CN116073924B - Anti-interference channel allocation method and system based on Stackelberg game - Google Patents
Anti-interference channel allocation method and system based on Stackelberg game Download PDFInfo
- Publication number
- CN116073924B CN116073924B CN202310206515.6A CN202310206515A CN116073924B CN 116073924 B CN116073924 B CN 116073924B CN 202310206515 A CN202310206515 A CN 202310206515A CN 116073924 B CN116073924 B CN 116073924B
- Authority
- CN
- China
- Prior art keywords
- user
- interference
- jammer
- channel
- channel access
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 230000006870 function Effects 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 8
- 238000005562 fading Methods 0.000 claims description 6
- 230000006854 communication Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000012907 honey Nutrition 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
- H04B17/345—Interference values
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/382—Monitoring; Testing of propagation channels for resource allocation, admission control or handover
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses an anti-interference channel allocation method and system based on a Stackelberg game, which comprehensively considers the mutual interference existing in the system and the malicious interference from the outside, builds a multi-layer Stackelberg game model, and updates a strategy according to a random automatic learning algorithm by taking a user as a follower; the jammer is the leader and updates the strategy according to the Q-learning algorithm. The anti-interference performance of the method is superior to that of a random selection algorithm, and the anti-interference performance of the network channel of the unmanned aerial vehicle is obviously improved.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicles, in particular to an anti-interference channel allocation method and system based on a Stackelberg game.
Background
By distributing Computing nodes at the Edge of a network, edge Computing (EC) can enable mobile equipment at a terminal to acquire services such as communication, computing, storage, perception and the like in a short distance, and compared with cloud Computing, the EC can better meet the application requirements of low time delay and high density. However, in the face of special scenarios such as natural disasters, equipment failures, complex terrains, etc., conventional methods are difficult to deploy computing nodes and cannot continuously guarantee normal service. Unmanned aerial vehicles have been attracting attention in recent years due to their high maneuverability, which is light and flexible. In the edge computing network, computing nodes can be deployed more flexibly by equipping the unmanned aerial vehicle, and the emergency service capability of the network is improved. With the increasing number of devices and task demands, the service resources (such as operation memory, network bandwidth, communication channels, etc.) of the system are consumed sharply, and it is significant to formulate efficient task allocation and resource management schemes.
In response to spectrum shortage and interference attack, the prior art uses a partially overlapped channel technology, so that the channel utilization rate is improved while the interference is reduced. The hypergraph theory in the prior art can accurately capture the interference condition existing in the system. However, these conventional approaches consider jammer strategies that are either predetermined or fixed and are insufficient to deal with dynamic jammer attacks. In the prior art, intelligent interference is avoided by changing the motion trail of the ground users, but the same-frequency interference among the users is also considered. In the prior art, by setting up a honey pot to actively attract an intelligent jammer, all researches assume that channel state information is completely observable, and future communication networks tend to be complex, and the completely observable channel information becomes unrealistic, so that an anti-interference strategy under incomplete information also needs to be considered. By adopting game theory and reinforcement learning, the problems of incomplete observation information and dynamic interference can be well solved. In addition, the deployment scale of unmanned aerial vehicles will gradually become larger in the future, the problem of resource shortage will be aggravated by high mobility of unmanned aerial vehicles, the problem of channel resource management added into unmanned aerial vehicle networks is considered in the prior art, but the application scene combined with edge calculation is still few.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention aims at providing an anti-interference channel allocation method based on a Stackelberg game, which comprehensively considers the mutual interference existing in a system and the malicious interference from the outside, and builds a multi-layer Stackelberg game model to improve the anti-interference performance. It is another object of the present invention to provide a tamper resistant channel allocation system based on the Stackelberg game which implements the above method.
In order to achieve the above purpose, the present invention provides an anti-interference channel allocation method based on a Stackelberg game, including:
step 1), constructing a multi-layer Stackelberg model according to different requirements of a user and an jammer, wherein the jammer is a leader, and the user is a follower; setting upA user consisting of an unload-accept pair of computing tasks, set->Available channels, set->A jammer;
step 2) setting a game model of a follower layer:
user' sThe received interference includes internal co-channel interference and external malicious interference, expressed as:
wherein ,indicating co-channel interference between user n and other users,/->Representing the malicious interference received by the user,for the transmission power of user m, +.>For the transmission power of jammer j, +.>For the instantaneous interference of user m to user n,instantaneous interference of the jammer j to the user n; />Interference channel access strategy for jammer j, +.>A channel access strategy for minimizing the total interference suffered by the user n and the user m respectively;
the sub-game of the follower layer can be expressed as:
step 3) setting a game model of a leader layer:
step 4) setting a multi-layer Stackelberg game, which is expressed as:
and 5) carrying out strategy iteration, and finally, achieving the balance of the Stackelberg, wherein all users can not obtain higher utility values by changing own strategies.
Further, the instantaneous interference of user m to user nInstantaneous interference of jammer j to user n>; wherein ,/>For the planar distance between user m and user n, < >>For the planar distance between jammer j and user n, < >>Is a path loss factor, +.>As a coefficient of instantaneous fading of the channel,is a Kronecker function.
Further, the utility function for user n is expressed as:
wherein For the planar distance between user n and jammer j, +.>Is a path loss factor, +.>For user->And the instantaneous fading coefficient of the channel between jammers j.
Further, the step 5) may be expressed as:
wherein ,a channel access policy is obtained for the optimization objective of user n to minimize the interference experienced.
Further, the optimization objective of user n is to obtain a channel access policy that minimizes the interference experienced, expressed as:
further, the optimization objective of the jammer layer is to maximize the disruption caused by the jammers, expressed as:
further, in the policy iteration, each jammer of the leader layer is atThe Q-learning algorithm is used for updating the channel access strategy in each round, and the method specifically comprises the following steps:
jammer j based on channel access probability at the beginning of each training roundSelect interference strategy->Calculate its utility value->The Q-table is then updated, namely:
for learning step length, satisfy->Updating the channel access probability on the basis of this +.>:
Further, in the policy iteration, each user of the follower layer divides in each roundThe channel access strategy is updated by using a random learning algorithm in each time slot, specifically:
at the position ofUpdating the channel access strategy by a random automatic learning algorithm within each time slot so that the interference is +.>Minimizing; />
At the beginning of each time slot t, according to the channel access probabilityChannel for selecting access->Then calculate its utility->Updating the channel access probability of the next time slot on the basis of this +.>Specifically, the method can be expressed as:
An anti-interference channel distribution system based on a Stackelberg game is used for implementing the anti-interference channel distribution method based on the Stackelberg game.
According to the invention, the mutual interference existing in the system and the malicious interference from the outside are comprehensively considered, and a multi-layer Stackelberg game model is constructed to improve the anti-interference performance, and the anti-interference performance is superior to that of a random selection algorithm.
Drawings
Fig. 1 is a schematic diagram of a problem existing in channel resource allocation;
FIG. 2 is a schematic diagram of an interference-free channel allocation system model;
FIG. 3 is an iterative graph of channel access probabilities for user 1 within a single epoch;
fig. 4 is an iterative chart of channel access probabilities of the jammer 1;
FIG. 5 is a graph showing performance comparisons in different user number scenarios;
fig. 6 is a schematic diagram showing performance comparison under a scene of different numbers of jammers.
Detailed Description
The following description of the embodiments of the present invention will be made more apparent and fully hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
Specific embodiments of the present invention are described in detail below with reference to fig. 1-6. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
According to the anti-interference channel allocation method and system based on the Stackelberg game, on one hand, as the number of legal channels is limited as communication equipment in a network is increased, different equipment can be connected to the same channel, and co-channel interference can occur to influence normal communication of the equipment. On the other hand, due to the exposure of the communication channel, a malicious jammer can eavesdrop on the communication process or apply an interfering signal, which presents challenges for the secure communication of the system. Thus, as shown in fig. 1, allocation management of channel resources needs to consider internal mutual interference and external malicious interference.
In the invention, in unmanned plane-assisted edge calculation, the resource allocation of a channel part is researched on the basis of an unloading allocation mechanism of a calculation task, a user comprehensively considers the mutual interference existing in a system and the malicious interference from the outside for unloading-receiving pairs of the calculation task, a multi-layer Stackelberg game model is constructed, and the user updates a strategy according to a random automatic learning algorithm for a follower; the jammer is the leader and updates the strategy according to the Q-learning algorithm.
The invention discloses an anti-interference channel allocation method based on a Stackelberg game, which comprises the following steps:
1. constructing a double-layer Stackelberg game model;
as shown in fig. 2, in the application scenario, there areA user composed of an unload-accept pair of computing tasks, available channels are +.>And each. By introducing an edge computing application scenario, consider +.>The intelligent jammer, jammer j is added according to the channel access interference strategy of the user>Selecting the interference channel with the greatest disruption, on the basis of which user n updates the channel access policy which minimizes the total interference suffered>。
According to different requirements of users and jammers, a multi-layer Stackelberg model is constructed, wherein the jammers are leaders, the users are followers, and utility expressions of players of each layer are described below.
(1) The following: game model of user layer
User' sThe received interference mainly comes from internal co-channel interference and external malicious interference, and can be expressed as follows:
wherein ,indicating co-channel interference between user n and other users,/->Representing the malicious interference received by the user,the transmission power of the user m and the interference unit j are respectively; />And (3) a channel access strategy for minimizing the total interference suffered by the user n and the user m respectively.
Respectively representing the instantaneous interference of the user m and the jammer j to the user n; />For the planar distance between user m and user n, < >>Is the planar distance between jammer j and user n; />Is a path loss factor, +.>For the instantaneous fading coefficient of the channel->Is a Kronecker function, namely:
thus, the utility function for user n can be expressed as:
wherein ,is->Is>The transmission power of user n and user m respectively,the method comprises the steps of carrying out a first treatment on the surface of the The optimization objective of user n is to obtain a channel access scheme (policy function) that minimizes the interference that is expressed as:
the sub-game of the follower layer can be expressed as:
(2) The leader: game model of jammer layer
wherein ,,/>for the planar distance between user n and jammer j, +.>Is a path loss factor, +.>Is the instantaneous fading coefficient of the channel between user n and jammer j.
The optimization goal is to maximize the disruption caused by the interference, namely:
the sub-game of the leader layer can be described as:
in summary, the multi-layer Stackelberg game can be expressed as:
through the strategy iteration of the intelligent learning algorithm, the system finally reaches the balance of the Stackelberg, namely, all users can not obtain higher utility values by changing own strategies any more, and the method can be specifically expressed as follows:
2. strategy iterative algorithm
After the parameter initialization is completed, each jammer in the leader layer is inUpdating channel access policies using Q-learning algorithm within a round of time, each user of the follower layer is inThe interior of each round is>The channel access strategy is updated by using a random learning algorithm in each time slot, so that malicious interference of an external jammer is dealt with. And finally outputting the channel access strategy after the players at each layer converge.
The parameter update expressions for each layer of game iterations are as follows:
(1) Leader layer: q-learning
As a leader, jammer j starts training each round according to the channel access probabilitySelect interference strategy->Calculate its utility value->The Q-table is then updated, namely:
wherein ,for learning step length, satisfy->Updating the channel access probability on the basis of this>:
The double-layer Stackelberg game anti-interference channel allocation algorithm is as follows:
(2) Follower layer: random automatic learning
User n as follower, inUpdating the channel access strategy by a random automatic learning algorithm within each time slot so that the interference is +.>Minimizing.
At the beginning of each time slot t, according to the channel access probabilityChannel for selecting access->Then calculate its utility->Updating the channel access probability of the next time slot on the basis of this +.>Specifically, the method can be expressed as:
The invention also provides an anti-interference channel distribution system based on the Stackelberg game, which is used for implementing the anti-interference channel distribution method based on the Stackelberg game.
In one embodiment of the invention, the simulation scenario is: as shown in FIG. 2, there are 2 base stations, 6 unmanned aerial vehicles and 8 terminal devices in the simulation scene, all distributed inWithin a range of (2). In addition, there are 3 jammers with coordinates (1200,0), (1200 ) and (0,1200), respectively. Each user is an off-load-receive pair of a computing task, number of usersThe number of available channels +.>The channel selection probability of the user and the jammer in the initial state is uniform, i.eTraining round +.>In each training round, the user has 100 time slots.
Taking the scenario shown in fig. 2 as an example, a specific embodiment is as follows:
1. coordinates of each end user: terminal 1 (633,958); terminal 2 (98,486); terminal 3 (859,801); terminal 4 (547,142); a terminal 5 (576,650); terminal 6 (60,732); terminal 7 (235,648); terminal 8 (354,451).
2. Coordinates of each unmanned aerial vehicle: a drone 1 (250 ); unmanned plane 2 (250, 750); an unmanned plane 3 (500, 250); an unmanned plane 4 (500, 750); unmanned plane 5 (750,250); unmanned aerial vehicle 6 (750).
3. Coordinates of each ground base station: base station 1 (250, 500), base station 2 (750,500).
4. According to the equipment conditions of connection establishment, obtaining equipment matching relations of a user 1 (terminal 6-unmanned aerial vehicle 2), a user 2 (terminal 7-unmanned aerial vehicle 2), a user 3 (terminal 2-base station 1), a user 4 (terminal 8-unmanned aerial vehicle 1), a user 5 (terminal 4-unmanned aerial vehicle 3), a user 6 (terminal 3-unmanned aerial vehicle 6), a user 7 (terminal 5-unmanned aerial vehicle 4-base station 2) and a user 8 (terminal 1-unmanned aerial vehicle 4).
5. The coordinates of each user take the geometric center coordinates of the matching equipment, and then the coordinates of each user are as follows: user 1 (566.5,854); user 2 (174,493); user 3 (804.5,775.5); user 4 (523.5,196); user 5 (608.7,633.3); user 6 (155,741); user 7 (242.5,699); user 8 (302,350.5).
6. The coordinates of each external intelligent jammer are 0,1200; (1200,0); (1200).
7. Training roundsNumber of slots per round +.>User transmission power +.>Jammer transmit power->Path loss factor->The number of available channels>Learning rate of jammer->Learning step size ∈of user>。
Output value of final result:
2. The total interference condition of the system is 0.0020 units, if a user adopts a random channel access scheme, the average value of the total interference of the system subjected to 50 repeated tests is 0.0022 units, and under the condition of no external jammer, the total interference condition of the system is 0.0010 units (mainly internal co-channel interference).
The simulation effect is as follows: fig. 3 is an iterative change chart of the selection probability of each channel in a certain training round of the user 1, and it can be found that, after 72 time slots, the probability of selecting the channel 2 by the user gradually converges to 1, and the selection probabilities of other channels gradually converges to 0, so that the user 1 finally exercises to select the channel 2 in the round. Fig. 4 is a probabilistic iteration diagram of jammer 1 accessing all channels in all training rounds. It can be seen that the probability of accessing channel 4 after 16 training gradually converges to 1, so in this scenario, the jammer 1 will eventually select the interfering channel 4.
Performance comparative analysis: fig. 5 shows the performance of the proposed algorithm in a scenario of 5 different numbers of users (2, 4, 5,6, 8, 10, respectively) compared with the random channel selection scheme and the case without jammers. First, the proposed algorithm can be found to suffer less interference than the random selection strategy, and the performance gap becomes more and more apparent as the number of users increases. In the interference-free machine scene, the interference suffered by the user is only the same-frequency interference. Further, it can be found that co-channel interference is 0 when the number of users is 2, because the number of available channels is sufficient, and co-channel interference does not exist. Second, it can be found that the interference experienced by users increases with the number of users, as the resources within the system become more and more competitive.
Fig. 6 shows a comparison of performance under different numbers of jammers, and it can be found that the total interference suffered by the system gradually increases as the number of jammers increases, and the anti-interference performance of the algorithm provided by the invention is better than that of the random selection algorithm under the three conditions.
Claims (7)
1. An anti-interference channel allocation method based on a Stackelberg game is characterized by comprising the following steps:
step 1), constructing a multi-layer Stackelberg model according to different requirements of a user and an jammer, wherein the jammer is a leader, and the user is a follower; setting upA user consisting of an unload-accept pair of computing tasks, set->Available channels, set->A jammer;
step 2) setting a game model of a follower layer:
user' sThe received interference includes internal co-channel interference and external malicious interference, expressed as:
wherein ,indicating co-channel interference between user n and other users,/->Indicating the malicious interference received by the user, < >>For the transmission power of user m, +.>For the transmission power of jammer j, +.>For usersm instantaneous interference to user n, +.>Instantaneous interference of the jammer j to the user n; />Interference channel access strategy for jammer j, +.>A channel access strategy for minimizing the total interference suffered by the user n and the user m respectively;
the sub-game of the follower layer can be expressed as:
step 3) setting a game model of a leader layer:
step 4) setting a multi-layer Stackelberg game, which is expressed as:
step 5) carrying out strategy iteration, and finally achieving the balance of the Stackelberg, wherein all users can not obtain higher utility values by changing own strategies;
the utility function for user n is expressed as:
wherein ,,/>for the planar distance between user n and jammer j, +.>Is a path loss factor, +.>Instantaneous fading coefficients for the channel between user n and jammer j;
2. The anti-interference channel allocation method based on the Stackelberg game according to claim 1, wherein the instantaneous interference of user m to user nInstantaneous interference of jammer j to user n; wherein ,/>For the planar distance between user m and user n, < >>For the planar distance between jammer j and user n, < >>Is a path loss factor, +.>Is the instantaneous fading coefficient of the channel.
6. the method for anti-interference channel allocation based on a Stackelberg game according to claim 1, wherein each jammer of a leader layer is in a strategy iterationThe Q-learning algorithm is used for updating the channel access strategy in each round, and the method specifically comprises the following steps:
jammer j based on channel access probability at the beginning of each training roundSelect interference strategy->Calculate its utility value->And then furtherThe new Q-table, namely:
for learning step length, satisfy->Updating channel access probability on the basis of the channel access probability:/>
7. The method for anti-interference channel allocation based on a Stackelberg game according to claim 1, wherein each user of a follower layer is distributed in each round in the policy iterationThe channel access strategy is updated by using a random learning algorithm in each time slot, specifically:
at the position ofUpdating the channel access strategy by a random automatic learning algorithm within each time slot so that the interference is +.>Minimizing;
at the beginning of each time slot t, according to the channel access probabilityChannel for selecting access->Then calculate its utility->Updating the channel access probability of the next time slot on the basis of this +.>Specifically, the method can be expressed as:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310206515.6A CN116073924B (en) | 2023-03-07 | 2023-03-07 | Anti-interference channel allocation method and system based on Stackelberg game |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310206515.6A CN116073924B (en) | 2023-03-07 | 2023-03-07 | Anti-interference channel allocation method and system based on Stackelberg game |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116073924A CN116073924A (en) | 2023-05-05 |
CN116073924B true CN116073924B (en) | 2023-05-30 |
Family
ID=86173341
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310206515.6A Active CN116073924B (en) | 2023-03-07 | 2023-03-07 | Anti-interference channel allocation method and system based on Stackelberg game |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116073924B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116634468B (en) * | 2023-07-21 | 2023-10-31 | 中国人民解放军军事科学院系统工程研究院 | Unmanned aerial vehicle channel selection method based on accurate potential game |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112188504A (en) * | 2020-09-30 | 2021-01-05 | 中国人民解放军陆军工程大学 | Multi-user cooperative anti-interference system and dynamic spectrum cooperative anti-interference method |
CN115603777A (en) * | 2022-10-12 | 2023-01-13 | 西安交通大学(Cn) | Master-slave game-based multi-domain wireless communication anti-interference method and system |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108616916B (en) * | 2018-04-28 | 2021-07-13 | 中国人民解放军陆军工程大学 | Anti-interference learning method based on cooperative anti-interference layered game model |
CN112423234B (en) * | 2020-11-20 | 2022-07-08 | 华侨大学 | Unmanned aerial vehicle-assisted internet of things anti-hostile interference method and system based on reinforcement learning |
US20220209885A1 (en) * | 2020-12-24 | 2022-06-30 | Viettel Group | Method and apparatus for adaptive anti-jamming communications based on deep double-q reinforcement learning |
CN114698128B (en) * | 2022-05-17 | 2022-09-13 | 中国人民解放军战略支援部队航天工程大学 | Anti-interference channel selection method and system for cognitive satellite-ground network |
-
2023
- 2023-03-07 CN CN202310206515.6A patent/CN116073924B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112188504A (en) * | 2020-09-30 | 2021-01-05 | 中国人民解放军陆军工程大学 | Multi-user cooperative anti-interference system and dynamic spectrum cooperative anti-interference method |
CN115603777A (en) * | 2022-10-12 | 2023-01-13 | 西安交通大学(Cn) | Master-slave game-based multi-domain wireless communication anti-interference method and system |
Also Published As
Publication number | Publication date |
---|---|
CN116073924A (en) | 2023-05-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109639377B (en) | Spectrum resource management method based on deep reinforcement learning | |
CN113162679A (en) | DDPG algorithm-based IRS (inter-Range instrumentation System) auxiliary unmanned aerial vehicle communication joint optimization method | |
CN112188504B (en) | Multi-user cooperative anti-interference system and dynamic spectrum cooperative anti-interference method | |
CN116073924B (en) | Anti-interference channel allocation method and system based on Stackelberg game | |
CN113038616B (en) | Frequency spectrum resource management and allocation method based on federal learning | |
CN114698128B (en) | Anti-interference channel selection method and system for cognitive satellite-ground network | |
CN113890564B (en) | Special ad hoc network frequency hopping anti-interference method and device for unmanned aerial vehicle based on federal learning | |
CN111381499B (en) | Internet-connected aircraft self-adaptive control method based on three-dimensional space radio frequency map learning | |
CN110290542B (en) | Communication coverage optimization method and system for offshore unmanned aerial vehicle | |
CN113971461A (en) | Distributed federal learning method and system for unmanned aerial vehicle ad hoc network | |
CN111417126A (en) | On-demand coverage method and device for space-sky-ground cooperative marine communication network | |
Elsayed et al. | Deep reinforcement learning for reducing latency in mission critical services | |
CN112672371A (en) | Air-ground collaborative hierarchical deployment model under heterogeneous demand and access method thereof | |
CN111417125A (en) | Method and device for optimizing capacity of space-air-ground cooperative marine communication network | |
Xu et al. | Play it by ear: Context-aware distributed coordinated anti-jamming channel access | |
Nasr-Azadani et al. | Distillation and ordinary federated learning actor-critic algorithms in heterogeneous UAV-aided networks | |
CN113672819A (en) | Content request processing system based on recommendation perception and cooperative edge caching | |
CN115378487A (en) | Satellite communication dynamic spectrum access method based on electromagnetic barrier | |
CN114339976A (en) | Resource allocation method meeting time delay constraint in unmanned aerial vehicle ad hoc network | |
Handouf et al. | Availability and pricing combined framework for rivalry flying access network providers | |
Xu et al. | Game theoretical secure bandwidth allocation in uav-assisted heterogeneous networks | |
CN117768010B (en) | Satellite anti-interference method based on layered Stanberg game and matched game | |
CN111065163A (en) | Cellular network resource allocation method, device and system | |
Xinwang et al. | Anti-jamming Channel Allocation in DAV-Enabled Edge Computing: A Stackelberg Game Approach | |
CN115314099B (en) | Unmanned aerial vehicle base station communication coverage network enhancement method and system |
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 |