CN111064667A - Satellite network route optimization method, controller and data system - Google Patents
Satellite network route optimization method, controller and data system Download PDFInfo
- Publication number
- CN111064667A CN111064667A CN201911229564.1A CN201911229564A CN111064667A CN 111064667 A CN111064667 A CN 111064667A CN 201911229564 A CN201911229564 A CN 201911229564A CN 111064667 A CN111064667 A CN 111064667A
- Authority
- CN
- China
- Prior art keywords
- satellite node
- data packet
- satellite
- sampling data
- load
- 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
- 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
- H04L45/125—Shortest path evaluation based on throughput or bandwidth
-
- 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
-
- 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
- H04B7/18578—Satellite systems for providing broadband data service to individual earth stations
- H04B7/18584—Arrangements for data networking, i.e. for data packet routing, for congestion control
-
- 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
- H04L45/123—Evaluation of link metrics
-
- 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
- H04L45/42—Centralised routing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Astronomy & Astrophysics (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention provides a satellite network route optimization method based on machine learning, a controller and a data system, wherein the method of the controller comprises the following steps: receiving a sampling data packet sent by a target satellite node of a data system at the current moment; decapsulating the sampled data packet, acquiring a queue depth field in each measurement header field included in the sampled data packet, and calculating the load capacity of each satellite node; determining the load of each satellite node and the obtained load of each link on each candidate path at the current time as a state set of the PPO model, inputting the state set into the PPO model, and obtaining the weight of the link in each candidate path at the next time at the current time; and determining the candidate path corresponding to the link with the minimum weight as a target issuing path, and issuing the target issuing path to the data system so that an intermediate satellite node in the data system forwards the sampling data packet based on the target issuing path.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a satellite network route optimization method, a controller and a data system.
Background
With the rapid development of communication technology, the demand of the current society for informatization is continuously increased, the satellite network is widely concerned due to the advantages of wide coverage range, flexible networking and small influence by geographic environment and climate conditions, and reliable satellite network routing is the key for realizing the efficient transmission of the satellite network.
Currently, a satellite Network architecture is mainly a multilayer satellite Network architecture based on an SDN (Software Defined Network), and the multilayer satellite Network architecture includes a data system and a controller. The data system comprises satellite nodes distributed all over the world, and a protocol related to the operation of the data system realizes the forwarding of a sampling data packet; the controller realizes centralized management and control of the data system, generates a satellite network routing decision and sends the decision to the data system to schedule the flow of each satellite node.
The channels linked between the satellite nodes are called links, the sampling data packets are forwarded from a plurality of satellite nodes, and the links through which the sampling data packets pass are connected to form a path. After the source satellite node receives the instruction of the controller, a plurality of intermediate satellite nodes exist between the source satellite node and the target satellite, a plurality of paths exist between the source satellite node and the target satellite, and the source satellite node forwards the sampling data packet to the target satellite node through one or more paths.
In the prior art, a satellite node connected with a target satellite node establishes a number of TCP connections not less than the number of flow service types with the target satellite according to the different flow service types, each TCP connection is called a TCP stream, the prior art obtains the transmission delay and the throughput of each TCP stream aiming at the target satellite node through a controller, then, the transmission delay and the throughput of each TCP stream aiming at the destination satellite node at the current moment are taken as the state in the state space of a DDPG (Deep Deterministic Policy Gradient) model, the state is input into the DDPG (Deep Deterministic Policy Gradient) model, the transmission proportion of the sampling data packet on each TCP stream at the next moment is predicted, and meanwhile, the weighted sum of the transmission delay and the throughput of each TCP stream at the next moment is used as a feedback value of the DDPG model, so that the DDPG model is updated. And then the controller issues the transmission proportion of the data packet to the source satellite node from the source satellite node to each TCP stream of the destination satellite node, and the source satellite node forwards the data packet to the destination satellite node according to the transmission proportion of the data packet on each TCP stream, so as to realize the flow scheduling of each satellite node.
In the prior art, the size of the state space in the DDPG model changes with the number of TCP streams, when the traffic type increases, the number of TCP streams increases, and the state space in the DDPG model also increases, which results in that the transmission ratio of the data packet on each TCP stream predicted by using the DDPG model is longer, and thus the delay of the controller in traffic scheduling of each satellite node is longer.
Disclosure of Invention
The embodiment of the invention aims to provide a satellite network route optimization method, a controller and a data system, so as to reduce the time delay of the controller in the process of dispatching the traffic of each satellite node. The specific technical scheme is as follows:
in a first aspect, a method for optimizing a satellite network route based on machine learning, provided by an embodiment of the present invention, is applied to a controller in a multilayer satellite network of a software defined network SDN, where the multilayer network further includes a data system, the data system includes a plurality of satellite nodes, and the satellite nodes include: a source satellite node, an intermediate satellite node, and a destination satellite node, a controller, and a data system, the method comprising:
receiving a sampling data packet sent by a target satellite node of a data system at the current moment;
decapsulating the sample data packet, and acquiring a queue depth field in each measurement header field included in the sample data packet, wherein one measurement header field corresponds to one satellite node;
calculating the load capacity of each satellite node based on the queue depth field in each measurement header field;
determining the load of each satellite node and the obtained load of each link on each candidate path at the current moment as a state set of a preset near-end strategy optimization PPO model, wherein the candidate path is a communication path from a source satellite node to a target satellite node;
inputting the state set into a PPO model to obtain the weight of a link in each candidate route at the next moment of the current moment;
for each candidate path, adding the weights of the links on each candidate path to obtain a weight sum, wherein the weight represents the degree of the bandwidth resources used by the link at the current moment;
determining a candidate path corresponding to the link with the minimum weight as a target issuing path, wherein the target issuing path carries data forwarding routing information among an active satellite node, an intermediate satellite node and a target satellite node;
and issuing the target issuing path to the data system so that an intermediate satellite node in the data system forwards the sampling data packet based on the target issuing path.
Optionally, the step of calculating the load amount of each satellite node based on the queue depth field in each measurement header field includes:
and for each measurement header field, determining the ratio of the value in the queue depth field in the measurement header field to the maximum queue length of the corresponding satellite node as the load capacity of the satellite node.
Optionally, the step of determining the load of each satellite node and the obtained load of each link on each candidate path at the current time as the state set of the preset PPO model includes:
determining the ratio of the obtained load of each link on each candidate path at the current moment to a first load as the load of each link after normalization, wherein the first load is the maximum load in the obtained load of each link on each candidate path at the current moment;
determining the ratio of the load capacity of each satellite node to a second load capacity as the normalized load capacity of each satellite node, wherein the second load capacity is the maximum load capacity in the load capacities of each satellite node;
and determining the load of each link after normalization and the load of each satellite node after normalization as a state set of the PPO model.
In a second aspect, an embodiment of the present invention provides a method for optimizing a satellite network route based on machine learning, which is applied to a data system in a multilayer satellite network of a software defined network SDN, where the data system includes a plurality of satellite nodes, and the satellite nodes include: the multi-layer network also comprises a controller, a communication connection between the controller and a data system, and the method comprises the following steps:
a source satellite node in a data system receives an original data packet sent by a user terminal;
when the difference value between the first time when the source satellite node receives the original data packet and the latest historical sampling time stamp at the first time is larger than a preset sampling period, decapsulating the original data packet, inserting a routing header field and a measurement header field into the header position of the decapsulated original data packet, wherein the routing header field comprises: a count field and a protocol field;
the source satellite node modifies the value in the protocol field in the routing header field into 1;
the source satellite node adds 1 to the numerical value in the counting field in the routing header field, and encapsulates the numerical value again to obtain a sampling data packet;
the source satellite node forwards the sampling data packet according to a preset target issuing path;
the method comprises the steps that a current satellite node in a data system processes a sampling data packet, the processed sampling data packet is forwarded to a next satellite node of the current satellite node according to a preset target issuing path, the current satellite node is a satellite node except a source satellite node in the data system, the target issuing path is generated by a controller based on a historical sampling data packet, and the target issuing path carries data forwarding routing information among the source satellite node, a middle satellite node and a target satellite node.
Optionally, the step of processing the sampling data packet by a current satellite node in a data system in the data system, and forwarding the processed sampling data packet to a next satellite node of the current satellite node according to the preset target delivery path includes:
receiving a sampling data packet by an intermediate satellite node in a data system;
the intermediate satellite node decapsulates the sampling data packet to obtain an decapsulated sampling data packet;
when the numerical value in the protocol field in the decapsulated sampling data packet is 1, inserting a measurement header field into a preset position of the decapsulated sampling data packet by the intermediate satellite node;
adding 1 to the numerical value in the counting field in the unsealed sampling data packet by the intermediate satellite node, and encapsulating again to obtain a first sampling data packet;
the intermediate satellite node forwards the first sampling data packet to a next satellite node according to a target issuing path;
a target satellite node in the data system receives a first sampling data packet;
the destination satellite node decapsulates the first sampling data packet;
when the numerical value in the protocol field in the first decapsulated sample data packet is 1, inserting a measurement header field into a preset position of the first decapsulated sample data packet by a destination satellite node;
the target satellite node adds 1 to the numerical value in the counting field in the first sampling data packet after decapsulation, and encapsulates the numerical value again to obtain a second sampling data packet;
the second sampled packet is forwarded to the controller.
In a third aspect, a controller provided in an embodiment of the present invention is applied to a multilayer satellite network of a software defined network SDN, where the multilayer network further includes a data system, the data system includes a plurality of satellite nodes, and the satellite nodes include: a source satellite node, an intermediate satellite node, and a destination satellite node, the controller to:
receiving a sampling data packet sent by a target satellite node of a data system at the current moment;
decapsulating the sample data packet, and acquiring a queue depth field in each measurement header field included in the sample data packet, wherein one measurement header field corresponds to one satellite node;
calculating the load capacity of each satellite node based on the queue depth field in each measurement header field;
determining the load of each satellite node and the acquired load of each link on each candidate path at the current moment as a state set of a preset PPO model, wherein the candidate path is a communication path from a source satellite node to a destination satellite node;
inputting the state set into a PPO model to obtain the weight of a link in each candidate route at the next moment of the current moment;
for each candidate path, adding the weights of the links on each candidate path to obtain a weight sum;
determining a candidate path corresponding to the link with the minimum weight as a target issuing path, wherein the target issuing path carries data forwarding routing information among an active satellite node, an intermediate satellite node, a target satellite node and a controller;
and sending the target issuing path to the data system so that an intermediate satellite node in the data system forwards the sampling data packet based on the target issuing path.
Optionally, the controller is specifically configured to:
and for each measurement header field, determining the ratio of the value in the queue depth field in the measurement header field to the maximum queue length of the corresponding satellite node as the load capacity of the satellite node.
Optionally, the controller is specifically configured to:
determining the ratio of the obtained load of each link on each candidate path at the current moment to a first load as the load of each link after normalization, wherein the first load is the maximum load in the obtained load of each link on each candidate path at the current moment;
and determining the ratio of the load capacity of each satellite node to the second load capacity as the normalized load capacity of each satellite node, wherein the second load capacity is the maximum load capacity in the load capacities of each satellite node.
And determining the load of each link after normalization and the load of each satellite node after normalization as a state set of the PPO model.
In a fourth aspect, an embodiment of the present invention provides a data system, where the data system includes: a source satellite node, an intermediate satellite node, and a destination satellite node,
the source satellite node in the data system is used for receiving an original data packet sent by a user terminal; when the difference value between the first time of receiving the original data packet and the latest historical sampling time stamp at the first time is larger than the preset sampling period, decapsulating the original data packet, and inserting a routing header field and a measurement header field into the header position of the decapsulated original data packet; modifying the value in the protocol field in the routing header field to 1; adding 1 to the numerical value in the counting field in the routing header field, and encapsulating again to obtain a sampling data packet; forwarding the sampling data packet according to a preset target issuing path, wherein the routing header field comprises: a count field and a protocol field;
the current satellite node in the data system is used for processing the sampling data packet and forwarding the processed sampling data packet to the next satellite node of the current satellite node according to a preset target issuing path, the current satellite node is a satellite node except a source satellite node in the data system, the target issuing path is generated by the controller based on historical sampling data packets, and the target issuing path carries data forwarding routing information among the source satellite node, a middle satellite node and a target satellite node.
Optionally, the current satellite node includes an intermediate satellite node and a destination satellite node, and the intermediate satellite node is configured to:
receiving a sampling data packet;
decapsulating the sampling data packet to obtain an decapsulated sampling data packet;
when the numerical value in the protocol field in the decapsulated sampling data packet is 1, inserting a measurement header field into a preset position of the decapsulated sampling data packet by the intermediate satellite node;
adding 1 to the numerical value in the counting field in the unsealed sampling data packet, and encapsulating again to obtain a first sampling data packet;
forwarding the first sampling data packet to a next satellite node according to a target issuing path;
the destination satellite node is used for:
receiving a first sampling data packet;
decapsulating the first sampling data packet, and inserting a measurement header field into a preset position of the decapsulated first sampling data packet when a numerical value in a protocol field in the decapsulated first sampling data packet is 1;
adding 1 to the numerical value in the counting field in the unsealed first sampling data packet, and encapsulating again to obtain a second sampling data packet;
the second sampled packet is forwarded to the controller.
Embodiments of the present invention further provide a computer program product containing instructions, which when run on a computer, cause the computer to perform any one of the above-mentioned methods for optimizing routing of a satellite network.
According to the satellite network route optimization method, the controller and the data system provided by the embodiment of the invention, when the method is applied to the controller end, the controller receives a sampling data packet sent by a target satellite node of the data system at the current moment; decapsulating the sample data packet, acquiring a queue depth field in each measurement header field included in the sample data packet, and calculating the load of each satellite node based on the queue depth field in each measurement header field; determining the load of each satellite node and the obtained load of each link on each candidate path at the current time as a preset state set of the PPO model, inputting the state set into the PPO model, and obtaining the weight of the link in each candidate path at the next time of the current time; for each candidate path, adding the weights of the links on each candidate path to obtain a weight sum, wherein the weight represents the degree of the bandwidth resources used by the link at the current moment; and determining the candidate path corresponding to the link with the minimum weight as a target issuing path, and issuing the target issuing path to the data system so that an intermediate satellite node in the data system forwards the sampling data packet based on the target issuing path. In the embodiment of the invention, the load of each satellite node is calculated by acquiring the queue depth field in each measurement header in the sampling data packet at the current time, the load of each link is acquired, the load of each satellite node and the acquired load of each link on each candidate path at the current time are determined as the state set of the preset PPO model, compared with the prior art, the size of the state set cannot be increased along with the increase of the traffic type, the state set is input into the PPO model, the input quantity of the preset PPO model is reduced, and then predicting the weight of the uplink of each candidate path at the next moment of the current moment, determining the weight and the minimum candidate path as a target issuing path, and issuing the target issuing path to a data system, so that the time delay of the controller for flow scheduling of each satellite node can be reduced. Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart of a method for optimizing a satellite network route according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating a method for determining a state set of a PPO model according to an embodiment of the present invention;
FIG. 3 is a flow chart of updating a PPO model provided by an embodiment of the present invention;
fig. 4 is a flowchart of another method for optimizing a satellite network route according to an embodiment of the present invention;
FIG. 5 is a flow chart of processing a sampled data packet by a current satellite node in a data system in accordance with an embodiment of the present invention;
FIG. 6 is a block diagram of a data system according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a multi-layer satellite network architecture based on SDN according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a satellite network route optimization method provided in an embodiment of the present invention is applied to a controller in a multilayer satellite network of a software defined network SDN, where the multilayer network further includes a data system, where the data system includes a plurality of satellite nodes, and each satellite node includes: a source satellite node, an intermediate satellite node, and a destination satellite node, a controller, and a data system, the method comprising:
s101, receiving a sampling data packet sent by a target satellite node of the data system at the current moment.
The satellite node in the embodiment of the present invention may be an LEO (Low Earth Orbit) satellite node, where the current time is the current time of the controller, a source satellite node in the data system receives an original data packet sent by a user terminal, and the original data packet is subjected to sampling processing by the data system to obtain a sampled data packet, and finally, the sampled data packet is sent to the controller by a destination satellite node of the data system.
S102, the sampling data packet is unpacked, and a queue depth field in each measurement header field included in the sampling data packet is obtained.
Wherein, a measurement header field corresponds to a satellite node, and the sampling data packet includes: a routing header field, a measurement header field, a packet field; measurement header field following the routing field, the routing header field includes: the method comprises a counting field, a path number field and a protocol field, wherein the counting field represents the number of times of inserting a satellite node into a measurement header field, the path number field represents the number of each candidate path between a source satellite node and a target satellite node, each candidate path is provided with a plurality of inter-satellite nodes, the number of intermediate satellite nodes on different candidate paths is different, the number of the intermediate satellite nodes or the sequence of the intermediate satellite nodes is different, the protocol field represents that a received data packet is a sampling data packet carrying a sampling task or an original data packet not carrying the sampling task, and the measurement header field comprises the following steps: the device comprises a satellite node number field and a queue depth field, wherein the satellite node number field represents the number of a satellite node for receiving a sampling data packet, the queue depth field represents the queue depth of the sampling data packet when the sampling data packet is received by the satellite node and enters a queue of the satellite node and then exits the queue, and the data packet field is a field carrying original data packet data.
As shown in table 1, the measurement header fields include:
table 1 measurement header fields
And S103, calculating the load of each satellite node based on the queue depth field in each measurement header field.
As an optional implementation manner provided by the embodiment of the present invention, for each measurement header field, a ratio of a value in a queue depth field in the measurement header field to a maximum queue length of a corresponding satellite node is determined as a load amount of the satellite node.
Wherein the maximum queue length is a value that each satellite node sets on itself.
And S104, determining the load of each satellite node and the acquired load of each link on each candidate path at the current moment as a preset state set of the PPO model.
The candidate path is a communication path from the source satellite node to the destination satellite node; the load of the link is a ratio of the number of bytes passed through the link to the link capacity, and in this embodiment, the number of bytes passed through the link may pass through a communication interface between the controller and the data system, where the communication interface is a port on a satellite node connected to two ends of the link.
As an optional implementation manner provided by the embodiment of the present invention, as shown in fig. 2, the step of S104 is implemented by the following steps:
s201, determining a ratio of the obtained load of each link on each candidate path at the current time to the first load as the load of each link after normalization.
The first load amount is the maximum load amount in the load amounts of each link on each candidate path at the acquired current time.
And S202, determining the ratio of the load capacity of each satellite node to the second load capacity as the load capacity of each satellite node after normalization.
And the second load capacity is the maximum load capacity in the load capacity of each satellite node.
And S203, determining the load of each link after normalization and the load of each satellite node after normalization as a state set of the PPO model.
Referring to fig. 1, S105, the state set is input into the PPO model, and the weight of the link in each candidate route at the next time to the current time is obtained.
It is understood that the time interval may be preset, and the time after the preset time interval is determined as the next time of the current time, with the current time as the starting point.
And S106, adding the weights of the links on each candidate path to obtain a weight sum.
Wherein the weight represents the size degree of the bandwidth resource utilized by the link at the current moment.
And S107, determining the candidate path corresponding to the link with the minimum weight as the target issuing path.
The target issuing path carries data forwarding routing information among the active satellite node, the intermediate satellite node and the target satellite node.
It can be understood that the smaller the weight of the link is, the more available bandwidth resources representing the link are, the smaller the time for transmitting the sampling data packet is, the smaller the weight and the candidate path corresponding to the smallest link are taken as the target delivery path, and the smaller the time for the satellite node in the data system to transmit the sampling data packet according to the target delivery path is, so that the routing optimization of each satellite node can be realized, and the time delay of the controller for traffic scheduling of each satellite node is reduced.
And S108, issuing the target issuing path to the data system so that an intermediate satellite node in the data system forwards the sampling data packet based on the target issuing path.
It can be understood that, after the controller issues the target delivery path to the data system, when the source satellite node in the data system receives an original data packet sent by the user terminal at the next moment of the current moment, and when the original data packet needs to be sampled, the source satellite node forwards a sampled data packet after sampling the original data packet to the intermediate satellite node according to the target delivery path, and the intermediate satellite node forwards the sampled data packet to the destination satellite node according to the target delivery path.
As an optional implementation manner provided by the embodiment of the present invention, for each measurement header field, a ratio of a value in a queue depth field in the measurement header field to a maximum queue length of a corresponding satellite node may be determined as a load amount of the satellite node, so as to implement the step of S103.
As an optional implementation manner provided by the embodiment of the present invention, as shown in fig. 3, after the step of inputting the state set into the PPO model to obtain the weight of the link in each candidate route at the next time of the current time, the method for optimizing a satellite network route provided by the embodiment of the present invention further includes:
and S301, taking the first load as a first feedback value of the PPO model.
The first load amount is the maximum load amount in the load amounts of the links on each candidate path at the acquired current time.
And S302, when the first feedback value is smaller than or equal to the second feedback value, adjusting the weight of the PPO model, and taking the PPO model after the weight is adjusted as an updated PPO model.
The second feedback value is a negative value of a third load, and the third load is a maximum load in the load of each link on each candidate path at the next moment when the current moment is obtained.
Compared with the prior art, the first load is used as the feedback value of the PPO model, the PPO model is updated by adjusting the weight of the PPO model, and the accuracy of the PPO model can be improved.
As shown in fig. 4, another satellite network route optimization method provided in an embodiment of the present invention is applied to a data system in a multilayer satellite network of an SDN, where the data system includes a plurality of satellite nodes, and the satellite nodes include: the multi-layer network also comprises a controller, and communication connection between the controller and a data system, and the method comprises the following steps:
s401, a source satellite node in a data system receives an original data packet sent by a user terminal.
S402, when the difference value between the first time when the source satellite node receives the original data packet and the latest historical sampling time stamp at the first time is larger than the preset sampling period, the original data packet is unpacked, and a routing header field and a measurement header field are inserted into the packet head position of the unpacked original data packet.
The historical sampling time stamp records the time of inserting the measurement header field into the source satellite node each time before the current time, and is stored in a register of the source satellite node. The routing header fields include: the counting field indicates the number of times the satellite node inserts the measurement header field, and the protocol field indicates that the received data packet is a sampling data packet carrying a sampling task or an original data packet not carrying the sampling task.
Illustratively, the first time to receive the original packet is 10: 00, the source satellite node inserts the measurement header field into the original data packet sent by the user terminal at 9:00, and the source satellite node inserts the measurement header field into the original data packet sent by the user terminal at 7:00, then the first time 10: 00 the most recent historical sample timestamp is 9: 00.
And S403, the source satellite node modifies the value in the protocol field in the routing header field into 1.
And S404, the source satellite node adds 1 to the numerical value in the counting field in the routing header field, and encapsulates the numerical value again to obtain a sampling data packet.
S405, the source satellite node forwards the sampling data packet according to a preset target issuing path.
And S406, the current satellite node in the data system processes the sampling data packet, and forwards the processed sampling data packet to the next satellite node of the current satellite node according to a preset target delivery path.
The current satellite node is a satellite node except a source satellite node in a data system, the target issuing path is generated by the controller based on a historical sampling data packet, the target issuing path carries data forwarding routing information among the source satellite node, an intermediate satellite node and a target satellite node, and the historical sampling data packet refers to a sampling data packet of a measurement header field and a routing field inserted into the source satellite node at the current moment.
It can be understood that satellite nodes on two candidate paths in a multilayer satellite network of the whole SDN may overlap, the overlapped satellite nodes are often very important satellite nodes, the current satellite node processes a sampling data packet, the processed sampling data packet is forwarded to a next satellite node of the current satellite node according to a preset target issuing path, and each satellite node on the target issuing path is sequentially inserted into a measurement header field until reaching a target satellite node, so that the load of the satellite node on the candidate path of the satellite node overlapping with the target issuing path can be collected.
It can be understood that the initial time is 0, that is, the historical sampling timestamp only includes the time of the initial time, and at this time, the source satellite node determines whether a difference between the first time of receiving the original data packet for the first time and the initial time 0 is greater than a preset sampling period.
The preset target issuing path refers to a target issuing path at the current moment, when the controller processes a measurement header field in a sampling data packet at the previous moment of the current moment, the target issuing path at the current moment is obtained and then is sent to the data system, and each satellite node in the data system stores the target issuing path and then serves as the preset target issuing path.
As an optional implementation manner provided by the embodiment of the present invention, as shown in fig. 5, the step S406 may be implemented by the following steps:
s501, an intermediate satellite node in the data system receives a sampling data packet.
And S502, the intermediate satellite node decapsulates the sampling data packet to obtain the decapsulated sampling data packet.
And S503, when the value in the protocol field in the decapsulated sampling data packet is 1, the intermediate satellite node inserts a measurement header field in the preset position of the decapsulated sampling data packet.
Wherein the preset position is a position adjacent after the measurement header field farthest from the route header field.
It is understood that the value in the protocol field is 1, which indicates that the received packet is a sampling packet carrying a sampling task, and the value in the protocol field is 0, which indicates that the received packet is an original packet not carrying a sampling task.
And S504, the intermediate satellite node adds 1 to the numerical value in the counting field in the unsealed sampling data packet, and encapsulates the numerical value again to obtain a first sampling data packet.
It will be appreciated that when the count field has the same value as the number of measurement header fields and the number of satellite nodes inserted into the measurement header fields.
And S505, the intermediate satellite node forwards the first sampling data packet to the next satellite node according to the target issuing path.
S506, when the next satellite node is the target satellite node, the destination satellite node in the data system receives the first sampling data packet.
And S507, the target satellite node decapsulates the first sampling data packet, and when the numerical value in the protocol field in the decapsulated first sampling data packet is 1, the target satellite node inserts a measurement header field in the preset position of the decapsulated first sampling data packet.
And S508, adding 1 to the numerical value in the counting field in the first unsealed sampling data packet by the destination satellite node, and encapsulating again to obtain a second sampling data packet.
S509, the second sampling data packet is forwarded to the controller.
As an optional implementation manner provided by the embodiment of the present invention, when the next satellite node is not the target satellite node, the next satellite node is an intermediate satellite node, the intermediate satellite node in the data system is repeatedly executed to receive the sampling data packet, decapsulate the sampling data packet, obtain an decapsulated sampling data packet, when a value in a protocol field in the sampling data packet is 1, a measurement header field is inserted into a preset position of the decapsulated sampling data packet, add 1 to a value in a count field in the decapsulated sampling data packet, and perform decapsulation again, obtain a first sampling data packet, and forward the first sampling data packet to the next satellite node according to a preset target delivery path until the next satellite node is the target satellite node.
It can be understood that, when the next satellite node is not the target satellite node, the next satellite node is an intermediate satellite node, and each intermediate satellite needs to execute steps S501 to S505 after receiving the sampling data packet forwarded by the previous intermediate satellite node according to the numbering sequence of the satellite nodes in the target delivery path, so that when the target satellite receives the first sampling data packet sent by the previous intermediate satellite, the first sampling data packet includes each satellite node before the target satellite node in the target delivery path, and the inserted measurement header field indicates that the load of each satellite node before the target satellite node is collected, and thus, the load condition of each satellite in the data system of the multi-layer satellite network of the SDN in the current time network environment can be obtained.
As an optional implementation manner provided in the embodiment of the present invention, after the step of receiving, by a source satellite node in a data system, an original data packet sent by a user terminal, the method further includes:
when the difference value between the first moment when the source satellite node receives the original data packet sent by the user terminal and the latest historical sampling timestamp which is away from the first moment is not more than the preset sampling period, the original data packet is forwarded to the target satellite node according to a preset target issuing path.
In the implementation of the invention, when the difference value between the first moment when the source satellite node receives the original data packet and the latest historical sampling timestamp which is away from the first moment is not more than the preset sampling period, the satellite node is not required to be sampled at the moment, the numerical value in the protocol field is modified to be 0, and the satellite node on the target issuing path is not required to be inserted into the measurement header field.
After the source satellite node receives the original data packet, whether the load condition of the source satellite node needs to be sampled is determined by judging whether the sampling period is reached, when the sampling is needed, a measurement header field and a routing field are inserted into the original data packet to obtain a sampling data packet, the sampling data packet is forwarded to a current satellite node, and after the measurement header field is inserted again into the current satellite node, the processed sampling data packet is forwarded to a next satellite node of the current satellite node according to a preset target issuing path, so that the sampling process of the satellite node is realized, and a controller receives the sampling data packet after the sampling processing is performed by a data system, and then the process of the target issuing path at the next moment is obtained.
The controller provided by the embodiment of the invention is applied to a multilayer satellite network of an SDN, the multilayer network further comprises a data system, the data system comprises a plurality of satellite nodes, and the satellite nodes comprise: a source satellite node, an intermediate satellite node, and a destination satellite node, the controller to:
and receiving a sampling data packet sent by a destination satellite node of the data system at the current moment.
And decapsulating the sample data packet, and obtaining a queue depth field in each measurement header field included in the sample data packet, wherein one measurement header field corresponds to one satellite node.
The amount of load of each satellite node is calculated based on the queue depth field in each measurement header field.
And determining the load of each satellite node and the acquired load of each link on each candidate path at the current time as a preset state set of the PPO model.
The candidate path is a communication path between the source satellite node and the destination satellite node.
And inputting the state set into the PPO model to obtain the weight of the link in each candidate route at the next moment of the current moment.
For each candidate path, adding the weights of the links on each candidate path to obtain a weight sum;
and determining the candidate path corresponding to the link with the minimum weight as a target issuing path, wherein the target issuing path carries data forwarding routing information among the active satellite node, the intermediate satellite node, the target satellite node and the controller.
And sending the target issuing path to the data system so that an intermediate satellite node in the data system forwards the sampling data packet based on the target issuing path.
Optionally, the controller is specifically configured to:
and for each measurement header field, determining the ratio of the value in the queue depth field in the measurement header field to the maximum queue length of the corresponding satellite node as the load capacity of the satellite node.
As an optional implementation provided in the embodiment of the present invention, the controller is specifically configured to:
and determining the ratio of the obtained load of each link on each candidate path at the current moment to the first load as the load of each link after normalization.
The first load amount is the maximum load amount in the load amounts of each link on each candidate path at the acquired current time.
And determining the ratio of the load capacity of each satellite node to the second load capacity as the normalized load capacity of each satellite node, wherein the second load capacity is the maximum load capacity in the load capacities of each satellite node.
And determining the load of each link after normalization and the load of each satellite node after normalization as a state set of the PPO model.
As shown in fig. 6, a data system provided in an embodiment of the present invention includes: a source satellite node, an intermediate satellite node, and a destination satellite node,
the source satellite node in the data system is used for receiving an original data packet sent by a user terminal; when the difference value between the first time of receiving the original data packet and the latest historical sampling time stamp at the first time is larger than the preset sampling period, decapsulating the original data packet, and inserting a routing header field and a measurement header field into the header position of the decapsulated original data packet; modifying the value in the protocol field in the routing header field to 1; adding 1 to the numerical value in the counting field in the routing header field, and encapsulating again to obtain a sampling data packet; and forwarding the sampling data packet according to a preset target issuing path.
The current satellite node in the data system is used for processing the sampling data packet and forwarding the processed sampling data packet to the next satellite node of the current satellite node according to a preset target issuing path, the current satellite node is a satellite node except a source satellite node in the data system, the target issuing path is generated by the controller based on the historical sampling data packet, and the target issuing path carries data forwarding routing information among the source satellite node, the middle satellite node and the target satellite node.
As an optional implementation provided by the embodiment of the present invention, as shown in fig. 6, the current satellite node may include a plurality of intermediate satellite nodes and a destination satellite node, where the intermediate satellite nodes are configured to:
a sampled data packet is received.
And unsealing the sampling data packet to obtain the unsealed sampling data packet.
And when the value in the protocol field in the unpacked sampling data packet is 1, the middle satellite node inserts a measurement header field in the preset position of the unpacked sampling data packet.
And adding 1 to the numerical value in the counting field in the unsealed sampling data packet, and encapsulating again to obtain a first sampling data packet.
And forwarding the first sampling data packet to the next satellite node according to the target issuing path.
The destination satellite node is used for:
a first sampled packet is received.
And decapsulating the first sampling data packet, and inserting a measurement header field into a preset position of the decapsulated first sampling data packet when a numerical value in a protocol field in the decapsulated first sampling data packet is 1.
And adding 1 to the numerical value in the counting field in the unsealed first sampling data packet, and encapsulating again to obtain a second sampling data packet.
The second sampled packet is forwarded to the controller.
As shown in fig. 7, a multi-layer satellite network of a software defined network SDN according to an embodiment of the present invention includes a controller of a satellite network route optimization method according to any one of the above embodiments of the present invention, and a data system of another satellite network route optimization method according to any one of the above embodiments of the present invention.
In the embodiment of the invention, the load of each satellite node is calculated by acquiring the queue depth field in each measurement header in the sampling data packet at the current time, the load of each link is acquired at the same time, the load of each satellite node and the acquired load of each link on each candidate path at the current time are determined as the state set of the preset PPO model, the size of the state set cannot be increased along with the increase of the type of the sampling data packet, the state set is input into the PPO model, the input quantity of the preset PPO model is reduced, then the weight of the link on each candidate path at the next time at the current time is predicted, the candidate path with the minimum weight is determined as the target issuing path, and the target issuing path is issued to the data system, so that the time delay of flow scheduling of each satellite node by a controller can be reduced.
In yet another embodiment of the present invention, a computer-readable storage medium is further provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of any one of the above-mentioned satellite network route optimization methods.
In yet another embodiment provided by the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any one of the above-described embodiments of the method for satellite network route optimization.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A satellite network route optimization method based on machine learning is applied to a controller in a multilayer satellite network of a Software Defined Network (SDN), the multilayer network further comprises a data system, the data system comprises a plurality of satellite nodes, and the satellite nodes comprise: a source satellite node, an intermediate satellite node, and a destination satellite node, the controller communicatively coupled to the data system, the method comprising:
receiving a sampling data packet sent by a target satellite node of the data system at the current moment;
decapsulating the sample data packet, and obtaining a queue depth field in each measurement header field included in the sample data packet, wherein one measurement header field corresponds to one satellite node;
calculating the load capacity of each satellite node based on the queue depth field in each measurement header field;
determining the load of each satellite node and the obtained load of each link on each candidate path at the current time as a state set of a preset near-end strategy optimization (PPO) model, wherein the candidate path is a communication path from the source satellite node to the destination satellite node;
inputting the state set into the PPO model to obtain the weight of the link in each candidate route at the next moment of the current moment;
for each candidate path, adding the weights of the links on each candidate path to obtain a weight sum, wherein the weight represents the size degree of the utilized bandwidth resource of the link at the current moment;
determining the candidate path corresponding to the link with the minimum weight as a target issuing path, wherein the target issuing path carries data forwarding routing information among an active satellite node, an intermediate satellite node and a target satellite node;
and issuing the target issuing path to a data system so that the intermediate satellite node in the data system forwards a sampling data packet based on the target issuing path.
2. The method according to claim 1, wherein the step of calculating the load amount of each satellite node based on the queue depth field in each measurement header field comprises:
and for each measurement header field, determining the ratio of the value in the queue depth field in the measurement header field to the maximum queue length of the corresponding satellite node as the load capacity of the satellite node.
3. The method according to claim 1, wherein the step of determining the load of each satellite node, the obtained load of each link on each candidate path at the current time, as the state set of the preset near-end policy optimization PPO model comprises:
determining the ratio of the obtained load of each link on each candidate path at the current moment to a first load as the load of each link after normalization, wherein the first load is the maximum load in the obtained load of each link on each candidate path at the current moment;
determining a ratio of the load capacity of each satellite node to a second load capacity as the normalized load capacity of each satellite node, wherein the second load capacity is the maximum load capacity in the load capacities of each satellite node;
and determining the load of each link after normalization and the load of each satellite node after normalization as the state set of the PPO model.
4. A satellite network route optimization method based on machine learning is applied to a data system in a multilayer satellite network of a Software Defined Network (SDN), wherein the data system comprises a plurality of satellite nodes, and the satellite nodes comprise: the multi-layer network further comprises a controller, the controller is in communication connection with the data system, and the method comprises the following steps:
the source satellite node in the data system receives an original data packet sent by a user terminal;
when the difference value between the first time when the source satellite node receives the original data packet and the latest historical sampling timestamp which is away from the first time is greater than a preset sampling period, decapsulating the original data packet, inserting a routing header field and a measurement header field into a packet header position of the decapsulated original data packet, wherein the routing header field comprises: a count field and a protocol field;
the source satellite node modifies the value in the protocol field in the routing header field to 1;
the source satellite node adds 1 to the numerical value in the counting field in the routing header field and encapsulates the numerical value again to obtain a sampling data packet;
the source satellite node forwards the sampling data packet according to a preset target issuing path;
the current satellite node in the data system processes the sampling data packet, and forwards the processed sampling data packet to a next satellite node of the current satellite node according to the preset target issuing path, wherein the current satellite node is a satellite node except the source satellite node in the data system, the target issuing path is generated by the controller based on a historical sampling data packet, and the target issuing path carries data forwarding routing information among the source satellite node, the middle satellite node and the target satellite node.
5. The method according to claim 4, wherein the step of processing the sampling data packet by a current satellite node in the data system and forwarding the processed sampling data packet to a next satellite node of the current satellite node according to the preset target delivery path comprises:
receiving the sampled data packet by the intermediate satellite node in the data system;
the intermediate satellite node decapsulates the sampling data packet to obtain an decapsulated sampling data packet;
when the numerical value in the protocol field in the decapsulated sampling data packet is 1, inserting a measurement header field into a preset position of the decapsulated sampling data packet by the intermediate satellite node;
the intermediate satellite node adds 1 to the numerical value in the counting field in the unpacked sampling data packet, and encapsulates the counting field again to obtain a first sampling data packet;
the intermediate satellite node forwards the first sampling data packet to a next satellite node according to the target issuing path;
a destination satellite node in the data system receives the first sampling data packet;
the destination satellite node decapsulates the first sampling data packet;
when the numerical value in the protocol field in the decapsulated first sampling data packet is 1, inserting a measurement header field into the destination satellite node at a preset position of the decapsulated first sampling data packet;
the destination satellite node adds 1 to the numerical value in the counting field in the decapsulated first sampling data packet, and encapsulates the numerical value again to obtain a second sampling data packet;
forwarding the second sampled packet to the controller.
6. A controller, applied to a multilayer satellite network of a software defined network SDN, the multilayer network further including a data system, the data system including a plurality of satellite nodes, the satellite nodes including: a source satellite node, an intermediate satellite node, and a destination satellite node, the controller to:
receiving a sampling data packet sent by a target satellite node of the data system at the current moment;
decapsulating the sample data packet, and obtaining a queue depth field in each measurement header field included in the sample data packet, wherein one measurement header field corresponds to one satellite node;
calculating the load capacity of each satellite node based on the queue depth field in each measurement header field;
determining the load of each satellite node and the obtained load of each link on each candidate path at the current time as a state set of a preset near-end strategy optimization (PPO) model, wherein the candidate path is a communication path from the source satellite node to the destination satellite node;
inputting the state set into the PPO model to obtain the weight of the link in each candidate route at the next moment of the current moment;
for each candidate path, adding the weights of the links on each candidate path to obtain a weight sum;
determining the candidate path corresponding to the link with the minimum weight as a target issuing path, wherein the target issuing path carries data forwarding routing information among an active satellite node, an intermediate satellite node, a target satellite node and a controller;
and sending the target issuing path to a data system so that the intermediate satellite node in the data system forwards a sampling data packet based on the target issuing path.
7. The controller according to claim 6, characterized in that the controller is specifically configured to:
and for each measurement header field, determining the ratio of the value in the queue depth field in the measurement header field to the maximum queue length of the corresponding satellite node as the load capacity of the satellite node.
8. The controller according to claim 6, characterized in that the controller is specifically configured to:
determining the ratio of the obtained load of each link on each candidate path at the current moment to a first load as the load of each link after normalization, wherein the first load is the maximum load in the obtained load of each link on each candidate path at the current moment;
determining a ratio of the load capacity of each satellite node to a second load capacity as the normalized load capacity of each satellite node, wherein the second load capacity is the maximum load capacity in the load capacities of each satellite node;
and determining the load of each link after normalization and the load of each satellite node after normalization as the state set of the PPO model.
9. A data system, characterized in that the system comprises: a source satellite node, an intermediate satellite node, and a destination satellite node,
the source satellite node in the data system is used for receiving an original data packet sent by a user terminal; when the difference value between the first time of receiving the original data packet and the latest historical sampling time stamp at the first time is larger than a preset sampling period, decapsulating the original data packet, and inserting a routing header field and a measurement header field into the header position of the decapsulated original data packet; modifying the value in the protocol field in the routing header field to 1; adding 1 to the numerical value in the counting field in the routing header field, and encapsulating again to obtain a sampling data packet; forwarding the sampling data packet according to a preset target issuing path, wherein the routing header field comprises: a count field and a protocol field;
the current satellite node in the data system is used for processing the sampling data packet and forwarding the processed sampling data packet to a next satellite node of the current satellite node according to the preset target delivery path, the current satellite node is a satellite node except the source satellite node in the data system, the target delivery path is generated by the controller based on a historical sampling data packet, and the target delivery path carries data forwarding routing information among the source satellite node, the middle satellite node and the target satellite node.
10. The data system of claim 9, wherein the current satellite node comprises an intermediate satellite node and a destination satellite node, the intermediate satellite node configured to:
receiving the sampling data packet;
decapsulating the sampling data packet to obtain an decapsulated sampling data packet;
when the numerical value in the protocol field in the decapsulated sampling data packet is 1, inserting a measurement header field into a preset position of the decapsulated sampling data packet by the intermediate satellite node;
adding 1 to the numerical value in the counting field in the unsealed sampling data packet, and encapsulating again to obtain a first sampling data packet;
forwarding the first sampling data packet to a next satellite node according to the target issuing path;
the destination satellite node is configured to:
receiving the first sampling data packet;
decapsulating the first sampling data packet, and inserting a measurement header field into a preset position of the decapsulated first sampling data packet when a numerical value in a protocol field in the decapsulated first sampling data packet is 1;
adding 1 to the numerical value in the counting field in the unsealed first sampling data packet, and encapsulating again to obtain a second sampling data packet;
forwarding the second sampled packet to the controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911229564.1A CN111064667A (en) | 2019-12-04 | 2019-12-04 | Satellite network route optimization method, controller and data system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911229564.1A CN111064667A (en) | 2019-12-04 | 2019-12-04 | Satellite network route optimization method, controller and data system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111064667A true CN111064667A (en) | 2020-04-24 |
Family
ID=70299923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911229564.1A Pending CN111064667A (en) | 2019-12-04 | 2019-12-04 | Satellite network route optimization method, controller and data system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111064667A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111835407A (en) * | 2020-07-09 | 2020-10-27 | 北京邮电大学 | Low-earth-orbit satellite network flow optimization method and device |
| CN112565078A (en) * | 2020-11-20 | 2021-03-26 | 普联技术有限公司 | Network routing method, device, equipment and computer readable storage medium |
| CN113037632A (en) * | 2021-02-26 | 2021-06-25 | 中国电子科技集团公司第五十四研究所 | Space-based network resource scheduling method based on path identification |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9094856B1 (en) * | 2014-02-25 | 2015-07-28 | Intelligent Fusion Technology, Inc. | Routing method for satellite communication network |
| CN107346988A (en) * | 2017-06-20 | 2017-11-14 | 大连大学 | A kind of appearance based on low-track satellite network late/hold circuit network route computing method |
| CN108307435A (en) * | 2018-01-29 | 2018-07-20 | 大连大学 | A kind of multitask route selection method based on SDSIN |
| CN110113783A (en) * | 2019-05-31 | 2019-08-09 | 中国科学技术大学 | A method of realizing the satellite network multihop routing of joint awareness driven |
-
2019
- 2019-12-04 CN CN201911229564.1A patent/CN111064667A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9094856B1 (en) * | 2014-02-25 | 2015-07-28 | Intelligent Fusion Technology, Inc. | Routing method for satellite communication network |
| CN107346988A (en) * | 2017-06-20 | 2017-11-14 | 大连大学 | A kind of appearance based on low-track satellite network late/hold circuit network route computing method |
| CN108307435A (en) * | 2018-01-29 | 2018-07-20 | 大连大学 | A kind of multitask route selection method based on SDSIN |
| CN110113783A (en) * | 2019-05-31 | 2019-08-09 | 中国科学技术大学 | A method of realizing the satellite network multihop routing of joint awareness driven |
Non-Patent Citations (1)
| Title |
|---|
| 李倩等: "《基于P4和机器学习的路由选择方案探讨》", 《邮电设计技术》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111835407A (en) * | 2020-07-09 | 2020-10-27 | 北京邮电大学 | Low-earth-orbit satellite network flow optimization method and device |
| CN112565078A (en) * | 2020-11-20 | 2021-03-26 | 普联技术有限公司 | Network routing method, device, equipment and computer readable storage medium |
| CN113037632A (en) * | 2021-02-26 | 2021-06-25 | 中国电子科技集团公司第五十四研究所 | Space-based network resource scheduling method based on path identification |
| CN113037632B (en) * | 2021-02-26 | 2021-12-17 | 中国电子科技集团公司第五十四研究所 | Space-based network resource scheduling method based on path identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101086545B1 (en) | Method for determining network proximity for global traffic load balancing using passive tcp performance instrumentation | |
| EP1705845B1 (en) | Load distributing method | |
| US7760718B2 (en) | Taxonomy based multiple ant colony optimization approach for routing in mobile ad hoc networks | |
| CN111064667A (en) | Satellite network route optimization method, controller and data system | |
| EP3780542A1 (en) | Data transmission method and device | |
| JP5645269B2 (en) | Network system | |
| CN103999409A (en) | Method for link buffer size and queue length estimation for bandwidth-varying mobile data networks | |
| CN112039796B (en) | Data packet transmission method and device, storage medium and electronic equipment | |
| CN112583636B (en) | Construction method of government network slice, electronic equipment and storage medium | |
| CN113676550B (en) | Network message time delay deterministic transmission method based on SRv and network measurement | |
| JP6647179B2 (en) | Route conversion control device, route conversion control method, and route conversion control program | |
| Syambas et al. | Performance Comparison of Named Data and IP-based Network-Case Study on the Indonesia Higher Education Network. | |
| Lou et al. | Boosting or hindering: AoI and throughput interrelation in routing-aware multi-hop wireless networks | |
| US11190430B2 (en) | Determining the bandwidth of a communication link | |
| US20110026533A1 (en) | Method and apparatus for advertising update messages to peers and peer groups in a border gateway protocol process | |
| Shahri et al. | Enhancing mqtt with real-time and reliable communication services | |
| US7571241B1 (en) | Method and apparatus for advertising update messages to peers and peer groups in a border gateway protocol process | |
| CN106105282A (en) | Link buffer zone state is utilized to carry out the system and method for traffic engineering | |
| US20080137678A1 (en) | Communication Device, Routing Method, and Program | |
| CN112436951A (en) | Method and device for predicting flow path | |
| CN115486041B (en) | Data message format for communication across different networks | |
| CN115277504A (en) | Network traffic monitoring method, device and system | |
| US9059917B2 (en) | Technique for processing flows in a communications network | |
| Mikheev et al. | Performance of transport connection with selective failure mode when competing for throughput of data transmission path | |
| US11025519B2 (en) | Systems, methods and computer-readable media for external non-intrusive packet delay measurement |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200424 |