CN116611505B - Satellite cluster observation task scheduling method, system, equipment and storage medium - Google Patents

Abstract

The invention discloses a satellite cluster observation task scheduling method, a system, equipment and a storage medium, wherein the method adopts preset constraint conditions to screen satellites in a satellite cluster; selecting an optimal strategy for a satellite for executing each observation task in an individual, and calculating an fitness value of each individual; selecting a plurality of individuals from the initial population as parents according to the fitness value; randomly selecting two parents to perform cross operation to obtain a first new individual; performing mutation operation on each parent to obtain a second new individual; forming a new population from the parent, the first new individual and the second new individual, and using the new population for the next iteration comprising fitness value calculation, parent selection, crossover operation and mutation operation until a maximum fitness value is obtained; and acquiring a second optimal strategy combination according to the maximum fitness value, and adopting the second optimal strategy combination to schedule satellite cluster observation tasks. The invention can improve the execution efficiency of the observation task and globally optimize the scheduling of the observation task.

Description

Satellite cluster observation task scheduling method, system, equipment and storage medium

Technical Field

The present invention relates to the field of satellite observation technologies, and in particular, to a satellite cluster observation task scheduling method, system, device, and storage medium.

Background

The scheduling of observation tasks for a satellite cluster is an important issue in the field of modern satellite technology. The satellite cluster consists of a plurality of satellites, and the observation task is executed through cooperation. With the rapid development and wide application of satellite technology, such as the fields of earth remote sensing, weather prediction, communication and the like, the observation task scheduling of satellite clusters becomes more and more complex and critical.

However, conventional satellite cluster observation task scheduling methods present some difficulties and challenges. First, there are problems of resource competition and scheduling conflict between satellites in a satellite cluster, resulting in inefficient execution of observation tasks. Secondly, due to diversity and complexity of observation tasks, the traditional observation task scheduling method often cannot fully consider the relevance and priority among the observation tasks, so that resource waste and observation requirements cannot be met. In addition, the traditional method is easy to fall into a local optimal solution, and the scheduling of the observation task cannot be globally optimized.

Disclosure of Invention

The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides a satellite cluster observation task scheduling method, a system, equipment and a storage medium, which can improve the execution efficiency of the observation task, reduce the resource waste, better meet different observation demands and globally optimize the scheduling of the observation task.

In a first aspect, an embodiment of the present invention provides a satellite cluster observation task scheduling method, where the satellite cluster observation task scheduling method includes:

taking a plurality of groups of observation task sequences as an initial population; wherein a set of observation task sequences is taken as an individual in the initial population;

screening satellites in the satellite cluster by adopting a preset constraint condition to obtain a first satellite cluster after satellite screening;

selecting an optimal strategy for satellites in the first satellite cluster for executing each observation task in the individuals, obtaining a first optimal strategy combination, and calculating the fitness value of each individual according to the first optimal strategy combination;

selecting a plurality of individuals from the initial population as parents according to the fitness value; randomly selecting two parents to perform cross operation to obtain a first new individual; performing mutation operation on each parent to obtain a second new individual; forming a new population by the father, the first new individual and the second new individual, and using the new population for the next iteration comprising fitness value calculation, father selection, crossover operation and mutation operation until reaching a preset termination condition, so as to obtain a maximum fitness value;

And acquiring a second optimal strategy combination according to the maximum fitness value, and adopting the second optimal strategy combination to schedule satellite cluster observation tasks.

Compared with the prior art, the first aspect of the invention has the following beneficial effects:

the method adopts the preset constraint condition to screen the satellites in the satellite cluster to obtain a first satellite cluster after the satellites are screened, and the satellites in the satellite cluster can be screened out by the constraint condition, so that the execution efficiency of the observation task is improved; selecting an optimal strategy for satellites in a first satellite cluster for executing each observation task in an individual, obtaining a first optimal strategy combination, calculating a fitness value of each individual according to the first optimal strategy combination, calculating the fitness value through the optimal strategy combination formed by the optimal strategy of each satellite, considering the interdependence and resource sharing among satellites, and being capable of more comprehensively considering the overall fitness; selecting a plurality of individuals from the initial population as parents according to the fitness value; randomly selecting two parents to perform cross operation to obtain a first new individual; performing mutation operation on each parent to obtain a second new individual; the parent, the first new individual and the second new individual form a new population, the new population is used for the next iteration comprising fitness value calculation, parent selection, crossover operation and mutation operation until reaching a preset termination condition, the maximum fitness value is obtained, the maximum fitness value can be selected as a whole by selecting the parent according to the fitness value and performing crossover operation, mutation operation and iteration, then a second optimal strategy combination is obtained according to the maximum fitness value, and satellite cluster observation task scheduling is performed by adopting the second optimal strategy combination, so that the execution efficiency of the observation task can be improved, the resource waste can be reduced, different observation requirements can be better met, and the scheduling of the observation task can be globally optimized.

According to some embodiments of the invention, the selecting an optimal strategy for satellites in the first satellite cluster that perform each observation task in the individual, to obtain a first optimal strategy combination, comprises:

step S111, initializing a strategy of each satellite in the first satellite cluster;

step S112, forming adjacent alliances by each satellite and adjacent satellites thereof;

step S113, calculating the benefits of each satellite selected strategy when cooperating with the adjacent alliances;

step S114, designing an alternative strategy for the satellite by changing the cooperation mode of the satellite and the adjacent satellite, and selecting an alternative strategy for maximizing the expected benefits of the satellite to update the strategy selected by the satellite;

step S115, repeating the step S114 for all satellites in the first satellite cluster until the expected benefits of the satellites are maximized and the convergence or the maximum iteration number is reached, so as to obtain a first optimal strategy combination.

According to some embodiments of the invention, the fitness value is calculated by:

；

wherein the first itemRepresenting resource utilization, second termRepresenting task coverage,/->Optimal policy combination representing satellite clusters, +. >Representing the number of satellites participating in an observation plan, +.> and />Representing the weight coefficient, ++>，/>Indicating satellite->Resource utilization of->Representing the ratio of the length of the observation task to the length of the observation time window performed, +.>Representing observation task->Weight of->Indicating satellite->Whether or not to execute the observation task->0 indicates no execution, 1 indicates execution, < ->Indicating the number of observation tasks.

According to some embodiments of the invention, the selecting a plurality of individuals from the initial population as parents according to the fitness value comprises:

calculating to obtain the total fitness value of all individuals according to the fitness value of each individual;

calculating the probability of each individual being selected according to the total fitness value;

calculating to obtain accumulated probabilities based on the selected probabilities of each individual, and forming an accumulated probability array from the accumulated probabilities of each individual;

generating a random number, and selecting a plurality of individuals as parents according to the position of the random number in the cumulative probability array.

According to some embodiments of the invention, the randomly selecting two parents for cross-over operation, obtaining a first new individual, comprises:

step S211, randomly selecting two parents including a first parent and a second parent;

Step S212, if the elements of the initial positions of the first parent and the second parent are the same, the intersection operation cannot form a closed loop, and the two parents are returned;

step S213, otherwise, selecting the next position of the initial position of the first parent as the initial position;

step S214, initializing a child, and taking the initial position of the first parent as the current position of the child;

step S215, finding the first position of the element equal to the current position of the child body from the second parent;

step S216, if the first position is equal to the current position of the child body, forming a closed loop, and terminating the cross operation;

step S217, if not, copying the element in the second parent to the corresponding position of the child, and setting the first position as the current position of the child;

step S219, repeating the step S215 to the step S217 until a closed loop is formed or a complete observation task sequence is traversed.

According to some embodiments of the invention, the mutating each of the parents to obtain a second new individual includes:

the design variation probability is as follows:

；

wherein ,representing the mutation probability under the current genetic algebra +. >Representing the maximum mutation probability under the initial genetic algebra, < ->Number representing current genetic algebra>Representing total genetic algebra>Representing a constant;

and carrying out mutation operation on each parent by adopting the mutation probability to obtain a second new individual.

According to some embodiments of the invention, the preset constraints include constraining each satellite resource, the observation tasks satisfying observability, the interval between the observation tasks satisfying a satellite transition time, each of the observation tasks being performed at most once, and the observation tasks being completed within a prescribed time.

In a second aspect, an embodiment of the present invention further provides a satellite cluster observation task scheduling system, where the satellite cluster observation task scheduling system includes:

the population initial unit is used for taking a plurality of groups of observation task sequences as initial populations; wherein a set of observation task sequences is taken as an individual in the initial population;

the satellite screening unit is used for screening satellites in the satellite cluster by adopting preset constraint conditions to obtain a first satellite cluster after satellite screening;

the strategy selection unit is used for selecting an optimal strategy for satellites in the first satellite cluster for executing each observation task in the individuals, obtaining a first optimal strategy combination, and calculating the fitness value of each individual according to the first optimal strategy combination;

The iterative calculation unit is used for selecting a plurality of individuals from the initial population as parents according to the fitness value; randomly selecting two parents to perform cross operation to obtain a first new individual; performing mutation operation on each parent to obtain a second new individual; forming a new population by the father, the first new individual and the second new individual, and using the new population for the next iteration comprising fitness value calculation, father selection, crossover operation and mutation operation until reaching a preset termination condition, so as to obtain a maximum fitness value;

and the task scheduling unit is used for acquiring a second optimal strategy combination according to the maximum fitness value and adopting the second optimal strategy combination to perform satellite cluster observation task scheduling.

In a third aspect, an embodiment of the present invention further provides an electronic device, including:

at least one memory;

at least one processor;

at least one computer program;

the at least one computer program is stored in the at least one memory, and the at least one processor executes the at least one computer program to implement a satellite cluster observation task scheduling method as described in the first aspect above.

In a fourth aspect, an embodiment of the present invention further provides a storage medium, where the storage medium is a computer readable storage medium, where the computer readable storage medium stores a computer program, where the computer program is configured to make a computer execute a satellite cluster observation task scheduling method according to the first aspect.

It is to be understood that the advantages of the second to fourth aspects compared with the related art are the same as those of the first aspect compared with the related art, and reference may be made to the related description in the first aspect, which is not repeated herein.

Drawings

The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:

FIG. 1 is a flow chart of a satellite cluster observation task scheduling method according to an embodiment of the invention;

FIG. 2 is a schematic view of the strategy selection of satellites in a population according to an embodiment of the invention;

FIG. 3 is a schematic diagram of a crossover operation according to one embodiment of the present invention;

FIG. 4 is a block diagram of a satellite cluster observation task scheduling system according to an embodiment of the present invention;

fig. 5 is a schematic hardware structure of an electronic device according to an embodiment of the invention.

Detailed Description

Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.

In the description of the present invention, the description of first, second, etc. is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.

In the description of the present invention, it should be understood that the direction or positional relationship indicated with respect to the description of the orientation, such as up, down, etc., is based on the direction or positional relationship shown in the drawings, is merely for convenience of describing the present invention and simplifying the description, and does not indicate or imply that the apparatus or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.

In the description of the present invention, unless explicitly defined otherwise, terms such as arrangement, installation, connection, etc. should be construed broadly and the specific meaning of the terms in the present invention can be determined reasonably by a person skilled in the art in combination with the specific content of the technical solution.

The scheduling of observation tasks for a satellite cluster is an important issue in the field of modern satellite technology. The satellite cluster consists of a plurality of satellites, and the observation task is executed through cooperation. With the rapid development and wide application of satellite technology, such as the fields of earth remote sensing, weather prediction, communication and the like, the observation task scheduling of satellite clusters becomes more and more complex and critical.

However, conventional satellite cluster observation task scheduling methods present some difficulties and challenges. First, there are problems of resource competition and scheduling conflict between satellites in a satellite cluster, resulting in inefficient execution of observation tasks. Secondly, due to diversity and complexity of observation tasks, the traditional observation task scheduling method often cannot fully consider the relevance and priority among the observation tasks, so that resource waste and observation requirements cannot be met. In addition, the traditional method is easy to fall into a local optimal solution, and the scheduling of the observation task cannot be globally optimized.

In order to solve the problems, the method adopts the preset constraint condition to screen the satellites in the satellite cluster, so as to obtain a first satellite cluster after the satellite is screened, and the satellite in the satellite cluster can be screened out by the constraint condition, so that the execution efficiency of the observation task is improved; selecting an optimal strategy for satellites in a first satellite cluster for executing each observation task in an individual, obtaining a first optimal strategy combination, calculating a fitness value of each individual according to the first optimal strategy combination, calculating the fitness value through the optimal strategy combination formed by the optimal strategy of each satellite, considering the interdependence and resource sharing among satellites, and being capable of more comprehensively considering the overall fitness; selecting a plurality of individuals from the initial population as parents according to the fitness value; randomly selecting two parents to perform cross operation to obtain a first new individual; performing mutation operation on each parent to obtain a second new individual; the parent, the first new individual and the second new individual form a new population, the new population is used for the next iteration comprising fitness value calculation, parent selection, crossover operation and mutation operation until reaching a preset termination condition, the maximum fitness value is obtained, the maximum fitness value can be selected as a whole by selecting the parent according to the fitness value and performing crossover operation, mutation operation and iteration, then a second optimal strategy combination is obtained according to the maximum fitness value, and satellite cluster observation task scheduling is performed by adopting the second optimal strategy combination, so that the execution efficiency of the observation task can be improved, the resource waste can be reduced, different observation requirements can be better met, and the scheduling of the observation task can be globally optimized.

Referring to fig. 1, an embodiment of the present invention provides a satellite cluster observation task scheduling method, which includes, but is not limited to, steps S100 to S500, wherein:

step S100, taking a plurality of groups of observation task sequences as initial populations; wherein a set of observation task sequences is taken as an individual in the initial population;

step 200, screening satellites in the satellite cluster by adopting a preset constraint condition to obtain a first satellite cluster after satellite screening;

step S300, selecting an optimal strategy for satellites in a first satellite cluster for executing each observation task in an individual, obtaining a first optimal strategy combination, and calculating the fitness value of each individual according to the first optimal strategy combination;

step S400, selecting a plurality of individuals from the initial population as parents according to the fitness value; randomly selecting two parents to perform cross operation to obtain a first new individual; performing mutation operation on each parent to obtain a second new individual; forming a new population by the father generation, the first new individual and the second new individual, and using the new population for the next iteration comprising fitness value calculation, father generation selection, crossover operation and mutation operation until reaching a preset termination condition to obtain a maximum fitness value;

And S500, acquiring a second optimal strategy combination according to the maximum fitness value, and adopting the second optimal strategy combination to schedule satellite cluster observation tasks.

In steps S100 to S500 of some embodiments, in order to screen out inappropriate satellites, the present embodiment screens satellites in a satellite cluster by adopting a preset constraint condition to obtain a first satellite cluster after satellite screening; in order to more comprehensively consider the overall fitness, the embodiment obtains a first optimal strategy combination by selecting an optimal strategy for satellites in a first satellite cluster for executing each observation task in an individual, and calculates a fitness value of each individual according to the first optimal strategy combination; in order to improve the execution efficiency of the observation task and reduce the resource waste, the scheduling of the observation task is globally optimized, and a plurality of individuals are selected from the initial population to serve as parents according to the fitness value; randomly selecting two parents to perform cross operation to obtain a first new individual; performing mutation operation on each parent to obtain a second new individual; and forming a new population by the father generation, the first new individual and the second new individual, using the new population for the next iteration comprising fitness value calculation, father generation selection, crossover operation and mutation operation until reaching a preset termination condition, obtaining a maximum fitness value, obtaining a second optimal strategy combination according to the maximum fitness value, and adopting the second optimal strategy combination to schedule satellite cluster observation tasks.

In some embodiments, selecting an optimal strategy for satellites in a first cluster of satellites that perform each observation task in an individual, obtaining a first optimal strategy combination includes:

step S111, initializing a strategy of each satellite in the first satellite cluster;

step S112, each satellite and adjacent satellites form adjacent alliances;

step S113, calculating the benefits of each satellite selected strategy when cooperating with adjacent alliances;

step S114, designing a replacement strategy for the satellite by changing the cooperation mode of the satellite and the adjacent satellite, and selecting the replacement strategy for maximizing the expected benefits of the satellite to update the strategy selected by the satellite;

step S115, repeating step S114 for all satellites in the first satellite cluster until the expected benefits of the maximized satellites reach convergence or the maximum iteration number is reached, and obtaining a first optimal strategy combination.

In this embodiment, by mutually cooperating satellites, an optimal policy selection is performed for each satellite, so that the efficiency of the satellite in executing the observation task can be improved.

In some embodiments, the fitness value is calculated by:

；

wherein the first itemRepresenting resource utilization, second termRepresenting task coverage,/- >Optimal policy combination representing satellite clusters, +.>Representing the number of satellites participating in an observation plan, +.> and />Representing the weight coefficient, ++>，/>Indicating satellite->Resource utilization of->Representing the ratio of the length of the observation task to the length of the observation time window performed, +.>Representing observation task->Weight of->Indicating satellite->Whether or not to execute the observation task->0 indicates no execution, 1 indicates execution, < ->Indicating the number of observation tasks.

In this embodiment, the fitness value is calculated by an optimal policy combination composed of optimal policies of each satellite, and the mutual dependence and resource sharing between satellites are considered, so that the overall fitness can be considered more comprehensively.

In some embodiments, selecting a plurality of individuals from the initial population as parents based on the fitness value comprises:

calculating to obtain the total fitness value of all individuals according to the fitness value of each individual;

calculating the probability of each individual being selected according to the total fitness value;

calculating to obtain accumulated probabilities based on the selected probabilities of each individual, and forming an accumulated probability array from the accumulated probabilities of each individual;

a random number is generated, and a plurality of individuals are selected as parents according to the position of the random number in the cumulative probability array.

In this embodiment, the cumulative probability array is used in calculating the probability that an individual is selected, avoiding the need to make roulette for each selection. By accumulating the probability arrays, individuals can be selected more efficiently and the randomness and proportionality of the selection maintained. This improved approach can better preserve population diversity during selection operations and explore search space more efficiently.

In some embodiments, randomly selecting two parents for crossover operations to obtain a first new individual includes:

step S211, randomly selecting two parents including a first parent and a second parent;

step S212, if the elements of the initial positions of the first parent and the second parent are the same, the intersection operation cannot form a closed loop, and the two parents are returned;

step S213, otherwise, selecting the next position of the initial position of the first parent as the initial position;

step S214, initializing a child, and taking the initial position of a first parent as the current position of the child;

step S215, finding the first position of the element equal to the current position of the child from the second parent;

step S216, if the first position is equal to the current position of the child body, forming a closed loop, and terminating the cross operation;

Step S217, if not, copying the element in the second parent to the corresponding position of the child, and setting the first position as the current position of the child;

step S219, repeat step S215 to step S217 until a closed loop is formed or the complete observation task sequence is traversed.

In this embodiment, the sequence of elements extracted from two parents is ensured to be always legal by improved round robin operation, and no illegal or repeated elements are introduced. The improved round robin operation avoids invalid round robin and repeat elements by detecting if a closed loop is formed, which maintains the randomness and diversity of the cross operations while ensuring the legitimacy of the resulting child.

In some embodiments, performing a mutation operation on each parent to obtain a second new individual comprises:

the design variation probability is as follows:

；

wherein ,representing the mutation probability under the current genetic algebra +.>Representing the maximum mutation probability under the initial genetic algebra, < ->Number representing current genetic algebra>Representing total genetic algebra>Representing a constant;

and carrying out mutation operation on each father by using mutation probability to obtain a second new individual.

In the embodiment, the mutation operation is performed by designing the proper mutation probability, so that the situation that the mutation probability is too small, the diversity of the population is reduced too fast, the effective genes are lost rapidly and the repair is not easy to perform can be prevented; and the probability of preventing variation is too large, and although diversity of the population can be ensured, the probability of damaging the higher-order mode is increased.

In some embodiments, the preset constraints include constraining each satellite resource, the observation tasks satisfying observability, the interval between the observation tasks satisfying the time required for satellite transitions, each observation task being performed at most once, and the observation tasks being completed within a specified time.

In this embodiment, satellites in the satellite cluster can be screened out by constraint conditions, so that the execution efficiency of the observation task is improved.

For ease of understanding by those skilled in the art, a set of preferred embodiments are provided below:

1. define the problem.

Set up the observation task setThe method comprises the following steps:

using a five-tupleTo characterize each observation task +.>. wherein ,/>Represents the earliest start time of observation,/->Indicating the latest end time of observation,/->Indicating the desired observation period +.>Indicating the priority of the observation task +.>Representing the minimum storage capacity required, +.>Indicating the number of observation tasks>。

Let the satellite cluster be:

wherein ,indicating the number of satellites>Any one element->Representing a satellite.

The observation time window resources are:

the observation time window resource is expressed as a five-tuple:

wherein ,indicating satellite->In observation task->Initial observation time on- >Representing satellitesIn observation task->Observation end time on->Indicating satellite->Storage resources available for observation (sufficient storage resources are needed for picture data after satellite observation) are added>Indicating satellite->Storage resource consumption rate of->Indicating satellite->Is a resource utilization of (a). The observation time window resources can be expressed as:

wherein ,representing the number of satellites.

Representing the actual observation period of the observation task on the satellite +.>。

2. Goals and constraints are designed.

Each satellite may choose to perform or not perform the observation task, so the policy set for each satellite is, wherein />Indicating no task is performed,/->Representing execution of a task.

Collaborative cost function (i.e., the function used later to calculate individual fitness):is a slave power set->To real number set->Function of->Representing the overall utility when a satellite cluster selects a set of strategies.

(1) Target object

The observed overall utility maximization is expressed as:

wherein the first itemRepresenting resource utilization, second termRepresenting task coverage,/->Optimal policy combination representing satellite clusters, +.>Representing the number of satellites participating in an observation plan, +.> and />Representing the weight coefficient, ++>，/>Indicating satellite->Resource utilization of- >Representing the ratio of the length of the observation task to the length of the observation time window performed, +.>Representing observation task->Weight of->Indicating satellite->Whether or not to execute the observation task->0 indicates no execution, 1 indicates execution, < ->Indicating the number of observation tasks.

(2) Constraint

1) The resource constraint of each satellite is preset, and only a limited number of observation tasks can be executed, which is expressed as follows:

wherein ,representing the satellite storage resource consumption rate, < >>Representing the maximum amount of available storage resources for the satellite,。

2) The preset observation task must satisfy observability expressed as:

。

3) The time required for meeting satellite transition is required for presetting the interval between observation tasks, and is expressed as:

wherein ,the preparation time for satellite observation is shown.

4) Presetting that each observation task is executed at most once, wherein the method comprises the following steps:

。

5) The preset observation task must be completed within a prescribed time, expressed as:

。

3. based on the foundation, the observation task scheduling optimization is carried out by combining with an improved genetic algorithm of the cooperative game

Step 1: an initial set of task sequence combinations is generated as individuals of the population. The method comprises the following steps:

for R observation tasks, they are mapped to integers between 1 and R. Each position in the task sequence corresponds to an observation task.

Hypothesized individualsThe task sequence combination of (2) is denoted->, wherein Representing the observation task. The initial population is marked as +.>The size is +.>。

The method for generating the initial population based on the rules is adopted, and specifically comprises the following steps:

step 11: multiple observation task sequences were randomly generated as 10% of the individuals in the initial population. Each individual is represented as:, wherein ,/>，/>。

Step 12: multiple observation task sequences were randomly generated as 30% of the individuals in the initial population. Each individual is represented as:, wherein ,/>，/>. The first 50% of the bit observation tasks for each individual are ranked from large to small in priority.

For individualsLet the first 50% of the set of bit observation tasks be +.>The ranked individuals are expressed as: />, wherein ,/>。

Step 13: multiple observation task sequences were randomly generated as 30% of the individuals in the initial population. Each individual is represented as, wherein ,/>，/>. The first 50% of the bits of each individual are sorted by proportion from small to large by the earliest observation time of operation.

For individualsLet the first 50% of the set of bit observation tasks be +.>The ordered individual is then denoted +.>, wherein ,/>。

Step 14: multiple observation task sequences were randomly generated as 30% of the individuals in the initial population. Recording the initial population as Wherein each individual is denoted +.>，/>，. The first 50% of the genes of each individual are sequenced according to a certain proportion from small to large according to the latest observation time of the observation task.

For individualsSet the first 50% of the bitsThe set of observation tasks is->The ordered individual is then denoted +.>, wherein ,/>。

It should be noted that, the rule-based initial population generation method in this embodiment may be modified according to the actual implementation, and this embodiment is not limited specifically.

Step 2: assessing individual fitness, and calculating the overall utility of each individual in the current population as follows:

wherein the first itemRepresenting resource utilization, second termRepresenting task coverage,/->Optimal policy combination representing satellite clusters, +.>Representing the number of satellites participating in an observation plan, +.> and />Representing the weight coefficient, ++>，/>Indicating satellite->Resource utilization of->Representing the ratio of the length of the observation task to the length of the observation time window performed, +.>Representing observation task->Weight of->Indicating satellite->Whether or not to execute the observation task->0 indicates no execution, 1 indicates execution, < ->Indicating the number of observation tasks.

To calculate the value of the fitness of an individual, all constraints 1), 2), 3), 4) and 5) above should be satisfied, and then a satellite strategy is assigned to each observation task in the individual. Therefore, this embodiment designs a method for selecting a satellite strategy to obtain an execution plan of a task, and a schematic diagram of the strategy selection of satellites in a population is shown in fig. 2, and fig. 2 shows a population including 10 individuals, where each individual includes 20 satellites and 20 tasks. The following is an explanation of the meaning of the graph:

Each subplot represents an individual, each subplot represents an individual in the population, and each subplot number (i.e., individual number) is a, b, c, d, e, f, g, h, i, j. Each sub-graph shows an individual satellite mission sequence combination.

The x-axis represents the task: the x-axis represents the number of tasks, each number corresponding to a particular task;

the y-axis represents satellite: the y-axis represents the satellite numbers, each number corresponding to a particular satellite;

the data points represent the assignment of tasks on the satellites: each data point (black dot) represents the allocation of a task on the satellite. For example, if the data point is located at the (x, y) coordinate location, it means that task x is assigned to satellite y for execution.

The satellite in each individual selects a different strategy to execute on each mission according to its own strategy selection. Each policy represents a behavior or decision to address a particular observation task, and different individuals may choose different policies to address the observation task, depending on the individual's genes or the results of the optimization algorithm. The satellite strategy selection method specifically comprises the following steps:

step 21: each satellite is provided withIs initialized to +.>, wherein />Indicating satellite->Policy selection of (2);

step 22: determining the neighbors of each satellite based on the communication links between the satellites, for each satelliteForm a ∈>Adjacent alliance of adjacent satellites>；

Step 23: for the followingEach satelliteCalculate and neighbor alliance->The benefits (i.e., overall utility) of all possible policy combinations; wherein, is provided with->Indicating satellite->Strategy of choice->And is in charge of alliance>Earnings in collaboration;

step 24: changing satellites by exploring the space of possible strategiesThe cooperation mode with its neighbor satellite is satellite +.>Consider alternative strategies->Alternative strategies are chosen which maximize their expected benefits +.>To update satellite +.>Strategy of choice->：/>；

Step 25: to a group in a clusterThere is a satellite that repeats step 24 until convergence is reached or a maximum number of iterations is reached. The final converged allocation vector is:，/>a stable policy selection scheme (i.e. optimal policy combination) representing a satellite cluster, wherein +.>Indicating satellite->The optimal strategy is selected.

Step 3: and selecting operation.

An improved roulette method is used to select a portion of individuals as parents based on their fitness. The method comprises the following steps:

step 31: for each individual in the population, calculating the overall utility of each individual according to step 2 ；

Step 32: the sum of the calculated utilities for all individuals in the population is:, wherein ,representing the number of individuals in the population;

step 33: for each individualCalculating the probability of being selected for gene manipulation>. The ratio of the individual's benefit (i.e. overall utility) to the total benefit (i.e. sum of utilities) is taken as a measure of probability, i.e.

wherein ,represents an adjustment parameter for controlling the degree of adjustment of the probability. Less->The value can reduce the probability of high-benefit individuals, increase the opportunity of low-benefit individuals and increase the diversity of the population. By introducing an improved probability calculation formula, the benefit and diversity of the individual can be balanced better, and the individual is prevented from falling into a local optimal solution;

step 34: improved roulette options, in particular:

creating an accumulated probability arrayThe initial value is zero. For every individual->Calculate the probability of being selected and then calculate the cumulative probability +.>Cumulative probability->Representing from the first individual to +.>The cumulative sum of all selection probabilities for the individual individuals. The calculation can be performed using the following formula:

wherein ,representing +.>Probability of being selected, and probability of being selected for gene manipulation +.>Equal.

Step 35: generating a random number The value range is->Between, according to random number->In cumulative probability array->Determining the selected individual and using the selected individual as a parent.

In this embodiment, the cumulative probability array is used in calculating the individual selection probabilities, avoiding the need to make roulette for each selection. By accumulating the probability arrays, individuals can be selected more efficiently and the randomness and proportionality of the selection maintained. This improved approach can better preserve population diversity during selection operations and explore search space more efficiently.

The adjustment parameters of the present embodimentThe selection of (a) may be adjusted according to specific problems and experimental results to obtain better performance and convergence, and the embodiment is not particularly limited.

Step 4: and (5) performing cross operation.

The schematic diagram of the crossover operation is shown in fig. 3, where a in fig. 3 represents a flow of cyclic crossover of two parent individuals and b in fig. 3 represents a new individual generated after the crossover is completed. The crossover operation is carried out on the father individual by using a cyclic crossover mutation operator to generate a new individual, which is specifically as follows:

assume that there are two parents and />Generating a child according to the following steps >：

Step 41: if it isThe crossover operation cannot form a closed loop and returns to the original parent and />；

Step 42: otherwise, select a starting position, wherein ,/>；

Step 43 initializing a childIts current position is set to +.>I.e.；

Step 44: from parent individualsFind and sub-individual->Equal element position ∈>；

Step 45: if the position isAnd sub-individuals->Is +.>Equal, it indicates that a closed loop has been formed, terminating the crossover operation;

step 46: otherwise, willReplication to child->Corresponding positions of (a), i.e.)；

Step 47: will beSet to the current position, i.e.)>；

Step 48: steps 44 through 47 are repeated until a closed loop is formed or the complete sequence is traversed.

In this embodiment, the improved loop-crossing operator ensures that sequences of elements extracted from two parents are always legal, without introducing illegal or duplicate elements. It avoids invalid loops and repeating elements by detecting whether a closed loop is formed. This improved method maintains the randomness and diversity of the crossover operation while guaranteeing the legitimacy of the resulting subunits.

Step 5: and (5) performing mutation operation.

The mutation operator dynamically updates the mutation probability, namely gradually reduces the mutation probability along with the increase of the genetic algebra until the mutation probability is zero. The probability of variation is calculated by the following formula:

wherein ,representing the mutation probability under the current genetic algebra +.>Representing the maximum mutation probability under the initial genetic algebra (first generation),>number representing current genetic algebra from +.>To->，/>Represents the total number of genetics (usually the preset maximum number of iterations),/and the total number of genetics (usually the total number of iterations)>The index, which represents a constant, is an index that controls the rate of decay of the probability of variation.

The mutation probability calculation formula represents a process in which mutation probability gradually decreases with an increase in the number of genetic algebra. Initially, the mutation probability isWith the increase of the genetic algebra, the mutation probability gradually decreases according to an exponential function until the genetic algebra reaches +.>When the mutation probability is zero.

Step 6: updating the population.

The parent and newly generated individuals are combined to form a next generation population. The operations of evaluating fitness, selecting, crossing and mutating are repeated until a termination condition is reached. The termination conditions were as follows:

the first condition is:

defining a counterFor recording successive unmodified iterations.

In each iteration, if the next generation individual is generated to be the same as the current generation individual, thenAnd adding one.

If it isReaching maximum unmodified algebra->The iterative process of the genetic algorithm is terminated.

The second condition is:

defining a counterFor recording the number of iterations.

In each iteration, willAnd adding one.

If it isReach maximum iteration number->The iterative process of the genetic algorithm is terminated.

So as long as at least one of the two conditions is satisfied, the iterative process of the algorithm ends.

Step 7: and executing a task scheduling scheme.

Step 6, obtaining a second optimal strategy combination according to the obtained maximum fitness value after iteration is finished; according to the second optimal strategy combination of each individual, determining the task execution condition of each satellite, distributing observation tasks to each satellite, and executing the observation tasks by each satellite by adopting the optimal strategy to ensure that the task coverage rate and the resource utilization rate reach the optimal.

In this embodiment, a cooperative game model is employed to describe the cooperative relationships between the satellite cluster members. By defining a collaboration cost function (i.e., the overall utility of the present embodiment), the overall utility of the satellite cluster in selecting a set of optimal strategies may be quantified. The cooperative game model considers the interdependence and resource sharing among satellites, so that the overall benefit can be considered more comprehensively by the observation task scheduling. Genetic algorithm is introduced as an optimization method of observation task scheduling, and the optimal observation task scheduling scheme is searched by utilizing selection, crossover and mutation operations of an improved genetic algorithm combined with the cooperative game. In calculating the individual selection probabilities, an array of cumulative probabilities is used, avoiding the need to make roulette for each selection. By accumulating the probability arrays, individuals can be selected more efficiently and the randomness and proportionality of the selection maintained. The improved loop-crossing operator ensures that sequences of elements extracted from two parents are always legal, without introducing illegal or duplicate elements. It avoids invalid loops and repetition elements by detecting whether a closed loop is formed, which maintains the randomness and diversity of the crossover operation while guaranteeing the validity of the generated child and more efficiently exploring the search space. The maximum fitness value is selected on the whole, then the second optimal strategy combination is obtained according to the maximum fitness value, and the second optimal strategy combination is adopted for satellite cluster observation task scheduling, so that the execution efficiency of the observation task can be improved, the resource waste can be reduced, different observation requirements can be better met, and the scheduling of the observation task can be globally optimized.

Referring to fig. 4, the embodiment of the present invention further provides a satellite cluster observation task scheduling system, where the satellite cluster observation task scheduling system includes a population initial unit 100, a satellite screening unit 200, a policy selection unit 300, an iterative calculation unit 400, and a task scheduling unit 500, where:

the population initial unit 100 is configured to use a plurality of groups of observation task sequences as initial populations; wherein a set of observation task sequences is taken as an individual in the initial population;

the satellite screening unit 200 is configured to screen satellites in the satellite cluster by adopting a preset constraint condition, so as to obtain a first satellite cluster after satellite screening;

the policy selection unit 300 is configured to select an optimal policy for a satellite in a first satellite cluster that performs each observation task in an individual, obtain a first optimal policy combination, and calculate an fitness value of each individual according to the first optimal policy combination;

an iterative computation unit 400 for selecting a plurality of individuals from the initial population as parents according to the fitness value; randomly selecting two parents to perform cross operation to obtain a first new individual; performing mutation operation on each parent to obtain a second new individual; forming a new population by the father generation, the first new individual and the second new individual, and using the new population for the next iteration comprising fitness value calculation, father generation selection, crossover operation and mutation operation until reaching a preset termination condition to obtain a maximum fitness value;

The task scheduling unit 500 is configured to obtain a second optimal policy combination according to the maximum fitness value, and perform satellite cluster observation task scheduling by using the second optimal policy combination.

It should be noted that, since a satellite cluster observation task scheduling system in this embodiment and the above-mentioned satellite cluster observation task scheduling method are based on the same inventive concept, the corresponding content in the method embodiment is also applicable to the system embodiment, and will not be described in detail herein.

The embodiment of the application also provides electronic equipment, which comprises: at least one memory, at least one processor, at least one computer program stored in the at least one memory, the at least one processor executing the at least one computer program to implement any of the satellite cluster observation task scheduling methods of the above embodiments. The electronic equipment can be any intelligent terminal including a tablet personal computer, a vehicle-mounted computer and the like.

Referring to fig. 5, fig. 5 illustrates a hardware structure of an electronic device according to another embodiment, the electronic device includes:

the processor 810 may be implemented by a general-purpose CPU (central processing unit), a microprocessor, an application-specific integrated circuit (ApplicationSpecificIntegratedCircuit, ASIC), or one or more integrated circuits, etc. for executing related programs to implement the technical solutions provided by the embodiments of the present application;

The memory 820 may be implemented in the form of read-only memory (ReadOnlyMemory, ROM), static storage, dynamic storage, or random access memory (RandomAccessMemory, RAM). Memory 820 may store an operating system and other application programs, and when implementing the technical solutions provided in the embodiments of the present disclosure by software or firmware, relevant program codes are stored in memory 820, and the processor 810 invokes a satellite cluster observation task scheduling method for executing the embodiments of the present disclosure;

an input/output interface 830 for implementing information input and output;

the communication interface 840 is configured to implement communication interaction between the device and other devices, and may implement communication in a wired manner (e.g. USB, network cable, etc.), or may implement communication in a wireless manner (e.g. mobile network, WIFI, bluetooth, etc.);

bus 850 transfers information between the various components of the device (e.g., processor 810, memory 820, input/output interface 830, and communication interface 840);

wherein processor 810, memory 820, input/output interface 830, and communication interface 840 enable communication connections among each other within the device via bus 850.

The embodiment of the application also provides a storage medium which is a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is used for enabling a computer to execute the satellite cluster observation task scheduling method in any one of the above embodiments.

The memory, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage, flash memory, or other non-transitory solid state storage. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The embodiments described in the embodiments of the present application are for more clearly describing the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application, and those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

It will be appreciated by those skilled in the art that the solution shown in fig. 1 is not limiting of the embodiments of the application and may include more or fewer steps than shown, or certain steps may be combined, or different steps.

The above described apparatus embodiments are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Those of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.

The terms "first," "second," "third," "fourth," and the like in the description of the application and in the above figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be understood that in the present application, "at least one (item)" means one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.

In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the above-described division of units is merely a logical function division, and there may be another division manner in actual implementation, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including multiple instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method of the various embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing a program.

The foregoing description of the preferred embodiments of the present application has been presented with reference to the drawings and is not intended to limit the scope of the claims. Any modifications, equivalent substitutions and improvements made by those skilled in the art without departing from the scope and spirit of the embodiments of the present application shall fall within the scope of the claims of the embodiments of the present application.

Claims (9)

1. The satellite cluster observation task scheduling method is characterized by comprising the following steps of:

taking a plurality of groups of observation task sequences as an initial population; wherein a set of observation task sequences is taken as an individual in the initial population;

screening satellites in the satellite cluster by adopting a preset constraint condition to obtain a first satellite cluster after satellite screening;

selecting an optimal strategy for satellites in the first satellite cluster for executing each observation task in the individuals, obtaining a first optimal strategy combination, and calculating the fitness value of each individual according to the first optimal strategy combination; wherein the fitness value is calculated by:

；

wherein ,representing a set of observation tasks, the first item +.>Representing resource utilization, second termRepresenting task coverage,/->Optimal policy combination representing satellite clusters, +. >Representing the number of satellites participating in an observation plan, +.> and />Representing the weight coefficient, ++>，/>Indicating satellite->Resource utilization of->Representing the ratio of the length of the observation task to the length of the observation time window performed, +.>Representing observation task->Weight of->Indicating satellite->Whether or not to execute the observation task->0 indicates no execution, 1 indicates execution, < ->Indicating the number of observation tasks>Indicating satellite->In observation task->Initial observation time on->Indicating satellite->In observation task->The last observation end time;

selecting a plurality of individuals from the initial population as parents according to the fitness value; randomly selecting two parents to perform cross operation to obtain a first new individual; performing mutation operation on each parent to obtain a second new individual; forming a new population by the father, the first new individual and the second new individual, and using the new population for the next iteration comprising fitness value calculation, father selection, crossover operation and mutation operation until reaching a preset termination condition, so as to obtain a maximum fitness value;

and acquiring a second optimal strategy combination according to the maximum fitness value, and adopting the second optimal strategy combination to schedule satellite cluster observation tasks.

2. The method of claim 1, wherein the selecting an optimal strategy for satellites in the first satellite cluster that perform each observation task in the individual to obtain a first optimal strategy combination comprises:

step S111, initializing a strategy of each satellite in the first satellite cluster;

step S112, forming adjacent alliances by each satellite and adjacent satellites thereof;

step S113, calculating the benefits of each satellite selected strategy when cooperating with the adjacent alliances;

step S114, designing an alternative strategy for the satellite by changing the cooperation mode of the satellite and the adjacent satellite, and selecting an alternative strategy for maximizing the expected benefits of the satellite to update the strategy selected by the satellite;

step S115, repeating the step S114 for all satellites in the first satellite cluster until the expected benefits of the satellites are maximized and the convergence or the maximum iteration number is reached, so as to obtain a first optimal strategy combination.

3. The satellite cluster observation task scheduling method of claim 1, wherein the selecting a plurality of individuals from the initial population as parents according to the fitness value comprises:

Calculating to obtain the total fitness value of all individuals according to the fitness value of each individual;

calculating the probability of each individual being selected according to the total fitness value;

calculating to obtain accumulated probabilities based on the selected probabilities of each individual, and forming an accumulated probability array from the accumulated probabilities of each individual;

generating a random number, and selecting a plurality of individuals as parents according to the position of the random number in the cumulative probability array.

4. The method of claim 1, wherein the randomly selecting two parents for cross-operations to obtain a first new individual comprises:

step S211, randomly selecting two parents including a first parent and a second parent;

step S212, if the elements of the initial positions of the first parent and the second parent are the same, the intersection operation cannot form a closed loop, and the two parents are returned;

step S213, otherwise, selecting the next position of the initial position of the first parent as the initial position;

step S214, initializing a child, and taking the initial position of the first parent as the current position of the child;

Step S215, finding the first position of the element equal to the current position of the child body from the second parent;

step S216, if the first position is equal to the current position of the child body, forming a closed loop, and terminating the cross operation;

step S217, if not, copying the element in the second parent to the corresponding position of the child, and setting the first position as the current position of the child;

step S219, repeating the step S215 to the step S217 until a closed loop is formed or a complete observation task sequence is traversed.

5. The method for scheduling satellite trunking observation tasks according to claim 1, wherein the performing a mutation operation on each parent to obtain a second new individual includes:

the design variation probability is as follows:

；

wherein ,representing the mutation probability under the current genetic algebra +.>Representing the maximum mutation probability under the initial genetic algebra, < ->Number representing current genetic algebra>Representing total genetic algebra>Representing a constant;

and carrying out mutation operation on each parent by adopting the mutation probability to obtain a second new individual.

6. The method of claim 1, wherein the predetermined constraint conditions include a resource constraint of each satellite, observability of the observation tasks being satisfied, a time required for an interval between the observation tasks to satisfy a satellite transition, each of the observation tasks being executed at most once, and the observation tasks being completed within a prescribed time.

7. A satellite cluster observation task scheduling system, the satellite cluster observation task scheduling system comprising:

the population initial unit is used for taking a plurality of groups of observation task sequences as initial populations; wherein a set of observation task sequences is taken as an individual in the initial population;

the satellite screening unit is used for screening satellites in the satellite cluster by adopting preset constraint conditions to obtain a first satellite cluster after satellite screening;

the strategy selection unit is used for selecting an optimal strategy for satellites in the first satellite cluster for executing each observation task in the individuals, obtaining a first optimal strategy combination, and calculating the fitness value of each individual according to the first optimal strategy combination; wherein the fitness value is calculated by:

；

wherein ,representing a set of observation tasks, the first item +.>Indicating the utilization of resources, the firstTwo itemsRepresenting task coverage,/->Optimal policy combination representing satellite clusters, +.>Representing the number of satellites participating in an observation plan, +.> and />Representing the weight coefficient, ++>，/>Indicating satellite->Resource utilization of->Representing the ratio of the length of the observation task to the length of the observation time window performed, +. >Representing observation task->Weight of->Indicating satellite->Whether or not to execute the observation task->0 indicates no execution, 1 indicates execution, < ->Indicating the number of observation tasks>Indicating satellite->In observation task->Initial observation time on->Indicating satellite->In observation task->The last observation end time;

the iterative calculation unit is used for selecting a plurality of individuals from the initial population as parents according to the fitness value; randomly selecting two parents to perform cross operation to obtain a first new individual; performing mutation operation on each parent to obtain a second new individual; forming a new population by the father, the first new individual and the second new individual, and using the new population for the next iteration comprising fitness value calculation, father selection, crossover operation and mutation operation until reaching a preset termination condition, so as to obtain a maximum fitness value;

and the task scheduling unit is used for acquiring a second optimal strategy combination according to the maximum fitness value and adopting the second optimal strategy combination to perform satellite cluster observation task scheduling.

8. An electronic device, comprising:

at least one memory;

at least one processor;

At least one computer program;

the at least one computer program is stored in the at least one memory, the at least one processor executing the at least one computer program to implement:

satellite cluster observation task scheduling method according to any one of claims 1 to 6.

9. A storage medium that is a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for causing a computer to execute:

satellite cluster observation task scheduling method according to any one of claims 1 to 6.