CN116073889B - Satellite communication network architecture based on semantic content - Google Patents

Satellite communication network architecture based on semantic content Download PDF

Info

Publication number
CN116073889B
CN116073889B CN202310100292.5A CN202310100292A CN116073889B CN 116073889 B CN116073889 B CN 116073889B CN 202310100292 A CN202310100292 A CN 202310100292A CN 116073889 B CN116073889 B CN 116073889B
Authority
CN
China
Prior art keywords
semantic
satellite
anchor point
resource management
service
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
Application number
CN202310100292.5A
Other languages
Chinese (zh)
Other versions
CN116073889A (en
Inventor
谢卓辰
周豪
吴妍君
晏睦彪
韩欣洋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Engineering Center for Microsatellites
Innovation Academy for Microsatellites of CAS
Original Assignee
Shanghai Engineering Center for Microsatellites
Innovation Academy for Microsatellites of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Engineering Center for Microsatellites, Innovation Academy for Microsatellites of CAS filed Critical Shanghai Engineering Center for Microsatellites
Priority to CN202310100292.5A priority Critical patent/CN116073889B/en
Publication of CN116073889A publication Critical patent/CN116073889A/en
Application granted granted Critical
Publication of CN116073889B publication Critical patent/CN116073889B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/14—Relay systems
    • H04B7/15—Active relay systems
    • H04B7/185—Space-based or airborne stations; Stations for satellite systems
    • H04B7/1851—Systems using a satellite or space-based relay
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Astronomy & Astrophysics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention relates to a satellite communication network architecture based on semantic content, comprising: the application layer comprises a semantic layer, the semantic layer is used for extracting semantic information and semantic tags of satellite communication data, and the application layer, the transmission layer and the network layer generate semantic content data packets according to the semantic information and the semantic tags; the system comprises at least one virtual anchor point, wherein the virtual anchor point comprises at least one satellite and a resource management node, the resource management node is used for managing each satellite in the virtual anchor point, and each satellite is used for acquiring a semantic content data packet and communicating based on a semantic content data packet protocol. The satellite communication network architecture realizes the functions of distributed caching and collaborative storage among the satellite groups, has high resource utilization rate of the space-based satellite communication network, can improve the transmission efficiency of space-based information, the fault tolerance rate of space-based communication and the service efficiency, and realizes the high-efficiency and high-quality communication of the space-based satellite communication network.

Description

Satellite communication network architecture based on semantic content
Technical Field
The invention mainly relates to the technical field of satellite communication network architecture, in particular to a satellite communication network architecture based on semantic content.
Background
The space-earth integrated information network is an important research direction of the current communication network technology, and is based on a space-based satellite communication network, an air-based communication network and a ground land communication network to realize space-earth information network integrated coordination, so that a global communication network for realizing everything interconnection by the space-earth integrated information network is formed.
The space-based satellite communication network has become an important component of a modern communication mode because of the advantages of wide coverage range, long communication distance and the like. However, with the development of mobile communications, especially the requirements of 5g+ technology and 6G technology for communication rate and communication data volume are continuously improved, which continuously approaches to the communication theoretical limit of information theory, the space-based satellite communication network has the problems of limited communication resources, low actual utilization rate of spectrum resources, large time delay of user request, difficult inter-satellite management and the like, so that the space-based satellite communication network is difficult to meet the continuously-increased requirements of the current mobile communication service. How to construct a space-based communication network architecture, so that the resource utilization rate of a space-based satellite communication network is improved, and the space-based satellite communication network is realized to realize high-efficiency and high-quality communication; the reasonable allocation and full utilization of the resources among the space bases are realized, the time delay of the user request is reduced, the multi-hop transmission among the satellites is reduced, the service content is cached as required, and the service content is distributed as required; the method realizes the collaborative management and allocation of the space-based relay nodes of the space-based satellite communication network, and is a problem to be solved in the development of the current space-based satellite communication network.
Current semantic communication technology is proposed to improve the communication bandwidth utilization rate to save communication resources, for example, in a manner based on cloud computing, fog computing and the like, so that time delay optimization of an space-based satellite communication network can be realized. The space-based satellite communication network is mainly based on network reconstruction, and the problem of space-based satellite network collaborative management is solved by designing a virtualization node to realize a routing algorithm and the like. The patent CN114615499a provides a semantic optical communication system and a method for image transmission, the system provides a change module and a picture coding module, the first change module performs semantic coding on a picture by using the picture coding module after cutting the picture by increasing the number of picture channels, and performs semantic decoding on a receiving end and then transmits the picture recovered by the transform module based on the semantic. Patent CN113315972a proposes a semantic-based video semantic communication method, by constructing a multi-layer signal perception network and a semantic abstraction network, extracting structural semantic features of video signals based on the signal perception network and the semantic abstraction network in a hierarchical knowledge base, then reconstructing the video signals according to the structural semantic features by using a semantic reconstruction network and a signal reconstruction network in the hierarchical knowledge base, and characterizing the semantics by mining semantic features of different scales and using a structural data structure, thereby realizing the semantic-based video semantic communication method.
Patent CN109525304a provides a spatial intelligent network architecture integrating sensing, computing and storage, is compatible with IP (Internet Protocol) networks, realizes data transmission and content sensing integration, and applies cross-layer cooperative service with the networks. The space router with the content perception capability is provided, the content is detected in the content storage, the on-line storage transmission is realized, the transmission delay is reduced, and the resource and energy consumption is reduced. Patent CN107343025a provides a distributed satellite cloud and fog network architecture and a time delay optimization method under energy consumption constraint, where the distributed satellite cloud and fog network architecture includes a satellite cloud layer, an access layer and a cloud computing layer. Under the energy consumption constraint, a time delay optimization strategy model under the energy consumption constraint is constructed by constructing an undirected graph of the distributed satellite cloud and fog network architecture, and a time delay optimization strategy under the energy consumption constraint condition is determined.
Patent CN110012558A provides a satellite network architecture with network reconfiguration capabilities, including a space-based network and a terrestrial backbone network. In the space-based network, the geosynchronous orbit satellites form a space-based backbone network, the low orbit satellite constellation forms a space-based access network, the remote sensing satellites, the meteorological satellites, the navigation satellites and the like form a space-based sensing network, the architecture design problem of the space-based information network by combining and utilizing high, medium and low orbit satellites to realize the cooperative work of communication, navigation and remote sensing satellites is solved, the integrated utilization of various satellite resources in the existing space is realized, and the satellite network architecture with the mixed isomerism and the satellite network flexible reconstruction function is built. Patent CN113543173a provides a network element deployment architecture and a network element deployment method of a satellite 5G converged network, which comprise an access network centralized unit deployed at a high-orbit satellite node and an access network distributed unit deployed at a low-orbit satellite node, and service coordination and migration are realized among satellite nodes through laser or microwave links. Through the high-low rail collaborative networking architecture, the high-efficiency utilization of network resources is realized, and the network opening capability is provided.
The satellite communication network architecture in the prior art still has the problems of low space-based information transmission efficiency and low space-based satellite communication quality.
Disclosure of Invention
The technical problem to be solved by the application is to provide a satellite communication network architecture based on semantic content, wherein the utilization rate of space-based satellite communication network resources in the network architecture is high, the transmission efficiency of space-based information can be improved, and the high-efficiency and high-quality communication of the space-based satellite communication network can be realized.
The technical scheme adopted by the application for solving the technical problems is a satellite communication network architecture based on semantic content, comprising: the application layer comprises a semantic layer, the semantic layer is used for extracting semantic information and semantic tags of satellite communication data, and the application layer, the transmission layer and the network layer generate semantic content data packets according to the semantic information and the semantic tags; the system comprises at least one virtual anchor point, wherein the virtual anchor point comprises at least one satellite and a resource management node, the resource management node is used for managing each satellite in the virtual anchor point, and each satellite is used for acquiring a semantic content data packet and communicating based on a semantic content data packet protocol.
In one embodiment of the application, the semantic layer comprises: the semantic layer extracts semantic information of satellite communication data according to the semantic information knowledge base; the semantic feature knowledge base is used for extracting semantic features of satellite communication data; the self-attention mechanism model is used for compressing semantic features to generate semantic tags.
In one embodiment of the present application, the satellite communication data includes an image, and the step of extracting semantic information and semantic tags of the satellite communication data by the semantic layer includes: semantic information extraction: dividing the image by using a neural network model to obtain a plurality of areas, calculating the importance degree of the semantic features of each area, and if the importance degree of the semantic features is greater than or equal to a preset threshold value, reserving the semantic information of all the areas; if the importance of the semantic features is smaller than a preset threshold, partially reserving the semantic information of the region; semantic tag extraction: generating semantic features of the image using a semantic feature knowledge base, the semantic features comprising descriptive language for the image; self-attentionThe step of the mechanism model compressing the semantic features to generate semantic tags includes: computing each word x in the semantic feature using the following formula i Attention value Attention (x) i )：
Where N is the length of the descriptive language,for word x i Logarithmic representation of Value i Representing word x i Weight index of (2); if Attention value Attention (x) i ) If the number is larger than or equal to the preset number, the word x is reserved i As semantic tags.
In one embodiment of the present application, the steps of generating the semantic content data packet by the application layer, the transport layer and the network layer according to the semantic information and the semantic tag include: the application layer obtains semantic information and semantic tags extracted by the semantic layer; the transmission layer packs semantic information as data bits, and adds an application layer packet header and a transmission layer packet header; and the network layer packages the semantic tags, adds a network layer packet header and completes packaging the semantic content data packet.
In one embodiment of the application, the step of each satellite communicating based on a semantic content data packet protocol comprises: the satellite receives the semantic content data packet, unpacks the semantic content data packet at a network layer, and obtains a semantic tag; continuously unpacking the semantic content data packet at the transmission layer to obtain semantic information; semantic information is cached at the application layer.
In an embodiment of the present application, the network architecture further includes a satellite communication management module and a user side, and the step of managing satellite communication by the satellite communication management module includes a request matching step, where the request matching step includes: when the semantic content data packet requested by the user side is routed to a certain satellite, the satellite forwards the semantic content data packet to a resource management node in the current virtual anchor point; unpacking the semantic content data packet at the network layer by the resource management node to obtain a semantic tag, and judging whether the current virtual anchor point can provide service or not by the resource management node according to the semantic tag; if the current virtual anchor point can not provide service, the resource management node transmits a semantic content data packet to another virtual anchor point; if all the virtual anchors can not provide service, the semantic content data packet is transmitted to the ground service content data center.
In an embodiment of the present application, the step of the resource management node determining whether the current virtual anchor point can provide the service according to the semantic tag includes: the resource management node obtains user request semantic features according to all user request data of the current virtual anchor point service area, and generates a common request Tag Comm_Tag; the resource management node calculates the User request semantic tag user_req= (RTag) using the following formula 1 ，RTag 2 ，...，RTag M ) Comm_tag= (CTag) with common request Tag 1 ，CTag 2 ，...，CTag N ) Match_lev1:
Match_Lev1＝Matching(Comm_Tag，User_Req)
wherein RTag i Representing the content of the user request semantic tags, M representing the number of user request semantic tags, CTag i Representing the content of the common request tags, and N represents the number of the common request tags; the resource management node judges whether the matching degree value Match_Lev1 is larger than or equal to a preset matching degree base line value Match_Basell1; if the matching degree value Match_Lev1 is larger than or equal to a preset matching degree base line value Match_BaseL1, carrying out data matching with corresponding service contents in the current virtual anchor point, and calculating a matching degree value Match_Lev2 related to the service contents; the resource management node calculates the User request semantic tag user_req= (RTag) using the following formula 1 ，RTag 2 ，...，RTag H ) Semantic Tag serv_tag= (STag) of service content involved after preliminary matching with current virtual anchor point 1 ，STag 2 ，...，STag G ) Match_lev2:
Match_Lev2＝Matching(User_Req，Serv_Tag)
wherein RTag i Representing the content of the user request semantic tags, H representing the number of user request semantic tags, STag i Content representing semantic tags of the service content, G representing the number of semantic tags of the current service content; the resource management node judges whether a matching degree value Match_Lev2 related to the service content is larger than or equal to a preset matching degree base line value Match_BaseL2; if the matching degree value Match_Lev2 is larger than or equal to a preset matching degree base line value Match_BaseL2, providing service by the current virtual anchor point; if the Match degree value Match_Lev1 is smaller than the preset Match degree base line value Match_BaseL1, the current virtual anchor point cannot provide service, and user request data is required to be routed to the subsequent virtual anchor point continuously.
In an embodiment of the present application, the step of managing satellite communications by the satellite communications management module further includes a requirement matching step, and the requirement matching step includes: in the process of returning the semantic content data packet for providing the service to the user terminal, when the semantic content data packet for providing the service is routed to a certain satellite, the satellite forwards the semantic content data packet for providing the service to a resource management node in the current virtual anchor point; unpacking the semantic content data packet for providing the service by the resource management node at the network layer to obtain a service content semantic tag for providing the service, and judging whether the semantic content data packet for providing the service needs to be cached or not by the resource management node according to the service content semantic tag; if the data packet needs to be cached, the resource management node caches the copy of the semantic content data packet for providing the service to any satellite in the current virtual anchor point.
In an embodiment of the present application, the step of the resource management node determining whether buffering of the semantic content data packet for providing the service is required according to the service content semantic tag includes: judging whether the service content semantic tags are requested by the current anchor point according to the history request within a certain time, judging whether the related semantic tags have cached certain content in the current virtual anchor point, and if not, directly caching semantic content data packets for providing services; the resource management node obtains user request semantic features according to all user request data of the current virtual anchor point service area, and generates a common request Tag Comm_Tag; the resource management node calculates the matching degree value Match_Lev3 of the service content semantic Tag Serv_Tag and the common request Tag Comm_Tag by using the following formula:
Match_Lev3＝Matching(Comm_Tag，Serv_Tag)
the resource management node judges whether a matching degree value Match_Lev3 is more than or equal to a preset matching degree base line value Match_BaseL3; if the matching degree value Match_Lev3 is larger than or equal to a preset matching degree base line value Match_BaseL3, a semantic content data packet for providing service needs to be cached; if the Match degree value Match_Lev3 is smaller than the preset Match degree base line value Match_BaseL3, the semantic content data packet for providing service does not need to be cached.
In one embodiment of the application, high orbit satellites are set in the virtual anchor as resource management nodes.
In an embodiment of the present application, a resource management node queue is preset by any low-orbit satellite, and the low-orbit satellites in the resource management node queue can synchronously move, and in the process of moving the low-orbit satellite to another virtual anchor point, the low-orbit satellites in the resource management node queue are always in one-to-one correspondence with the virtual anchor point, and the low-orbit satellites in one-to-one correspondence with the virtual anchor point are used as resource management nodes.
In an embodiment of the present application, the satellite communication network architecture further includes a satellite motion management module, and the step of managing satellite motion by the satellite motion management module includes: when a certain satellite leaves the current virtual anchor point and enters another virtual anchor point, the resource management node distributes the cache content of the satellite to at least one satellite in the current virtual anchor point; and the resource management node of the other virtual anchor point judges the matching degree of the cache content and the virtual anchor point; if the matching degree is high, the satellite reserves own cache content, and the resource management node of the other virtual anchor point distributes service content based on the cache space of the satellite; if the matching degree is low, the satellite deletes the self cache content, and the resource management node of the other virtual anchor point distributes corresponding service content copies to the satellite.
The technical scheme of the application constructs a satellite communication network architecture comprising an application layer, a transmission layer and a network layer, and embeds a semantic layer based on semantics in the application layer, wherein the semantic layer realizes functions of extracting and recovering semantic information and extracting semantic labels for satellite communication data in the application layer; the application generates the semantic content data packet based on the extracted semantic information and the semantic tag in the application layer, the transmission layer and the network layer, designs the semantic content data packet protocol for satellite communication, realizes the light design and transparent transmission of the protocol, can save the space-based communication data volume and improve the communication bandwidth utilization rate; the application designs the virtual anchor point based on the service area, satellites in the virtual anchor point form satellite clusters to cooperatively serve the virtual anchor point, and a resource management node is introduced into the virtual anchor point to manage the satellite clusters, wherein the resource management node can be matched with semantic content data packets among satellites as required, so that the functions of distributed caching and cooperative storage among the satellite clusters are realized, the caching resources of the space-based communication network are saved, the cooperative processing capacity among the satellite clusters is improved, the service content distribution time delay is reduced, and the number of route hops among the satellites is reduced; the satellite communication network architecture can integrally improve the transmission efficiency of the space-based information, save space-based communication and cache resources and improve the fault tolerance rate and service efficiency of the space-based communication.
Drawings
In order to make the above objects, features and advantages of the present application more comprehensible, embodiments accompanied with figures are described in detail below, wherein:
FIG. 1 is an exemplary architecture diagram of a semantic content based satellite communications network architecture according to one embodiment of the present application;
FIG. 2 is an exemplary architecture diagram of a semantic content based satellite communications network architecture according to another embodiment of the present application;
FIG. 3 is an exemplary flow chart of generating semantic content data packets and satellite semantic content data packet protocol based communications in an embodiment of the present application;
FIG. 4 is an exemplary flow chart of request matching of semantic content data packets according to one embodiment of the present application;
FIG. 5 is an exemplary flow chart of demand matching of semantic content data packets according to one embodiment of the present application;
FIG. 6 is an exemplary flow chart of satellite movement in different virtual anchors and satellite cache content movement in accordance with one embodiment of the present application.
Detailed Description
In order to make the above objects, features and advantages of the present application more comprehensible, embodiments accompanied with figures are described in detail below.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, but the present application may be practiced in other ways than as described herein, and therefore the present application is not limited to the specific embodiments disclosed below.
As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously. At the same time, other operations are added to or removed from these processes.
The application provides a satellite communication network architecture based on semantic content, which can be applied to a communication scene between Yu Tianji satellites and a communication scene between a space-based satellite and a ground user.
FIG. 1 is an exemplary architecture diagram of a semantic content based satellite communications network architecture according to one embodiment of the present application, and with reference to FIG. 1, the semantic content based satellite communications network architecture comprises: the application layer 301, the transmission layer 302 and the network layer 303, wherein the application layer 301 comprises a semantic layer 3011, the semantic layer 3011 is used for extracting semantic information and semantic tags of satellite communication data, and the application layer 301, the transmission layer 302 and the network layer 303 generate a semantic content data packet 304 according to the semantic information and the semantic tags; at least one virtual anchor (e.g., virtual anchor 100), virtual anchor 100 includes at least one satellite (e.g., satellite 1-satellite N) and one satellite is selected as resource management node 1001, resource management node 1001 is configured to manage each satellite within virtual anchor 100, each satellite is configured to obtain semantic content data packets 304 and communicate based on a semantic content data packet protocol. For example, when only one satellite is included in the virtual anchor point, the satellite needs to have the function of a resource management node, and the application does not limit the number of satellites included in the virtual anchor point.
The space-based satellite communication network has a large coverage service area and involves a large number of space-based satellites, so the application proposes to divide the service area, design a virtual anchor scheme based on the service area, and each virtual anchor serves a certain area. Because the middle-low orbit satellites can move at high speed relative to the ground, the addressing of the satellite communication network is realized based on virtual anchor points, each virtual anchor point is static relative to the ground and corresponds to a satellite cluster formed by dynamically changing satellites (the number of the satellites in the satellite cluster is one at least). The satellite cluster corresponding to each virtual anchor point is provided with a satellite node serving as a resource management node of the virtual anchor point, and the resource management node is responsible for managing the content stored by the satellite node in the virtual anchor point, the content entering the satellite cluster node in the inter-satellite transmission relay process, the requirements of the region corresponding to the virtual anchor point and the like. The resource management node of the virtual anchor point is introduced, so that the problems of distributed caching and management of the satellite cluster of the virtual anchor point are effectively solved, and the utilization rate of the space-based resource is further improved.
Illustratively, when the semantic content data packet 304 is routed to a virtual anchor point in the space-based communication network architecture of the present application, the space-based satellite in the virtual anchor point forwards the semantic content data packet 304 to the current resource management node of the current virtual anchor point, and after the current resource management node performs network layer unpacking on the semantic content data packet in the network layer 303, the current resource management node performs demand matching based on the semantic label, and performs a copy caching function on the service content based on the demand matching result and the caching policy. When the copy caching function is executed, the resource management node of the virtual anchor point caches the current copy to any one satellite in the satellite cluster of the virtual anchor point, and the step of matching the requirements will be described later.
Illustratively, due to the high dynamic nature of the space-based satellites, when a certain space-based satellite leaves the current virtual anchor point to enter the next virtual anchor point, the resource management node distributes the cached content of the space-based satellite to the other satellites in the satellite cluster. And the data management node of the next virtual anchor point simultaneously distributes relevant service content copies to be cached in the space-based satellite moving across the virtual anchor point. The motion management content about satellites across virtual anchors will be described later.
The technical scheme of the application constructs a satellite communication network architecture comprising an application layer 301, a transmission layer 302 and a network layer 303, and embeds a semantic layer 3011 based on semantics in the application layer 301, wherein the semantic layer 3011 realizes semantic information extraction, recovery and semantic tag extraction functions on satellite communication data in the application layer 301; the application generates the semantic content data packet 304 based on the extracted semantic information and the semantic tag in the application layer 301, the transmission layer 302 and the network layer 303, designs the semantic content data packet protocol for satellite communication, realizes the light design and transparent transmission of the protocol, can save space-based communication data volume and improve the utilization rate of communication bandwidth; the application designs the virtual anchor point 100 based on the service area, satellites 1 to N in the virtual anchor point 100 form satellite clusters to cooperatively serve the virtual anchor point 100, a resource management node 1001 is introduced into the virtual anchor point 100 to manage the satellite clusters, the resource management node 1001 can match semantic content data packets 304 among satellites as required, the functions of distributed caching and cooperative storage among the satellites are realized, the caching resources of an space-based communication network are saved, the cooperative processing capacity among the satellites is improved, the service content distribution time delay is reduced, and the number of route hops among the satellites is reduced; the satellite communication network architecture can integrally improve the transmission efficiency of the space-based information, save space-based communication and cache resources and improve the fault tolerance rate and service efficiency of the space-based communication.
Fig. 2 is an exemplary architecture diagram of a semantic content based satellite communications network architecture according to another embodiment of the present application. The satellite communications network architecture of the embodiment of fig. 2 is described first. Referring to fig. 2, the entire network architecture includes a virtual anchor a and a virtual anchor B (the virtual anchor may be extended to a plurality as needed). The virtual anchor point a comprises a satellite cluster formed by a plurality of space-based satellites (for example, satellites A1 to N1) and one space-based satellite serving as a resource management node a 1001; the virtual anchor point B includes a satellite cluster formed by a plurality of space-based satellites (for example, satellites B1 to N2) and one space-based satellite serving as a resource management node B1001; each satellite node in the virtual anchor point can perform request matching and demand matching, and inter-satellite routing and data migration can be performed between the virtual anchor point A and the virtual anchor point B.
With continued reference to fig. 2, each space-based satellite includes a semantic layer 3011 at the application layer 301, a semantic information knowledge base (not shown), a semantic feature knowledge base (not shown), and a self-attention mechanism model (not shown) at the semantic layer 3011, semantic information and semantic features extraction are performed on the service content at the semantic layer 3011, and the application layer 301 may perform service content caching. The semantic content data packet transmission layer packaging is carried out at the transmission layer 302, the semantic content data packet transmission network layer packaging is carried out at the network layer 303, the demand matching is carried out, and the request matching is carried out. The ground user 200 requests 101 an uplink user of the space-based satellite communication network; the service content data 1011 of the space-based satellite communication network is derived from the service content data 1011 generated by the ground service content data center 400 and the space-based satellite itself.
In some embodiments, referring to FIG. 2, the semantic layer 3011 includes: semantic information knowledge base, semantic layer 3011 extracts the semantic information of satellite communication data according to the semantic information knowledge base; the semantic feature knowledge base is used for extracting semantic features of satellite communication data; the self-attention mechanism model is used for compressing semantic features to generate semantic tags. Illustratively, the semantic information knowledge base and the semantic feature knowledge base respectively comprise a neural network model, and the neural network model is trained by a ground end and cached in each satellite in advance. Based on the semantic information knowledge base and the semantic feature knowledge base, the semantic layer 3011 respectively realizes semantic information extraction and semantic feature extraction of satellite communication data service contents. And compressing and extracting the semantic features based on a Self-Attention (Self-Attention) mechanism model aiming at the extracted semantic features to obtain the semantic tags with the specified length as the service content.
In some embodiments, the satellite communication data comprises an image, and the step of the semantic layer extracting semantic information and semantic tags of the satellite communication data comprises:
step Sa1, semantic information extraction step: dividing the image by using a neural network model to obtain a plurality of areas, calculating the importance degree of the semantic features of each area, and if the importance degree of the semantic features is greater than or equal to a preset threshold value, reserving the semantic information of all the areas; if the importance of the semantic features is smaller than a preset threshold, partially reserving the semantic information of the region;
Step Sa2, semantic tag extraction: generating semantic features of the image using a semantic feature knowledge base, the semantic features comprising descriptive language for the image; the step of compressing the semantic features by the self-attention mechanism model to generate semantic tags includes: calculating each word x in the semantic feature using the following formulas (1) to (2) i Attention value Attention (x) i )：
Where N is the length of the descriptive language,for word x i Logarithmic representation of Value i Representing word x i Weight index of (2); if the Attention value Attention (xi) is larger than or equal to the preset value, the word x is reserved i As semantic tags.
For example, the space-based satellite has rich application scenes, rich service content media formats and different service content forms aimed by different application scenes, so the satellite communication network architecture of the application supports service contents in various formats. Taking the service content in the image format as an example, the extraction and recovery of the semantic information and the extraction of the semantic tag of the image are described.
In the foregoing step Sa1, for the semantic information extraction of an image, the image is first divided into a plurality of blocks of size n×n, for each block, the semantic feature importance of the block is calculated based on the neural network model, for the block of high importance, all the information is retained, for the block of low importance, the maximum pixel of the block is calculated, and only the pixel content is retained. The block part of the important information is reserved, namely the semantic information of the image. The scheme of blurring processing is carried out on unimportant information by reserving important information so as to realize the extraction of semantic information of the image. In the subsequent recovery process, the service content is recovered only based on the semantic information for the important semantic information part of the reserved service content; and aiming at the low importance information, the image is restored according to the reserved part, so that the semantic information extraction and restoration functions of the image are realized.
In the foregoing step Sa2, a section of descriptive language is generated for the image based on the image identification scheme, i.e. semantic features of the image are generated based on the semantic feature knowledge base, for semantic tag extraction of the image. For example, for an image, the semantic feature generated may be "a gray rabbit bounces around the wild grasslands to eat grasses". For the generated semantic features, extracting semantic tags of the semantic features for a plurality of times based on a self-attention mechanism, taking the semantic features generated by a semantic feature knowledge base as the input of a self-attention mechanism model, and performing Word segmentation on the semantic features by the self-attention mechanism to obtain a Word sequence Source_word [ x ] 1 ，x 2 ，x 3 ，...，x N ]Calculate each word x i The Softmax normalization function of (2) to obtain an intermediate result a i Then continue to calculate word x i Attention value of (a), i.e. the wordx i Is a semantic feature importance of (1). Based on the calculated Attention value Attention (x i ) And judging the semantic importance of each word, thereby extracting the semantic tag. In practical application, the semantic features are often longer, so that the semantic tag is designed to be light, and the semantic tag is subjected to multiple self-attention training, so that the semantic tag with the specified length is obtained.
The application can realize the compression of the transmission data volume of the space-based communication network by extracting the semantic information from the satellite communication data service content, saves communication resources and improves the utilization rate of communication bandwidth; by extracting the semantic tags from the satellite communication data service content, the request matching and demand matching functions based on the semantic tags can be realized, the request time delay of a user is reduced, and the inter-satellite multi-hop transmission is reduced.
In some embodiments, referring to fig. 1 and 2, the steps of the application layer 301, the transport layer 302, and the network layer 303 generating semantic content data packets from semantic information and semantic tags include: the application layer 301 obtains semantic information and semantic tags extracted by the semantic layer 3011; the transmission layer 302 packages the semantic information as data bits, and adds an application layer packet header and a transmission layer packet header; the network layer 303 packages the semantic tags, adds a network layer packet header, and completes packaging the semantic content data packet. Illustratively, after the space-based semantic layer 3011 extracts the semantic information and the semantic tag from the service content, the transport layer 302 packages the semantic information as data bits, and adds an application layer packet header and a transport layer packet header, packages the semantic tag in the network layer 303 and adds a network layer packet header, thereby completing the package processing of the semantic content data packet. According to the application, the semantic information extracted by the semantic layer 3011 is packaged in the data packet at the transmission layer 302, and the semantic label is packaged at the network layer 303, so that the light weight and transparent design of the semantic content data packet are realized, the space-based satellite communication network realizes the functions of demand matching and request matching based on the semantic label at the network layer 303, and the space-based computing resource is saved.
In some embodiments, referring to fig. 1 and 2, the step of each satellite communicating based on a semantic content data packet protocol includes: the satellite receives the semantic content data packet, unpacks the semantic content data packet at the network layer 303, and obtains a semantic tag; continuing to unpack the semantic content data packet at the transmission layer 302 to obtain semantic information; semantic information is cached at the application layer 301. Illustratively, the semantic information knowledge base of the semantic layer 3011 supports retrieval of service content based on semantic information. When receiving the semantic content data packet, the day base judges to directly cache the service content or restore the service content according to actual requirements, and if only the service content is required to be cached, the semantic information after unpacking the semantic content data packet is directly cached so as to save cache resources; if the service content needs to be recovered, unpacking the semantic content data packet to obtain semantic information, and recovering according to the semantic information knowledge base to obtain the original service content.
Illustratively, the present application contemplates semantic content packet protocols based on semantic content. And obtaining the semantic information of the service content and the semantic label based on the semantic information knowledge base and the semantic feature knowledge base of the semantic layer 3011, and packaging. The semantic information sequentially performs application layer encapsulation and transport layer encapsulation in the application layer 301 and the transport layer 302 to obtain a transport layer data packet with the semantic information as a data bit. Before the semantic label is added to the transport layer packet in the network layer 303, a network layer packet header is added to realize network layer packet, so as to complete the semantic content packet. The service content semantic information realizes the compression of the service content data volume, and the semantic information is used as a data bit, so that the lightweight design of the semantic content data packet is realized. After the semantic tags are packaged in the network layer 303, the space-based satellite directly obtains the semantic tags when unpacking the semantic content data packets in the network layer 303, so that the space-based satellite directly realizes the functions of request matching and demand matching based on the semantic tags in the network layer 303 without continuing unpacking in the transmission layer 302 and the application layer 301, thereby reducing the routing time delay of the semantic content data packets, saving space-based cache and computing resources, and realizing the transparent design of the semantic content data packets.
The semantic content data packet protocol of the present application is presented herein. FIG. 3 is an exemplary flow chart for generating semantic content data packets and satellite based semantic content data packet protocol communications in accordance with one embodiment of the present application, and referring to FIG. 3, at step S310 a first satellite generates semantic tags and semantic information for service content at the application layer; at step S320, the first satellite encapsulates the semantic information at the transport layer; step S330, the first satellite encapsulates the semantic tags at the network layer; the first satellite transmits the generated semantic content data packet to the resource management node through an inter-satellite link in step S340; step S350, the resource management node unpacks the semantic content data packet at the network layer to obtain a semantic label; step S360 judges whether the request matching is successful, if not, the resource management node transmits the semantic content data packet to another virtual anchor point in step S361; if the judgment is successful, the resource management node unpacks the semantic content data packet at the transmission layer to obtain semantic information in step S370; the resource management node caches the semantic information at the application layer at step S380.
In some embodiments, referring to fig. 2, the network architecture further includes a satellite communication management module and a user terminal 200, and the step of managing satellite communication by the satellite communication management module includes a request matching step, where the request matching step includes:
Step Sb1, when a semantic content data packet requested by a user side 200 is routed to a certain satellite, forwarding the semantic content data packet to a resource management node in a current virtual anchor point by the satellite;
step Sb2, unpacking the semantic content data packet at the network layer by the resource management node to obtain a semantic tag, and judging whether the current virtual anchor point can provide service or not by the resource management node according to the semantic tag;
step Sb3, if the current virtual anchor point cannot provide service, the resource management node transmits a semantic content data packet to another virtual anchor point; if all virtual anchors are not capable of providing service, the semantic content data packet is transmitted to the ground service content data center 400.
Illustratively, when the semantic content data packet requested by the user end 200 is routed to a virtual anchor point, the resource management node of the virtual anchor point unpacks the semantic content data packet, determines the matching degree of the service content requested by the user and the service content cached by the current virtual anchor point, if the service content or the similar content is cached by the current virtual anchor point satellite cluster, the space-based satellite cached with the service content in the current virtual anchor point satellite cluster provides the service content for the user, and the user does not need to continue to route the user request to the subsequent inter-satellite nodes, so that the service content can be distributed as required, the time delay of the user request is reduced, and the multi-hop transmission condition of the inter-satellite route is reduced.
The request matching function of the present application is described herein. FIG. 4 is an exemplary flow chart of request matching for semantic content data packets according to one embodiment of the present application, referring to FIG. 4, the semantic content data packets requested by the terrestrial client are routed to the current satellite at step S410; the current satellite routes the semantic content data packet to the current resource management node in the current virtual anchor point at step S420; step S430, unpacking the semantic content data packet by the current resource management node; the current resource management node calculates the matching degree in step S440, judges whether the request matching is successful, if so, the current virtual anchor point directly provides the service content in step S450; if it is determined that the service is unsuccessful, the current resource management node transmits the semantic content data packet to other virtual anchors in step S441, and if all the virtual anchors cannot provide the service, the semantic content data packet is finally transmitted to the ground service content data center.
In some embodiments, in step Sb2 described above, the step of the resource management node determining whether the current virtual anchor point can provide the service according to the semantic tag includes:
step Sc1, the resource management node obtains user request semantic features according to all user request data of the current virtual anchor point service area, and generates a common request Tag Comm_Tag;
Step Sc2, the resource management node calculates the User request semantic tag user_req= (RTag) using the following equation (3) based on the matching algorithm 1 ，RTag 2 ，...，RTag M ) Comm_tag= (CTag) with common request Tag 1 ，CTag 2 ，...，CTag N ) Match_lev1:
Match_Lev1＝Matching(Comm_Tag，User_Req) (3)
wherein RTag i Representing user requestsContent of semantic tags, M represents the number of semantic tags requested by the user, CTag i Representing the content of the common request tags, and N represents the number of the common request tags;
step Sc3, the resource management node judges whether a matching degree value Match_Lev1 is more than or equal to a preset matching degree base line value Match_BaseL1;
step Sc4, if the matching degree value Match_Lev1 is larger than or equal to a preset matching degree baseline value Match_BaseL1 (namely, representing that the matching degree is high), performing data matching with corresponding service content in the current virtual anchor point, and calculating a matching degree value Match_Lev2 related to the service content;
in step Sc5, the resource management node calculates the User request semantic tag user_req= (RTag) using the following equation (4) 1 ，RTag 2 ，...，RTag H ) Semantic Tag serv_tag= (STag) of service content involved after preliminary matching with current virtual anchor point 1 ，STag 2 ，...，STag G ) Match_lev2:
Match_Lev2＝Matching(User_Req，Serv_Tag) (4)
wherein RTag i Representing the content of the user request semantic tags, H representing the number of user request semantic tags, STag i Content representing semantic tags of the service content, G representing the number of semantic tags of the current service content;
step Sc6, the resource management node judges whether a match_Lev2 related to the service content is larger than or equal to a preset Match baseline value match_BaseL2;
sc7, if the matching degree value Match_Lev2 is larger than or equal to a preset matching degree baseline value Match_BaseL2 (namely, the matching degree is high), providing service by the current virtual anchor point, namely, providing service content for the user request by the satellite cluster to which the current virtual anchor point belongs, and coordinating the space-based satellite to provide the service content for the user request by the data management node based on the user request;
and step Sc8, if the matching degree value Match_Lev1 is smaller than the preset matching degree baseline value Match_BaseL1 (namely, the matching degree is low) in the step Sc3, the current virtual anchor point cannot provide service, and the user request data is required to be routed to the subsequent virtual anchor point continuously.
The request matching function of the application realizes the on-demand distribution function of the space-based satellite for the user request, and the semantic content data packet of the user request is not required to be routed to the ground service content data center with the most complete data volume and longer distance, thereby reducing the time delay of the user request, reducing the inter-satellite multi-hop transmission and saving the communication resources of the space-based satellite communication network.
In some embodiments, the step of the satellite communication management module managing satellite communications further comprises a demand matching step comprising:
in the step Sd1, in the process that the space-based satellite communication network returns the semantic content data packet for providing the service to the user terminal, when the semantic content data packet for providing the service is routed to a certain satellite of the virtual anchor point, the satellite forwards the semantic content data packet for providing the service to a resource management node in the current virtual anchor point;
step Sd2, the resource management node unpacks the semantic content data packet for providing the service in the network layer to obtain a service content semantic tag for providing the service, and the resource management node judges whether the semantic content data packet for providing the service needs to be cached or not according to the service content semantic tag;
and step Sd3, if the cache is needed, the resource management node caches the copy of the semantic content data packet for providing the service to any satellite in the current virtual anchor point.
Illustratively, after the resource management node distributes the copy of the semantic content data packet to the virtual anchor satellite cluster for buffering, the semantic content data packet continues to be routed backwards, and the semantic content data packet for providing the service is finally transmitted to the ground user terminal. The demand matching function designed by the application realizes the on-demand data storage of the space-based satellite communication network, relevant contents are cached in the virtual anchor point according to the common request of the current service area, and when a user initiates a content request, the service content can be directly distributed and provided for the user on demand at the current virtual anchor point, thereby reducing the time delay of the user request and saving the communication resources of the space-based satellite communication network.
The demand matching function of the present application is described herein. FIG. 5 is an exemplary flow chart for demand matching of semantic content data packets according to one embodiment of the present application, and referring to FIG. 5, the semantic content data packets for providing services are routed to a current satellite at step S510; the current satellite routes semantic content data packets for providing services to the current resource management node in the current virtual anchor at step S520; unpacking the semantic content data packet for providing the service by the current resource management node at step S530; the current resource management node calculates the matching degree in step S540, judges whether the demand matching is successful, if so, the current resource management node caches the copy of the semantic content data packet for providing service to any satellite in the current virtual anchor point in step S550; if it is determined that the service is unsuccessful, the current resource management node transmits the semantic content data packet for providing the service to other virtual anchors in step S541, where the semantic content data packet for providing the service is finally transmitted to the ground client.
In some embodiments, in step Sd2 described above, the step of the resource management node determining whether buffering the semantic content data packet for providing the service is needed according to the service content semantic tag includes:
Step Se1, judging whether the semantic tags of the service content are requested by the current anchor point according to the history request within a certain time, judging whether the related semantic tags have certain content cached in the current virtual anchor point, and if not, directly caching semantic content data packets for providing the service; and
step Se2, the resource management node obtains user request semantic features according to all user request data of the current virtual anchor point service area, and generates a common request Tag Comm_Tag;
step Se3, the resource management node calculates a matching degree value match_lev3 of the service content semantic Tag serv_tag and the common request Tag comm_tag by using the following formula (5) based on a matching algorithm:
Match_Lev3＝Matching(Comm_Tag，Serv_Tag) (5)
step Se4, the resource management node judges whether a matching degree value Match_Lev3 is more than or equal to a preset matching degree base line value Match_BaseL3;
step Se5, if the matching degree value Match_Lev3 is larger than or equal to a preset matching degree baseline value Match_BaseL3 (namely, the matching degree is high), buffering semantic content data packets for providing services is needed;
and step Se6, if the matching degree value Match_Lev3 is smaller than a preset matching degree baseline value Match_BaseL3 (namely, the matching degree is low), buffering of semantic content data packets for providing services is not needed.
Illustratively, the resource management node of the virtual anchor point caches a common service request tag of the current virtual anchor point, and is used for a requirement matching and request matching function, and the resource management node of the virtual anchor point also negotiates and caches the service content copy cached to the current virtual anchor point satellite cluster. Aiming at the problem that the space-based satellite cache resources are insufficient when the satellite communication network cache resources are limited and the resource management node distributes service contents to the space-based satellite for cache, the application designs the resource management node to carry out negotiation cache aiming at the situation. Based on the caching policy, a portion of the duplicate or highly approximated service content is deleted or relocated, leaving only minimal capacity content to be stored that can meet the quality of service (Quality of Service, qoS) requirements. The application realizes centralized management on the space-based satellite communication network by setting the virtual anchor point and the resource management node, and improves the resource utilization rate of the space-based satellite communication network and the cooperative processing capability among the stars.
In some embodiments, high orbit satellites are set in the virtual anchor as resource management nodes. The coverage range of the high-orbit satellite is wide, the high-orbit satellite is preferably used as a resource management node of the virtual anchor point, the high-orbit satellite has poor dynamic property compared with the low-orbit satellite, the high-orbit satellite can be kept above the virtual anchor point for a relatively long time, the condition of frequently replacing the resource management node is avoided, and communication resources are saved.
In some embodiments, a resource management node queue is preset by any low-orbit satellite, the low-orbit satellites in the resource management node queue can synchronously move, and in the process that the low-orbit satellites move to another virtual anchor point, the low-orbit satellites in the resource management node queue are always in one-to-one correspondence with the virtual anchor points, and the low-orbit satellites in one-to-one correspondence with the virtual anchor points serve as resource management nodes. Illustratively, any low-orbit satellite is pre-assigned to form a resource management node queue, for example, the first virtual anchor A, B, C corresponds to the resource management nodes a, B and C respectively, and later the resource management nodes a, B and C synchronously move in a predetermined sequence, the resource management node a moves to the virtual anchor B, the resource management node B moves to the virtual anchor C, the resource management node C moves to the virtual anchor a, and the low-orbit satellites a, B and C are always used as the resource management nodes of the current area.
According to the application, a plurality of low-orbit satellites are selected from the whole low-orbit satellite constellation as resource management nodes of the virtual anchor points, so that each virtual anchor point is always kept to be used as the resource management node of the virtual anchor point in the high-dynamic period of the low-orbit satellite, and the problem of high-speed change of the satellite management node caused by the high dynamic of the low-orbit satellite is solved.
In some embodiments, the satellite communications network architecture further comprises a satellite motion management module, the step of managing satellite motion by the satellite motion management module comprising:
step Sf1, when a certain satellite leaves a current virtual anchor point and enters another virtual anchor point, a resource management node distributes the cache content of the satellite to at least one satellite in the current virtual anchor point;
step Sf2, the resource management node of another virtual anchor point judges the matching degree of the cache content and the virtual anchor point;
step Sf3, if the matching degree is high, the satellite reserves own cache content, and the resource management node of the other virtual anchor point distributes service content based on the cache space of the satellite;
and step Sf4, if the matching degree is low, deleting the self cache content by the satellite, and distributing corresponding service content copies to the satellite by the resource management node of the other virtual anchor point.
For example, due to the high dynamic nature of the satellite communication network, the satellite cluster managed by the virtual anchor point often has a situation that the space-based satellite leaves the current virtual anchor point and enters the next virtual anchor point, so that the problem of data movement of the satellite cache content needs to be solved. In order to solve the problem, when the space-based satellite leaves the current virtual anchor point, the application designs that the self cache service content is sent to a resource management node of the virtual anchor point, and the resource management node deletes or distributes the partial service content to other space-based satellites for caching based on a cache strategy. After the space-based satellite enters the next virtual anchor point, matching the service content of the space-based satellite with the resource management node of the next virtual anchor point, if the matching degree is high, reserving the partial service content, and distributing the service content by the resource management node of the next virtual anchor point based on the cache space of the space-based satellite; if the matching degree is low, the current cached service content is directly deleted, and the service content distributed by the resource management node of the next virtual anchor point is received and cached. In addition, due to shortage of space for space-based satellite caching resources, a problem of insufficient caching space when space-based satellite caching service content copies may occur, and based on the problem, when the copy content is cached, if space for space-based satellite caching is insufficient, scheduling is performed through a resource management node, so that a space-based negotiation caching function among virtual anchor satellite clusters is realized.
The process of data migration for the space-based satellite of the present application is described herein. FIG. 6 is an exemplary flow chart of satellite movement in different virtual anchors and movement of the cached content of the satellite in accordance with one embodiment of the present application, and with reference to FIGS. 2 and 6, satellite A1 leaves the current virtual anchor A and enters another virtual anchor B at step S610; in step S621, the satellite A1 returns its own cache content to the resource management node a1001; in step S631, the resource management node a1001 distributes the service content cached by the satellite A1 to at least one satellite in the virtual anchor a; satellite A1 transmits its own cache contents to resource management node B1001 at step S622; in step S632, the resource management node B1001 of the virtual anchor point B determines that the matching degree between the cached content and the current virtual anchor point is high, if the matching degree is high, in step S640, the satellite A1 reserves its cached content, and the resource management node B1001 of the virtual anchor point B distributes service content based on the cached space of the satellite A1; if the matching degree is low, in step S633, the satellite A1 deletes the own cache content, and the resource management node B1001 of the virtual anchor B distributes the corresponding service content to the satellite A1.
The satellite communication network architecture, namely the space-based high-dynamic memory transmission integrated network architecture based on semantic content, can improve the utilization rate of space-based communication resources, save space-based cache resources and reduce space-based communication time delay. The application mainly comprises the following designs: (1) The semantic layer scheme is designed to be embedded into the space-based application layer, semantic features based on semantics, semantic information extraction and semantic label generation are realized for the service content, space-based communication resources can be saved, and the communication bandwidth utilization rate is improved; and designing a semantic content data packet protocol based on semantic information and semantic labels, and realizing the lightweight design and efficient distribution of the space-based communication data packet. (2) The semantic content-based demand matching function of user request matching and virtual anchor points in the space-based communication network is designed, the on-demand storage and on-demand distribution scheme is realized, the time delay of the user request of the space-based satellite communication network can be reduced, inter-satellite multi-hop transmission is reduced, and space-based communication resources are saved. (3) Designing a virtual anchor point scheme of a space-based satellite communication network, dividing a service area, constructing virtual anchor points, wherein each virtual anchor point comprises a satellite cluster formed by at least one space-based satellite, setting resource management nodes of the satellite clusters in each satellite cluster, managing and coordinating each space-based relay node in the current virtual anchor point satellite cluster, realizing distributed caching and collaborative caching of the space-based relay nodes, realizing uniform resource management among the satellite clusters, and improving the resource utilization rate of the space-based satellite communication network.
While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements and adaptations of the application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within the present disclosure, and therefore, such modifications, improvements, and adaptations are intended to be within the spirit and scope of the exemplary embodiments of the present disclosure.
Meanwhile, the present application uses specific words to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the application may be combined as suitable.
Some aspects of the application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. The processor may be one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital signal processing devices (DAPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or a combination thereof. Furthermore, aspects of the application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media. For example, computer-readable media can include, but are not limited to, magnetic storage devices (e.g., hard disk, floppy disk, tape … …), optical disk (e.g., compact disk CD, digital versatile disk DVD … …), smart card, and flash memory devices (e.g., card, stick, key drive … …).
The computer readable medium may comprise a propagated data signal with the computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer readable medium can be any computer readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer readable medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signals, or the like, or a combination of any of the foregoing.
Similarly, it should be noted that in order to simplify the description of the present disclosure and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are required by the subject application. Indeed, less than all of the features of a single embodiment disclosed above.
In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations in some embodiments for use in determining the breadth of the range, in particular embodiments, the numerical values set forth herein are as precisely as possible.
While the application has been described with reference to the specific embodiments presently, it will be appreciated by those skilled in the art that the foregoing embodiments are merely illustrative of the application, and various equivalent changes and substitutions may be made without departing from the spirit of the application, and therefore, all changes and modifications to the embodiments are intended to be within the scope of the appended claims.

Claims (11)

1. A semantic content based satellite communications network architecture comprising:
the application layer comprises a semantic layer, the semantic layer is used for extracting semantic information and semantic tags of satellite communication data, and the application layer, the transmission layer and the network layer generate semantic content data packets according to the semantic information and the semantic tags, wherein the semantic layer comprises: the semantic layer extracts the semantic information of the satellite communication data according to the semantic information knowledge base; the semantic feature knowledge base is used for extracting semantic features of the satellite communication data; a self-attention mechanism model for compressing the semantic features to generate the semantic tags;
the system comprises at least one virtual anchor point, wherein the virtual anchor point comprises at least one satellite and a resource management node, the resource management node is used for managing each satellite in the virtual anchor point, and each satellite is used for acquiring the semantic content data packet and communicating based on the semantic content data packet protocol.
2. The satellite communication network architecture of claim 1, wherein the satellite communication data comprises an image, and the step of extracting semantic information and semantic tags of the satellite communication data by the semantic layer comprises:
Semantic information extraction: dividing the image by using a neural network model to obtain a plurality of areas, calculating the importance degree of the semantic features of each area, and if the importance degree of the semantic features is greater than or equal to a preset threshold value, completely reserving the semantic information of the areas; if the importance of the semantic features is smaller than the preset threshold, partially reserving the semantic information of the region, wherein partially reserving the semantic information of the region comprises: calculating the maximum pixel of the duty ratio in the region, and reserving the content of the pixel;
semantic tag extraction: generating semantic features of the image using the semantic feature knowledge base, the semantic features comprising a descriptive language for the image; the step of the self-attention mechanism model compressing the semantic features to generate the semantic tags includes: calculating each word x in the semantic feature using the following formula i Attention value Attention (x) i )：
Wherein N is the length of the descriptive language,for word x i Logarithmic representation of Value i Representing word x i Weight index of (2);
if the Attention value Attention (x i ) If the number is larger than or equal to a preset number, the word x is reserved i As the semantic tags.
3. The satellite communications network architecture of claim 1, wherein the steps of the application layer, the transport layer, and the network layer generating semantic content data packets from the semantic information and the semantic tags comprise:
the application layer obtains the semantic information and the semantic tag extracted by the semantic layer;
the transmission layer packs the semantic information as data bits and adds an application layer packet header and a transmission layer packet header;
and the network layer packages the semantic tags, adds a network layer packet header and completes packaging the semantic content data packet.
4. A satellite communications network architecture according to claim 3, wherein the step of each satellite communicating based on the semantic content data packet protocol comprises:
the satellite receives the semantic content data packet, unpacks the semantic content data packet at the network layer, and obtains the semantic tag;
continuing unpacking the semantic content data packet at the transmission layer to obtain the semantic information;
and caching the semantic information at the application layer.
5. The satellite communication network architecture of claim 1, wherein the network architecture further comprises a satellite communication management module and a user side, the step of managing satellite communications by the satellite communication management module comprising a request matching step comprising:
When the semantic content data packet requested by the user side is routed to a certain satellite, the satellite forwards the semantic content data packet to the resource management node in the current virtual anchor point;
the resource management node unpacks the semantic content data packet at the network layer to obtain the semantic tag, and the resource management node judges whether the current virtual anchor point can provide service according to the semantic tag;
if the current virtual anchor point can not provide service, the resource management node transmits the semantic content data packet to another virtual anchor point;
and if all the virtual anchors can not provide service, the semantic content data packet is transmitted to a ground service content data center.
6. The satellite communications network architecture of claim 5, wherein the step of the resource management node determining whether the current virtual anchor point can provide service based on the semantic tag comprises:
the resource management node obtains user request semantic features according to all user request data of the current virtual anchor point service area, and generates a common request Tag Cimm_tag;
the resource management node calculates a User request semantic tag user_req= (RTag) using the following formula 1 ，RTag 2 ，...，RTag M ) Comm_tag= (CTag) with the common request Tag 1 ，CTag 2 ，...，CTag N ) Match_lev1:
Match_Lev1＝Matching(Comm_Tag，User_Req)
wherein RTag i Representing the content of the user request semantic tags, M representing the number of the user request semantic tags, CTag i Representing the content of the common request tags, and N represents the number of the common request tags;
the resource management node judges whether the matching degree value Match_Lev1 is more than or equal to a preset matching degree base line value Match_BaseL1;
if the matching degree value Match_Lev1 is larger than or equal to the preset matching degree baseline value Match_BaseL1, performing data matching with corresponding service contents in the current virtual anchor point, and calculating a matching degree value Match_Lev2 related to the service contents;
the resource management node calculates the User request semantic tag user_req= (RTag) using the following formula 1 ，RTag 2 ，...，RTag H ) Semantic Tag serv_tag= (STag) of service content involved after preliminary matching with current virtual anchor point 1 ，STag 2 ，...，STag G ) Match_lev2:
Match_Lev2＝Matching(User_Req，Serv_Tag)
wherein RTag i Representing the content of the user request semantic tags, H representing the number of the user request semantic tags, STag i Content representing semantic tags of the service content, G representing the number of semantic tags of the current service content;
The resource management node judges whether the Match degree value Match_Lev2 about the service content is larger than or equal to a preset Match degree base line value Match_BaseL2;
if the matching degree value Match_Lev2 is larger than or equal to the preset matching degree baseline value Match_BaseL2, providing service by the current virtual anchor point;
if the Match degree value match_lev1 is smaller than the preset Match degree baseline value match_basel1, the current virtual anchor point cannot provide service, and the user request data is required to be routed to a subsequent virtual anchor point continuously.
7. The satellite communication network architecture of claim 5, wherein the step of the satellite communication management module managing satellite communications further comprises a demand matching step comprising:
in the process of returning the semantic content data packet for providing the service to the user side, when the semantic content data packet for providing the service is routed to a certain satellite, the satellite forwards the semantic content data packet for providing the service to the resource management node in the current virtual anchor point;
the resource management node unpacks the semantic content data packet for providing the service at the network layer to obtain a service content semantic tag for providing the service, and the resource management node judges whether the semantic content data packet for providing the service needs to be cached according to the service content semantic tag;
And if the cache is needed, the resource management node caches the copy of the semantic content data packet for providing the service to any satellite in the current virtual anchor point.
8. The satellite communication network architecture of claim 7, wherein the step of the resource management node determining whether buffering of the semantic content data packets for providing services is required based on the service content semantic tags comprises:
judging whether the service content semantic tags are requested by the current anchor point according to the history request within a certain time, judging whether the related semantic tags have cached certain content in the current virtual anchor point, and if not, directly caching the semantic content data packet for providing service; and
the resource management node obtains user request semantic features according to all user request data of the current virtual anchor point service area, and generates a common request Tag Comm_Tag;
the resource management node calculates a matching degree value Match_Lev3 of the service content semantic Tag Serv_Tag and the common request Tag Comm_Tag by using the following formula:
Match_Lev3＝Matching(Comm_Tag，Serv_Tag)
the resource management node judges whether the matching degree value Match_Lev3 is more than or equal to a preset matching degree base line value Match_BaseL3;
If the matching degree value Match_Lev3 is larger than or equal to the preset matching degree baseline value Match_BaseL3, the semantic content data packet for providing service needs to be cached;
if the matching degree value Match_Lev3 is smaller than the preset matching degree baseline value Match_BaseL3, the semantic content data packet for providing service does not need to be cached.
9. The satellite communication network architecture of claim 1, wherein a high orbit satellite is set in the virtual anchor as the resource management node.
10. The satellite communication network architecture of claim 1, wherein a resource management node queue is formed by presetting any low-orbit satellite, the low-orbit satellites in the resource management node queue can synchronously move, and in the process that the low-orbit satellites move to another virtual anchor point, the low-orbit satellites in the resource management node queue are always in one-to-one correspondence with the virtual anchor point, and the low-orbit satellites in one-to-one correspondence with the virtual anchor point serve as the resource management nodes.
11. The satellite communications network architecture of claim 1, further comprising a satellite motion management module, the satellite motion management module managing satellite motion comprising: when a certain satellite leaves a current virtual anchor point and enters another virtual anchor point, the resource management node distributes the cache content of the satellite to at least one satellite in the current virtual anchor point; and
The resource management node of the other virtual anchor point judges the matching degree of the cache content and the virtual anchor point;
if the matching degree is high, the satellite reserves the self cache content, and the resource management node of the other virtual anchor point distributes service content based on the cache space of the satellite;
and if the matching degree is low, deleting the self cache content by the satellite, and distributing corresponding service content copies to the satellite by the resource management node of the other virtual anchor point.
CN202310100292.5A 2023-02-06 2023-02-06 Satellite communication network architecture based on semantic content Active CN116073889B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310100292.5A CN116073889B (en) 2023-02-06 2023-02-06 Satellite communication network architecture based on semantic content

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310100292.5A CN116073889B (en) 2023-02-06 2023-02-06 Satellite communication network architecture based on semantic content

Publications (2)

Publication Number Publication Date
CN116073889A CN116073889A (en) 2023-05-05
CN116073889B true CN116073889B (en) 2023-09-01

Family

ID=86172920

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310100292.5A Active CN116073889B (en) 2023-02-06 2023-02-06 Satellite communication network architecture based on semantic content

Country Status (1)

Country Link
CN (1) CN116073889B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9998207B1 (en) * 2017-07-19 2018-06-12 Vector Launch Inc. Orbital network layering in satellite platforms
CN110012516A (en) * 2019-03-28 2019-07-12 北京邮电大学 A kind of low orbit satellite routing policy method based on deeply study framework
CN113315972A (en) * 2021-05-19 2021-08-27 西安电子科技大学 Video semantic communication method and system based on hierarchical knowledge expression
CN113824489A (en) * 2021-11-22 2021-12-21 凯睿星通信息科技(南京)股份有限公司 Satellite network resource dynamic allocation method, system and device based on deep learning
WO2022039302A1 (en) * 2020-08-20 2022-02-24 엘지전자 주식회사 Method for controlling calculations of deep neural network in wireless communication system, and apparatus therefor
CN114549405A (en) * 2022-01-10 2022-05-27 中国地质大学（武汉） High-resolution remote sensing image semantic segmentation method based on supervised self-attention network
CN114615499A (en) * 2022-05-07 2022-06-10 北京邮电大学 Semantic optical communication system and method for image transmission

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113328777B (en) * 2021-04-25 2022-08-30 西安电子科技大学 Hierarchical network operation and maintenance and resource management and control system and method for giant satellite constellation

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9998207B1 (en) * 2017-07-19 2018-06-12 Vector Launch Inc. Orbital network layering in satellite platforms
CN110012516A (en) * 2019-03-28 2019-07-12 北京邮电大学 A kind of low orbit satellite routing policy method based on deeply study framework
WO2022039302A1 (en) * 2020-08-20 2022-02-24 엘지전자 주식회사 Method for controlling calculations of deep neural network in wireless communication system, and apparatus therefor
CN113315972A (en) * 2021-05-19 2021-08-27 西安电子科技大学 Video semantic communication method and system based on hierarchical knowledge expression
CN113824489A (en) * 2021-11-22 2021-12-21 凯睿星通信息科技(南京)股份有限公司 Satellite network resource dynamic allocation method, system and device based on deep learning
CN114549405A (en) * 2022-01-10 2022-05-27 中国地质大学（武汉） High-resolution remote sensing image semantic segmentation method based on supervised self-attention network
CN114615499A (en) * 2022-05-07 2022-06-10 北京邮电大学 Semantic optical communication system and method for image transmission

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于图像超分辨重建的低轨卫星频谱感知数据空间分辨率提高方法;蔚瑞 等;《中国科学院大学学报》;第39卷(第3期);第386-392页 *

Also Published As

Publication number Publication date
CN116073889A (en) 2023-05-05

Similar Documents

Publication Publication Date Title
Zhang et al. Satellite mobile edge computing: Improving QoS of high-speed satellite-terrestrial networks using edge computing techniques
Zhang et al. Cooperative content caching in 5G networks with mobile edge computing
Wang et al. A dynamic resource scheduling scheme in edge computing satellite networks
CN109391681B (en) MEC-based V2X mobility prediction and content caching offloading scheme
Hou et al. Edge intelligence for mission-critical 6G services in space-air-ground integrated networks
CN111124647B (en) Intelligent edge calculation method in Internet of vehicles
Wang et al. Mobility-aware partial computation offloading in vehicular networks: A deep reinforcement learning based scheme
CN111010684A (en) Internet of vehicles resource allocation method based on MEC cache service
CN110928694B (en) Computer system
Nguyen et al. Towards flying mobile edge computing
CN110881054A (en) Edge caching method, device and system
CN113206796A (en) Transfer, calculation and storage integrated cooperative system and method
CN102752799A (en) Routing method, device and system for delay tolerant network
CN117040594A (en) Internet remote sensing satellite real-time service system oriented to mobile terminal user
CN116073889B (en) Satellite communication network architecture based on semantic content
Aloqaily et al. Trustworthy cooperative UAV-based data management in densely crowded environments
CN117196014B (en) Model training method and device based on federal learning, computer equipment and medium
WO2024078132A1 (en) Information freshness perception distributed cache method for high definition map
Chowdhury et al. An optimal strategy for UAV-assisted video caching and transcoding
Han et al. Space edge cloud enabling service migration for on-orbit service
CN109617960B (en) Attribution separation-based web AR data presentation method
CN110661566A (en) Unmanned aerial vehicle cluster networking method and system adopting depth map embedding
CN111787594A (en) Decision tree algorithm-based unmanned aerial vehicle ad hoc network DSR protocol implementation method
Liu et al. User-Driven Cache Replacement Strategy for Satellite-Terrestrial Networks Based on SDN
CN117118495B (en) Space-based general calculation integrated network system and remote sensing data on-orbit processing method

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