Shore station broadcast simulation method, apparatus and device, and storage medium

Abstract

The invention provides a base station broadcast simulation method and device, equipment and a storage medium. Relates to the technical field of broadcast simulation. The method comprises the following steps: acquiring the proportion of each broadcast station in the total telegraph text amount at a set time; encoding the proportion of each broadcast station in the total telegraph text amount at the set time to obtain an initial population; setting three fitness indexes; determining a fitness calculation formula; the fitness of each individual in the initial population is calculated, two different individuals are randomly selected from the initial population to compare the fitness, the individual with the large fitness is selected, the operation is repeated for multiple times, and a preferred population containing multiple individuals is obtained; and carrying out crossover and variation on the optimized population to obtain a next-generation population, calculating the fitness of the next-generation population, carrying out iteration for multiple times until an iteration termination condition is reached, and outputting the population with the highest fitness as a simulation broadcast plan. The simulation broadcast plan obtained by the method is high in fitness and can meet corresponding simulation requirements.

Description

Technical Field

[0001] The present application relates to the field of broadcast simulation technology, and in particular to a shore station broadcast simulation method, apparatus, device and storage medium. Background Art

[0002] NAVTEX (Navigational Telex) simulator is an important part of GMDSS simulator. Research specifically on NAVTEX simulators includes the following: "Guo Lei, Ren Hongxiang, Tao Rui. Simulation and practical evaluation of NAVTEX receivers for navigation simulators [J]. China Water Transport (Second Half of the Month), 2015, 15(11): 132-135." Research using NAVTEX simulators as sub-parts of GMDSS simulators includes the following: "Yu Jin. Research on operation simulation of FURUNO series GMDSS equipment [D]. Dalian Maritime University, 2013.", "Zhao Liangbin, Yang Jiaxuan, Shang Sinian. Design and implementation of GMDSS simulation system based on B / S [J]. China Navigation, 2016, 39(04): 61-65.", "Wei Wei, Lin Yi. Design and implementation of ship communication system simulator [J]. China Navigation, 2013, 36(04): 21-24+37." These studies have done very well in interface appearance simulation and single-machine operation simulation, but have not involved NAVTEX shore station broadcast simulation.

[0003] In the NAVTEX simulator, receiving messages, setting radio rejection and message rejection are very important functions. If there is no realistic broadcast simulation model to broadcast messages to it, the trainees will not be able to feel the effect of the radio and message rejection settings. More importantly, they will not be able to feel some important situations of actually receiving messages, such as which radio stations are often received and which radio stations are not often received at a certain location, which types of messages are often received, and how the messages broadcast by long-distance radio stations are received. Therefore, the research in the above literature has shortcomings. In this regard, the literature "Cui Kuntao, Sun Wenli, Sun Wenqiang et al. Research on the innovative sharing of GMDSS high-quality experimental teaching resources under the background of new engineering [J]. Laboratory Research and Exploration, 2022, 41(02): 160-163+192. DOI: 10.19927 / j.cnki.syyt.2022.02.034." points out that trainees cannot obtain intuitive cognition through the existing GMDSS virtual simulation teaching, and the training effect is subject to certain restrictions. The document "Han Yundong, Zhong Yunhai, Lan Guohui, Wang Su, Ma Hairui. Research on Virtual NAVTEX Simulation Teaching System [J]. China Educational Technology Equipment, 2019(22):13-15." is equipped with a NAVTEX shore station broadcast model, but it is too simple and does not achieve multi-directional and multi-angle simulation.

[0004] The NAVTEX system is a medium-frequency (MF)-based maritime safety message broadcast system. It broadcasts a wide variety of information, primarily navigational warnings and weather messages. It's difficult to determine when this information is broadcast in high volumes, when it's broadcast in low volumes, and what the broadcast patterns are for each type of message (for example, weather messages are typically broadcast daily, while the broadcast volume for critical messages has no specific pattern). Acquiring data through on-site inspections is prohibitively expensive. Furthermore, messages broadcast by some distant stations can be received under certain conditions (MF waves can extend their transmission range at night due to ionospheric reflection). Therefore, simply asserting in simulations that "a certain broadcast station is too far from the receiver and its message cannot be received" is unwise. Furthermore, due to the inherent characteristics of MF radio communications and other factors (such as multipath, fading, signal interference, station transmit power, and the height and location of the transmitting and receiving antennas), actual reception is difficult to predict.

[0005] In summary, the use of direct methods (similar to communication system modeling and simulation) and on-site investigation methods to establish a shore station working simulation model is labor-intensive and costly, and improper parameter settings can cause large errors. Summary of the Invention

[0006] The present application provides a shore station broadcast simulation method, device, equipment and storage medium, which adopts an indirect method to treat the telegrams broadcast by each NAVTEX broadcasting station as an information flow, collects and collects them through instrument monitoring and statistics and analyzes them, and designs an algorithm to find the best approximation to achieve the simulation purpose.

[0007] In a first aspect, the present application provides a shore station broadcast simulation method, comprising:

[0008] Get the proportion of each broadcast station in the total number of telegrams at a set time;

[0009] The proportion of each broadcasting station in the total amount of telegrams at a set time is encoded to obtain the initial population;

[0010] Three fitness indicators are set: indicator A, indicator B, and indicator C. Indicator A is the degree to which the proportion of telegram volume is within the range obtained from the survey, indicator B is the degree to which the sum of all proportions is close to 1, and indicator C is the degree to which the sum of the proportions of the volume of disadvantaged radio stations is within the set ratio range. Disadvantaged radio stations are radio stations with less than a set number of telegrams.

[0011] Determine a fitness calculation formula based on the three fitness indicators;

[0012] Calculating the fitness of each individual in the initial population based on the fitness calculation formula, randomly selecting two different individuals from the initial population and comparing their fitness, selecting the individual with the larger fitness, and repeating the process multiple times to obtain a preferred population containing multiple individuals;

[0013] The preferred population is subjected to crossover and mutation to obtain the next generation population, and the fitness of the next generation population is calculated. The iteration is repeated multiple times until the iteration termination condition is reached, and the population with the highest fitness is output as the simulated broadcast plan; wherein the simulated broadcast plan includes the proportion of each broadcast station in the total amount of telegrams at a set time.

[0014] In one possible design, the proportion of each broadcast station in the total amount of telegrams at a set time is encoded to obtain the initial population, including:

[0015] Multiply the resolution by decimal 0 to 31 and assign the corresponding Gray code to form the basic scale;

[0016] The proportion of each broadcasting station in the total amount of telegrams at a set time is used as a decision variable, which is converted into a multi-bit Gray code based on the basic ruler and connected into a gene sequence with a multi-bit binary code as the initial population.

[0017] In one possible design, the resolution is calculated as follows:

[0018]

[0019] Where δ is the resolution and ξ is the maximum value of the reference allocation.

[0020] In one possible design, the fitness calculation formula is:

[0021]

[0022] Where K is the fitness, m1, m2, and m3 are the weights of indicator A, indicator B, and indicator C, respectively, F is the sum of the fitness of indicator A of each broadcast station, f2(x) is the fitness of indicator B, and f3(x) is the fitness of indicator C.

[0023] In a possible design, based on the three fitness indicators, a method for determining a fitness calculation formula includes:

[0024] Determine the fitness function of indicator A, expressed as:

[0025]

[0026] Where f1(x) is the fitness of indicator A, x represents the actual proportion, η min Indicates the minimum proportion of the total number of messages sent by a broadcasting station at a set time, η max Indicates the largest proportion of the total number of telegrams in a given time period by the broadcasting station;

[0027] The sum F of the fitness of the indicator A of each broadcast station is calculated by the following formula:

[0028]

[0029] Where i represents the serial number of the broadcasting station;

[0030] Determine the fitness function of indicator B, expressed as:

[0031]

[0032] Where X represents the sum of the proportions of all broadcast stations in the total amount of telegrams at a set time, and f2(x) is the fitness of indicator B;

[0033] Determine the fitness function of indicator C, expressed as:

[0034]

[0035] Where Y represents the sum of the proportions of all disadvantaged radio stations in the total number of messages at a set time; f3(x) is the fitness of indicator C;

[0036] The fitness calculation formula is determined based on the sum of the fitness of indicator A of each broadcasting station, the fitness function of indicator B, and the fitness function of indicator C.

[0037] In one possible design, after outputting the population with the highest fitness as the simulation broadcast plan, the method further includes:

[0038] Get the distribution of the number of types of messages from the broadcasting station at a set time;

[0039] Based on the distribution of the number of types of telegrams received by the broadcasting station at a set time, the integers between the minimum number of received and the maximum number of received for each type of telegram are combined to form a hierarchical directed graph. Combinations that meet the constraints are searched in the hierarchical directed graph and randomly selected as output solutions; wherein the output solution is the broadcast volume of each type of telegram at the set time.

[0040] In one possible design, after outputting the population with the highest fitness as the simulation broadcast plan, the method further includes:

[0041] Generate multiple unit time period broadcast plans based on the proportion of each broadcast station in the total number of telegrams in a set time period; wherein the unit time period broadcast plan includes the number of broadcast telegrams of each broadcast station in the unit time period;

[0042] According to the number of broadcast messages of each radio station in a unit time period, the variance is calculated using the following formula:

[0043]

[0044] Where D is the variance, Kj is the number of broadcast messages of the radio station in unit time period j, and J is the total number of unit time periods;

[0045] Based on a preset variance threshold range of each broadcasting station, a unit time period broadcasting scheme within the variance threshold range is selected from a plurality of unit time period broadcasting schemes.

[0046] In a second aspect, the present application provides a shore station broadcast simulation device, the device comprising:

[0047] The data acquisition module is configured to obtain the proportion of each broadcast station in the total amount of telegrams at a set time;

[0048] The data encoding module is configured to encode the proportion of each broadcast station in the total amount of telegrams at a set time to obtain an initial population;

[0049] The indicator setting module is configured to set three fitness indicators, namely indicator A, indicator B, and indicator C; wherein indicator A is the degree to which the proportion of telegram volume is within the range obtained by the survey, indicator B is the degree to which the sum of all proportions is close to 1, and indicator C is the degree to which the sum of the proportions of the volume of disadvantaged radio stations falls within a set ratio value range, where disadvantaged radio stations are radio stations with a volume of telegrams less than a set number;

[0050] A fitness calculation module is configured to determine a fitness calculation formula based on the three fitness indicators;

[0051] a population optimization module configured to calculate the fitness of each individual in the initial population based on the fitness calculation formula, randomly select two different individuals from the initial population to compare their fitnesses, select the individual with the larger fitness, and repeat the process multiple times to obtain a preferred population containing multiple individuals;

[0052] The iterative calculation module is configured to perform crossover and mutation on the preferred population to obtain the next generation population, calculate the fitness of the next generation population, repeat the iteration multiple times until the iteration termination condition is reached, and output the population with the highest fitness as the simulated broadcast plan; wherein the simulated broadcast plan includes the proportion of each broadcast station in the total amount of telegrams at a set time.

[0053] In a third aspect, an embodiment of the present application provides an electronic device comprising: at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the shore station broadcast simulation method described in the first aspect and various possible designs of the first aspect.

[0054] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the processor executes the computer execution instructions, the shore station broadcast simulation method described in the first aspect and various possible designs of the first aspect is implemented.

[0055] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the shore station broadcast simulation method described in the first aspect and various possible designs of the first aspect.

[0056] The shore station broadcast simulation method, apparatus, device, and storage medium provided in this application have at least the following beneficial effects:

[0057] This application can simulate the actual NAVTEX shore station message broadcasts and improve the effectiveness of practical training. First, based on the survey data on the proportion of broadcast messages of each station, the simulation design is carried out from four steps: encoding, selection, crossover, and mutation. The experimental results show that the output solution has high adaptability and can meet the corresponding simulation requirements. Secondly, the survey data on the distribution of broadcast message types and the distribution of the number of messages received per day in a unit time period are given. Based on this data, the intelligent search method is used for simulation analysis, and a fitness function that reflects the actual situation is given, providing effective support for the implementation of multi-dimensional simulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0059] Figure 1 A flowchart of a shore station broadcast simulation method provided in an embodiment of the present application;

[0060] Figure 2 A basic scale diagram provided for the embodiments of this application;

[0061] Figure 3 A gene sequence diagram provided in an embodiment of this application;

[0062] Figure 4 A new basic scale diagram provided for the embodiments of the present application;

[0063] Figure 5 A schematic diagram of group cross-connection provided in an embodiment of the present application;

[0064] Figure 6 A cross-sectional detail diagram provided for an embodiment of the present application;

[0065] Figure 7 A layered directed graph provided in an embodiment of the present application;

[0066] Figure 8 This is a structural diagram of the shore station broadcast simulation device provided in an embodiment of the present application.

[0067] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0068] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0069] In the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of information such as financial data or user data involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0070] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0071] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0072] The embodiment of the present application provides a shore station broadcast simulation method, such as Figure 1 FIG. 1 is a flowchart of a shore station broadcast simulation method provided in an embodiment of the present application. The shore station broadcast simulation method includes the following steps S100 - S700 .

[0073] S100: Obtain the proportion of each broadcasting station in the total amount of telegrams at a set time.

[0074] In this embodiment, the proportion of each broadcast station in the total number of telegrams at a set time is obtained by the following method:

[0075] Since October 2022, the NAVTEX real machine has been kept in the power-on state for a long time, and data monitoring has been carried out for 2 months from the aspects of the types of receiving radio stations, the distribution of the number of received telegrams, the distribution of the types and numbers of received telegrams, and the distribution of the time of receiving telegrams. The monitoring frequency is 518KHz. During the monitoring period, a total of 17 telegrams were received from radio stations. Taking six days as the counting unit, the number of telegrams received every six days ranges from 128 to 166. The number of telegrams received from each station is mostly not fixed, and is a value that varies within a certain range. For example, the number of telegrams from station P is between 19 and 29, and that from station H is between 0 and 7. Because determining the number of telegrams to be broadcast is the basis for subsequent simulation (just as the number of questions of each type must be determined first in the automatic test paper), this embodiment proposes a simulation requirement, that is, a simulation requirement for the proportion of each broadcasting station in the total number of telegrams in six days.

[0076] First, practical training for GMDSS general operators typically lasts five to six days (the Maritime Administration requires one to two days of rest on weekends). Here, six days are used as the unit for counting the number of messages to be broadcast. Once the simulated broadcast program is initiated, a search algorithm is used to develop a six-day broadcast plan (primarily determining the number of messages to be broadcast by each station). The simulation is based on actual survey data, as shown in Table 1.

[0077] Table 1: Proportion of 17 radio stations in the total number of telegrams in six days

[0078]

[0079]

[0080] As shown in Table 1, if the corresponding data for each broadcast station is given as a specific number, it is not flexible. For example, if the total number of broadcast messages over six days is set at 150, and the W station ratio range given in Table 1 is 0.047, the planned number of broadcast messages for this station is 7. If, to increase the number of messages in the LAN and enhance the effectiveness of practical training, the total number of messages is set at 300, the planned number of broadcast messages becomes 14. Clearly, expressing data as a ratio has a clear advantage, overcoming the mechanical rigidity of specific numbers.

[0081] Secondly, when generating a simulation broadcast plan, it is necessary to determine the specific proportion of broadcast message volume for each station, and the following constraints must be met: 1) The sum of the broadcast message proportions for all stations must be 1 or close to 1; 2) The proportion for each station must be roughly within the range given in Table 1; 3) The proportion of broadcast message volume for some stations with low message volume (remarked as disadvantaged stations in Table 1) cannot be too large. As can be seen from Table 1, the proportion of message volume for each station is within a range, and some stations have a very large range. Using a traversal search, the search space is large.

[0082] Finally, the number of broadcast messages from each radio station has a certain degree of uncertainty, which requires the search output solution to be diverse.

[0083] S200: Encode the proportion of each broadcasting station in the total amount of telegrams at a set time to obtain an initial population.

[0084] In this embodiment, Gray code is used for encoding. The characteristic of Gray code is that the binary code between adjacent numbers changes by only one bit, so that the value changes will not be too drastic during crossover and mutation.

[0085] The more binary digits there are, the higher the encoding accuracy and the more accurate the calculations involved in the search (such as fitness calculation and numerical comparison). For the sake of convenience, a 5-bit encoding is used here. In this case, the distance between adjacent binary codes is shown in formula (1), which is defined as the resolution (denoted by δ, the smaller the value, the higher the resolution accuracy). At the same time, the numerator in formula (1) is defined as the maximum value of the benchmark allocation (denoted by ξ)

[0086]

[0087] When encoding is performed under the condition that the maximum value of the reference allocation in formula (1) is 1, the resolution is first multiplied by the decimal 0 to 31 and assigned the corresponding Gray code to form the basic scale, such as Figure 2 As shown. When a double-precision decimal is input to be encoded, the Gray code corresponding to the closest scale is the encoding result. For example, when the input decimal is 0.135, the encoding result is 00110. Obviously, based on Figure 2 Decoding can also be completed, but due to the small number of binary bits used, there will be some errors in the decoding.

[0088] When simulating according to Table 1, we first take the proportion of each Taiwan power volume as the decision variable, and then Figure 2 They are converted into 5-bit Gray codes respectively and then connected into a gene sequence with 85-bit binary code. Figure 3 is an example.

[0089] Figure 3 Sequence based on Figure 2 The decoded ratios for each station are: 0.0323; 0.1938; 0.2907; 0.969; 0.4522; 0.2584; ...; 0.7752. Clearly, this sequence contains a large number of ratios that differ significantly from reality. For example, the ratio of a particular station's message could not possibly reach 0.969. When a genetic algorithm randomly generates binary sequences using this method and forms an initial population of a predetermined size, a large number of useless genes will appear, resulting in very poor search performance. The average output fitness measured experimentally is only around 0.43.

[0090] According to Table 1, considering that the ratio of radio messages cannot exceed 0.20, in order to have a certain redundancy, this embodiment sets the maximum value of the benchmark allocation to 0.22, which greatly improves the resolution accuracy. The corresponding basic scale is as follows: Figure 4 At this time, the ratios corresponding to the above binary sequences become: 0.0071; 0.0426; 0.0639; 0.213; 0.0994; 0.0568; ………; 0.1704. In this way, the number of invalid genes in the chromosome is greatly reduced, which can help improve the search performance.

[0091] S300: Three fitness indices are set, namely, indicator A, indicator B and indicator C; wherein, indicator A is the extent to which the proportion of telegram volume is within the range obtained from the survey, indicator B is the extent to which the sum of all proportions is close to 1, and indicator C is the extent to which the sum of the proportions of the telegram volume of disadvantaged radio stations falls within the set proportion value range, and disadvantaged radio stations are radio stations whose telegram volume is less than the set number.

[0092] S400: Determine a fitness calculation formula based on the three fitness indicators.

[0093] In this embodiment, the fitness calculation formula is determined in the following way:

[0094] The fitness function of indicator A is:

[0095]

[0096] Where f1(x) is the fitness of indicator A, x represents the actual proportion, η min Indicates the minimum proportion of the total number of messages sent by a broadcasting station at a set time, η max Indicates the maximum proportion of the total number of telegrams in the set time by the broadcasting station, η min ,η max Corresponding to the minimum and maximum ratios in Table 1.

[0097] Since there are 17 radio stations, they need to be calculated separately and then added up. The total score is:

[0098]

[0099] Where i represents the serial number of the broadcast station.

[0100] For indicator B, first calculate the sum of the actual proportions of all stations:

[0101]

[0102] Where x i represents the proportion of the i-th broadcast station in the total number of telegrams at the set time, and X represents the sum of the proportions of all broadcast stations in the total number of telegrams at the set time;

[0103] Then calculate the degree to which X deviates from 1, and obtain the fitness function of indicator B as follows:

[0104]

[0105] Where f2(x) is the fitness of indicator B.

[0106] For indicator C, according to Table 1, stations numbered 11, 13, 15, and 16 are disadvantaged stations. First, calculate the sum of their proportions:

[0107] Y=x 11 +x 13 +x 15 +x 16

[0108] Here, it is stipulated that Y cannot exceed 0.023. Then, the degree to which Y belongs to the interval (0, 0.023) is calculated, and the fitness function of indicator C is obtained as follows:

[0109]

[0110] Where Y represents the sum of the proportions of all disadvantaged radio stations in the total number of messages at a set time; f3(x) is the fitness of indicator C.

[0111] Assuming the weights of the above three indicators are m1, m2 and m3 respectively, the fitness calculation formula is:

[0112]

[0113] Where K is the fitness, m1, m2, and m3 are the weights of indicator A, indicator B, and indicator C, respectively, F is the sum of the fitness of indicator A of each broadcast station, f2(x) is the fitness of indicator B, and f3(x) is the fitness of indicator C.

[0114] In formula (6), the purpose of dividing the first term on the right side of the equation by 17 is normalization.

[0115] Based on formula (6), the fitness of each individual in the population is calculated to implement selection. There are many selection methods, and common methods include roulette and tournament methods. In this embodiment, the population size is set to 600. If roulette is used, the interval occupied by each individual in the roulette wheel is very small, and the effect is not good. Therefore, the tournament method is adopted, that is, two different individuals are randomly selected from the population and their fitness is compared. The individual with the larger fitness wins. A total of 600 comparisons are performed to obtain a new population containing 600 individuals.

[0116] S500: Based on the fitness calculation formula, calculate the fitness of each individual in the initial population, randomly select two different individuals from the initial population to compare their fitness, select the individual with the larger fitness, repeat the process multiple times to obtain a preferred population containing multiple individuals.

[0117] In this embodiment, crossover refers to randomly selecting two individuals from the optimized population as parents and exchanging genes to form offspring. Here, the grouped multi-point crossover method is used, that is, the entire gene segment (a total of 85 codes) is divided into four groups, the first three groups each with 20 codes, and the fourth group with 25 codes. Crossover is performed between the corresponding groups of the two parent individuals (a total of four times), as shown in FIG. Figure 5 shown.

[0118] In each crossover, first generate four unequal random numbers between 1 and 20 (because the fourth group has 25 codes, the fourth crossover generates random numbers between 1 and 25). Then, sort them from small to large to form an array {y1, y2, y3, y4}, and exchange the gene segments between y1-y2 and y3-y4 to complete this crossover. Figure 5 Taking the first crossover as an example, Figure 6 Details are given.

[0119] After the crossover is completed, mutation is performed. Figure 5 The grouping method divides the entire gene segment into four groups. For each group, two random numbers are generated within the corresponding numerical range. The binary codes they point to are then inverted to complete the mutation. Since each group mutates two bits, the entire gene segment mutates eight bits, with a mutation rate of 0.0941.

[0120] S600: Crossover and mutation are performed on the preferred population to obtain the next generation population, and the fitness of the next generation population is calculated. The iteration is repeated multiple times until the iteration termination condition is reached, and the population with the highest fitness is output as the simulated broadcast plan; wherein the simulated broadcast plan includes the proportion of each broadcast station in the total amount of telegrams at the set time.

[0121] In this example, the evolutionary period is set to 300 generations, and the weights of the three fitness indicators, m1, m2, and m3, are set to 0.49, 0.27, and 0.24, respectively. Furthermore, to further improve resolution accuracy, smaller values ​​of ξ are used for the four disadvantaged stations listed in Table 1. The proposed method is implemented in C# from a low-level programming perspective. Global variables are used to record and compare the fitness of each individual in each generation, with the one with the highest fitness being the output solution.

[0122] Table 2 shows the output of four runs of the proposed method. The algorithm outputs ratio values ​​as double-precision numbers, rounded to six decimal places, and prefixed with the station number corresponding to Table 1. The ratios for each station are separated by semicolons. The fitness values ​​are rounded to four decimal places.

[0123] Table 2 Output of the proposed method and its corresponding fitness

[0124]

[0125] The data in Table 2 show that the proposed method can output a variety of solutions with high and stable adaptability. It is believed that the adaptability of the output solutions can be further improved by using more binary codes and improving the resolution accuracy.

[0126] The method proposed in this application was run five times in an environment with Intel(R) Core(TM) i7-10510U CPU@1.80GHz 2.30GHz memory 8G and Windows 10 Home Chinese version as the operating system, with an average speed of 3.7 seconds, which is acceptable.

[0127] Different situations require different weights, and changes in weights should not significantly affect the algorithm's performance. Therefore, we tested the algorithm under two common weight values. For each weight, we ran the proposed method five times. The results are shown in Table 3.

[0128] Table 3 Test results under two weight values

[0129]

[0130] The data in Table 3 show that the change in weights does not have much impact on the algorithm, and the method proposed in this application is highly robust.

[0131] S700: Obtain the distribution of the number of types of telegrams of the broadcasting station at the set time; based on the distribution of the number of types of telegrams of the broadcasting station at the set time, combine the integers contained between the minimum number of receptions and the maximum number of receptions of each type of telegram to form a hierarchical directed graph, search for a combination that meets the constraint conditions in the hierarchical directed graph, and randomly select it as an output solution; wherein, the output solution is the broadcast volume of each type of telegram at the set time.

[0132] In this embodiment, the types and quantity distribution of messages received from station G are shown in Table 4. Messages of type A (navigation warning), B (weather warning), D (search and rescue information), and L (navigation warning, a supplement to type A) are the most commonly received messages and are most closely related to maritime navigation safety. Message type Z, representing "no message on hand," is also received in practice. Therefore, this embodiment provides the survey results of these message types as simulation examples.

[0133] Table 4 Distribution of the number of each message type on G station

[0134]

[0135] Table 4 shows that the types of broadcast messages from station G are mainly concentrated in categories A and B, and are not widely distributed. Therefore, we attempt to use a breadth- or depth-based search. Specifically, we combine the integers contained in the minimum and maximum reception numbers for each type of message to form a hierarchical directed graph. We then search for combinations that satisfy the constraints in the graph and randomly select a solution as the output.

[0136] For example, the aforementioned steps S100-S600 determine that station G broadcasts a total of 30 messages in a certain six-day period. Based on the statistical results in Table 4, the directed graph formed is as follows: Figure 7 shown.

[0137] Figure 7 In the figure, the broadcast volume of Class A messages ranges from 18 to 25, that of Class B messages from 4 to 10, that of Class D messages from 1 to 2, and that of Class E messages from 1 to 2. Other messages have no broadcast volume and are not shown in the figure. Fitness is the degree to which the sum of the broadcast volume values ​​of each message type deviates from 30; smaller deviations indicate higher fitness.

[0138] Figure 7 In the example above, if the starting node is "18" on the first layer, the search yields a feasible solution of 18; 9; 2; 1, achieving a fitness of 100%. Clearly, the traversal search finds the theoretically optimal solution, avoiding the errors and cumbersome algorithm design often associated with genetic algorithms (or other biomimetic search algorithms). Furthermore, the graph traversal search space is relatively small, at 8 × 7 × 2 × 2 = 224, making the search cost low.

[0139] In artificial intelligence theory, traversal search is a blind search, and the search algorithm proposed to reduce the search space and increase the search speed is an informed search or a natural system-like search. Figure 7 In the network, the nodes between adjacent layers are fully connected. If the number of directed layers increases and the number of nodes in each layer increases, the cost of traversal search will increase sharply. In this case, the aforementioned genetic algorithm or informed search method can be used.

[0140] It should be noted that for ease of explanation, specific integers are used here. In actual implementation, integers can be converted to more flexible proportional values. Furthermore, different stations broadcast different message types. For example, station P, which receives the second-highest volume of messages after station G, broadcasts primarily messages in categories A, B, and D, but also includes a small number of category Z messages.

[0141] In some embodiments, after step S700, the CRSC broadcast simulation method further includes step S800: determining a broadcast plan for a unit time period through simulation. Step S800 includes:

[0142] S801: Generate multiple unit time period broadcast plans based on the proportion of each broadcast station in the total number of telegrams during a set time period; wherein the unit time period broadcast plan includes the number of telegrams broadcast by each broadcast station in the unit time period;

[0143] S802: Calculate the variance based on the number of broadcast messages of each broadcast station in a unit time period using the following formula:

[0144]

[0145] Where D is the variance, K j is the number of broadcast messages of the radio station in unit time period j, and J is the total number of unit time periods;

[0146] S803: Based on a preset variance threshold range of each broadcasting station, a unit time period broadcasting plan within the variance threshold range is selected from a plurality of unit time period broadcasting plans.

[0147] As an embodiment of the present application, after obtaining the total number (or total proportion) of broadcast messages for each radio station over six days in steps S100-S600, the simulation also requires obtaining the distribution of the number of broadcast messages for each station on each day. The survey data for station G is shown in Table 5.

[0148] Table 5 Distribution of the number of daily broadcast messages of station G in a unit time period

[0149]

[0150] It can be seen that the daily broadcast volume of station G is relatively average, but there are certain fluctuations. According to the distribution law, the search space is moderate, and either traversal search or genetic algorithm or other optimization search methods can be used. However, in terms of fitness, it is necessary to meet the requirements of the total amount of broadcast messages for six days and reflect the fluctuations from the perspective of variance. The calculation formula of variance is as shown in formula (7). The variance threshold range of station G is between 1.806 and 4.333. The variance interval values ​​of different stations are different. For example, according to the survey, the variance threshold range of station P is 1.806 to 10.822, which is quite different from that of station G.

[0151] In summary, the method proposed in this application simulates the ratio of broadcast messages of each radio station, which is the basis of all simulations, and the simulation results are ideal; combined with other survey results (the distribution of the number of various types of messages and the distribution of the number of broadcast messages per day), through the selection of search methods and the determination of fitness functions, the simulation degree of NAVTEX shore station broadcasts is greatly improved, and the practical training effect of NAVTEX simulators is improved, which has important practical significance.

[0152] The embodiment of the present application also provides a shore station broadcast simulation device, such as Figure 8 As shown, the shore station broadcast simulation device includes:

[0153] The data acquisition module 801 is configured to obtain the proportion of each broadcast station in the total amount of telegrams at a set time;

[0154] The data encoding module 802 is configured to encode the proportion of each broadcast station in the total amount of telegrams at a set time to obtain an initial population;

[0155] The indicator setting module 803 is configured to set three fitness indicators, namely indicator A, indicator B, and indicator C; wherein indicator A is the degree to which the proportion of telegram volume is within the range obtained by the survey, indicator B is the degree to which the sum of all proportions is close to 1, and indicator C is the degree to which the sum of the proportions of the volume of disadvantaged radio stations falls within a set ratio value range, where disadvantaged radio stations are radio stations with less than a set number of telegrams;

[0156] The fitness calculation module 804 is configured to determine a fitness calculation formula based on the three fitness indicators;

[0157] The population optimization module 805 is configured to calculate the fitness of each individual in the initial population based on the fitness calculation formula, randomly select two different individuals from the initial population, compare their fitness, select the individual with the larger fitness, and repeat the process multiple times to obtain a preferred population containing multiple individuals;

[0158] The iterative calculation module 806 is configured to perform crossover and mutation on the preferred population to obtain the next generation population, calculate the fitness of the next generation population, repeat the iteration multiple times until the iteration termination condition is reached, and output the population with the highest fitness as the simulated broadcast plan; wherein the simulated broadcast plan includes the proportion of each broadcast station in the total amount of telegrams at a set time.

[0159] In some embodiments, the data encoding module is further configured to:

[0160] Multiply the resolution by decimal 0 to 31 and assign the corresponding Gray code to form the basic scale;

[0161] The proportion of each broadcasting station in the total amount of telegrams at a set time is used as a decision variable, which is converted into a multi-bit Gray code based on the basic ruler and connected into a gene sequence with a multi-bit binary code as the initial population.

[0162] In some embodiments, the resolution is calculated as follows:

[0163]

[0164] Where δ is the resolution and ξ is the maximum value of the reference allocation.

[0165] In some embodiments, the fitness calculation formula is:

[0166]

[0167] Where K is the fitness, m1, m2, and m3 are the weights of indicator A, indicator B, and indicator C, respectively, F is the sum of the fitness of indicator A of each broadcast station, f2(x) is the fitness of indicator B, and f3(x) is the fitness of indicator C.

[0168] In some embodiments, the fitness calculation module is configured to:

[0169] Determine the fitness function of indicator A, expressed as:

[0170]

[0171] Where f1(x) is the fitness of indicator A, x represents the actual proportion, η min Indicates the minimum proportion of the total number of messages sent by a broadcasting station at a set time, η max Indicates the largest proportion of the total number of telegrams in a given time period by the broadcasting station;

[0172] The sum F of the fitness of the indicator A of each broadcast station is calculated by the following formula:

[0173]

[0174] Where i represents the serial number of the broadcasting station;

[0175] Determine the fitness function of indicator B, expressed as:

[0176]

[0177] Where X represents the sum of the proportions of all broadcast stations in the total amount of telegrams at a set time, and f2(x) is the fitness of indicator B;

[0178] Determine the fitness function of indicator C, expressed as:

[0179]

[0180] Where Y represents the sum of the proportions of all disadvantaged radio stations in the total number of messages at a set time; f3(x) is the fitness of indicator C;

[0181] The fitness calculation formula is determined based on the sum of the fitness of indicator A of each broadcasting station, the fitness function of indicator B, and the fitness function of indicator C.

[0182] In some embodiments, the apparatus further comprises a first simulation module, wherein the first simulation module is configured to:

[0183] Get the distribution of the number of types of messages from the broadcasting station at a set time;

[0184] Based on the distribution of the number of types of telegrams received by the broadcasting station at a set time, the integers between the minimum number of received and the maximum number of received for each type of telegram are combined to form a hierarchical directed graph. Combinations that meet the constraints are searched in the hierarchical directed graph and randomly selected as output solutions; wherein the output solution is the broadcast volume of each type of telegram at the set time.

[0185] In some embodiments, the apparatus further includes a second simulation module, wherein the second simulation module is configured to:

[0186] Generate multiple unit time period broadcast plans based on the proportion of each broadcast station in the total number of telegrams in a set time period; wherein the unit time period broadcast plan includes the number of broadcast telegrams of each broadcast station in the unit time period;

[0187] According to the number of broadcast messages of each radio station in a unit time period, the variance is calculated using the following formula:

[0188]

[0189] Where D is the variance, K j is the number of broadcast messages of the radio station in unit time period j, and J is the total number of unit time periods;

[0190] Based on a preset variance threshold range of each broadcasting station, a unit time period broadcasting scheme within the variance threshold range is selected from a plurality of unit time period broadcasting schemes.

[0191] An embodiment of the present application provides an electronic device, which may include a processor and a memory, wherein the processor and the memory can communicate with each other; illustratively, the processor and the memory communicate with each other via a communication bus.

[0192] The processor executes the computer-executable instructions stored in the memory, so that the processor implements the solutions in the above embodiments. The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0193] The communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. System buses can be categorized as address buses, data buses, and control buses. Transceivers enable communication between the database access device and other computers (e.g., clients, read-write libraries, and read-only libraries). Memory may include random access memory (RAM) or non-volatile memory.

[0194] The electronic device provided in the embodiment of the present application may be the terminal device of the above embodiment.

[0195] An embodiment of the present application further provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes the technical solution of the shore station broadcast simulation method of the above embodiment.

[0196] An embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When at least one processor executes the computer program, it can implement the technical solution of the shore station broadcast simulation method in the above embodiment.

[0197] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or module, which can be electrical, mechanical or other forms.

[0198] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of these modules may be selected to implement the solution of this embodiment based on actual needs.

[0199] In addition, the functional modules in the various embodiments of the present application may be integrated into a single processing unit, or each module may exist physically separately, or two or more modules may be integrated into a single unit. The above-mentioned modules may be implemented in the form of hardware or hardware plus software functional units.

[0200] The above-mentioned integrated module implemented in the form of a software functional module can be stored in a computer-readable storage medium. The above-mentioned software functional module is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform some steps of the methods of various embodiments of the present application.

[0201] It should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), or application-specific integrated circuits (ASICs). A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented by a hardware processor or implemented by a combination of hardware and software modules in the processor.

[0202] The memory may include a high-speed RAM memory, and may also include non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk.

[0203] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be divided into address buses, data buses, and control buses.

[0204] The storage medium may be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0205] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic control unit or a main control device.

[0206] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0207] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A shore station broadcast simulation method, characterized in that: The method comprises: Get the proportion of each broadcast station in the total number of telegrams at a set time; The proportion of each broadcasting station in the total amount of telegrams at a set time is encoded to obtain the initial population; Three fitness indicators are set: indicator A, indicator B, and indicator C. Indicator A is the degree to which the proportion of telegram volume is within the range obtained from the survey, indicator B is the degree to which the sum of all proportions is close to 1, and indicator C is the degree to which the sum of the proportions of the volume of disadvantaged radio stations is within the set ratio range. Disadvantaged radio stations are radio stations with less than a set number of telegrams. Determine a fitness calculation formula based on the three fitness indicators; Calculating the fitness of each individual in the initial population based on the fitness calculation formula, randomly selecting two different individuals from the initial population and comparing their fitness, selecting the individual with the larger fitness, and repeating the process multiple times to obtain a preferred population containing multiple individuals; Performing crossover and mutation on the selected population to obtain a next-generation population, calculating the fitness of the next-generation population, and repeating the iteration multiple times until an iteration termination condition is met. The population with the highest fitness is output as a simulated broadcast plan; wherein the simulated broadcast plan includes the proportion of each broadcast station in the total number of telegrams at a set time; Obtain the distribution of the number of types of telegrams sent by a broadcasting station at a set time; based on the distribution of the number of types of telegrams sent by the broadcasting station at the set time, combine the integers between the minimum number of received and the maximum number of received for each type of telegram to form a hierarchical directed graph, search for combinations that satisfy the constraints in the hierarchical directed graph, and randomly select them as output solutions; wherein the output solution is the broadcast volume of each type of telegram sent by the broadcasting station at the set time.

2. The shore station broadcast simulation method according to claim 1, characterized in that: The proportion of each broadcast station in the total amount of telegrams at a set time is encoded to obtain the initial population, including: Multiply the resolution by decimal 0 to 31 and assign the corresponding Gray code to form the basic scale; The proportion of each broadcasting station in the total amount of telegrams at a set time is used as a decision variable, which is converted into a multi-bit Gray code based on the basic ruler and connected into a gene sequence with a multi-bit binary code as the initial population.

3. The shore station broadcast simulation method according to claim 1, characterized in that: The resolution is calculated as follows: Where δ is the resolution and ξ is the maximum value of the reference allocation.

4. The shore station broadcast simulation method according to claim 1, characterized in that: The fitness calculation formula is: Where K is the fitness, m1, m2, and m3 are the weights of indicator A, indicator B, and indicator C, respectively, F is the sum of the fitness of indicator A of each broadcast station, f2(x) is the fitness of indicator B, and f3(x) is the fitness of indicator C.

5. The shore station broadcast simulation method according to claim 1 or 4, characterized in that: According to the three fitness indicators, the fitness calculation formula is determined as follows: Determine the fitness function of indicator A, expressed as: Where f1(x) is the fitness of indicator A, x represents the actual proportion, η min Indicates the minimum proportion of the total number of messages sent by a broadcasting station at a set time, η max Indicates the largest proportion of the total number of telegrams in a given time period by the broadcasting station; The sum F of the fitness of the indicator A of each broadcast station is calculated by the following formula: Where i represents the serial number of the broadcasting station; Determine the fitness function of indicator B, expressed as: Where X represents the sum of the proportions of all broadcast stations in the total amount of telegrams at a set time, and f2(x) is the fitness of indicator B; Determine the fitness function of indicator C, expressed as: Where Y represents the sum of the proportions of all disadvantaged radio stations in the total number of messages at a set time; f3(x) is the fitness of indicator C; The fitness calculation formula is determined based on the sum of the fitness of indicator A of each broadcasting station, the fitness function of indicator B, and the fitness function of indicator C.

6. The shore station broadcast simulation method according to any one of claims 1 to 4, characterized in that: After outputting the population with the highest fitness as the simulation broadcast plan, the method further includes: Generate multiple unit time period broadcast plans based on the proportion of each broadcast station in the total number of telegrams in a set time period; wherein the unit time period broadcast plan includes the number of broadcast telegrams of each broadcast station in the unit time period; According to the number of broadcast messages of each radio station in a unit time period, the variance is calculated using the following formula: Where D is the variance, K j is the number of broadcast messages of the radio station in unit time period j, and J is the total number of unit time periods; Based on a preset variance threshold range of each broadcasting station, a unit time period broadcasting scheme within the variance threshold range is selected from a plurality of unit time period broadcasting schemes.

7. A shore station broadcast simulation device, characterized in that: The device comprises: The data acquisition module is configured to obtain the proportion of each broadcast station in the total amount of telegrams at a set time; The data encoding module is configured to encode the proportion of each broadcast station in the total amount of telegrams at a set time to obtain an initial population; The indicator setting module is configured to set three fitness indicators, namely indicator A, indicator B, and indicator C; wherein indicator A is the degree to which the proportion of telegram volume is within the range obtained by the survey, indicator B is the degree to which the sum of all proportions is close to 1, and indicator C is the degree to which the sum of the proportions of the volume of disadvantaged radio stations falls within a set ratio value range, where disadvantaged radio stations are radio stations with a volume of telegrams less than a set number; A fitness calculation module is configured to determine a fitness calculation formula based on the three fitness indicators; a population optimization module configured to calculate the fitness of each individual in the initial population based on the fitness calculation formula, randomly select two different individuals from the initial population to compare their fitnesses, select the individual with the larger fitness, and repeat the process multiple times to obtain a preferred population containing multiple individuals; The iterative calculation module is configured to perform crossover and mutation on the preferred population to obtain the next generation population, calculate the fitness of the next generation population, repeat the iteration multiple times until the iteration termination condition is reached, and output the population with the highest fitness as the simulated broadcast plan; wherein the simulated broadcast plan includes the proportion of each broadcast station in the total amount of telegrams at a set time.

8. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the shore station broadcast simulation method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the shore station broadcast simulation method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The method comprises a computer program, which, when executed by a processor, implements the shore station broadcast simulation method according to any one of claims 1 to 6.

Images