Latin hypercube-based multi-objective co-evolution resource configuration optimization method, system and equipment and medium

Abstract

The invention discloses a multi-target co-evolution resource configuration optimization method, system and device based on Latin hypercube, and a medium. The method comprises the following steps: initializing a multi-target optimization (CMSC) algorithm based on beam space division and beam coverage detection; generating an initial population Pop1 and an initial population Pop2 with the same size by using a Latin hypercube design (LHD) method; performing population loop iteration, and optimizing a satellite communication transmission resource configuration strategy through a coevolution algorithm; the system, the equipment and the medium are used for realizing the method. Through Latin hypercube design (LHD) initialization population, a coevolution framework of an original problem and an auxiliary problem and progeny strategy selection, multi-dimensional resources of a satellite energy domain and a beam domain can be efficiently allocated, and a generated satellite resource allocation strategy can reduce communication energy consumption, reduce transmission time delay and improve communication efficiency. The method has the advantages that the satellite communication transmission resource allocation strategy is generated quickly, and different ground user distributions can be adapted.

Description

Technical Field

[0001] The present invention belongs to the field of wireless communication technology, and particularly relates to a multi-objective co-evolution resource allocation optimization method, system, device and medium based on Latin hypercube. Background Art

[0002] With the rapid development of Internet of Things (IoT) and 5G / 6G network technologies, achieving interconnection of all things and seamless communication coverage has become one of the goals of global communication systems. In this context, Low Earth Orbit (LEO) communication satellites, as an important supplement to existing terrestrial communication networks, are receiving increasing attention. Due to their characteristics of operating in low Earth orbits, LEO satellites can provide efficient communication services for remote areas on the ground and oceans where traditional network coverage is weak. Compared with Geostationary Earth Orbit (GEO) satellites, LEO satellites have the advantages of low latency, high bandwidth and flexible coverage, and can better meet the needs of modern communication networks. With the development of technologies such as satellites and antennas, the communication capabilities of LEO satellites have been significantly improved, and the flexibility of on-board payloads has been enhanced, enabling LEO satellites to meet more diverse communication needs.

[0003] LEO satellites have multi-dimensional resources such as time, frequency, space, energy, and wave. The flexible scheduling and efficient utilization of these multi-dimensional resources are the key to improving their communication performance. Some existing studies focus on the flexible allocation of on-board multi-dimensional resources and propose a variety of innovative solutions. For example, in the allocation of time-frequency resources, some studies have proposed dynamic resource scheduling schemes based on time division multiplexing and frequency division multiplexing, which can dynamically adjust resource configuration according to user needs and communication environment; in terms of space resources, beamforming technology has been widely applied. By intelligently adjusting the satellite antenna array, focusing beam energy, and achieving directional communication, the spectrum efficiency is improved; in addition, beam energy management is also one of the current research hotspots. Through adaptive power allocation, the energy consumption efficiency of the satellite is optimized, and the operating life of the satellite is extended; some studies have proposed resource allocation schemes based on beam cascading, which optimize on-board resource scheduling by combining multi-dimensional information of time, space, and frequency.

[0004] Facing the complex multi-dimensional resource allocation problems in the above scenarios, there are mainly two types of solutions. One is traditional algorithms, which are mainly based on classical mathematical theories such as convex optimization, game theory, and graph theory. Convex optimization methods can effectively solve some linearized resource allocation problems; game theory models the resource competition problems among multiple satellites and solves the optimal solution through strategy iteration. Graph theory technology is widely used in inter-satellite link management and network topology optimization to improve communication efficiency by finding the optimal communication link. However, as the complexity of resource allocation problems increases, these problems often belong to Mixed Integer Nonlinear Programming (MINLP) problems, and it is difficult for traditional algorithms to obtain the optimal solution within a limited time.

[0005] Another type of research on solutions based on intelligent algorithms has gradually become a research focus in multidimensional resource allocation problems. Intelligent algorithms, such as simulated annealing algorithms, particle swarm optimization algorithms, and reinforcement learning algorithms, can explore the solution space of large-scale complex problems through a heuristic search process. Due to the nonlinearity and complexity of MINLP problems, traditional methods are often unable to solve them independently, while intelligent algorithms provide a more flexible and efficient solution approach that can adapt to uncertain and complex environments. In short, with the increasing complexity of multidimensional resource allocation problems, intelligent algorithms have gradually become the main research direction in this field due to their efficient global search capabilities and advantages in handling nonlinear problems. Through intelligent methods such as simulated annealing, particle swarm optimization, and reinforcement learning, flexible and efficient resource allocation solutions can be provided for LEO satellite networks. In the future, the application of intelligent algorithms in the field of satellite communications will provide more powerful technical support for achieving seamless global communication coverage.

[0006] The patent application document with publication number CN 118709461 A discloses "Multi-objective optimization method for cantilever beam structure based on Hall effect tension sensor". It selects samples through optimal Latin hypercube sampling and combines the GPR-NSGA-II algorithm to optimize the cantilever beam structure parameters, thereby improving the prediction efficiency of the Gaussian process regression model. However, since the algorithm relies on the combination of Gaussian process regression (GPR) and NSGA-II, its efficiency is limited for high-dimensional or nonlinear problems and lacks versatility.

[0007] The patent application document with publication number CN 117669095A discloses "A method for optimizing variable parameters of centrifugal impeller of combined pump based on proxy model", which uses Latin hypercube sampling and NSGA-II algorithm to optimize the design parameters of the centrifugal impeller of the fuel pump, significantly improving the head and efficiency. However, since its algorithm relies on the superposition of models such as full factor screening and high-order surface response, the algorithm has high calculation cost, is difficult to handle large-scale variable problems, and has poor scenario robustness. Summary of the invention

[0008] In order to overcome the problems of poor global convergence and high computational complexity of multidimensional resource allocation in the prior art, the purpose of the present invention is to provide a multi-objective co-evolutionary resource configuration optimization method, system, device and medium based on Latin hypercube. By initializing the population, the co-evolutionary framework of the original problem and the auxiliary problem and the offspring strategy selection method through Latin hypercube design (LHD), the present invention can efficiently allocate multi-dimensional resources in the satellite energy domain and beam domain. The generated satellite resource configuration strategy can reduce communication energy consumption and transmission delay, and has the technical effect of rapid generation of satellite communication transmission resource configuration strategy and being able to adapt to different ground user distributions.

[0009] In order to achieve the above object, the technical solution adopted by the present invention is:

[0010] A multi-objective co-evolution resource allocation optimization method based on Latin hypercube, comprising the following steps:

[0011] Step 1: Initialization of the multi-objective optimization (CMSC) algorithm based on beamspace division and beam coverage detection:

[0012] Input the initial parameter list: the original problem f origin , the auxiliary problem f help , the population size N, and the maximum number of iterations I max ;

[0013] Among them, the original problem f origin refers to the satellite communication optimization problem, and the auxiliary problem f help refers to the energy consumption and delay constraints of the satellite communication optimization problem; the population size N refers to the number of decision variables participating in the optimization process, and the decision variables determine the configuration of two types of satellite resources, namely the transmission power and the antenna beam; the maximum number of iterations I max refers to the maximum number of calculation steps preset in the optimization process, which is used to ensure the optimization of resource allocation within a reasonable time;

[0014] Step 2: Initialize the population:

[0015] Use the Latin hypercube design (LHD) method to generate two initial populations Pop 1 and Pop 2 of the same size, and the two initial populations Pop 1 and Pop 2 represent different satellite communication transmission resource allocation strategies respectively;

[0016] Step 3: Based on the initial parameters in Step 1 and the two initial populations Pop 1 and Pop 2 of the same size generated in Step 2, perform population cyclic iteration, and optimize the satellite communication transmission resource allocation strategy through the co-evolution algorithm.

[0017] The specific steps of Step 2 are as follows:

[0018] Step 2.1: Given the available range of the transmission power and the antenna beam width corresponding to each element in the decision variables in the actual physical system, and the initial population size N, divide the interval;

[0019] Step 2.2: For each decision variable, after interval division, which represents different resource allocation ranges, randomly select a sample point from each interval divided in Step 2.1, and the sample point represents different satellite resource allocation combinations in the satellite resource allocation parameters;

[0020] Step 2.3: Randomly pair the sample points generated for all variables to form a complete sample set consisting of multiple different sample points, and there is no fixed combination of sample points for different variables;

[0021] Step 2.4: For the complete sample set formed in Step 2.3, calculate the Kolmogorov-Smirnov values of the sample distributions in each dimension through statistical uniformity tests to ensure sample coverage uniformity; if the distribution in some areas is sparse, re-divide the intervals and supplement the sampling, adopting an adaptive interval subdivision strategy, and preferentially adding sample points in the sparse areas until the distribution in all areas is uniform, thus completing the generation of the sample set;

[0022] Step 2.5: Use the sample set generated in Step 2.4 as the initial population. Each sample point represents an individual in the population. The characteristics of the individual are determined by its corresponding variable values. Each individual corresponds to a satellite multi-dimensional resource allocation scheme, and two initial populations Pop 1 and Pop 2 .

[0023] The specific steps of Step 3 are as follows:

[0024] Step 3.1: Count and accumulate: i = i + 1;

[0025] Step 3.2: Crossover operation: Select half of the individuals from the initial populations Pop 1 and Pop 2 generated in Step 2 to obtain the parental population 1 and the parental population 2, that is, two sets containing different satellite resource allocation combinations are obtained;

[0026] Step 3.3: Mutation operation: Perform mutation operations on each individual in the parental population 1 and the parental population 2 obtained in Step 3.2 to obtain new individuals, and the new individuals form the offspring population 1 and the offspring population 2;

[0027] Step 3.4: Population update: Take the intersection of the initial population Pop 1 generated in Step 2, the offspring population 1 and the offspring population 2 generated in Step 3.3 as the new population Pop new ;

[0028] Step 3.5: Population evaluation: Use the original problem f origin and the auxiliary problem f help in Step 1 to evaluate the initial populations Pop 1 and Pop 2 generated in Step 2 and the new population Pop new obtained in Step 3.4. Based on the average delay and average energy consumption, perform coverage detection, and calculate the initial populations Pop 1 and Pop2 and the fitness scores of each individual in the new population Pop new ;

[0029] Step 3.6: Environmental selection: Based on the fitness scores calculated in Step 3.5, which are used to evaluate the performance of the satellite communication transmission resource allocation strategy in satellite communication, select the initial population Pop 1 generated in Step 2 2 and the new population Pop new obtained in Step 3.4, select the dominant individuals with higher fitness scores and eliminate the inferior individuals with lower fitness scores, and go to Step 3.7;

[0030] Step 3.7: Judgment of termination condition: When the number of iteration loops i ≤ I max , execute Step 3.1; when the number of iteration loops i > I max , complete the population cycle iteration;

[0031] Step 3.8: Retain the dominant individuals obtained in Step 3.7 when i = I max as the optimal solution output, that is, obtain a set of satellite communication transmission resource allocation strategies.

[0032] The present invention also provides a multi-objective co-evolutionary resource allocation optimization system based on Latin hypercube, including:

[0033] An algorithm initialization module, used to implement the initialization of the multi-objective optimization (CMSC) algorithm based on beam space division and beam coverage detection:

[0034] Input the initial parameter list: the original problem f origin , the auxiliary problem f help , the population size N, and the maximum number of iterations I max ;

[0035] Among them, the original problem f origin refers to the satellite communication optimization problem, and the auxiliary problem f help refers to the energy consumption and delay constraints of the satellite communication optimization problem; the population size N refers to the number of decision variables participating in the optimization process, and the decision variables determine the allocation of two types of satellite resources, namely the transmit power and the antenna beam; the maximum number of iterations I max refers to the preset maximum number of calculation steps in the optimization process, which is used to ensure the completion of the resource allocation optimization within a reasonable time;

[0036] A population initialization module, used to generate two initial populations Pop 1 and Pop 2 of the same size using the Latin hypercube design (LHD) method, and two initial populations Pop 1 and Pop2 respectively represent different satellite communication transmission resource allocation strategies;

[0037] The satellite communication transmission resource allocation strategy optimization module is used to implement population cyclic iteration based on initial parameters and two initial populations Pop 1 and Pop 2 with the same size, and optimize the satellite communication transmission resource allocation strategy through the co-evolution algorithm.

[0038] The present invention also provides a multi-objective co-evolution resource allocation optimization device based on Latin hypercube, including:

[0039] A memory: storing a computer program of the above-mentioned multi-objective co-evolution resource allocation optimization method based on Latin hypercube, which is a computer-readable device;

[0040] A processor: used to implement the above-mentioned multi-objective co-evolution resource allocation optimization method based on Latin hypercube when executing the computer program.

[0041] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it can implement the above-mentioned multi-objective co-evolution resource allocation optimization method based on Latin hypercube.

[0042] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0043] 1. In the present invention, in the initialization stage of step 2, Latin hypercube design (LHD) is used to generate an initial population with uniform distribution. At the same time, in step 3.6, the environmental selection strategy is used to eliminate invalid solutions of beam coverage constraints, and a co-evolution strategy (CMSC) of "beam space division and coverage detection" is constructed, which improves the convergence speed of the algorithm and makes the solution set more global. It solves the problem of slow convergence caused by the low quality of the initial solution set of traditional intelligent algorithms (such as particle swarm optimization algorithm), and improves the problem of scenario dependence and enhances the cross-domain adaptability of the algorithm.

[0044] 2. The present invention uses the original problem f origin input in step 1 and the auxiliary problem f help to construct the original problem of satellite communication performance and the auxiliary problem of energy consumption and delay constraints, forming a framework of "co-evolution of the original problem and the auxiliary problem" for multi-objective joint optimization. While meeting the low age of information (AoI) requirements of 5G / 6G, it reduces satellite energy consumption and solves the mixed integer non-linear programming problem that is difficult to handle by traditional convex optimization methods.

[0045] 3. Through step 3.5 population evaluation and step 3.6 environment selection, the present invention generates a dynamic beam coverage detection and adaptive resource allocation strategy, which automatically adjusts the beam space division granularity and resource allocation weight for different ground user distribution scenarios such as urban dense areas and remote sparse areas, taking into account the robustness of different user distribution scenarios.

[0046] In summary, through the dynamic interference suppression method of LHD initialization and offspring strategy selection under the multi-objective co-evolution framework, the present invention solves the problems of slow convergence and high complexity in LEO satellite resource allocation, and has high robustness, can adapt to different user distributions, and provides a more general resource optimization scheme for satellite communication systems. Brief Description of the Drawings

[0047] Figure 1 is the algorithm flowchart of the present invention.

[0048] Figure 2 is a schematic diagram of the coupling relationship between different parameters of the individual genes of the present invention.

[0049] Figure 3 is a schematic diagram of the individual crossover and mutation operations of the present invention.

[0050] Figure 4 is the specific logical structure diagram of the individual gene coding method of the present invention.

[0051] Figure 5 is a performance simulation comparison chart of the CMSC algorithm of the present invention with five existing multi-objective algorithms in the rural sparse ground user scenario.

[0052] Figure 6 is a performance simulation comparison chart of the CMSC algorithm of the present invention with five existing multi-objective algorithms in the urban sparse ground user scenario.

[0053] Figure 7 is a performance simulation comparison chart of the CMSC algorithm of the present invention with five existing multi-objective algorithms in the urban dense ground user scenario.

[0054] Figure 8 is a performance simulation comparison chart of the CMSC algorithm of the present invention with five existing multi-objective algorithms in the mixed area dense user scenario. Detailed Embodiments

[0055] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0056] The present invention proposes a multi-objective optimization algorithm based on beam space division and beam coverage detection, abbreviated as CMSC, to solve the problem of satellite downlink communication resource allocation.

[0057] A multi-objective co-evolution resource allocation optimization method based on Latin hypercube, including the following steps, and the specific algorithm process is as Figure 1 shown:

[0058] Step 1: Initialization of the multi-objective optimization (CMSC) algorithm based on beam space division and beam coverage detection:

[0059] Input the initial parameter list: the original problem f origin , the auxiliary problem f help , the population size N, and the maximum number of iterations I max ;

[0060] Among them, the original problem f origin refers to the satellite communication optimization problem, and the auxiliary problem f help refers to the energy consumption and delay constraints of the satellite communication optimization problem; the population size N refers to the number of decision variables participating in the optimization process, and the decision variables determine the configuration of two types of satellite resources, namely transmission power and antenna beam; the maximum number of iterations I max refers to the preset maximum number of calculation steps in the optimization process, which is used to ensure the optimization of resource allocation within a reasonable time;

[0061] Step 2: Initialize the population:

[0062] Use the Latin hypercube design (LHD) method to generate two initial populations Pop 1 and Pop 2 with the same size, and the two initial populations Pop 1 and Pop 2 represent different satellite communication transmission resource allocation strategies respectively; the specific steps are as follows:

[0063] Step 2.1: Divide the intervals: According to the ranges of the optimization decision variables (antenna beam width and transmission power), divide these ranges into n uniform intervals; for example, if the antenna beam width range is [B min , B max , and the transmission power range is [P min , P max , then they can be evenly divided into multiple intervals;

[0064] Step 2.2: Randomly select samples: For each decision variable (antenna beam width and transmission power), randomly select a sample point from each interval divided in Step 2.1. The sample points represent different satellite resource allocation combinations in the satellite resource allocation parameters; ensure that the selected samples can represent the characteristics of each interval;

[0065] Step 2.3: Combine Samples: Randomly pair the sample points generated by all variables to form a complete sample set composed of multiple different sample points; in this process, ensure that there is no fixed combination of sample points for different variables, thereby improving the diversity of the samples;

[0066] Step 2.4: Verification and Adjustment: For the complete sample set formed in Step 2.3, through statistical uniformity tests, calculate the Kolmogorov-Smirnov values of the sample distributions in each dimension to ensure the uniformity of sample coverage; if the distribution in some areas is sparse, re-divide the intervals and supplement the sampling, adopting an adaptive interval subdivision strategy, and preferentially adding sample points in the sparse areas until the distribution in all areas is uniform, thus completing the generation of the sample set. For example, if the samples in a certain area are too concentrated, the coverage can be ensured better by increasing the number of samples in that area;

[0067] Step 2.5: Generate the Initial Population: Use the sample set generated in Step 2.4 as the initial population. Each sample point represents an individual in the population, and the characteristics of the individual are determined by its corresponding variable values (beam width and power). Each individual corresponds to a satellite multi-dimensional resource allocation scheme, and two initial populations Pop 1 and Pop 2 .

[0068] As Figure 2 shown, the individual gene coding method generates individuals to form the initial population. Each individual includes K genes, denoted as SBP(π K ), and each gene consists of a beam width parameter group Θ k and a power parameter group . Among them, the beam width parameter group Θ k includes a beam width parameter Θ k =θ k , and the power parameter group includes a set of power values. There is a coupling relationship between the beam width parameter group Θ k and the power parameter group in each gene of the individual. The beam width parameter group Θ k will affect the number of power values included in the power parameter group . The specific coupling relationship of individual gene parameters is as Figure 3 shown.

[0069] Step 3: Based on the initial parameters in Step 1 and the two initial populations Pop 1 and Pop 2 generated in Step 2, perform population cyclic iteration to optimize the satellite communication transmission resource allocation strategy through the co-evolution algorithm.

[0070] Perform the following operations in a loop until the maximum number of iterations is reached:

[0071] Step 3.1: Count accumulation: i = i + 1;

[0072] Step 3.2: Crossover operation: Select half of the individuals from the initial population Pop 1 and Pop 2 to obtain the parental population 1 and the parental population 2, that is, two sets containing different satellite resource allocation combinations are obtained, thus increasing the exploration scope of the search space;

[0073] Step 3.3: Mutation operation: Perform mutation operations on each individual in the parental population 1 and the parental population 2 obtained in Step 3.2 to obtain new individuals, and the new individuals form the offspring population 1 and the offspring population 2; The mutation operation can be achieved by fine-tuning the values of the beam width and power to increase the diversity of individuals;

[0074] As Figure 4 shown, in the crossover and mutation operations, the gene groups of the beam width parameters and the gene groups of the power parameters in each individual perform crossover and mutation operations independently.

[0075] Step 3.4: Population update: Take the intersection of the initial population Pop 1 generated in Step 2, the offspring population 1 and the offspring population 2 generated in Step 3.3 as the new population Pop new ;

[0076] Step 3.5: Population evaluation: Use the original problem f origin and the auxiliary problem f help in Step 1 to evaluate the initial population Pop 1 and Pop 2 generated in Step 2 and the new population Pop new obtained in Step 3.4. Perform coverage detection based on the average delay and average energy consumption, and calculate the fitness scores of each individual in the initial population Pop 1 and Pop 2 as well as the new population Pop new ;

[0077] Step 3.6: Environmental selection: According to the fitness scores calculated in Step 3.5, which are used to evaluate the performance of the satellite communication transmission resource allocation strategy in satellite communication, select the dominant individuals with higher fitness scores from the initial population Pop 1 and Pop 2 generated in Step 2 and the new population Pop new obtained in Step 3.4, and eliminate the inferior individuals with lower fitness scores to ensure the continuous improvement of the population quality; Go to Step 3.7;

[0078] Step 3.7: Termination condition judgment: When the number of iteration loops \(i\leq I\) max , execute Step 3.1; when the number of iteration loops \(i > I\) max , complete the population loop iteration;

[0079] Step 3.8: Retain the dominant individuals obtained in Step 3.7 when \(i = I\) max as the optimal solution output, that is, a set of satellite communication transmission resource allocation strategies is obtained.

[0080] This set of satellite communication transmission resource allocation strategies has better beam width parameters and power parameters, so as to achieve lower average delay and average energy consumption in the satellite downlink scenario.

[0081] Simulation conditions

[0082] 1. The satellite orbital altitude is 780 km, the orbital inclination is 53°, the satellite - to - satellite spacing is 5 km, the maximum diameter of the target ground area is 500 km, and the time slot length is 1 s.

[0083] 2. The communication system parameters include: the maximum satellite power is 500 W, the beam bandwidth is 200 MHz, the Ku - band carrier frequency is 12 GHz, the noise power spectral density is - 174 dBm / Hz, the user receiving antenna gain is 30 dBi, and the minimum elevation angle is 25°.

[0084] Simulation content

[0085] Compare the performance of six multi - objective evolutionary algorithms (MOEAs) in a specific area. Evaluate the algorithm performance through the Pareto fronts (PFs), with the average age of information (AoI) on the horizontal axis and the average energy consumption on the vertical axis. The simulation objective is to evaluate the optimization effect of different algorithms in the satellite multi - dimensional resource allocation problem, and focus on analyzing the trade - off ability of the algorithms between information timeliness and energy consumption. By comparing the Pareto fronts (PFs) of the six MOEA algorithms, verify the optimization effect of the algorithm proposed in the present invention on the average AoI and average energy consumption in resource allocation, and reflect its superiority.

[0086] Brief introduction of five existing comparison algorithms:

[0087] ToP (Tournament - based Selection): ToP is an algorithm based on tournament selection. By comparing within a subset, the individual with the best performance is selected as the parent for crossover and mutation operations.

[0088] PPS (Pareto-based Population Selection): PPS is an algorithm based on Pareto front selection. Its core idea is to guide the evolution of the population by selecting individuals located on the Pareto front.

[0089] ARMOEA (Adaptive Reference-point-based Multi-Objective Evolutionary Algorithm): ARMOEA is an adaptive multi-objective evolutionary algorithm based on reference points. It guides the selection of individuals by dynamically adjusting the reference points to promote the diversity and convergence of solutions.

[0090] MOEA / D (Multi-Objective Evolutionary Algorithm Based on Decomposition): MOEA / D is a multi-objective optimization algorithm based on the decomposition idea. It transforms the multi-objective problem into multiple single-objective optimization sub-problems and seeks the global optimal solution by optimizing the combination of these sub-problems.

[0091] NSGA-II (Non-dominated Sorting Genetic Algorithm II): NSGA-II is a classic multi-objective evolutionary algorithm based on non-dominated sorting. It selects the next generation of individuals through non-dominated sorting and crowding distance comparison, and has strong diversity and convergence of the solution set.

[0092] Simulation results

[0093] Figure 5 It is a performance simulation comparison chart of the CMSC algorithm of the present invention with five existing multi-objective algorithms in the rural sparse ground user scenario.

[0094] Figure 6 It is a performance simulation comparison chart of the CMSC algorithm of the present invention with five existing multi-objective algorithms in the urban sparse ground user scenario.

[0095] Figure 7 It is a performance simulation comparison chart of the CMSC algorithm of the present invention with five existing multi-objective algorithms in the urban dense ground user scenario.

[0096] Figure 8 It is a performance simulation comparison chart of the CMSC algorithm of the present invention with five existing multi-objective algorithms in the mixed area dense user scenario.

[0097] Figures 5 to 8The figure shows the comparison results of the CMSC algorithm of the present invention with five existing multi-objective algorithms under four different scenarios. It can be seen from the figure that in the four scenarios, the CMSC algorithm of the present invention shows significant performance improvement compared with the ToP, PPS, ARMOEA, MOEA / D, and NSGA-II algorithms.

[0098] To facilitate the intuitive comparison of the performance of the six algorithms in terms of balancing convergence and diversity, the figure presents the solution distribution in the objective space under four different scenarios. The approximate Pareto frontiers obtained by NSGA-II, MOEA / D, ARMOEA, PPS, ToP, and CMSC are respectively marked with sky blue, green, purple, yellow, orange, and navy blue. In each subfigure, the x-axis represents the average age of information (AoI) (unit: millisecond), and the y-axis represents the average transmission energy consumption (unit: joule). According to the designed optimization problem, the smaller the value of the objective function, the better the performance of the algorithm. Through intuitive observation, the CMSC algorithm proposed by the present invention is superior to the other five existing multi-objective algorithms in terms of the distribution and convergence of the solutions to the multi-objective problem, and the present invention shows the best optimization result. Specifically, the CMSC algorithm of the present invention always obtains the non-dominated solution set of the minimum Pareto front in the four scenarios, indicating that it achieves the best trade-off between the average AoI and the average energy.

[0099] The present invention also provides a multi-objective co-evolution resource allocation optimization system based on Latin hypercube, including:

[0100] An algorithm initialization module, which is used to implement the initialization of the multi-objective optimization (CMSC) algorithm based on beam space division and beam coverage detection in step 1:

[0101] Input the initial parameter list: the original problem f origin , the auxiliary problem f help , the population size N, and the maximum number of iterations I max ;

[0102] Among them, the original problem f origin refers to the satellite communication optimization problem, and the auxiliary problem f help refers to the energy consumption and delay constraints of the satellite communication optimization problem; the population size N refers to the number of decision variables participating in the optimization process, and the decision variables determine the configuration of two types of satellite resources, namely the transmit power and the antenna beam; the maximum number of iterations I max refers to the preset maximum number of calculation steps in the optimization process, which is used to ensure the optimization of resource allocation within a reasonable time;

[0103] A population initialization module, which is used to implement the generation of two initial populations Pop 1 and Pop 2, two initial populations Pop with the same size 1 and Pop 2 respectively represent different satellite communication transmission resource allocation strategies;

[0104] The satellite communication transmission resource allocation strategy optimization module is used to implement the population cyclic iteration based on the initial parameters in step 1 and the two initial populations Pop with the same size generated in step 2 1 and Pop 2 to optimize the satellite communication transmission resource allocation strategy through the co-evolution algorithm.

[0105] The present invention also provides a multi-objective co-evolution resource allocation optimization device based on Latin hypercube, including:

[0106] A memory: storing a computer program of the above-mentioned multi-objective co-evolution resource allocation optimization method based on Latin hypercube, which is a computer-readable device;

[0107] A processor: used to implement the above-mentioned multi-objective co-evolution resource allocation optimization method based on Latin hypercube when executing the computer program.

[0108] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it can implement the above-mentioned multi-objective co-evolution resource allocation optimization method based on Latin hypercube.

Claims

1. A multi-objective co-evolutionary resource allocation optimization method based on Latin hypercube, characterized in that: The following steps are involved: Step 1: Initialize the CMSC algorithm based on beam space partitioning and beam coverage detection: Enter the initial parameter list: original problem f origin , auxiliary problem f help , population size N, maximum number of iterations I max ; Among them, the original problem f origin Refers to the satellite communication optimization problem; auxiliary problem f help Refers to the energy consumption and delay constraints of satellite communication optimization problems; the population size N refers to the number of decision variables involved in the optimization process, which determines the configuration of two types of satellite resources: transmission power and antenna beam; the maximum number of iterations I max Refers to the preset maximum number of calculation steps in the optimization process, which is used to ensure that the optimization of resource allocation is completed within a reasonable time; Step 2: Initialize the population: The Latin Hypercube Design (LHD) method is used to generate two initial populations Pop1 and Pop2 of the same size, and the two initial populations Pop1 and Pop2 of the same size represent different satellite communication transmission resource configuration strategies respectively. Step 3: Based on the initial parameters of step 1 and the two initial populations Pop1 and Pop2 of the same size generated in step 2, a population cycle iteration is performed to optimize the satellite communication transmission resource allocation strategy through a co-evolutionary algorithm.

2. The multi-objective collaborative evolutionary resource allocation optimization method based on Latin hypercube according to claim 1 is characterized in that: The specific steps of step 2 are as follows: Step 2.1: Given the possible range of transmit power and antenna beam width corresponding to each element in the decision variable in the actual physical system and the initial population size N, divide the intervals; Step 2.2: For each decision variable, after interval division, representing different resource configuration ranges, a sample point is randomly selected from each interval divided in step 2.1, and the sample point represents a different satellite resource configuration combination in the satellite resource configuration parameter; Step 2.3: Randomly pair the sample points generated by all variables to form a complete sample set consisting of multiple different sample points, and there is no fixed combination of sample points of different variables; Step 2.4: For the complete sample set formed in step 2.3, calculate the Kolmogorov-Smirnov value of the sample distribution in each dimension through statistical uniformity test to ensure sample coverage uniformity; if the distribution in some areas is sparse, re-divide the interval and supplement the sampling, adopt the adaptive interval subdivision strategy, give priority to adding sample points in the sparse area, until the distribution in all areas is uniform, and complete the generation of sample set; Step 2.5: Use the sample set generated in step 2.4 as the initial population. Each sample point represents an individual in the population. The characteristics of the individual are determined by the corresponding variable value. Each individual corresponds to a satellite multi-dimensional resource allocation scheme. The individuals form two initial populations of the same size, Pop1 and Pop2.

3. The multi-objective collaborative evolutionary resource allocation optimization method based on Latin hypercube according to claim 1 is characterized in that: The specific steps of step 3 are as follows: Step 3.1: count accumulation: i=i+1; Step 3.2: Crossover operation: select half of the individuals from each of the initial populations Pop1 and Pop2 generated in step 2 to obtain parent population 1 and parent population 2, that is, obtain two sets containing different satellite resource configuration combinations; Step 3.3: Mutation operation: Perform mutation operation on each individual in parent population 1 and parent population 2 obtained in step 3.2 to obtain new individuals, which constitute offspring population 1 and offspring population 2; Step 3.4: Population update: Take the intersection of the initial population Pop1 generated in step 2, the offspring population 1 generated in step 3.3, and the offspring population 2 as the new population Pop new ; Step 3.5: Population evaluation: Using the original problem f in step 1 origin and auxiliary problem f help For the initial populations Pop1 and Pop2 generated in step 2 and the new population Pop obtained in step 3.4 new Evaluation is performed, coverage detection is performed based on average delay and average energy consumption, and the initial populations Pop1 and Pop2 and the new population Pop are calculated respectively. new The fitness score of each individual in ; Step 3.6: Environment selection: Based on the fitness score calculated in step 3.5, the performance of the satellite communication transmission resource allocation strategy in satellite communication is evaluated. The initial populations Pop1 and Pop2 generated in step 2 and the new population Pop obtained in step 3.4 are selected. new The superior individuals with higher fitness scores are selected, and the inferior individuals with lower fitness scores are eliminated, and go to step 3.7; Step 3.7: Termination condition judgment: when the number of iterations i ≤ I max When , execute step 3.1; When the number of iterations i>I max When , the population cycle iteration is completed; Step 3.8: Keep step 3.7 at i = I max The dominant individual obtained at this time is output as the optimal solution, that is, a set of satellite communication transmission resource configuration strategies is obtained.

4. A multi-objective collaborative evolutionary resource allocation optimization system based on Latin hypercube based on the method according to any one of claims 1 to 3, characterized in that: include: Algorithm initialization module, used to implement the multi-objective optimization (CMSC) algorithm initialization based on beam space division and beam coverage detection: Enter the initial parameter list: original problem f origin , auxiliary problem f help , population size N, maximum number of iterations I max ; Among them, the original problem f origin Refers to the satellite communication optimization problem, auxiliary problem f help Refers to the energy consumption and delay constraints of satellite communication optimization problems; the population size N refers to the number of decision variables involved in the optimization process, which determines the configuration of two types of satellite resources: transmission power and antenna beam; the maximum number of iterations I max Refers to the preset maximum number of calculation steps in the optimization process, which is used to ensure that the optimization of resource allocation is completed within a reasonable time; A population initialization module is used to generate two initial populations Pop1 and Pop2 of the same size using a Latin Hypercube Design (LHD) method, wherein the two initial populations Pop1 and Pop2 of the same size represent different satellite communication transmission resource configuration strategies respectively; The satellite communication transmission resource configuration strategy optimization module is used to implement population cycle iteration based on initial parameters and two initial populations Pop1 and Pop2 of the same size, and optimize the satellite communication transmission resource configuration strategy through a co-evolutionary algorithm.

5. A multi-objective co-evolutionary resource allocation optimization device based on Latin hypercube, characterized in that: include: Memory: a computer program storing a method for optimizing resource allocation based on Latin hypercube with multi-objective co-evolution described in any one of claims 1 to 3, which is a computer-readable device; Processor: used to implement the multi-objective collaborative evolutionary resource allocation optimization method based on Latin hypercube as described in any one of claims 1 to 3 when executing the computer program.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it can implement a multi-objective collaborative evolutionary resource configuration optimization method based on Latin hypercube as described in any one of claims 1 to 3.

Images