CN111211831A - Multi-beam low-orbit satellite intelligent dynamic channel resource allocation method - Google Patents
Multi-beam low-orbit satellite intelligent dynamic channel resource allocation method Download PDFInfo
- Publication number
- CN111211831A CN111211831A CN202010033133.4A CN202010033133A CN111211831A CN 111211831 A CN111211831 A CN 111211831A CN 202010033133 A CN202010033133 A CN 202010033133A CN 111211831 A CN111211831 A CN 111211831A
- Authority
- CN
- China
- Prior art keywords
- low
- orbit satellite
- state
- channel resource
- resource allocation
- 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.)
- Pending
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
-
- 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
- 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
- H04B7/1853—Satellite systems for providing telephony service to a mobile station, i.e. mobile satellite service
- H04B7/18539—Arrangements for managing radio, resources, i.e. for establishing or releasing a connection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Astronomy & Astrophysics (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Radio Relay Systems (AREA)
Abstract
The invention relates to the technical field of air-space-earth-sea integrated communication, in particular to an intelligent dynamic channel resource allocation method for a multi-beam low-orbit satellite; the method takes a low earth orbit satellite as an Agent, maps the number of users requesting each wave beam service at the current service request moment and the initial state occupied by the wave beam to a channel as an environment, observes the environment state and acquires an environment reward signal by using a Q-learning algorithm according to the environment of the low earth orbit satellite at each service request moment, learns a state-action value function, gradually changes a channel resource allocation strategy, completes the dynamic channel resource allocation of the low earth orbit satellite mobile communication system, can avoid the allocation of the same channel resource to the users or the wave beams within a multiplexing distance, and realizes a channel resource allocation scheme which can enable the overall performance of the low earth orbit satellite mobile communication system to be optimal.
Description
Technical Field
The invention relates to the technical field of air-space-earth-sea integrated communication, in particular to an intelligent dynamic channel resource allocation method for a multi-beam low-orbit satellite.
Background
The air, space, ground and sea integrated information network is based on a ground network, is expanded by a space-based network, adopts a unified technical architecture, a unified technical system and a unified standard specification, is formed by interconnecting and intercommunicating a space-based information network, the internet and a mobile communication network, and has the characteristics of diversified service bearing, heterogeneous network interconnection, global resource management and the like. The air, space, ground and sea integrated information network is used as an important national information infrastructure and has important significance in a plurality of fields such as homeland security, emergency disaster relief, transportation, economic development and the like.
The low-orbit satellite communication is used as an important component in an air-space-earth-sea integrated information network and has the advantages of less transmission path loss, small communication time delay, wide coverage range, flexible access and the like. In the multi-beam low-orbit satellite mobile communication system, each satellite carries a plurality of beams, different beams can be utilized under the same frequency to meet frequency multiplexing to cover different areas on the ground, and the beams are combined together to complete the coverage of the ground visible area of a single satellite, so that the communication capacity is greatly increased. However, multi-beam low-orbit satellite communications also have some unavoidable problems. On one hand, when a user establishes a call, the user must access a channel in a certain beam of the satellite or switch from one beam to another beam, and in order to ensure that the communication is not interrupted, the user must be in the boundary of the coverage area of the adjacent beam, and a channel is allocated for the communication to complete the switching, so that the call can be ensured to be continuously carried out. On the other hand, satellite channel resources are limited, the demand of the channel resources is increasing along with the increasing number of communication users and the types of communication services, and the limited resources are managed and distributed by adopting scientific and effective measures, so that the satellite channel resources become a key for providing reliable services for users by a multi-beam low-orbit satellite communication system.
However, the low-earth satellite terminals are not uniformly distributed in the geographic space, so that the difference of communication traffic among beams of the low-earth satellite mobile communication system is large, and the demand of channel resources is different. If the fixed spectrum allocation mode is adopted, even if the user in the beam does not use the resource, other beam users cannot use the resource, and the waste of channel resources is easily caused. For the dynamic resource allocation mode, all channel resources can be used by each beam user, and the resource allocation is performed according to the number of service request users of each beam, so that the dynamic resource allocation mode has the advantage of higher resource utilization rate compared with a fixed frequency spectrum allocation mode. However, each beam user may use all channel resources, and the same channel may be allocated to a user in a short distance in the resource allocation process, thereby generating interference and affecting the communication service quality of the system.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an intelligent dynamic channel resource allocation method for a multi-beam low-orbit satellite.
In one aspect, the present invention provides a method for allocating multi-beam low-earth orbit satellite intelligent dynamic channel resources, comprising the following steps:
s1, initializing a low-orbit satellite state-action value function Q (S, a), and setting an initial learning rate lambda and a discount factor β;
s2: the low-orbit satellite communication system forms N beams on the ground through satellite-borne multi-beam load, and the N beams are expressed as B ═ { N ═ 1,2, … N }; the available channel set C ═ { M ═ 1,2, … M }, where M is the number of channel resources; channel resource allocation state w for beam nn＝[wn，1,wn，2，…,wn,M]Wherein each term wn,mE {0,1} represents the occupation situation of the beam n to the subchannel m, 1 represents occupation, and 0 represents idle and unoccupied; the channel allocation vectors of all beams in the low-earth satellite system form the total channel allocation matrix of the satellite system, which is W ═ W1,w2，…,wN](ii) a The channel resource matrix V ═ V [ V ] currently available for each beam1,v2，…,vN]Wherein v isn＝[vn，1,vn，2，…,vn,M]Representing the available channel resource situation of each beam, the state of the t moment is constructed
S3: predicting actions to be taken by the low-orbit satellite according to the constructed state, and acquiring a Q value from a Q value characterization module of the low-orbit satellite;
s4: the low orbit satellite gathers a(s) from the feasible actions depending on the environment and state of the satellitet) Selecting the action with the maximum Q value according to the probability epsilon to execute;
s5: giving a reward function r after the low-orbit satellite reaches a termination state;
s6: the low-orbit satellite brings the state-action value function Q (s, a) into a Bellman formula for iterative updating, selects the next action according to the reward function r as estimation, and optimizes the state-action value function;
s7, when each iteration is finished, updating the discount factor β and judging whether the discount factor β is less than 0.01, if so, obtaining a channel distribution result Wt(ii) a If not, the process returns to step S6.
Optionally, the channel resource v available for each beam is selected from the group consisting of a plurality of beams, and a plurality of beams are arranged in a same beamnThe value and the represented meaning of each element in the vector are as follows:
optionally, the action atIs shown in state stSelecting a wave beam n from the available channel resource set, and allocating a channel resource m for the wave beam n, wherein the calculation expression is as follows: a ist＝{(n,m)|n,m∈Α(st),n∈B,m∈M}。
Optionally, the calculation expression of the state-action value function Q (s, a) substituted into the Bellman formula for iterative update is as follows: q(s)i,ai)＝(1-λ)Q(si,ai)+λ(ri+βmaxQ(si,a))。
Optionally, the discount factor β needs to satisfy β e [0,1), which is set to gradually decrease with the learning process according to the negative exponential rule of e, so as to satisfy the convergence requirement of learning.
Optionally, the reward function r is designed as a scalar value positively correlated to the system performance, and the system performance is measured by using the system blocking probability, that is, the optimization target is that the number of blocked users of the system is minimum, and considering that at each service request time, a channel resource optimal allocation manner is learned according to the amount of users requesting the service of each beam, the designed reward function r should be correlated to the system performance in the termination state, so that a reward function r is given after the low-orbit satellite reaches the termination state, where the reward function r calculates an expression as follows:
wherein the content of the first and second substances,Rmaxthe maximum reward value represented is a scalar positive value; u shapeblockIndicating the number of current system blocking users, UallRepresenting the number of users in the system that request the service in total.
The invention has the beneficial effects that:
(1) the invention discloses a multi-beam low-orbit satellite intelligent dynamic channel resource allocation method, which is combined with a reinforcement learning algorithm in artificial intelligence, realizes dynamic allocation of low-orbit satellite communication system resources according to service requests of various beam users through state information of low-orbit satellites and the current communication environment, and improves the communication service performance of the system.
(2) According to the multi-beam low-orbit satellite intelligent dynamic channel resource allocation method, interference among users is considered when a dynamic resource allocation scheme is designed, and the influence of same frequency interference can be avoided.
(3) According to the intelligent dynamic channel resource allocation method for the multi-beam low-orbit satellite, the environment state is observed and the environment reward signal is acquired by using the Q-learning algorithm, the state-action value function is learned, the channel resource allocation strategy is changed step by step, and the learning speed and the learning effect of the system are greatly improved.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
FIG. 1 is a schematic flow chart of an intelligent dynamic channel resource allocation method for a multi-beam low-orbit satellite according to the present invention;
fig. 2 is a diagram of the relationship between the system blocking rate and the traffic arrival rate under the condition of uniform traffic distribution.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
At present, satellite channel resources are limited, and the demand of the channel resources is larger and larger as the number of communication users and the types of communication services are increased continuously; the low-orbit satellite terminals are unevenly distributed in the geographic space, so that the difference of communication traffic among beams of a low-orbit satellite mobile communication system is large; each beam user can use all channel resources, and the same channel can be allocated to users with close distance in the process of resource allocation, so that the problems of interference, influence on the communication service quality of the system and the like are caused; in order to solve the above problems, it is necessary to develop an intelligent dynamic channel resource allocation method for a multi-beam low-earth satellite, which observes an environment state and obtains an environmental reward signal by using a Q-learning algorithm, learns a state-action value function, gradually changes a channel resource allocation strategy, completes dynamic channel resource allocation of a low-earth satellite mobile communication system, can avoid allocating the same channel resource to users or beams within a multiplexing distance, and implements a channel resource allocation scheme capable of optimizing the overall performance of the low-earth satellite mobile communication system.
The specific implementation of the present invention provides a multi-beam low-orbit satellite intelligent dynamic channel resource allocation method, as shown in fig. 1-2, including the following steps:
in step S1, the low-earth satellite state-action value function Q (S, a) is initialized, and the initial learning rate λ and the discount factor β are set.
In the embodiment of the present invention, the step is the initialization of data, where s represents the state and a represents the action.
In step S2, the low earth orbit satellite communication system forms N beams on the ground by the satellite-borne multi-beam load, denoted as B ═ { N | N ═ 1,2, … N }; the available channel set C ═ { M ═ 1,2, … M }, where M is the number of channel resources; channel resource allocation state w for beam nn＝[wn，1,wn，2，…,wn,M]Wherein each term wn,mE {0,1} represents the occupation situation of the beam n to the subchannel m, 1 represents occupation, and 0 represents idle and unoccupied; the channel allocation vectors of all beams in the low-earth satellite system form the total channel allocation matrix of the satellite system, which is W ═ W1,w2，…,wN](ii) a The channel resource matrix V ═ V [ V ] currently available for each beam1,v2，…,vN]Wherein v isn＝[vn，1,vn，2，…,vn,M]Representing the available channel resource situation of each beam, the state of the t moment is constructed
In the embodiment of the present invention, the step is a component of a state, and the state is an abstraction of environment formalization and is also a basis for determining the executed action; channel resources v available for said respective beamnThe value and the represented meaning of each element in the vector are as follows:
in step S3, the low-earth satellite predicts an action to be taken based on the constructed state, and acquires a Q value from its own Q value characterization module.
In the embodiment of the invention, the step is the acquisition of the Q value, and in the step, in order to check the effectiveness of the algorithm, the predicted value of the prediction module is assumed to be accurate.
In step S4, the low orbit satellite aggregates a (S) from the set of feasible actions according to the environment and state of the satellitet) The action with the largest Q value is selected to be executed according to the probability epsilon.
In an embodiment of the invention, this step is the selection and execution of the action that the low orbiting satellite gets a(s) from the set of feasible actions depending on the environment and state it is int) Selecting the action with the maximum Q value according to the probability epsilon to execute; the action atIs shown in state stThe set of channel resources available at the bottom (i.e. state s)tThe element set with the median value of 0), selecting a beam n, and allocating a channel resource m for the beam n, wherein the calculation expression is as follows: e.g. of the type-xat＝{(n,m)|n,m∈Α(st),n∈B,m∈M}。
In step S5, a reward function r is given after each low-orbiting satellite reaches a termination state.
In the embodiment of the invention, the step is to obtain the return, the return is the feedback from the environment in the interactive process of the low-orbit satellite and the environment, the evaluation is carried out after the action is selected in a determined state, and the return is also an index for measuring the performance of the dynamic resource allocation algorithm; for convenience of calculation, the reward function r can be designed as a scalar value positively correlated to the system performance, and the system performance is measured by using the system blocking probability, that is, the optimization target is that the number of blocked users of the system is minimum, and in consideration of each service request moment, a channel resource optimal allocation mode is learned according to the amount of users requesting the service of each beam, the designed reward function r should be correlated to the system performance in the termination state, so that a reward function r is given after the low-orbit satellite reaches the termination state, wherein the reward function r calculates the expression as follows:
wherein R ismaxThe maximum reward value represented is a scalar positive value; u shapeblockIndicating the number of current system blocking users, UallRepresenting the number of users in the system that request the service in total.
In step S6, the low earth orbit satellite iteratively updates the state-action value function Q (S, a) into the Bellman equation, selects the next action based on the reward function r as an estimate, and optimizes the state-action value function.
In the embodiment of the invention, the step is the updating of the Q value; the calculation expression of the state-action value function Q (s, a) substituted into the Bellman formula for iterative updating is: q(s)i,ai)＝(1-λ)Q(si,ai)+λ(ri+βmaxQ(si,a))。
In step S7, when each iteration is finished, the discount factor β is updated, and whether the discount factor β is smaller than 0.01 is determined, if yes, the channel allocation result W is obtainedt(ii) a If not, the process returns to step S6.
In the embodiment of the present invention, the step is parameter updating, the discount factor β needs to satisfy β e [0,1), it is set to gradually decrease with the learning process according to the negative exponential rule of e, and the expression is β -e-xWherein x is automatically added with 1 at the end of each iteration to meet the convergence requirement of learning, and when the requirement of the set discount factor β is met, a channel allocation result W is obtainedt。
The multi-beam low-orbit satellite intelligent dynamic Channel resource Allocation method is applied to practice, a multi-beam low-orbit satellite is assumed to be 54 beams, a service arrival model obeys Poisson distribution with a parameter of lambda, service duration obeys negative exponential distribution with a parameter of mu, the number of channels M is 204, a learning rate lambda is 0.005, a discount factor β is 0.90, and a maximum reward value is 100.
The invention has designed a multibeam low orbit satellite intelligence dynamic channel resource allocation method, this method regards low orbit satellite as Agent, every wave beam business under the present business request moment asks user's quantity and wave beam to initial state mapping that the channel occupies as the environment, under each business request moment, according to the environment that the low orbit satellite locates, utilize Q-learning algorithm to observe the environment state and obtain the reward signal of the environment, study the state-function of the action value, change the resource allocation tactics of the channel step by step, finish the dynamic channel resource allocation of the low orbit satellite mobile communication system, can avoid the same channel resource from allocating users or wave beams within the multiplexing distance, realize a can make the overall performance of the low orbit satellite mobile communication system reach the optimal channel resource allocation scheme; the method combines a reinforcement learning algorithm in artificial intelligence, realizes dynamic allocation of low-orbit satellite communication system resources according to service requests of each beam user through state information of the low-orbit satellite and the current communication environment, and improves the communication service performance of the system. The method considers the interference among users when designing the dynamic resource allocation scheme, and can avoid the influence of the same frequency interference. A Q-learning algorithm is utilized to observe the environment state and acquire the reward signals of the environment, a state-action value function is learned, a channel resource allocation strategy is changed step by step, and the learning speed and the learning effect of the system are greatly improved.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (6)
1. A multi-beam low-orbit satellite intelligent dynamic channel resource allocation method is characterized by comprising the following steps:
s1, initializing a low-orbit satellite state-action value function Q (S, a), and setting an initial learning rate lambda and a discount factor β;
s2: the low-orbit satellite communication system forms N beams on the ground through satellite-borne multi-beam load, and the N beams are expressed as B ═ { N ═ 1,2, … N }; the available channel set C ═ { M ═ 1,2, … M }, where M is the number of channel resources; channel resource allocation state w for beam nn＝[wn，1,wn，2，…,wn,M]Wherein each term wn,mE {0,1} represents the occupation situation of the beam n to the subchannel m, 1 represents occupation, and 0 represents idle and unoccupied; the channel allocation vectors of all beams in the low-earth satellite system form the total channel allocation matrix of the satellite system, which is W ═ W1,w2，…,wN](ii) a The channel resource matrix V ═ V [ V ] currently available for each beam1,v2，…,vN]Wherein v isn＝[vn，1,vn，2，…,vn,M]Representing the available channel resource situation of each beam, the state of the t moment is constructed
S3: predicting actions to be taken by the low-orbit satellite according to the constructed state, and acquiring a Q value from a Q value characterization module of the low-orbit satellite;
s4: the low orbit satellite gathers a(s) from the feasible actions depending on the environment and state of the satellitet) Selecting the action with the maximum Q value according to the probability epsilon to execute;
s5: giving a reward function r after the low-orbit satellite reaches a termination state;
s6: the low-orbit satellite brings the state-action value function Q (s, a) into a Bellman formula for iterative updating, selects the next action according to the reward function r as estimation, and optimizes the state-action value function;
s7, when each iteration is finished, updating the discount factor β and judging whether the discount factor β is less than 0.01, if so, obtaining a channel distribution result Wt(ii) a If not, the process returns to step S6.
2. The method of claim 1, wherein the channel resources v available for each beam are defined by a number of available channel resources vnThe value and the represented meaning of each element in the vector are as follows:
3. the method of claim 1, wherein the action atIs shown in state stSelecting a wave beam n from the available channel resource set, and allocating a channel resource m for the wave beam n, wherein the calculation expression is as follows: a ist＝{(n,m)|n,m∈Α(st),n∈B,m∈M}。
4. The method of claim 1, wherein the state-action value function Q (s, a) is substituted into the calculation expression of Bellman's formula for iterative updating as: q(s)i,ai)＝(1-λ)Q(si,ai)+λ(ri+βmaxQ(si,a))。
5. The method of claim 1, wherein the discount factor β is set to satisfy β e [0,1), and is gradually decreased along with the learning process according to the negative exponential rule of e to satisfy the convergence requirement of learning.
6. The method according to claim 1, wherein the reward function r is designed as a scalar positively correlated to the system performance, and the system performance is measured by the system blocking probability, that is, the optimization goal is that the number of blocked users of the system is minimum, and considering that at each service request time, an optimal channel resource allocation manner is learned according to the number of users requesting the service of each beam, the designed reward function r should be correlated to the system performance at the termination state, so that a reward function r is given after the low-orbit satellite reaches the termination state, wherein the reward function r calculates the expression as follows:
wherein R ismaxThe maximum reward value represented is a scalar positive value; u shapeblockIndicating the number of current system blocking users, UallRepresenting the number of users in the system that request the service in total.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010033133.4A CN111211831A (en) | 2020-01-13 | 2020-01-13 | Multi-beam low-orbit satellite intelligent dynamic channel resource allocation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010033133.4A CN111211831A (en) | 2020-01-13 | 2020-01-13 | Multi-beam low-orbit satellite intelligent dynamic channel resource allocation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111211831A true CN111211831A (en) | 2020-05-29 |
Family
ID=70787960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010033133.4A Pending CN111211831A (en) | 2020-01-13 | 2020-01-13 | Multi-beam low-orbit satellite intelligent dynamic channel resource allocation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111211831A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111770544A (en) * | 2020-07-29 | 2020-10-13 | 南京邮电大学 | Q-Learning-based satellite Internet of things routing strategy |
| CN111970047A (en) * | 2020-08-25 | 2020-11-20 | 桂林电子科技大学 | LEO satellite channel allocation method based on reinforcement learning |
| CN112615695A (en) * | 2020-12-16 | 2021-04-06 | 中电科航空电子有限公司 | Method, device and equipment for sharing AFDX (avionics full Duplex switched Ethernet) network by electromagnetic wave equipment |
| CN113038387A (en) * | 2021-03-12 | 2021-06-25 | 重庆邮电大学 | Q learning-based switching judgment method in low-earth-orbit satellite network |
| CN113260009A (en) * | 2021-04-25 | 2021-08-13 | 昆明乐子科技有限公司 | Method for switching a communication connection to another channel (handover) |
| CN113259950A (en) * | 2021-05-13 | 2021-08-13 | 重庆邮电大学 | Low-orbit satellite spot beam closing method based on service prediction |
| CN113258988A (en) * | 2021-05-13 | 2021-08-13 | 重庆邮电大学 | DQN-based multi-service low-orbit satellite resource allocation method |
| CN113342537A (en) * | 2021-07-05 | 2021-09-03 | 中国传媒大学 | Satellite virtual resource allocation method, device, storage medium and equipment |
| CN113541770A (en) * | 2021-07-12 | 2021-10-22 | 军事科学院系统工程研究院网络信息研究所 | Space-time-frequency refined resource management method for multi-beam satellite communication system |
| CN113709876A (en) * | 2021-07-08 | 2021-11-26 | 北京邮电大学 | Satellite service resource allocation method and electronic equipment |
| CN114499625A (en) * | 2021-12-08 | 2022-05-13 | 中国卫通集团股份有限公司 | Service transfer method based on multi-objective constraint optimization and related equipment |
| CN115483960A (en) * | 2022-08-23 | 2022-12-16 | 爱浦路网络技术(南京)有限公司 | Beam hopping scheduling method, system, device and storage medium for low-earth-orbit satellite |
| CN118042606A (en) * | 2024-04-11 | 2024-05-14 | 广州程星通信科技有限公司 | Resource fusion dynamic allocation method based on multi-system multi-band beam satellite system |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101466111A (en) * | 2009-01-13 | 2009-06-24 | 中国人民解放军理工大学通信工程学院 | Dynamic spectrum access method based on policy planning constrain Q study |
| CN101699895A (en) * | 2004-10-20 | 2010-04-28 | 高通股份有限公司 | Multiple frequency band operation in wireless networks |
| CN102256262A (en) * | 2011-07-14 | 2011-11-23 | 南京邮电大学 | Multi-user dynamic spectrum accessing method based on distributed independent learning |
| US20170105163A1 (en) * | 2015-10-13 | 2017-04-13 | The Board Of Trustees Of The University Of Alabama | Artificial intelligence-augmented, ripple-diamond-chain shaped rateless routing in wireless mesh networks with multi-beam directional antennas |
| CN106850039A (en) * | 2016-12-29 | 2017-06-13 | 航天东方红卫星有限公司 | A kind of method that multichannel payload data efficient low-consume is transmitted over the ground |
| CN108112082A (en) * | 2017-12-18 | 2018-06-01 | 北京工业大学 | A kind of wireless network distributed freedom resource allocation methods based on statelessly Q study |
| CN108449151A (en) * | 2018-05-02 | 2018-08-24 | 河海大学常州校区 | Frequency spectrum access method in a kind of cognitive radio networks based on machine learning |
| CN108647542A (en) * | 2018-04-26 | 2018-10-12 | 广西大学 | The more reader anti-collision algorithms of RFID based on Q-learning |
| CN108809452A (en) * | 2018-05-02 | 2018-11-13 | 河海大学常州校区 | Optimal perceived channel selecting method in dynamic spectrum access system |
| CN108966352A (en) * | 2018-07-06 | 2018-12-07 | 北京邮电大学 | Dynamic beam dispatching method based on depth enhancing study |
| CN109039505A (en) * | 2018-06-29 | 2018-12-18 | 河海大学常州校区 | Channel status transition probability prediction technique in a kind of cognitive radio networks |
| US20190030370A1 (en) * | 2017-07-25 | 2019-01-31 | Elekta, Inc. | Systems and methods for determining radiation therapy machine parameter settings |
| CN109474980A (en) * | 2018-12-14 | 2019-03-15 | 北京科技大学 | A kind of wireless network resource distribution method based on depth enhancing study |
| CN109743735A (en) * | 2018-12-18 | 2019-05-10 | 北京邮电大学 | A kind of dynamic channel assignment method based on depth enhancing study in satellite communication system |
| CN109787696A (en) * | 2018-12-11 | 2019-05-21 | 杭州电子科技大学 | The cognitive radio resource allocation methods of case-based reasioning and cooperation Q study |
| CN109862610A (en) * | 2019-01-08 | 2019-06-07 | 华中科技大学 | A kind of D2D subscriber resource distribution method based on deeply study DDPG algorithm |
| CN110061982A (en) * | 2019-04-02 | 2019-07-26 | 广州大学 | A kind of confrontation intelligence attack safe transmission method based on intensified learning |
-
2020
- 2020-01-13 CN CN202010033133.4A patent/CN111211831A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699895A (en) * | 2004-10-20 | 2010-04-28 | 高通股份有限公司 | Multiple frequency band operation in wireless networks |
| CN101466111A (en) * | 2009-01-13 | 2009-06-24 | 中国人民解放军理工大学通信工程学院 | Dynamic spectrum access method based on policy planning constrain Q study |
| CN102256262A (en) * | 2011-07-14 | 2011-11-23 | 南京邮电大学 | Multi-user dynamic spectrum accessing method based on distributed independent learning |
| US20170105163A1 (en) * | 2015-10-13 | 2017-04-13 | The Board Of Trustees Of The University Of Alabama | Artificial intelligence-augmented, ripple-diamond-chain shaped rateless routing in wireless mesh networks with multi-beam directional antennas |
| CN106850039A (en) * | 2016-12-29 | 2017-06-13 | 航天东方红卫星有限公司 | A kind of method that multichannel payload data efficient low-consume is transmitted over the ground |
| US20190030370A1 (en) * | 2017-07-25 | 2019-01-31 | Elekta, Inc. | Systems and methods for determining radiation therapy machine parameter settings |
| CN108112082A (en) * | 2017-12-18 | 2018-06-01 | 北京工业大学 | A kind of wireless network distributed freedom resource allocation methods based on statelessly Q study |
| CN108647542A (en) * | 2018-04-26 | 2018-10-12 | 广西大学 | The more reader anti-collision algorithms of RFID based on Q-learning |
| CN108809452A (en) * | 2018-05-02 | 2018-11-13 | 河海大学常州校区 | Optimal perceived channel selecting method in dynamic spectrum access system |
| CN108449151A (en) * | 2018-05-02 | 2018-08-24 | 河海大学常州校区 | Frequency spectrum access method in a kind of cognitive radio networks based on machine learning |
| CN109039505A (en) * | 2018-06-29 | 2018-12-18 | 河海大学常州校区 | Channel status transition probability prediction technique in a kind of cognitive radio networks |
| CN108966352A (en) * | 2018-07-06 | 2018-12-07 | 北京邮电大学 | Dynamic beam dispatching method based on depth enhancing study |
| CN109787696A (en) * | 2018-12-11 | 2019-05-21 | 杭州电子科技大学 | The cognitive radio resource allocation methods of case-based reasioning and cooperation Q study |
| CN109474980A (en) * | 2018-12-14 | 2019-03-15 | 北京科技大学 | A kind of wireless network resource distribution method based on depth enhancing study |
| CN109743735A (en) * | 2018-12-18 | 2019-05-10 | 北京邮电大学 | A kind of dynamic channel assignment method based on depth enhancing study in satellite communication system |
| CN109862610A (en) * | 2019-01-08 | 2019-06-07 | 华中科技大学 | A kind of D2D subscriber resource distribution method based on deeply study DDPG algorithm |
| CN110061982A (en) * | 2019-04-02 | 2019-07-26 | 广州大学 | A kind of confrontation intelligence attack safe transmission method based on intensified learning |
Non-Patent Citations (1)
| Title |
|---|
| 刘召等: "多波束卫星动态信道资源分配算法", 《移动通信》 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111770544A (en) * | 2020-07-29 | 2020-10-13 | 南京邮电大学 | Q-Learning-based satellite Internet of things routing strategy |
| CN111770544B (en) * | 2020-07-29 | 2023-02-10 | 南京邮电大学 | Q-Learning-based satellite Internet of things routing method |
| CN111970047A (en) * | 2020-08-25 | 2020-11-20 | 桂林电子科技大学 | LEO satellite channel allocation method based on reinforcement learning |
| CN111970047B (en) * | 2020-08-25 | 2022-03-25 | 桂林电子科技大学 | LEO satellite channel allocation method based on reinforcement learning |
| CN112615695B (en) * | 2020-12-16 | 2022-03-22 | 中电科航空电子有限公司 | Method, device and equipment for sharing AFDX (avionics full Duplex switched Ethernet) network by electromagnetic wave equipment |
| CN112615695A (en) * | 2020-12-16 | 2021-04-06 | 中电科航空电子有限公司 | Method, device and equipment for sharing AFDX (avionics full Duplex switched Ethernet) network by electromagnetic wave equipment |
| CN113038387A (en) * | 2021-03-12 | 2021-06-25 | 重庆邮电大学 | Q learning-based switching judgment method in low-earth-orbit satellite network |
| CN113038387B (en) * | 2021-03-12 | 2024-02-20 | 深圳泓越信息科技有限公司 | Switching judgment method based on Q learning in low orbit satellite network |
| CN113260009A (en) * | 2021-04-25 | 2021-08-13 | 昆明乐子科技有限公司 | Method for switching a communication connection to another channel (handover) |
| CN113258988A (en) * | 2021-05-13 | 2021-08-13 | 重庆邮电大学 | DQN-based multi-service low-orbit satellite resource allocation method |
| CN113259950A (en) * | 2021-05-13 | 2021-08-13 | 重庆邮电大学 | Low-orbit satellite spot beam closing method based on service prediction |
| CN113259950B (en) * | 2021-05-13 | 2022-03-11 | 重庆邮电大学 | Low-orbit satellite spot beam closing method based on service prediction |
| CN113258988B (en) * | 2021-05-13 | 2022-05-20 | 重庆邮电大学 | DQN-based multi-service low-orbit satellite resource allocation method |
| CN113342537A (en) * | 2021-07-05 | 2021-09-03 | 中国传媒大学 | Satellite virtual resource allocation method, device, storage medium and equipment |
| CN113342537B (en) * | 2021-07-05 | 2023-11-14 | 中国传媒大学 | Satellite virtual resource allocation method, device, storage medium and equipment |
| CN113709876A (en) * | 2021-07-08 | 2021-11-26 | 北京邮电大学 | Satellite service resource allocation method and electronic equipment |
| CN113709876B (en) * | 2021-07-08 | 2023-06-20 | 北京邮电大学 | Satellite service resource allocation method and electronic equipment |
| CN113541770A (en) * | 2021-07-12 | 2021-10-22 | 军事科学院系统工程研究院网络信息研究所 | Space-time-frequency refined resource management method for multi-beam satellite communication system |
| CN113541770B (en) * | 2021-07-12 | 2022-02-01 | 军事科学院系统工程研究院网络信息研究所 | Space-time-frequency refined resource management method for multi-beam satellite communication system |
| CN114499625A (en) * | 2021-12-08 | 2022-05-13 | 中国卫通集团股份有限公司 | Service transfer method based on multi-objective constraint optimization and related equipment |
| CN114499625B (en) * | 2021-12-08 | 2024-04-12 | 中国卫通集团股份有限公司 | Service transfer method based on multi-objective constraint optimization and related equipment |
| CN115483960A (en) * | 2022-08-23 | 2022-12-16 | 爱浦路网络技术(南京)有限公司 | Beam hopping scheduling method, system, device and storage medium for low-earth-orbit satellite |
| CN115483960B (en) * | 2022-08-23 | 2023-08-29 | 爱浦路网络技术(南京)有限公司 | Wave beam jumping scheduling method, system and device for low orbit satellite and storage medium |
| CN118042606A (en) * | 2024-04-11 | 2024-05-14 | 广州程星通信科技有限公司 | Resource fusion dynamic allocation method based on multi-system multi-band beam satellite system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111211831A (en) | Multi-beam low-orbit satellite intelligent dynamic channel resource allocation method | |
| CN111277437B (en) | Network slice resource allocation method for smart power grid | |
| CN111953758B (en) | Edge network computing unloading and task migration method and device | |
| CN114362810A (en) | Low-orbit satellite beam hopping optimization method based on migration depth reinforcement learning | |
| CN110518956B (en) | Time slot allocation algorithm-based hopping pattern optimization method and device, and storage medium | |
| CN109951873B (en) | Task unloading mechanism under asymmetric and uncertain information in fog computing of Internet of things | |
| CN109600798B (en) | Multi-domain resource allocation method and device in network slice | |
| CN111711666B (en) | Internet of vehicles cloud computing resource optimization method based on reinforcement learning | |
| CN115021799B (en) | Low-orbit satellite switching method based on multi-agent cooperation | |
| CN117041330B (en) | Edge micro-service fine granularity deployment method and system based on reinforcement learning | |
| Xia et al. | Joint resource allocation at edge cloud based on ant colony optimization and genetic algorithm | |
| Marbukh | Towards fog network utility maximization (FoNUM) for managing fog computing resources | |
| CN115474281A (en) | Resource allocation method in satellite-ground converged network | |
| CN116546624B (en) | Method and device for predicting wave-hopping satellite service and distributing multidimensional link dynamic resources | |
| CN116886172A (en) | Multi-beam satellite communication user selection and spectrum division method based on machine learning | |
| CN116505998A (en) | Multi-beam satellite communication resource distribution system and method based on deep reinforcement learning | |
| Chen et al. | Reinforcement learning based signal quality aware handover scheme for LEO satellite communication networks | |
| Wang et al. | A dynamic channel-borrowing approach with fuzzy logic control in distributed cellular networks | |
| CN108540246B (en) | Resource allocation method based on cognitive radio | |
| CN110234167B (en) | Channel allocation method, channel allocation device and electronic equipment | |
| Gao et al. | A distributed virtual network function placement approach in satellite edge and cloud computing | |
| CN117979452A (en) | Dynamic resource allocation method and system based on satellite link quality | |
| WO2023220975A1 (en) | Method, apparatus and system for managing network resources | |
| CN115623366B (en) | Route wavelength distribution method, device, terminal and medium of satellite all-optical network | |
| CN117279072B (en) | Terminal access method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200529 |
|
| RJ01 | Rejection of invention patent application after publication |