CN114629543B - Satellite network self-adaptive flow scheduling method based on deep supervised learning - Google Patents
Satellite network self-adaptive flow scheduling method based on deep supervised learning Download PDFInfo
- Publication number
- CN114629543B CN114629543B CN202210106549.3A CN202210106549A CN114629543B CN 114629543 B CN114629543 B CN 114629543B CN 202210106549 A CN202210106549 A CN 202210106549A CN 114629543 B CN114629543 B CN 114629543B
- Authority
- CN
- China
- Prior art keywords
- network
- flow
- satellite network
- satellite
- node
- 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 24
- 239000011159 matrix material Substances 0.000 claims description 32
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 8
- 230000003044 adaptive effect Effects 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 10
- 230000008569 process Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
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
- H04B7/18521—Systems of inter linked satellites, i.e. inter satellite service
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/02—Topology update or discovery
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/22—Alternate routing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/50—Routing or path finding of packets in data switching networks using label swapping, e.g. multi-protocol label switch [MPLS]
-
- 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)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Astronomy & Astrophysics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Radio Relay Systems (AREA)
Abstract
The invention discloses a satellite network self-adaptive flow scheduling method based on deep supervision learning, which realizes the calculation of a fast routing path, ensures the minimum and maximum link utilization rate under the condition of delay, and solves the problems of low speed and small throughput of the traditional algorithm. The invention uses a supervised learning algorithm to train an intelligent route model for each satellite node pair with non-zero flow demand, simplifies a complex route calculation process into simple input and output, avoids multiple iterations in calculation so as to realize rapid calculation of a route path, accelerates the speed of the routing algorithm, reduces forwarding delay, enables data packets which are discarded due to ttl expiration to survive and successfully forward, and increases network throughput. The invention is provided with two stages of offline training and online training, and updates parameters in a dynamic environment to select an optimal path, so that the invention has topology self-adaptability.
Description
Technical Field
The invention particularly relates to a satellite network self-adaptive flow scheduling method based on deep supervised learning, and belongs to the field of satellite data transmission.
Background
Efficient networking is required among satellites. For the efficient ad hoc network of the small satellite constellation, how to provide an efficient and reliable traffic scheduling scheme for the satellite network is particularly important. In a low orbit satellite network, satellite nodes move fast, the network topology changes frequently, and therefore the satellite network has the characteristics of poor expandability, low node link resource utilization rate, high service dynamic change and the like, and traffic scheduling becomes a difficult problem of the satellite network. How to handle network time-varying topology and high dynamic traffic due to node movement is a key problem in solving satellite network traffic scheduling.
Most of the traditional flow scheduling methods are based on shortest path algorithms, the routing parameters are configured to determine the routing information of the service by adjusting the link weight, and some simple network parameters (such as path hop count, time delay and the like) are used as optimization targets of the algorithms, so that the routing optimization of the service flow is realized, and the load balancing is achieved. However, in a high dynamic service scenario, due to frequent topology changes, a single measurement standard and an optimization target easily cause partial key link congestion and cause the problem of unbalanced network load. Although the shortest path meeting multiple constraint conditions can be found by the shortest path algorithm based on Lagrange relaxation, the heuristic algorithm can obtain the optimal path through multiple iterations, and is high in calculation cost, poor in timeliness and not ideal in optimizing effect under the high dynamic change environment of the network.
Disclosure of Invention
The invention aims at: aiming at the defects in the prior art, the satellite network self-adaptive flow scheduling method based on deep supervised learning solves the problems in the prior art.
In order to achieve the aim of the invention, the invention adopts the following technical scheme:
a satellite network self-adaptive flow scheduling method based on deep supervised learning comprises the following steps:
s1, acquiring flow matrixes at a plurality of moments from a satellite network, and obtaining flow requirements among all node pairs in the satellite network at the plurality of moments;
s2, calculating an alternative path set of all non-zero flow demand node pairs in the satellite network by using a K shortest path algorithm;
s3, obtaining optimal data forwarding paths of all non-zero flow demand node pairs under each flow matrix by using a tag data generation algorithm, and generating a tag data set;
s4, performing offline training on the intelligent routing model of each non-zero flow demand node pair by using a back propagation algorithm according to the tag data set, and deploying the trained model in a satellite network;
s5, collecting a real-time flow matrix at the current moment from a network;
s6, the satellite network calculates the optimal forwarding paths of all nodes to the data route according to the real-time flow matrix at the current moment by using the trained intelligent routing model;
s7, the satellite network performs data transmission according to the calculated optimal path;
s8, detecting whether the topological structure of the satellite network is changed, if so, entering a step S9, otherwise, repeating the step S8;
s9, performing online training, retraining the intelligent routing model of each node pair, and performing data transmission by using the updated intelligent routing model.
Further, in the step S1, the traffic matrix is the traffic demand between all source node pairs and destination node pairs in the satellite network, and the mth row and nth column of the traffic matrix represent the traffic demand from node m to node n.
Further, step S2 uses a K-shortest algorithm to calculate K different loop-free alternatives for each non-zero traffic demand node pair in the network, as a set of alternatives for that node pair.
Further, the step S3 obtains the optimal data forwarding paths of all the non-zero traffic demand node pairs under each traffic matrix by using a tag data generating algorithm, and generates a tag data set, specifically:
s31, initializing the sum of the flows of all links in a satellite network to be 0 for each flow matrix, and sequencing D business flows to enable a count value i=1;
s32, placing the ith service into the network topology, namely from the alternative path set P d Taking out an alternative path p, adding the occupied bandwidth of the service to the sum of the flows of links passing through the path p, and calculating the maximum link utilization rate z of the current network; comparing the z values of all the alternative paths, and selecting the alternative path corresponding to the minimum value as a routing scheme of the service;
s33, checking whether the maximum link utilization z of the current network exceeds a preset value z max The method comprises the steps of carrying out a first treatment on the surface of the If yes, executing step S34, otherwise executing step S36;
s34, taking out the put-in last N services from the network, wherein N is more than 0, and subtracting the demand of the N services from the sum of the flow of the links;
s35, re-ordering the extracted N services, and executing the step S33 after putting the N services into the network again according to the current sequence;
s36, if i is less than or equal to D, adding 1 to the value of i, executing the step S32, otherwise, ending, and outputting the routing scheme of all traffic services;
s37, the routing scheme of each service is represented by an optimal path label, and each flow matrix is provided with an optimal path label corresponding to the flow matrix on each node pair of the non-zero flow service requirement; when the routing strategies of the N traffic matrixes are calculated, each node pair generates N pieces of training data to form a training database of the node pair, namely a label data set.
Further, in the step S4, the intelligent routing model is a BP fully-connected neural network; the BP fully-connected neural network input comprises network states of an SDN network, wherein the network states are network topology, flow matrix, bandwidth requirements and time delay requirements; the BP full-connection neural network comprises an input layer, a full-connection layer and an output layer which are sequentially connected.
Further, the neural network model of each node pair is trained offline by adopting a back propagation algorithm, specifically:
input quantity x i And weight w i And a given threshold b i Making a difference, which is passed through a transfer function f to obtain an output value y i The method comprises the steps of carrying out a first treatment on the surface of the Meanwhile, errors of the output value and the expected value of the network are compared, and the link weight and the threshold value among all layers of the network are continuously adjusted and modified by utilizing a gradient descent method through counter propagation of the errors, so that the output result is more approximate to a true value, and simultaneously, the output result is converged to a preset target error function value E; changing a weight coefficient through a back propagation algorithm, randomly assigning an initial weight by a network, and then adjusting according to a network iteration result until a target error is met; model training is completed when the variation values of all parameters are smaller than the iteration threshold or the maximum number of iterations is reached.
Further, in step S9, the network controller monitors the network topology change in real time, detects whether the network topology changes, and when the network topology changes more than expected, retrains and deploys the neural network model offline, and the model parameters are adjusted to adapt to the new environment, so as to realize the self-adaptation.
Compared with the prior art, the invention has the advantages that:
(1) The invention realizes the calculation of the fast routing path, maximizes the throughput under the condition of guaranteeing the delay, and solves the problems of low speed and small throughput of the traditional algorithm.
(2) The invention uses the supervised learning algorithm, the algorithm simplifies the route calculation process into simple input and output, multiple iterations during calculation are avoided, thereby realizing the rapid calculation of the route path, the speed of the routing algorithm is accelerated, the forwarding delay is reduced, the data packet which is discarded due to the ttl expiration is survived and successfully forwarded with higher probability, and the network throughput is increased.
(3) The invention is provided with two stages of offline training and online training, and updates parameters in a dynamic environment to select the optimal path, so that the invention has topology self-adaptability.
Drawings
FIG. 1 is a flow chart of a satellite network adaptive flow scheduling method based on deep supervised learning;
FIG. 2 is a model diagram of a satellite network adaptive flow scheduling method based on deep supervised learning;
FIG. 3 is a schematic diagram of a labeled training database;
fig. 4 is a schematic structural diagram of a BP neural network.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
Embodiments of the present invention are described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the invention provides a satellite network self-adaptive flow scheduling method based on deep supervised learning, which comprises the following steps:
s1, collecting flow matrixes at a plurality of moments from a network, and obtaining flow requirements among all node pairs at the plurality of moments.
The traffic matrix in step S1 is the traffic demand between all source and destination node pairs in the network, for example, the mth row and the nth column of the traffic matrix represent the traffic demand from node m to node n.
S2, calculating an alternative path set of all non-zero flow demand node pairs in the network by using a K shortest algorithm.
The step S2 uses a K shortest path algorithm to calculate K different loop-free alternative routes for each non-zero flow demand node pair in the network, and the K different loop-free alternative routes are used as an alternative route set of the node pair.
As shown in fig. 2, each node pair of non-zero traffic demands in the network maintains a network intelligent routing model for the routing decisions of that node pair traffic. The network controller receives updated network states (such as traffic matrix, link residual bandwidth, service end-to-end delay and the like) in real time, sends the updated network states to the network intelligent routing model of each node pair to carry out routing decision, and receives the network overall routing scheme of the current moment formed by the optimal path scheme of each node pair at the same time, so that flow scheduling is realized.
And S3, obtaining the optimal data forwarding paths of all non-zero flow demand node pairs under each flow matrix by using a tag data generation algorithm, and generating a tag data set.
Further, the step S3 includes the following sub-steps:
s31, initializing the sum of the flows of all links in the network to be 0 for each flow matrix, and sequencing the D business flows to enable the count value i=1.
S32, placing the ith service into the network topology, namely from the alternative path set P d Taking out an alternative path p, adding the occupied bandwidth of the service to the sum of the flows of links passing through the path p, and calculating the maximum link utilization rate z of the current network; and comparing the z values of all the alternative paths, and selecting the alternative path corresponding to the minimum value as a routing scheme of the service.
S33, checking whether the maximum link utilization z of the current network exceeds a preset value z max . If yes, go to step S34, otherwise go to step S36.
S34, the put post-N (N > 0) business is taken out from the network, and the demand of the N business is subtracted from the sum of the flow of the passed links.
S35, the extracted N services are reordered and put into the network again according to the current sequence, and then the step S33 is executed.
S36, if i is less than or equal to D, let i=i+1, execute step S32, otherwise, end, output the routing scheme of all traffic.
S37, the routing scheme of each service is represented by an optimal path label, and each flow matrix is provided with an optimal path label corresponding to the flow matrix on each node pair of the non-zero flow service requirement; when the routing strategies of the N traffic matrixes are calculated, each node pair generates N pieces of training data to form a training database of the node pair, namely a label data set.
After the traffic matrix is collected from the network, the optimal routing scheme of each service can be quickly solved through the steps. The routing scheme for each traffic is represented by an optimal path label, e.g. when the set of alternative paths contains 5 alternative paths, the label is represented by a 3-bit binary number, i.e. the first alternative path is represented as 000, the second alternative path is represented as 001, and so on. Thus, each traffic matrix has an optimal path label corresponding to the traffic matrix on each node pair for non-zero traffic demand. When the routing policies of the N traffic matrices are calculated, each node pair generates N pieces of training data, which form a training database of the node pair, as shown in fig. 3.
S4, performing offline training on the intelligent routing model of each non-zero flow demand node pair by using a back propagation algorithm according to the tag data set, and deploying the trained model in a satellite network.
As shown in fig. 4, the intelligent routing model is a BP fully-connected neural network; the input of the neural network model comprises network states of an SDN network, wherein the network states are network topology, a flow matrix, bandwidth requirements and time delay requirements; the BP full-connection neural network comprises an input layer, a full-connection layer and an output layer which are sequentially connected.
And (5) offline training the neural network model of each node pair by adopting a back propagation algorithm. Input quantity x i And weight w i And a given threshold b i Making a difference, and obtaining an output value y by the transfer function f i . At the same time comparing networksAnd continuously adjusting and modifying the link weight and the threshold value between each layer of the network by using a gradient descent method through the counter-propagation of the error, so that the output result is more similar to a true value, and simultaneously converges to a preset target error function value E. And changing the weight coefficient through a back propagation algorithm, randomly assigning the initial weight by a network, and then adjusting according to the iteration result of the network until the target error is met. Model training is completed when the variation values of all parameters are smaller than the iteration threshold or the maximum number of iterations is reached.
S5, collecting a real-time traffic matrix at the current moment from the network.
And S6, calculating the optimal forwarding paths of all nodes to the data route by the satellite network according to the real-time flow matrix at the current moment by using the trained intelligent routing model.
And S7, the satellite network performs data transmission according to the calculated optimal path.
S8, detecting whether the topological structure of the satellite network is changed, if so, entering a step S9, otherwise, repeating the step S8.
S9, performing online training, retraining the intelligent routing model of each node pair, and performing data transmission by using the updated intelligent routing model.
Whether the network topology is changed is detected by the network controller. When a large number of links in the network fail, if the original neural network model is still used for path prediction, the obtained path may contain failed nodes or links, so that the routing decision is deteriorated. Therefore, the network controller monitors the network topology change condition in real time, when the network topology is changed greatly, the neural network model is retrained offline and deployed, and model parameters can be adjusted to adapt to a new environment, so that the network controller has self-adaptability.
The invention realizes the calculation of the fast routing path, maximizes the throughput under the condition of guaranteeing the delay, and solves the problems of low speed and small throughput of the traditional algorithm.
Claims (6)
1. The satellite network self-adaptive flow scheduling method based on deep supervised learning is characterized by comprising the following steps of:
s1, acquiring flow matrixes at a plurality of moments from a satellite network, and obtaining flow requirements among all node pairs in the satellite network at the plurality of moments;
s2, calculating an alternative path set of all non-zero flow demand node pairs in the satellite network by using a K shortest path algorithm;
s3, obtaining optimal data forwarding paths of all non-zero flow demand node pairs under each flow matrix by using a tag data generation algorithm, and generating a tag data set, wherein the method specifically comprises the following steps of:
s31, initializing the sum of the flows of all links in a satellite network to be 0 for each flow matrix, and sequencing D business flows to enable a count value i=1;
s32, placing the ith service into the network topology, namely from the alternative path set P d Taking out an alternative path p, adding the occupied bandwidth of the service to the sum of the flows of links passing through the path p, and calculating the maximum link utilization rate z of the current network; comparing the z values of all the alternative paths, and selecting the alternative path corresponding to the minimum value as a routing scheme of the service;
s33, checking whether the maximum link utilization z of the current network exceeds a preset value z max The method comprises the steps of carrying out a first treatment on the surface of the If yes, executing step S34, otherwise executing step S36;
s34, taking out the put-in last N services from the network, wherein N is more than 0, and subtracting the demand of the N services from the sum of the flow of the links;
s35, re-ordering the extracted N services, and executing the step S33 after putting the N services into the network again according to the current sequence;
s36, if i is less than or equal to D, adding 1 to the value of i, executing the step S32, otherwise, ending, and outputting the routing scheme of all traffic services;
s37, the routing scheme of each service is represented by an optimal path label, and each flow matrix is provided with an optimal path label corresponding to the flow matrix on each node pair of the non-zero flow service requirement; when the routing strategies of the N flow matrixes are calculated, each node pair generates N pieces of training data to form a training database of the node pair, namely a label data set;
s4, performing offline training on the intelligent routing model of each non-zero flow demand node pair by using a back propagation algorithm according to the tag data set, and deploying the trained model in a satellite network;
s5, collecting a real-time flow matrix at the current moment from a network;
s6, the satellite network calculates the optimal forwarding paths of all nodes to the data route according to the real-time flow matrix at the current moment by using the trained intelligent routing model;
s7, the satellite network performs data transmission according to the calculated optimal path;
s8, detecting whether the topological structure of the satellite network is changed, if so, entering a step S9, otherwise, repeating the step S8;
s9, performing online training, retraining the intelligent routing model of each node pair, and performing data transmission by using the updated intelligent routing model.
2. The satellite network adaptive traffic scheduling method based on deep supervised learning as set forth in claim 1, characterized by the following: in the step S1, the traffic matrix is the traffic demand between all source node and destination node pairs in the satellite network, and the mth row and nth column of the traffic matrix represent the traffic demand from node m to node n.
3. The satellite network adaptive traffic scheduling method based on deep supervised learning as set forth in claim 1, characterized by the following: step S2 uses a K-shortest algorithm to calculate K different loop-free alternatives for each non-zero traffic demand node pair in the network as a set of alternatives for that node pair.
4. The satellite network adaptive traffic scheduling method based on deep supervised learning as set forth in claim 1, characterized by the following: the intelligent routing model in the step S4 is a BP fully connected neural network; the BP fully-connected neural network input comprises network states of an SDN network, wherein the network states are network topology, flow matrix, bandwidth requirements and time delay requirements; the BP full-connection neural network comprises an input layer, a full-connection layer and an output layer which are sequentially connected.
5. The satellite network adaptive traffic scheduling method based on deep supervised learning as set forth in claim 4, characterized by the following: the neural network model of each node pair is trained offline by adopting a back propagation algorithm, and the method specifically comprises the following steps:
input quantity x i And weight w i And a given threshold b i Making a difference, which is passed through a transfer function f to obtain an output value y i The method comprises the steps of carrying out a first treatment on the surface of the Meanwhile, errors of the output value and the expected value of the network are compared, and the link weight and the threshold value among all layers of the network are continuously adjusted and modified by utilizing a gradient descent method through counter propagation of the errors, so that the output result is more approximate to a true value, and simultaneously, the output result is converged to a preset target error function value E; changing a weight coefficient through a back propagation algorithm, randomly assigning an initial weight by a network, and then adjusting according to a network iteration result until a target error is met; model training is completed when the variation values of all parameters are smaller than the iteration threshold or the maximum number of iterations is reached.
6. The satellite network adaptive traffic scheduling method based on deep supervised learning as set forth in claim 1, characterized by the following: in step S9, the network controller monitors the network topology change in real time, detects whether the network topology changes, and when the network topology changes more than expected, retrains and deploys the neural network model offline, and the model parameters are adjusted to adapt to the new environment, thereby realizing self-adaptation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210106549.3A CN114629543B (en) | 2022-01-28 | 2022-01-28 | Satellite network self-adaptive flow scheduling method based on deep supervised learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210106549.3A CN114629543B (en) | 2022-01-28 | 2022-01-28 | Satellite network self-adaptive flow scheduling method based on deep supervised learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114629543A CN114629543A (en) | 2022-06-14 |
| CN114629543B true CN114629543B (en) | 2024-03-29 |
Family
ID=81898805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210106549.3A Active CN114629543B (en) | 2022-01-28 | 2022-01-28 | Satellite network self-adaptive flow scheduling method based on deep supervised learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114629543B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115150335B (en) * | 2022-06-30 | 2023-10-31 | 武汉烽火技术服务有限公司 | Optimal flow segmentation method and system based on deep reinforcement learning |
| CN116827658B (en) * | 2023-07-17 | 2024-01-16 | 青岛启弘信息科技有限公司 | AI intelligent application security situation awareness prediction system and method |
| CN116708273B (en) * | 2023-07-28 | 2023-10-31 | 中国电子科技网络信息安全有限公司 | Method for generating stopping judgment classification model, network topology detection method and device |
| CN117674961B (en) * | 2023-11-20 | 2024-05-28 | 航天恒星科技有限公司 | Low orbit satellite network time delay prediction method based on space-time feature learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109688056A (en) * | 2018-12-07 | 2019-04-26 | 南京理工大学 | Intelligent Network Control System and method |
| CN110611619A (en) * | 2019-09-12 | 2019-12-24 | 西安电子科技大学 | Intelligent routing decision method based on DDPG reinforcement learning algorithm |
| CN112187342A (en) * | 2020-09-30 | 2021-01-05 | 西安交通大学 | Satellite traffic routing method and system based on energy perception and load balancing |
| CN113472811A (en) * | 2021-08-23 | 2021-10-01 | 北京交通大学 | Heterogeneous service function chain forwarding protocol and method in intelligent fusion identification network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7609626B2 (en) * | 2004-04-16 | 2009-10-27 | Alcatel-Lucent Usa Inc. | Nodes for managing congestion and traffic flow by considering the minimization of link utilization values |
-
2022
- 2022-01-28 CN CN202210106549.3A patent/CN114629543B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109688056A (en) * | 2018-12-07 | 2019-04-26 | 南京理工大学 | Intelligent Network Control System and method |
| CN110611619A (en) * | 2019-09-12 | 2019-12-24 | 西安电子科技大学 | Intelligent routing decision method based on DDPG reinforcement learning algorithm |
| CN112187342A (en) * | 2020-09-30 | 2021-01-05 | 西安交通大学 | Satellite traffic routing method and system based on energy perception and load balancing |
| CN113472811A (en) * | 2021-08-23 | 2021-10-01 | 北京交通大学 | Heterogeneous service function chain forwarding protocol and method in intelligent fusion identification network |
Non-Patent Citations (6)
| Title |
|---|
| Local Fast Reroute With Flow Aggregation in Software Defined Networks;Xiaoning Zhang 等;IEEE Communications Letters;785-788 * |
| 分布式星群网络组网技术研究;陈浩澜 等;通信技术;1647-1657 * |
| 基于机器学习的智能路由算法综述;刘辰屹 等;计算机研究与发展(第04期);第671-687页 * |
| 宽带通信网中Valiant负载平衡技术研究;章小宁;中国博士学位论文全文数据库 信息科技辑;I136-11 * |
| 星座网络关键链路代价增量路由算法;蒋文娟;宗鹏;;解放军理工大学学报(自然科学版)(第03期);全文 * |
| 智慧标识网络域间流量工程机制研究;李佳伟;中国博士学位论文全文数据库 信息科技辑;I139-6 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114629543A (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114629543B (en) | Satellite network self-adaptive flow scheduling method based on deep supervised learning | |
| CN109818865B (en) | SDN enhanced path boxing device and method | |
| CN114697229B (en) | Construction method and application of distributed routing planning model | |
| CN113328938A (en) | Network autonomous intelligent management and control method based on deep reinforcement learning | |
| CN107317697B (en) | Route configuration method of OSPF (open shortest Path first) and SDN (software defined network) hybrid network | |
| WO2019026684A1 (en) | Route control method and route setting device | |
| CN114143264A (en) | Traffic scheduling method based on reinforcement learning in SRv6 network | |
| CN113794638B (en) | SDN data center network elephant flow scheduling method based on differential evolution algorithm | |
| CN113938415A (en) | Network route forwarding method and system based on link state estimation | |
| CN111917642A (en) | SDN intelligent routing data transmission method for distributed deep reinforcement learning | |
| CN115396366A (en) | Distributed intelligent routing method based on graph attention network | |
| Sun et al. | Improving the scalability of deep reinforcement learning-based routing with control on partial nodes | |
| Zeng et al. | Multi-agent reinforcement learning for adaptive routing: A hybrid method using eligibility traces | |
| Panayiotou et al. | A data-driven QoT decision approach for multicast connections in metro optical networks | |
| Geng et al. | Distributed and adaptive traffic engineering with deep reinforcement learning | |
| Abou El Houda et al. | Cost-efficient federated reinforcement learning-based network routing for wireless networks | |
| Ibraheem et al. | A multi QoS genetic-based adaptive routing in wireless mesh networks with Pareto solutions | |
| Almasan et al. | Enero: Efficient real-time routing optimization | |
| CN103619047B (en) | A kind of chance method for routing in many concurrently stream wireless mesh networks | |
| An et al. | Dynamically split the traffic in software defined network based on deep reinforcement learning | |
| CN114726770A (en) | Traffic engineering method applied to segmented routing network environment | |
| CN117014355A (en) | TSSDN dynamic route decision method based on DDPG deep reinforcement learning algorithm | |
| Dong et al. | Intelligent routing control for MANET based on reinforcement learning | |
| Han | Optimal routing path calculation for SDN using genetic algorithm | |
| Girgis et al. | Using GA, PSO and hybrid GA-PSO based algorithms for solving the least-cost multicast problem with QoS constraints |
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 |