CN115347940B - Satellite communication time window planning method and system with punishment mechanism - Google Patents
Satellite communication time window planning method and system with punishment mechanism Download PDFInfo
- Publication number
- CN115347940B CN115347940B CN202210991668.1A CN202210991668A CN115347940B CN 115347940 B CN115347940 B CN 115347940B CN 202210991668 A CN202210991668 A CN 202210991668A CN 115347940 B CN115347940 B CN 115347940B
- Authority
- CN
- China
- Prior art keywords
- time window
- sequences
- time
- fitness value
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/14—Relay systems
- H04B7/15—Active relay systems
- H04B7/185—Space-based or airborne stations; Stations for satellite systems
- H04B7/1851—Systems using a satellite or space-based relay
- H04B7/18513—Transmission in a satellite or space-based system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/04—Wireless resource allocation
- H04W72/044—Wireless resource allocation based on the type of the allocated resource
- H04W72/0446—Resources in time domain, e.g. slots or frames
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
- H04W84/04—Large scale networks; Deep hierarchical networks
- H04W84/06—Airborne or Satellite Networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention provides a satellite communication time window planning method and system with a punishment mechanism. The method comprises the following steps: selecting a plurality of communication time window sequences to obtain an initial population; obtaining a real fitness value of each time window sequence in the initial population by using a fitness function model and a punishment function model; performing iterative operation on the initial population; and after each iteration is completed, calculating the real fitness value of each time window sequence in the new generation population, stopping iteration if the change rate of the real fitness value of the time window sequence in the new generation population is smaller than a threshold value or the cycle number reaches a preset upper limit, and taking the time window sequence corresponding to the optimal real fitness value as a final time window planning scheme. The planning effect of the invention is obviously improved.
Description
Technical Field
The invention relates to the technical field of time window planning, in particular to a satellite communication time window planning method and system with a punishment mechanism.
Background
Under the conditions that the number of satellites is increased and the demands of users are complex, some satellites cannot complete complex tasks submitted by users due to the limitation of the orbits and the capability of processing tasks by the satellites. However, because the satellites are in joint communication, when a single satellite cannot finish a received complex task, the satellite can split the received complex task, and then the split simple subtasks are distributed to other satellites of different types and ground stations for processing respectively, so that the utilization rate of the satellite is improved. Therefore, the joint scheduling problem of a plurality of satellites is considered, namely, the available satellites of different types are optimally distributed and utilized from the system perspective as a whole. However, considering joint scheduling of multiple satellites also brings a series of new problems, such as how to ensure efficient and orderly operation among multiple satellites and multiple stations, how to fully and effectively utilize time windows of satellite-to-ground communication, etc.
The satellite-ground communication time window is planned with the difficulty that the number of satellites and ground stations is not fixed, the time window number and the time window length are not fixed, the multi-satellite multi-station task scheduling has the characteristic of combining and optimizing problems, when the number of tasks and the number of satellites and ground stations are increased, the number of planned possible solutions is increased in an exponential multiple way, and the problems can only be approximately solved and cannot be accurately solved. The prior planning and scheduling technology mainly performs time window planning on image data transmission tasks of remote sensing satellites, and the core point of the technology is to execute high-priority data transmission tasks on the premise that conflicts are removed from the time windows, so that a large amount of waste of communication time windows of the satellites and ground stations is always caused under the strategy, and the technology has three obvious defects: 1. the time window cannot be guaranteed to cover a sufficiently wide time range; 2. the total duration of the time window cannot be ensured to be as long as possible; 3. when the time window conflict is removed, the resource preparation and release time of the ground station is not fully considered, so that the time window is wasted.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to provide a satellite communication time window planning method and system with a punishment mechanism.
In order to achieve the above object of the present invention, the present invention provides a satellite communication time window planning method with a penalty mechanism, comprising the following steps:
selecting a plurality of communication time window sequences, wherein each time window sequence comprises a plurality of time windows, and coding each time window sequence to obtain an initial population;
constructing an adaptability function model and a punishment function model of the time window sequence;
calculating the preliminary fitness value of each time window sequence in the initial population by using the fitness function model, punishing the preliminary fitness value of each time window sequence by using the punishment function model, and obtaining the real fitness value of each time window sequence in the initial population;
performing iterative operation on the initial population, selecting partial time window sequences in the parent population to perform genetic operation in the iterative process, calculating the real fitness value of each time window sequence after the genetic operation, selecting partial time window sequences after the genetic operation according to the real fitness value, merging the partial time window sequences in the parent population with the partial time window sequences in the parent population to form a new generation population, wherein the number of the new generation population is consistent with that of the time window sequences in the parent population, and the initial population is the parent population in the first iteration;
calculating the real fitness value of each time window sequence in the new generation population once every iteration is completed, stopping iteration if the change rate of the real fitness value of the time window sequence in the new generation population is smaller than a threshold value or the cycle number reaches a preset upper limit, and taking the time window sequence corresponding to the optimal real fitness value as a final time window planning scheme; otherwise, continuing to iterate the new generation population as the parent population until the real fitness value change rate of the time window sequence in the new generation population is smaller than a threshold value or the circulation times reach a preset upper limit.
The satellite communication time window planning method with the punishment mechanism adopts the fitness function and the punishment function to plan the satellite communication time window in a coordinated manner, so that the final planning effect is obviously improved compared with the prior art.
The satellite communication time window planning method with punishment mechanism has the preferable scheme that: the method for coding each time window sequence in the initial population comprises the following steps: randomly selecting a time windows from the time window sequence, filling binary numbers 1 into the selected a time windows respectively, filling binary numbers 0 into all other non-selected time windows respectively, wherein the binary numbers 1 indicate that the time windows are selected for use, the binary numbers 0 indicate that the time windows are not selected for use, a is smaller than or equal to the total number of the time windows of the time window sequence, and a is a positive integer.
The preferred scheme changes the conventional numerical code into a binary code representing yes or no, simplifying the time window selection problem.
The satellite communication time window planning method with punishment mechanism has the preferable scheme that: the fitness function is as follows:
The fitness function adopted in the preferred scheme fully reflects the total duration of the time window and the coverage of the time window, ensures that the time window covers a sufficiently wide time range and ensures the total duration of the time window to be as long as possible, and the final planning effect is obviously improved.
The satellite communication time window planning method with punishment mechanism has the preferable scheme that: the penalty function is:
where p=max (TWC ie )-MIN(TWC is )-∑(TWC ie -TWC is )，R C Preparation and release for resourcesLength of time, TWC is For the start time of the selected time window, TWC ie When v=1, v=0 indicates that the penalty condition is not satisfied, and v=1 indicates that the penalty condition is satisfied, for the end time of the selected time window.
In the preferred scheme, the penalty function considers the resource preparation time and the resource release time, so that the waste of a time window is avoided, and the final planning effect is obviously improved.
The satellite communication time window planning method with punishment mechanism has the preferable scheme that: when the punishment condition is met, multiplying the preliminary fitness value of the time window sequence meeting the punishment condition by a punishment coefficient M to punish;
when the penalty condition is not satisfied, no penalty is performed.
In the preferred scheme, the punishment coefficient is utilized to correct the fitness objective function, and the punishment degree can be adjusted by adjusting the punishment coefficient so as to flexibly restrict the result
The satellite communication time window planning method with punishment mechanism has the preferable scheme that: the genetic manipulation comprises the following steps:
selecting part of time window sequences from the parent population randomly, and selecting the first m time window sequences from the part of time window sequences according to the real fitness values corresponding to the part of time window sequences respectively and the sequence from the large to the small of the real fitness values;
the cross operation, randomly selecting two time window sequences from the m time window sequences, randomly selecting a plurality of cross points from the two time window sequences according to the cross probability, performing cross exchange on the cross points, and directly carrying out the subsequent generation of points which are not subjected to the cross exchange; the number of the cross points in the two time window sequences is the same, and the positions of the cross points in the two time window sequences are in one-to-one correspondence;
and performing mutation operation, namely randomly selecting one time window sequence from the m time window sequences, randomly selecting a plurality of mutation points in the time window sequence according to mutation probability, and performing local random disturbance on the mutation points.
The satellite communication time window planning method with punishment mechanism has the preferable scheme that: when the time window sequence after partial genetic operation is combined with partial time window sequence in parent population to form offspring population,
and selecting the first N time window sequences which are ordered from high to low according to the real fitness value from the time window sequences after genetic operation, then selecting the first N 'time window sequences which are ordered from high to low according to the real fitness value from the parent population, and combining the two to obtain a new generation population, wherein N+N' =the number of the time window sequences in the initial population.
The satellite communication time window planning method with punishment mechanism has the preferable scheme that: recording and selecting an optimal real fitness value and a time window sequence corresponding to the real fitness value in each iteration once each iteration is completed; if the iteration times are smaller than the set highest iteration times in the iteration process, the real fitness value change rate of the time window sequences in the new generation population with Q times is smaller than a threshold value, Q is a positive integer, stopping iteration, and selecting a time window sequence with the optimal real fitness value from the time window sequences corresponding to the optimal real fitness values selected in the previous iteration as a final time window planning scheme. This preferred solution improves the final planning effect.
The satellite communication time window planning method with punishment mechanism has the preferable scheme that: recording and selecting an optimal real fitness value and a time window sequence corresponding to the real fitness value in each iteration once each iteration is completed; if the iteration number reaches the set highest iteration number and the real fitness value change rate of the time window sequence in the new generation population is not smaller than the threshold value, stopping iteration, and selecting a time window sequence with the optimal real fitness value from the time window sequences corresponding to the optimal real fitness value selected from the previous iteration as a final time window planning scheme. This preferred solution improves the final planning effect.
The invention also provides a satellite communication time window planning system, which comprises a data input module and a processing module connected with the data input module, wherein the data input module inputs a plurality of time window sequences of satellite communication to the processing module, and the processing module performs satellite communication time window planning according to the satellite communication time window planning method with the punishment mechanism. The satellite communication time window planning system has all the advantages of the satellite communication time window planning method with the punishment mechanism.
The beneficial effects of the invention are as follows: the invention introduces a binary coding mode in the planning of the satellite communication time window, firstly intuitively shows whether the time window is used or not in a mathematical mode, and secondly, is convenient for the realization of conflict elimination of the time window; in addition, the adopted fitness function and punishment function fully reflect the total time length of the time window, the coverage of the time window and the time for resource preparation and release is fully considered when the time window conflict is solved, so that the final planning effect is obviously improved compared with the prior art, the utilization total time length of the time window and the coverage of the time window are ensured to the maximum degree under the condition that the time window conflict is completely avoided, and finally the optimal solution of the time window planning is calculated in various factors.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
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 communication time window planning method with penalty mechanism according to the present invention;
FIG. 2 is a schematic diagram of a time window encoding;
FIG. 3 is a schematic diagram of a crossover operation;
FIG. 4 is a schematic diagram of a variation operation;
FIG. 5 is a graph of fitness function of one embodiment of a satellite communications time window planning method with a penalty mechanism.
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, unless otherwise specified and defined, it should be noted that the terms "mounted," "connected," and "coupled" are to be construed broadly, and may be, for example, mechanical or electrical, or may be in communication with each other between two elements, directly or indirectly through intermediaries, as would be understood by those skilled in the art, in view of the specific meaning of the terms described above.
To overcome the difficulties mentioned in the background art, as shown in fig. 1, the present invention provides an embodiment of a satellite communication time window planning method with a penalty mechanism, which specifically includes the following steps:
a plurality of communication time window sequences are selected, each time window sequence comprises a plurality of time windows, an initial population is obtained, and then the initial population is encoded.
In this embodiment, the initial population includes 150 time window sequences, each of which includes 33 time windows. In the encoding process, as shown in fig. 2, for each time window sequence in the initial population, randomly selecting a time windows from the time window sequence, filling binary numbers 1 into the selected a time windows respectively, filling binary numbers 0 into all the other non-selected time windows respectively, wherein the binary numbers 1 indicate that the time window is selected for use, the binary numbers 0 indicate that the time window is not selected for use, a is less than or equal to the total number of the time windows of the time window sequence, and a is a positive integer.
And constructing an adaptability function model and a penalty function model of the time window sequence.
And calculating the preliminary fitness value of each time window sequence in the initial population by using the fitness function model, and punishing the preliminary fitness value of each time window sequence by using the punishment function model to obtain the real fitness value of each time window sequence in the initial population.
In this embodiment, the fitness function model is:
In this embodiment, the penalty function model is:
where p=max (TWC ie )-MIN(TWC is )-∑(TWC ie -TWC is )，R C For the length of time for resource preparation and release, v=1 indicates that the penalty condition is not satisfied, and v=0 indicates that the penalty condition is satisfied.
When the penalty function v=0 for a time window sequence, multiplying the preliminary fitness value for the time window sequence by a penalty factor M,0< M <1, in this embodiment, preferably but not limited to 0.3; when the penalty function v=1 of a certain time window sequence, no penalty is given to the preliminary fitness value of the time window sequence, i.e. the preliminary fitness value of the time window sequence is the true fitness value thereof.
And then carrying out iterative operation on the initial population, wherein the initial population is a parent population in the first iteration. And in the iteration process, selecting part of time window sequences in the parent population for genetic operation, calculating the real fitness value of each time window sequence after genetic operation, and combining the time window sequences after the part of genetic operation and part of time window sequences in the parent population according to the real fitness value to form a new generation population, wherein the number of the new generation population is consistent with that of the time window sequences in the parent population. The specific operation is as follows: and selecting the first N time window sequences which are ordered from high to low according to the real fitness value from the time window sequences after genetic operation, then selecting the first N ' time window sequences which are ordered from high to low according to the real fitness value from the parent population, and combining the two to obtain a new generation population, wherein the number of the time window sequences in the N+N ' =initial population, and N, N ' is a positive integer.
The genetic manipulation referred to herein includes the steps of:
selecting, namely randomly selecting partial time window sequences from the parent population, preferably but not limited to selecting 70% of the time window sequences in the parent population, and selecting the first m time window sequences from the partial time window sequences according to the real fitness values respectively corresponding to the partial time window sequences and the order of the real fitness values from large to small, wherein m is a positive integer.
After the first m time window sequences are selected, performing cross operation: as shown in fig. 3, two time window sequences are randomly selected from the m time window sequences, and a plurality of intersecting points are randomly selected from the two time window sequences according to the intersecting probability, namely, the number of the intersecting points selected from the time window sequences is equal to the number of the time windows in the time window sequences; the number of the cross points in the two time window sequences is the same, and the positions of the cross points in the two time window sequences are in one-to-one correspondence. Thus, each of the m time window sequences is interleaved.
Mutation operation: as shown in fig. 4, a time window sequence is randomly selected from the m time window sequences, a plurality of variation points in the time window sequence are randomly selected according to variation probability, namely, the number of the variation points selected from the time window sequence is the time window number in the time window sequence, the variation points are subjected to local random disturbance, namely, the variation points are randomly replaced by points (time windows) different from the previous points, so as to generate a new time window sequence, for example, the new time window sequence is coded in binary mode, if the variation point is 1, the variation point is 0 when the variation point is changed, and if the variation point is 0, the variation point is changed into 1 when the variation is changed. And thus, each time window sequence in the m time window sequences is subjected to mutation operation.
There is no inheritance relationship between the mutation operation and the crossover operation.
The value of m in this embodiment is preferably but not limited to 50% of the number of time window sequences in the parent population, the crossover probability is preferably but not limited to 0.7, and the mutation probability is preferably but not limited to 0.5.
Calculating the real fitness value of each time window sequence in the new generation population once every iteration is completed, recording and selecting the optimal real fitness value in each iteration and the time window sequence corresponding to the real fitness value, stopping iteration if the real fitness value change rate of the time window sequence in the new generation population is smaller than a threshold value or the iteration times reach a preset upper limit, and taking the time window sequence corresponding to the optimal real fitness value as a final time window planning scheme; specifically, if the number of iterations reaches the set highest number of iterations and the real fitness value change rate of the time window sequences in the new generation population is not smaller than the threshold value, stopping iteration, and selecting a time window sequence with the optimal real fitness value from the time window sequences corresponding to the optimal real fitness value selected from the previous iteration as a final time window planning scheme; if the real fitness value change rate of the time window sequences in the new generation population is smaller than the threshold value in the iteration process, stopping iteration, and selecting the time window sequence with the optimal real fitness value from the time window sequences corresponding to the optimal real fitness value selected in the previous iteration as a final time window planning scheme.
If the real fitness value change rate of the time window sequence in the new generation population is not less than the threshold value and the cycle number does not reach the preset upper limit in the iteration process, continuing to iterate the new generation population serving as the parent population until the real fitness value change rate of the time window sequence in the new generation population is less than the threshold value or the cycle number reaches the preset upper limit, stopping iterating, and taking the time window sequence corresponding to the optimal real fitness value as a final time window planning scheme.
In a preferred scheme of this embodiment, if in the iteration process, the number of iterations is smaller than the set highest number of iterations, and the rate of change of the real fitness value of the time window sequence in the new generation population occurring Q times is smaller than the threshold value, Q is a positive integer, for example 3, the iteration is stopped, and the time window sequence with the optimal real fitness value is selected from the time window sequences corresponding to the optimal real fitness value selected from the previous iterations as the final time window planning scheme.
The number of iterations is not more than 2 times the length of the time window sequence, in this embodiment, the number of iterations is preferably, but not limited to, 47.
As shown in fig. 5, as the number of iterations increases, the population optimal time window sequence fitness objective function value and the population average time window sequence fitness objective function value are both continuously increased, and are stabilized at the maximum value when the number of iterations approaches the upper limit number of iterations, and finally inheritance is terminated, and an optimal solution is found.
The embodiment of the satellite communication time window planning system comprises a data input module and a processing module connected with the data input module, wherein the data input module inputs a plurality of time window sequences of satellite communication to the processing module, and the processing module performs satellite communication time window planning according to the satellite communication time window planning method with the punishment mechanism.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. A satellite communication time window planning method with a punishment mechanism is characterized by comprising the following steps:
selecting a plurality of communication time window sequences, wherein each time window sequence comprises a plurality of time windows, and coding each time window sequence to obtain an initial population;
constructing an adaptability function model and a punishment function model of the time window sequence;
calculating the preliminary fitness value of each time window sequence in the initial population by using the fitness function model, punishing the preliminary fitness value of each time window sequence by using the punishment function model, and obtaining the real fitness value of each time window sequence in the initial population;
performing iterative operation on the initial population, selecting partial time window sequences in the parent population to perform genetic operation in the iterative process, calculating the real fitness value of each time window sequence after the genetic operation, selecting partial time window sequences after the genetic operation according to the real fitness value, merging the partial time window sequences in the parent population with the partial time window sequences in the parent population to form a new generation population, wherein the number of the new generation population is consistent with that of the time window sequences in the parent population, and the initial population is the parent population in the first iteration;
calculating the real fitness value of each time window sequence in the new generation population once every iteration is completed, stopping iteration if the change rate of the real fitness value of the time window sequence in the new generation population is smaller than a threshold value or the cycle number reaches a preset upper limit, and taking the time window sequence corresponding to the optimal real fitness value as a final time window planning scheme; otherwise, continuing to iterate the new generation population as the parent population until the real fitness value change rate of the time window sequence in the new generation population is smaller than a threshold value or the circulation times reach a preset upper limit.
2. The method for planning a time window for satellite communication with a penalty mechanism of claim 1, wherein the method for encoding each time window sequence in the initial population comprises: randomly selecting a time windows from the time window sequence, filling binary numbers 1 into the selected a time windows respectively, filling binary numbers 0 into all other non-selected time windows respectively, wherein the binary numbers 1 indicate that the time windows are selected for use, the binary numbers 0 indicate that the time windows are not selected for use, a is smaller than or equal to the total number of the time windows of the time window sequence, and a is a positive integer.
3. The method for planning a satellite communication time window with a penalty mechanism according to claim 1, wherein the fitness function is:
4. The method for planning a satellite communication time window with a penalty mechanism according to claim 1, wherein the penalty function is:
where p=max (TWC ie )-MIN(TWC is )-∑(TWC ie -TWC is )，R C TWC for the length of time that resources are prepared and released is For the start time of the selected time window, TWC ie When v=1, v=0 indicates that the penalty condition is not satisfied, and v=1 indicates that the penalty condition is satisfied, for the end time of the selected time window.
5. The satellite communication time window planning method with punishment mechanism according to claim 1 or 4, wherein when the punishment condition is satisfied, the preliminary fitness value of the time window sequence satisfying the punishment condition is multiplied by a punishment coefficient M to punish;
when the penalty condition is not satisfied, no penalty is performed.
6. The method for planning a satellite communication time window with penalty mechanism of claim 1, wherein said genetic manipulation comprises the steps of:
selecting part of time window sequences from the parent population randomly, and selecting the first m time window sequences from the part of time window sequences according to the real fitness values corresponding to the part of time window sequences respectively and the sequence from the large to the small of the real fitness values;
the cross operation, randomly selecting two time window sequences from the m time window sequences, randomly selecting a plurality of cross points from the two time window sequences according to the cross probability, performing cross exchange on the cross points, and directly carrying out the subsequent generation of points which are not subjected to the cross exchange; the number of the cross points in the two time window sequences is the same, and the positions of the cross points in the two time window sequences are in one-to-one correspondence;
and performing mutation operation, namely randomly selecting one time window sequence from the m time window sequences, randomly selecting a plurality of mutation points in the time window sequence according to mutation probability, and performing local random disturbance on the mutation points.
7. The method for planning satellite communication time window with punishment mechanism according to claim 1, wherein when partial time window sequences after genetic operation and partial time window sequences in parent population are combined into new generation population according to the real fitness value,
and selecting the first N time window sequences which are ordered from high to low according to the real fitness value from the time window sequences after genetic operation, then selecting the first N 'time window sequences which are ordered from high to low according to the real fitness value from the parent population, and combining the two to obtain a new generation population, wherein N+N' =the number of the time window sequences in the initial population.
8. The satellite communication time window planning method with punishment mechanism according to claim 1, wherein each iteration is completed, recording and selecting the optimal real fitness value and the time window sequence corresponding to the real fitness value in each iteration; if the iteration times are smaller than the set highest iteration times in the iteration process, the real fitness value change rate of the time window sequences in the new generation population with Q times is smaller than a threshold value, Q is a positive integer, stopping iteration, and selecting a time window sequence with the optimal real fitness value from the time window sequences corresponding to the optimal real fitness values selected in the previous iteration as a final time window planning scheme.
9. The satellite communication time window planning method with punishment mechanism according to claim 1, wherein each iteration is completed, recording and selecting the optimal real fitness value and the time window sequence corresponding to the real fitness value in each iteration; if the iteration number reaches the set highest iteration number and the real fitness value change rate of the time window sequence in the new generation population is not smaller than the threshold value, stopping iteration, and selecting a time window sequence with the optimal real fitness value from the time window sequences corresponding to the optimal real fitness value selected from the previous iteration as a final time window planning scheme.
10. The satellite communication time window planning system is characterized by comprising a data input module and a processing module connected with the data input module, wherein the data input module inputs a plurality of time window sequences of satellite communication to the processing module, and the processing module performs satellite communication time window planning according to the satellite communication time window planning method with punishment mechanism according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210991668.1A CN115347940B (en) | 2022-08-18 | 2022-08-18 | Satellite communication time window planning method and system with punishment mechanism |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210991668.1A CN115347940B (en) | 2022-08-18 | 2022-08-18 | Satellite communication time window planning method and system with punishment mechanism |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115347940A CN115347940A (en) | 2022-11-15 |
| CN115347940B true CN115347940B (en) | 2023-06-20 |
Family
ID=83952077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210991668.1A Active CN115347940B (en) | 2022-08-18 | 2022-08-18 | Satellite communication time window planning method and system with punishment mechanism |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115347940B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110515708A (en) * | 2019-07-17 | 2019-11-29 | 赛德雷特(珠海)航天科技有限公司 | The in-orbit autonomous mission planning method and system of satellite |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111874267B (en) * | 2020-04-30 | 2021-09-28 | 中国人民解放军战略支援部队航天工程大学 | Low-orbit satellite off-orbit control method and system based on particle swarm optimization |
-
2022
- 2022-08-18 CN CN202210991668.1A patent/CN115347940B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110515708A (en) * | 2019-07-17 | 2019-11-29 | 赛德雷特(珠海)航天科技有限公司 | The in-orbit autonomous mission planning method and system of satellite |
Non-Patent Citations (2)
| Title |
|---|
| 基于动态罚函数遗传算法的电磁探测卫星多星规划方法;陈浩;李军;唐宇;景宁;;国防科技大学学报;31(02);44-50 * |
| 应急任务响应时间最优的多星成像规划方法;陈书剑;李智;胡敏;张雅声;;中国空间科学技术;40(02);17-28 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115347940A (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111628855B (en) | Industrial 5G dynamic multi-priority multi-access method based on deep reinforcement learning | |
| CN108880663A (en) | Incorporate network resource allocation method based on improved adaptive GA-IAGA | |
| CN113222179B (en) | Federal learning model compression method based on model sparsification and weight quantification | |
| CN112543049B (en) | Energy efficiency optimization method and device of integrated ground satellite network | |
| CN108566242B (en) | Spatial information network resource scheduling system for remote sensing data transmission service | |
| CN110300417B (en) | Energy efficiency optimization method and device for unmanned aerial vehicle communication network | |
| CN111711962A (en) | Cooperative scheduling method for subtasks of mobile edge computing system | |
| CN111429038A (en) | Active power distribution network real-time random optimization scheduling method based on reinforcement learning | |
| CN115347940B (en) | Satellite communication time window planning method and system with punishment mechanism | |
| CN112261725A (en) | Data packet transmission intelligent decision method based on deep reinforcement learning | |
| CN116938323B (en) | Satellite transponder resource allocation method based on reinforcement learning | |
| CN113573363A (en) | MEC calculation unloading and resource allocation method based on deep reinforcement learning | |
| CN106411469A (en) | Multicast resource allocation and transmission method based on scalable video in multi-base station heterogeneous network | |
| CN111796880A (en) | Unloading scheduling method for edge cloud computing task | |
| CN113946423B (en) | Multi-task edge computing, scheduling and optimizing method based on graph attention network | |
| CN113269324B (en) | Low-orbit satellite time window planning method and system based on genetic algorithm | |
| CN116939866A (en) | Wireless federal learning efficiency improving method based on collaborative computing and resource allocation joint optimization | |
| CN114884957B (en) | Method and device for unloading computing tasks in air-space-ground network and electronic equipment | |
| CN116112488A (en) | Fine-grained task unloading and resource allocation method for MEC network | |
| CN113157344B (en) | DRL-based energy consumption perception task unloading method in mobile edge computing environment | |
| CN111555794B (en) | Resource allocation method for space-based information system | |
| CN103427951B (en) | With the data forwarding method that coding redundancy controls | |
| CN113127167A (en) | Heterogeneous resource intelligent parallel scheduling method based on improved genetic algorithm | |
| CN107070511B (en) | User access control optimization method for MISO wireless fairness network | |
| CN114364007B (en) | Subcarrier power control method of low-orbit satellite and unmanned aerial vehicle cellular fusion network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |