the site equipment configuration schemes, and forms a fitness vector of the total strategy benefit, the regional coverage rate and the total cost of each set of scheme; finally maximizes the sum of the components of the fitness vector, and obtains the corresponding site equipment configuration scheme as the optimal communication resource allocation scheme when the sum of the components of the fitness vector is the maximum value by using the non-dominated sorting genetic algorithm for iterative optimization.

[0030] The application constructs a hybrid coding chromosome and a multi-dimensional evaluation model, and uses a non-dominated sorting genetic algorithm to globally and iteratively optimize short wave communication resources. The method can comprehensively balance site layout cost, regional guarantee performance and strategy benefit, realizes optimal configuration under limited resource constraints, effectively improves communication guarantee performance and overall resource utilization, and overcomes the defects of the prior art of lacking an overall optimization framework.

[0031] Embodiment 2 The embodiment provides an intelligent short wave communication resource allocation method based on strategy benefit, including: The communication resource data of short wave communication includes communication station basic data, equipment frequency characteristic parameters, historical communication service data and electromagnetic environment sensing data; It should be noted that in the embodiment, the communication station basic data includes the name, type, geographical position, serviceable state of fixed / mobile station, and the model and number of configured transmitting / receiving equipment and antenna, etc. The equipment frequency characteristic parameters include the static parameters of each station transmitting / receiving equipment and antenna, including start / stop frequency, transmitting power, receiving sensitivity, antenna gain, directional diagram, equipment type, antenna angle. The historical communication service data includes the communication parties, used frequency, communication effect evaluation, time length, place and time. The electromagnetic environment sensing data includes real-time or near real-time collected electromagnetic spectrum monitoring data, short wave detection data and sunspot number.

[0032] Step one, constructing a plurality of hybrid coding chromosomes based on the communication station basic data; It should be noted that in the embodiment, a plurality of hybrid coding chromosomes are constructed based on the communication station basic data, and the chromosome coding is as shown in Figure 2 includes: A certain number of hybrid coding chromosomes are generated based on heuristic rules, and each chromosome represents a complete and assessable station equipment configuration scheme. The hybrid coding chromosome adopts segmented hybrid coding. Each station occupies a gene in the hybrid coding chromosome, and each station equipment in the station occupies at least two gene bits in the corresponding gene of the station. The first gene bit represents whether to enable the type of station equipment, and the second gene bit represents the antenna pointing angle of the station equipment. Step two, decoding each hybrid coding chromosome into a corresponding station equipment configuration scheme, and calculating the corresponding frequency use scheme and path total performance evaluation value for each station equipment configuration scheme. It should be noted that in the embodiment, each hybrid coding chromosome is decoded into a corresponding station equipment configuration scheme, and the corresponding frequency use scheme and path total performance evaluation value are calculated for each station equipment configuration scheme, including: Each hybrid coding chromosome is decoded into a corresponding specific station equipment configuration scheme. The station equipment configuration scheme is mapped to a time-frequency grid with time as the horizontal axis and frequency as the vertical axis, as shown in Figure 3 . The frequency performance and transfer loss of each grid are calculated. According to the frequency usage efficiency and the transition loss of each, an optimal frequency usage path of the time-frequency grid is planned by using Dijkstra algorithm, the optimal frequency usage path is set as the frequency usage scheme, and a path total efficiency evaluation value of the optimal frequency usage path is calculated.

[0033] It should be noted that in the embodiment, the frequency usage efficiency calculation method is as follows:

[0034] Wherein, is the subtask using frequency the frequency usage efficiency at the time; is the subtask using frequency propagation loss; is the maximum allowable propagation loss; is the invalid frequency weight parameter; is the transmission power of the th station type device; is the transmission gain of the antenna; is the user terminal antenna gain at the receiving point; is the receiving point coverage determination threshold.

[0035] It should be noted that in the embodiment, the transition loss calculation method is as follows:

[0036] Wherein, is the transition loss from the frequency at the time point to the frequency at the time point ; is the state transition weight parameter; , is the frequency value of different frequency points.

[0037] It should be noted that in the embodiment, the Dijkstra algorithm is used to dynamically plan an optimal frequency usage path from the starting time to the ending time in the grid, the path is set as the frequency usage scheme under the equipment configuration, and a path total efficiency evaluation value is solved, and the path total efficiency evaluation value calculation method is as follows:

[0038] Wherein, is the path total efficiency evaluation value, is the total task time period data; is the transmission power of the a frequency index selected in a time period; is the frequency used in the first time period; is the frequency efficiency of the frequency used in the first time period; is the frequency value actually used in the first time period; is the transition loss from the frequency used in the first time period to the frequency used in the second time period; is the total cost of frequency switching in the whole task, the greater the value, the more optimal the frequency selection in each time period, is the total sum of the communication quality of the selected frequencies in all time periods during the whole task, the greater the value, the more optimal the frequency selection in each time period, is the total cost of frequency switching in the whole task, the greater the value, the more optimal the frequency selection in each time period,

[0039] Based on the equipment frequency feature parameters, historical communication service data, electromagnetic environment perception data and path total efficiency evaluation value, a site layout cost model, a regional guarantee efficiency model and a strategy benefit model are established; Each of the site equipment configuration schemes and its corresponding frequency use scheme is input into the site layout cost model, the regional guarantee efficiency model and the strategy benefit model, respectively, to calculate the total strategy benefit, the regional coverage rate and the total cost of each of the site equipment configuration schemes, and the total strategy benefit, the regional coverage rate and the total cost of each set of scheme are combined to form a fitness vector; It should be noted that in the embodiment, the strategy benefit weighting coefficient table is shown in Table 1: Table 1 Strategy benefit weighting coefficient table

[0040] The total strategy benefit is calculated as follows: The single-task strategy benefit is calculated as follows:

[0041] wherein, is the task priority benefit, is the site cost benefit, is the equipment performance benefit, is the communication effect benefit; The total strategy benefit is calculated as follows: .

[0042] The sum of the components of the fitness vector is maximized, and a non-dominated sorting genetic algorithm is used for iterative optimization to obtain the site equipment configuration scheme corresponding to the maximum sum of the components of the fitness vector as the optimal communication resource allocation scheme.

[0043] It should be noted that, in this embodiment, the area coverage rate is calculated as follows: Predict path loss using a pre-trained propagation loss model:

[0044] in, , The coordinates of the sender and receiver points, Calculate the time for loss. For usage frequency, The number of sunspots; Calculate the coverage status of the site based on path loss; Site The Type of equipment at all times Frequency of use For receiving point The coverage status is calculated as follows:

[0045] Obtain the protection area of ​​the solution, and then mesh the protection area to obtain... A set of spatial points Discretize the time to obtain A set of time points ; Calculate the area coverage:

[0046] in, It is a spatiotemporal grid point The weight, It is an indicator function. It is the minimum number of sites that can be covered simultaneously. It is the time-frequency path efficiency factor; The time-frequency path efficiency factor is calculated as follows:

[0047] in, and These are weight parameters.

[0048] It should be noted that, in this embodiment, the total cost is calculated as follows:

[0049] in, This represents the total number of selectable sites in the system. This represents the total number of types of optional equipment. It is a binary decision variable; It is a website the fixed deployment cost of the equipment; is the operation cost of using the first type equipment on the site .

[0050] Step three, using non-dominated sorting genetic algorithm to iteratively optimize the sum of each component of the fitness vector, and obtain the corresponding site equipment configuration scheme when the sum of each component of the fitness vector is maximum as the optimal communication resource allocation scheme, including: It should be noted that in this embodiment, the total strategy benefit, the area coverage rate and the total cost are set as a vector , and a non-dominated sorting genetic algorithm (NSGA-II) is used as a global search engine, and a hybrid coding chromosome is used to represent the optimization basic framework of the site equipment configuration scheme, to find a solution that can maximize the fitness vector at the same time, and the process is as shown in Figure 4 . First, according to the calculated fitness vector , the NSGA-II performs non-dominated sorting and congestion calculation on all individuals in the current population, and selects excellent individuals according to the calculation; Genetic operation: including crossover and mutation; Perform genetic operation on the selected individuals to produce new offspring.

[0051] Crossover operation: randomly select two parent chromosomes, and for the genes of the same site, if the equipment activation state is different, exchange, and if the same, perform arithmetic crossover on the antenna angle: , wherein is a random number uniformly distributed in the interval [0, 1].

[0052] Mutation operation: change the equipment activation state of a certain site or apply random disturbance to the antenna pointing angle with a certain probability: , wherein is a variance parameter of the mutation strength. Convergence judgment Repeat steps two and three until the maximum number of iterations is reached or the solution set quality is stable. Finally, output a set of Pareto optimal solutions, that is, a series of resource allocation schemes that achieve the best trade-off in strategy benefit, guarantee performance and cost, for the decision maker to finally select.

[0053] In actual use, the communication effect data and electromagnetic environment data generated by the new task are also used as new samples through incremental learning for periodic retraining of the shortwave propagation loss model and updating of the strategy benefit evaluation standard, so that the entire system can adapt to environmental changes and realize continuous performance improvement.

[0054] The modeling and training of the shortwave propagation loss model are as followsFigure 5 As shown in the figure, the network of the short-wave propagation loss model adopts a hybrid model of a convolutional neural network (CNN) and a bidirectional gated recurrent unit (Bi-GRU), and the structure is as shown in the figure Figure 6 As shown in the figure, the CNN is responsible for extracting spatial local features from the input data, and the Bi-GRU captures the time sequence dependence; The loss function for training is:

[0055] Among them, is the mean square error loss, which ensures the prediction accuracy; is a regularization term to prevent overfitting; is the predicted loss value of the model for the i-th sample; is the corresponding true loss value; is the batch size of training; is a regularization coefficient used to control the regularization speed; , is the weight matrix and bias vector of the CNN network; , is the weight matrix and bias vector of the Bi-GRU network; is the square of the norm.

[0056] The effectiveness of the present application is also verified by simulation and field test. In the simulation, various allocation schemes under the scene of 1, 2, and 3 sites guaranteeing 3 mobile users are compared, and the present application algorithm can stably recommend the scheme with the maximum sum of the components of the fitness vector, and the recommended results are as shown in Figure 7 、 Figure 8 、 Figure 9 ; In the actual communication test, 120 voice services are carried out using the resource allocation scheme recommended by the present application (including the center frequency planned according to the day and night frequency of the station, and the schematic diagram is shown in Figure 10 ). Compared with the traditional manual allocation method, the present application scheme reaches 97.15% and 88.26% in the communication link establishment success rate and the communication quality excellent rate, respectively, and the performance is significantly improved (at least increased by 5.48% and 11.84%), and the statistical results are shown in Figure 11 . This fully proves the great advantage of the present application in improving the communication reliability and resource utilization efficiency.

[0057] Embodiment 3 The present embodiment provides an intelligent short-wave communication resource allocation system based on strategy revenue, which is used to realize the method of embodiment 1 or 2, as shown in Figure 12 , including: ​The communication resource data acquisition module is configured to acquire communication resource data of short-wave communication, including communication station basic data, equipment frequency use characteristic parameters, historical communication service data and electromagnetic environment sensing data. The hybrid encoding chromosome construction module is configured to construct a plurality of hybrid encoding chromosomes based on the communication station basic data. The configuration scheme solving module is configured to decode each of the hybrid encoding chromosomes into a corresponding station equipment configuration scheme, and calculate a corresponding frequency use scheme and path total performance evaluation value for each of the station equipment configuration schemes. The model construction module is configured to establish a station layout cost model, a regional guarantee performance model and a strategy benefit model based on the equipment frequency use characteristic parameters, the historical communication service data and the electromagnetic environment sensing data and the path total performance evaluation value. The fitness vector composition module is configured to input each of the station equipment configuration schemes and its corresponding frequency use scheme into the station layout cost model, the regional guarantee performance model and the strategy benefit model respectively, calculate total strategy benefit, regional coverage rate and total cost of each of the station equipment configuration schemes, and compose total strategy benefit, regional coverage rate and total cost of each set of scheme into a fitness vector. The iterative optimization module is configured to maximize the sum of components of the fitness vector, and obtain a station equipment configuration scheme corresponding to the maximum sum of components of the fitness vector as an optimal communication resource allocation scheme by iterative optimization using a non-dominated sorting genetic algorithm.

[0058] The same or similar reference signs correspond to the same or similar components; The terms describing the positional relationship in the drawings are only used for illustrative description, and should not be understood as a limitation to the patent; Obviously, the above-described embodiments of the present application are only examples for clearly illustrating the present application, and are not intended to limit the implementation modes of the present application. Based on the above description, other different forms of changes or variations can be made by those skilled in the art. Here, all the implementation modes are not required or can not be exhausted. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the protection scope of the claims of the present application.

Claims

1. A method for intelligent short-wave communication resource allocation based on policy benefit, characterized in that, The method comprises the following steps: Obtaining communication resource data of short wave communication, including communication site basic data, equipment frequency use characteristic parameters, historical communication service data and electromagnetic environment sensing data; Constructing a plurality of hybrid encoding chromosomes based on the communication site basic data; Decoding each of the hybrid encoding chromosomes into a corresponding site equipment configuration scheme, and calculating a corresponding frequency use scheme and a path total performance evaluation value for each of the site equipment configuration schemes; Based on the equipment frequency use characteristic parameters, historical communication service data, electromagnetic environment sensing data and path total performance evaluation value, a site layout cost model, a regional guarantee performance model and a strategy benefit model are established; Each of the site equipment configuration schemes and its corresponding frequency use scheme is input into the site layout cost model, the regional guarantee performance model and the strategy benefit model respectively, the total strategy benefit, the regional coverage rate and the total cost of each of the site equipment configuration schemes are calculated, and the total strategy benefit, the regional coverage rate and the total cost of each scheme are combined into a fitness vector; The sum of the components of the fitness vector is maximized as the target, and a non-dominated sorting genetic algorithm is used for iterative optimization, so that the site equipment configuration scheme corresponding to the maximum sum of the components of the fitness vector is obtained as the optimal communication resource allocation scheme.

2. The method of claim 1, wherein, Constructing a plurality of hybrid encoding chromosomes based on the communication site basic data, comprising: The hybrid encoding chromosome adopts segmented hybrid encoding; Each site occupies one gene in the hybrid encoding chromosome, and each site equipment in each site occupies at least two gene bits in the corresponding gene of the site, the first gene bit indicating whether the type of site equipment is enabled, and the second gene bit indicating the antenna pointing angle of the site equipment.

3. The method of claim 2, wherein, Decoding each of the hybrid encoding chromosomes into a corresponding site equipment configuration scheme, and calculating a corresponding frequency use scheme and a path total performance evaluation value for each of the site equipment configuration schemes, comprising: Decoding each of the hybrid encoding chromosomes into a corresponding specific site equipment configuration scheme; Mapping the site equipment configuration scheme to a time-frequency grid with time as the horizontal axis and frequency as the vertical axis; Calculating the frequency use performance and transfer loss of each grid; According to the frequency use performance and transfer loss of each, the Dijkstra algorithm is used to plan the optimal frequency use path of the time-frequency grid, the optimal frequency use path is set as the frequency use scheme, and the path total performance evaluation value of the optimal frequency use path is calculated.

4. The method of claim 3, wherein, The frequency use performance calculation method is as follows: wherein is a sub-task is a frequency of use is a propagation loss at the time of use; is a maximum allowable propagation loss; is a frequency of use is a propagation loss at the time of use; is a maximum allowable propagation loss; is an invalid frequency weight parameter; is a transmission power of a first is a transmission power of a first is a transmission power of a first is a transmission power of a first is a transmission power of a first is a transmission power of a first 5. The method of claim 3, wherein, The transfer loss calculation method is as follows: wherein, is the frequency of transition from time point to time point is the frequency of transition from time point to time point is the transition loss of the transition from time point is a state transition weight parameter; , is the frequency value of different frequency points.

6. The method of claim 3, wherein the method is characterized by: The path total performance evaluation value calculation method is as follows: wherein, is the path total performance evaluation value, is the total task time period data; is the frequency index selected in the first time period; is the frequency performance in the first time period using the frequency ; is the frequency value actually used in the time period ; is the transition loss from the frequency of the time period to the frequency of the time period ; represents the total sum of the communication quality of the selected frequencies of all time periods during the entire task, represents the total cost generated in the frequency switching process.

7. The method of claim 1, wherein, The total strategy benefit calculation method is as follows: Calculating single task strategy benefit: wherein, is a task priority benefit, is a site cost benefit, is an equipment performance benefit, is a communication effectiveness benefit; Compute total strategy returns: .

8. The method of claim 1, wherein, The regional coverage rate calculation method is as follows: A pre-trained propagation loss model is used to predict the path loss: wherein, , is a transceiver point coordinate, is a loss calculation time, is a usage frequency, is a sunspot number; According to the path loss, the coverage state of the site is calculated; station of the first type of equipment at time , using frequency of the coverage state of the receiving point is calculated as follows: acquiring a guarantee area of the scheme, meshing the guarantee area to obtain a set of space points ; discretizing time to obtain a set of time points ; The regional coverage rate is calculated: wherein, is a weight of a space-time grid point , is an indicator function, is a minimum number of simultaneous covered sites required, is a time-frequency path performance factor; The time-frequency path performance factor calculation method is as follows: wherein and are weight parameters.

9. The method of claim 1, wherein, The total cost calculation method is as follows: wherein, is the total number of optional sites in the system; is the total number of kinds of optional equipment; is a binary decision variable; is the fixed deployment cost of a site is the operating cost of using the first kind of equipment at a site is the operating cost of using the second kind of equipment at a site 10. A strategy benefit based intelligent short wave communication resource allocation system for implementing the strategy benefit based intelligent short wave communication resource allocation method of claims 1-9, characterized in that, The method comprises the following steps: A communication resource data acquisition module is configured to obtain communication resource data of short wave communication, including communication site basic data, equipment frequency use characteristic parameters, historical communication service data and electromagnetic environment sensing data; A hybrid encoding chromosome construction module is configured to construct a plurality of hybrid encoding chromosomes based on the communication station basic data; A configuration scheme solving module is configured to decode each of the hybrid encoding chromosomes into a corresponding station equipment configuration scheme, and to calculate a corresponding frequency usage scheme and path total performance evaluation value for each of the station equipment configuration schemes; A model construction module is configured to establish a station layout cost model, a regional guarantee performance model and a strategy benefit model based on the equipment frequency feature parameters, historical communication service data, electromagnetic environment sensing data and path total performance evaluation value; A fitness vector composition module is configured to input each of the station equipment configuration schemes and its corresponding frequency usage scheme into the station layout cost model, the regional guarantee performance model and the strategy benefit model respectively, to calculate the total strategy benefit, regional coverage rate and total cost of each of the station equipment configuration schemes, and to compose the total strategy benefit, regional coverage rate and total cost of each set of scheme into a fitness vector; An iterative optimization module is configured to maximize the sum of components of the fitness vector, and to obtain the corresponding station equipment configuration scheme as the optimal communication resource allocation scheme when the sum of components of the fitness vector is maximum by using the non-dominated sorting genetic algorithm for iterative optimization.

Images