Aircraft continuous communication service method

Abstract

The invention relates to the technical field of communication, and discloses an aircraft continuous communication service method, which comprises the following steps: receiving a continuous communication service registration request, and generating a prediction request based on the continuous communication service registration request; on the basis of the prediction request, a link prediction result list is generated, and the link prediction result list is used for representing predicted link conditions of the aircraft and other nodes in the whole flight process; respectively sending broadcast messages of registration information and session information corresponding to the registration request to satellite nodes and ground base station nodes in the link prediction list; and after receiving the broadcast message, the ground base station node sends a registration reply of the continuous communication service. According to the method, the link prediction result list is generated based on the prediction model, the broadcast messages of the registration information and the session information are sent to the related satellite nodes and the ground base station nodes according to the link prediction result list, preparation is made for communication requirements in the flight process of an aircraft, and therefore the communication service continuity of airborne users in the flight process is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method for continuous communication service of an aircraft. Background Art

[0002] Commercial aircraft are being equipped with more and more communication systems to provide a wide range of services, from passenger internet access to in-flight operations. Connectivity is a key driver of the digital transformation of the aviation industry, leading to the development of fully connected aircraft.

[0003] The aviation market is expected to take advantage of standardized solutions based on 5G systems that will operate with terrestrial networks (TN) and non-terrestrial networks (NTN). These solutions include 5G cellular networks for airport operations, as well as 5G air-to-ground and 5G-NTN air connectivity through satellite communication systems. Summary of the invention

[0004] In view of this, the present invention provides a method for continuous communication service of an aircraft to solve the current problem of failure to ensure the continuity of communication service for aircraft users.

[0005] In a first aspect, the present invention provides a system for ensuring continuous communication services for aircraft, the system comprising:

[0006] The airborne terminal is used to send a continuous communication service registration request, wherein the continuous communication service registration request includes an estimated departure time, an estimated arrival time, an estimated route information, and registration information of the airborne terminal;

[0007] A radio access network, configured to receive and forward a continuous communication service registration request to an access and mobility management function;

[0008] Access and mobility management function, used to receive continuous communication service registration requests and send registration information query requests to unified data management;

[0009] Unified data management, used to receive registration information query requests and send prediction requests to the network data analysis function;

[0010] The network data analysis function is used to receive prediction requests, generate a link prediction result list, and send a prediction request response containing the link prediction result list to the unified data management; the link prediction list is used to represent the expected link status of the aircraft with other nodes during the entire flight process;

[0011] The access and mobility management function is also used to send broadcast messages of pre-cached registration information and session information to corresponding satellite nodes and ground base station nodes according to the link prediction result list, and send continuous communication service registration replies to the wireless access network.

[0012] The system for ensuring continuous communication services for aircraft provided by the embodiment of the present invention supports seamless switching of aircraft between different communication nodes, including low-orbit satellites and ground base stations. At the same time, it can generate a link prediction result list according to the prediction request to obtain the communication nodes that the aircraft may need during the flight, and cache the registration information and session information of the aircraft on these nodes in advance, ensuring that the aircraft can seamlessly switch communication nodes during the flight, thereby improving the continuity of communication services and reducing the risk of communication interruption. It can ensure continuous communication of aircraft based on low-orbit satellites.

[0013] In an optional implementation, the access and mobility management function is further used to receive cache result replies from the satellite node and the ground base station node, and calculate the cache success rate based on the received cache result replies.

[0014] The system for ensuring continuous communication services for aircraft provided by the embodiment of the present invention receives cache result replies from satellites and ground base stations, and calculates the cache success rate based on these replies, which is an important indicator for measuring system performance and can reflect the efficiency and effect of information pre-caching. The access and mobility management function can understand the pre-caching status of information in real time, which helps the system monitor and ensure the integrity of communication service preparation, and promptly discover and solve possible problems.

[0015] In an optional implementation, a prediction model is deployed on the network data analysis function, and the prediction model is used to generate a link prediction result list based on a hypervariable graph; the hypervariable graph is obtained based on the estimated departure time, the estimated arrival time and the estimated route information.

[0016] The system for ensuring continuous communication services for aircraft provided by an embodiment of the present invention can fully utilize the data processing and analysis capabilities of NWDAF by deploying the prediction model on NWDAF. The prediction model can generate a hypervariable graph based on key data such as the estimated take-off time, the estimated arrival time, and the estimated route information, so as to accurately predict the connection status of the aircraft with other communication nodes during the flight.

[0017] In a second aspect, the present invention provides a method for continuous communication service of an aircraft, the method is applied to the system for ensuring continuous communication service of an aircraft in the first aspect, and the method comprises:

[0018] receiving a continuous communication service registration request, the continuous communication service registration request including an estimated departure time, an estimated arrival time, and an estimated route information;

[0019] Based on the continuous communication service registration request, a prediction request is generated; the prediction request includes an estimated departure time, an estimated arrival time, an estimated route information, and registration information of the airborne terminal;

[0020] Based on the prediction request, a link prediction result list is generated. The link prediction list is used to represent the expected link status between the aircraft and other nodes during the entire flight process;

[0021] Sending a broadcast message of registration information and session information corresponding to the registration request to the satellite node and the ground base station node in the link prediction linked list respectively;

[0022] When the ground base station node receives the broadcast message, it sends a registration reply for the continuous communication service.

[0023] The method for providing continuous communication services for aircraft provided in an embodiment of the present invention generates a link prediction result list based on the estimated take-off time, the estimated arrival time and the estimated route information, and accordingly sends a broadcast message of registration information and session information to relevant satellite nodes and ground base station nodes, thereby being able to prepare in advance for the communication needs of the aircraft during flight, thereby significantly improving the continuity of communication services for onboard users during flight.

[0024] In an optional implementation, based on the prediction request, a link prediction result list is generated, including:

[0025] Construct a hypervariable graph based on the estimated departure time, estimated arrival time, and estimated route information;

[0026] The hypervariable graph is fed into the prediction model to obtain a list of link prediction results.

[0027] The method for continuous communication service of an aircraft provided in an embodiment of the present invention can comprehensively and accurately reflect the communication needs and environmental changes during the flight of the aircraft by integrating key data such as the estimated take-off time, the estimated arrival time and the estimated route information into a hypervariable graph. At the same time, in addition to the route information, the construction of the hypervariable graph also incorporates time dimension data such as the take-off and arrival times, which enables the prediction model to more accurately capture the link relationship between the aircraft and other communication nodes, thereby improving the accuracy of the prediction.

[0028] In an optional implementation, constructing a hypervariable graph based on the estimated departure time, the estimated arrival time, and the estimated route information includes:

[0029] Obtain the longitude and latitude coordinates of the aircraft, satellite nodes, and ground base station nodes;

[0030] Convert latitude and longitude coordinates to Earth-centered Earth-fixed coordinates;

[0031] Calculate the straight-line distance between the aircraft and each satellite node and the ground base station node based on the aircraft, each satellite node and the ground base station node;

[0032] If the straight-line distance between the aircraft and the target node is less than the maximum visible distance, a connecting line is added between the aircraft and the target node;

[0033] Add connections between adjacent nodes to obtain a fully connected hypervariable graph.

[0034] The method for aircraft continuous communication service provided by an embodiment of the present invention accurately obtains the longitude and latitude coordinates of the aircraft, each satellite node and ground base station node, and converts them into a unified geocentric and earth-fixed coordinate system. The straight-line distance between the aircraft and each node is calculated based on the converted coordinates. This can more realistically reflect the relative position relationship between the aircraft and each communication node during flight, thereby improving the prediction accuracy of the prediction model for the communication link status of the aircraft during flight.

[0035] In an optional implementation, the hypervariable graph is input into the prediction model to obtain a link prediction result list, including:

[0036] The multivariate time series window at the preset time point is used as input data and embedded into the hypervariable graph as the feature of each node;

[0037] Perform discrete Fourier transform on node features to obtain frequency output;

[0038] Based on the frequency output, an inverse discrete Fourier transform is performed on the node features;

[0039] Perform feature extraction and nonlinear transformation on node features to obtain transformation results;

[0040] Generate a list of link prediction results based on the transformation results.

[0041] The method for aircraft continuous communication service provided by an embodiment of the present invention includes a step of performing discrete Fourier transform (DFT) on node features, so that the prediction model can analyze the performance of node features in the frequency domain, and then performing an inverse discrete Fourier transform on the node features, so that the prediction model can return to the time domain after processing the frequency domain information, thereby maintaining the integrity and coherence of the original time series data, and finally extracting key information through feature extraction and nonlinear transformation to generate a link prediction result list.

[0042] In an optional implementation, the registration reply of the continuous communication service includes a cache success rate; the cache success rate is calculated based on the reply of the cache result sent by the ground base station after receiving the broadcast message.

[0043] The method for aircraft continuous communication service provided by an embodiment of the present invention provides an intuitive indicator for users by introducing a cache success rate, so that users can more accurately understand which ground base stations and satellite nodes perform better in receiving and caching registration information. A high cache success rate means that the aircraft's link with each communication node during flight is more stable, thereby reducing the risk of communication interruption and improving the overall user experience.

[0044] In an optional implementation, the method further includes monitoring QoE indicators throughout the flight and adjusting network resources and service strategies based on the QoE indicators, wherein the QoE indicators include freeze rate, end-to-end delay, and continuous service duration.

[0045] The method for continuous communication service of an aircraft provided in an embodiment of the present invention can timely detect and respond to problems that may affect the user's communication experience through real-time monitoring of QoE indicators such as freeze rate, end-to-end delay, and continuous service duration.

[0046] In a third aspect, the present invention provides an aviation networking system, the system comprising:

[0047] The airborne terminal is used to send a continuous communication service registration request, wherein the continuous communication service registration request includes an estimated departure time, an estimated arrival time, and an estimated route information and registration information of the airborne terminal;

[0048] The satellite space segment includes at least one satellite for providing a wireless communication link between the onboard terminal and the ground base station;

[0049] The ground base station is used to receive signals from the satellite space segment and forward them to the corresponding network node;

[0050] The Internet of Things gateway is used to receive the service data of the ground base station, perform data transparent transmission and distribution, and allocate IPv6 addresses to the connected airborne terminals;

[0051] A traffic control center, used to connect the airborne terminal to the network;

[0052] The air traffic control business service center includes several local air traffic control centers, which are used to provide aviation traffic business and Internet of Things business services.

[0053] In a fourth aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for aircraft continuous communication service of the above-mentioned second aspect or any corresponding embodiment thereof by executing the computer instructions.

[0054] In a fifth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for providing continuous aircraft communication services in the second aspect or any corresponding embodiment thereof.

[0055] In a sixth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method for providing continuous aircraft communication services according to the second aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 is a schematic diagram of a system for ensuring continuous communication services for aircraft according to an embodiment of the present invention;

[0058] Figure 2 is a schematic diagram of the architecture of a prediction model according to an embodiment of the present invention;

[0059] Figure 3 is a schematic diagram of an interface design of a prediction model according to an embodiment of the present invention;

[0060] Figure 4 is a flowchart of a method for aircraft continuous communication service according to an embodiment of the present invention;

[0061] Figure 5 is a schematic diagram of a hypervariable graph according to an embodiment of the present invention;

[0062] Figure 6 is a schematic diagram of QoE indicators of onboard user service behavior according to an embodiment of the present invention;

[0063] Figure 7 is a schematic diagram of a QoS detector according to an embodiment of the present invention;

[0064] Figure 8 is a general architecture diagram of aviation networking according to an embodiment of the present invention;

[0065] Fig. 9 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0067] Commercial aircraft are being equipped with more and more communication systems to provide a wide range of services, from passenger internet access to in-flight operations. Connectivity is a key driver of the digital transformation of the aviation industry, leading to the development of fully connected aircraft.

[0068] The aviation market is expected to take advantage of standardized solutions based on 5G systems that will operate with terrestrial networks (TN) and non-terrestrial networks (NTN). These solutions include 5G cellular networks for airport operations, as well as 5G air-to-ground and 5G-NTN air connectivity through satellite communication systems.

[0069] According to an embodiment of the present invention, a system for ensuring continuous communication services for aircraft is provided, the system comprising:

[0070] The airborne terminal is used to send a continuous communication service registration request, wherein the continuous communication service registration request includes an estimated departure time, an estimated arrival time, and an estimated route information and registration information of the airborne terminal;

[0071] A radio access network, configured to receive and forward a continuous communication service registration request to an access and mobility management function;

[0072] Access and mobility management function, used to receive continuous communication service registration requests and send registration information query requests to unified data management;

[0073] Unified data management, used to receive registration information query requests and send prediction requests to the network data analysis function;

[0074] The network data analysis function is used to receive prediction requests, generate a link prediction result list, and send a prediction request response containing the link prediction result list to the unified data management; the link prediction list is used to represent the expected link status of the aircraft with other nodes during the entire flight process;

[0075] The access and mobility management function is also used to send broadcast messages of pre-cached registration information and session information to corresponding satellite nodes and ground base station nodes according to the link prediction result list, and send continuous communication service registration replies to the wireless access network.

[0076] like Figure 1As shown in the figure, the system mainly includes the following key components: airborne terminal (i.e., aircraft), radio access network (Radio Access Network, RAN), access and mobility management function (Access and Mobility Management Function, AMF), unified data management (Unified Data Management, UDM) and network data analysis function (Network Data Analytics Function, NWDAF), specifically:

[0077] The airborne terminal is used to send a continuous communication service registration request, which includes the estimated take-off time (DT), the estimated arrival time (AT), the estimated route information (Rmap) and the registration information of the airborne terminal (P UE ).

[0078] The radio access network, located at the airport, is responsible for receiving and forwarding the continuous communication service registration requests sent by the onboard terminals to the access and mobility management function.

[0079] The network data analysis function receives the prediction request from UDM and generates a list of prediction results of the links between the aircraft and other nodes during the entire flight process.

[0080] The access and mobility management function is responsible for receiving the registration request forwarded by the RAN; sending a registration information query request to the unified data management to obtain the UE's subscription data and the list of nodes that need to pre-store registration information and session information.

[0081] Unified data management, receiving registration information query requests from AMF. Send prediction requests to the network data analysis function, carrying the estimated departure time, estimated arrival time and estimated route information. Receive prediction request responses from NWDAF, including a list of linked prediction results. Send registration information query replies to AMF.

[0082] At the same time, the access and mobility management function is also used to send broadcast messages of pre-cached registration information and session information to the corresponding satellite nodes and ground base station nodes according to the link prediction result list, and send continuous communication service registration replies to the RAN.

[0083] In some optional implementations, the access and mobility management function is further used to receive cache result replies from satellite nodes and ground base station nodes, and calculate the cache success rate based on the received cache result replies.

[0084] After receiving the broadcast message from AMF, the ground base station will send a reply of the cache result to AMF; AMF is also used to receive each cache result reply and calculate the cache success rate SCache based on each cache result reply. SCache is used as one of the indicators in the user experience mechanism to ensure the continuous communication experience of airborne users. AMF sends a reply of continuous communication service registration to the airport's RAN, including SCache.

[0085] In some optional implementations, a prediction model is deployed on the network data analysis function, and the prediction model is used to generate a link prediction result list based on a hypervariable graph; the hypervariable graph is obtained based on the estimated departure time, the estimated arrival time and the estimated route information.

[0086] The prediction model is based on the FourierGNN network architecture to predict the links between the aircraft node and other nodes in the upcoming flight. Specifically, the schematic diagram of the prediction model architecture is as follows: Figure 2 As shown in Figure 1, the prediction model takes the multivariate time series window Xt∈RN×T of N variables at a given timestamp T as input data, constructs a fully connected hypervariable graph gt=(Xgt,Agt) with NT nodes, and regards each element of Xt as a node of Gt, where Xgt∈RNT×1 represents the node feature and Agt∈RNT×NT is the adjacency matrix. Therefore, the multivariate time series prediction task can be reformulated as the prediction of the hypervariable graph, where θg represents the network parameters of the hypervariable graph:

[0087]

[0088] The prediction model specifically includes:

[0089] DFT module: Discrete Fourier Transform, mainly responsible for performing discrete Fourier transform (DFT) on each embedded discrete space-time dimension to obtain frequency output.

[0090] FGO module: Fourier Graph Operator, is a learnable network layer in Fourier space, which mainly captures richer graph structure information by converting the node features on the graph into the frequency domain for operation and then converting it back to the spatial domain.

[0091] IDFT module: Inverse discrete Fourier transform, which is mainly responsible for converting the features processed in the frequency domain back to the spatial domain.

[0092] FFN module: Feedforward neural network, which mainly provides deeper feature extraction and nonlinear transformation capabilities in the spatial domain, and is used to process and transform node features.

[0093] The prediction model is used to generate a list of link prediction results based on a hypervariable graph; the hypervariable graph is obtained based on the estimated departure time, the estimated arrival time, and the estimated route information.

[0094] Optionally, the dataset is divided into training, validation, and test sets in a ratio of 7:2:1 in time to train the model.

[0095] The method for constructing the communication node hypervariable graph is as follows: first, the longitude and latitude, that is, the geographic coordinates of each node, are converted into ECEF coordinates. Then, the distance formula in three-dimensional space is used to calculate the distance between each satellite or ground base station node and the aircraft node. If the straight-line distance between the aircraft node and the satellite or ground base station node is less than the maximum visible distance, a connecting line is added between the two nodes of the aircraft and the satellite or ground base station in the hypervariable graph; in addition, connecting lines are also added between adjacent satellite or ground base station nodes.

[0096] Mark all nodes by time. Assuming there are N nodes and T time, there are NT new nodes. Based on these new nodes, a graph is constructed. When the time lag principle is considered, each point may be connected, thus obtaining a super-element graph Gt.

[0097] In addition, the interface design between the prediction model and the continuous communication system of NWDAF is as follows Figure 3 As shown, specifically: interface FNN1 is used for NWDAF to interact with the prediction model through FNN-1; interface FNN-2 is used for the prediction model to interact with NWDAF through FNN-2.

[0098] According to an embodiment of the present invention, a method for continuous communication service of an aircraft is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0099] An embodiment of the present invention provides a method for continuous communication service of an aircraft, and the method is applied to a system for ensuring continuous communication service of an aircraft in the above embodiment. Figure 4 is a flow chart of a method for aircraft continuous communication service according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:

[0100] Step S401: receiving a continuous communication service registration request.

[0101] Specifically, in the preparation stage before the aircraft takes off, the airborne terminal will actively initiate a continuous communication service registration request to the ground core network. The continuous communication service registration request includes the estimated take-off time, estimated arrival time, estimated route information and the registration information of the airborne terminal.

[0102] Furthermore, the continuous communication service registration request contains various data information so that the ground core network can accurately understand the aircraft's flight plan and communication needs. These data information mainly include but are not limited to: Estimated take-off time (DT): the specific time when the aircraft is scheduled to take off; Estimated arrival time (AT): the time when the aircraft is expected to arrive at the destination; Estimated route information (Rmap): detailed flight route, which may include the starting point, end point, key points along the way, and expected flight altitude and speed; Airborne terminal registration information (PUE): including the UE identifier (such as SUCI or IMSI) and the requested NSSAI (network slice selection information), which are used to identify the aircraft and the type of communication service it requests.

[0103] Furthermore, the wireless access network located at the airport is responsible for receiving continuous communication service registration requests from onboard terminals and forwarding them to the AMF.

[0104] Step S402: Generate a prediction request based on the continuous communication service registration request.

[0105] Specifically, after receiving the continuous communication service registration request, the AMF sends a registration information query request to the UDM, requesting to obtain the UE's subscription data and a list of nodes that need to pre-store registration information and session information.

[0106] Furthermore, UDM sends a prediction request to NWDAF, and the prediction request carries the estimated take-off time DT, the estimated arrival time AT, and the estimated route Rmap information.

[0107] Step S403: Generate a link prediction result list based on the prediction request.

[0108] Specifically, the link prediction list is used to characterize the expected links between the aircraft and other nodes during the entire flight process.

[0109] In some optional implementations, the above step S203 includes:

[0110] Step S4031, constructing a hypervariable graph based on the estimated departure time, the estimated arrival time and the estimated route information;

[0111] Specifically, NWDAF constructs a hypervariable graph based on the estimated take-off time, estimated arrival time, and estimated route information. The hypervariable graph is a complex mathematical model used to represent the link relationships that the aircraft may establish with other communication nodes, such as satellites, ground base stations, etc. during the flight.

[0112] Step S4032, input the hypervariable graph into the prediction model to obtain a link prediction result list.

[0113] Specifically, the prediction model analyzes the information in the hypervariable graph and outputs the above-mentioned link prediction result list. This list includes which nodes the aircraft is expected to establish links with during the flight, as well as the expected quality of these links, such as signal strength, bandwidth, and duration.

[0114] Step S404: Send a broadcast message of registration information and session information corresponding to the registration request to the satellite node and the ground base station node in the link prediction linked list respectively.

[0115] Specifically, based on the link prediction result list generated by the prediction request, identifiers and related information of all nodes that need to receive registration information and session information, ie, satellite nodes and ground base station nodes, are extracted.

[0116] Furthermore, for each node that needs to receive information, the system prepares corresponding registration information and a broadcast message of session information according to the identifier of the satellite or ground base station node.

[0117] Optionally, the registration information includes the airborne terminal registration information and session information including the session identifier and service quality requirements. In addition, the broadcast message may also include some additional information, such as the message sending timestamp, the message sequence number, etc., so that the receiving node can correctly process and verify the message.

[0118] Step S405: After receiving the broadcast message, the ground base station node sends a registration reply for the continuous communication service.

[0119] Specifically, after receiving the broadcast message from the AMF through its communication interface, the ground base station node extracts the registration information and session information of the aircraft and stores them in the local cache.

[0120] Further, the ground base station node sends the registration reply message back to the AMF through its communication interface, and the AMF then sends a reply for the continuous communication service registration to the RAN at the airport. Finally, the RAN forwards the continuous communication service registration reply to the onboard terminal.

[0121] In summary, the method for providing continuous communication service for an aircraft provided in an embodiment of the present invention sends a continuous communication service registration request to the ground core network before the aircraft takes off. The request includes the estimated departure time DT, the estimated arrival time AT, the detailed estimated route Rmap, and the airborne terminal registration information P. UE， This includes the UE identifier, such as SUCI or IMSI, and the requested network service slice selection information NSSAI.

[0122] Next, the relevant network elements in the ground core network will generate a prediction request based on the received continuous communication service registration request. The prediction request also contains key information such as the estimated take-off time, estimated arrival time and estimated route.

[0123] This information is then fed into a prediction model deployed on the NWDAF network element to build a hypervariable graph. The hypervariable graph predicts the links between the aircraft node and other nodes in the upcoming flight based on the FourierGNN network architecture; through complex algorithms and data analysis, the prediction model generates a list of link prediction results, which details which nodes the aircraft is expected to establish communication links with during the flight.

[0124] The AMF network element then sends broadcast messages to satellite nodes and ground base station nodes that are expected to establish communication links with the aircraft based on the information in the list. These messages contain the aircraft's registration information and session information to ensure that these nodes can quickly establish communication links when the aircraft enters its coverage area.

[0125] Finally, when the ground base station node receives these broadcast messages, it will perform a series of processing and verification work. Once the validity and integrity of the message are confirmed, the ground base station node will send a registration reply for continuous communication service to the AMF. This reply indicates that the ground base station node is ready to provide continuous communication services for the aircraft, thereby ensuring the communication continuity of the aircraft during flight.

[0126] In some optional implementations, a hypervariable graph is constructed based on the estimated departure time, the estimated arrival time, and the estimated route information, including:

[0127] Obtain the longitude and latitude coordinates of the aircraft, satellite nodes, and ground base station nodes;

[0128] Convert latitude and longitude coordinates to Earth-centered Earth-fixed coordinates;

[0129] Calculate the straight-line distance between the aircraft and each satellite node and the ground base station node based on the aircraft, each satellite node and the ground base station node;

[0130] If the straight-line distance between the aircraft and the target node is less than the maximum visible distance, a connecting line is added between the aircraft and the target node;

[0131] Add connections between adjacent nodes to obtain a fully connected hypervariable graph.

[0132] First, convert the longitude, latitude and height (geographic coordinates) into ECEF coordinates. For a given longitude τ, latitude φ and height h, we use the following conversion formula:

[0133]

[0134] x=(N(φ)+h)cos(φ)cos(τ),y=(N(φ)+h)cos(φ)sin(τ)

[0135] z=(N(φ)(1-e 2 )+h)sin(φ)

[0136] Psat = (τsat, φsat, hsat) is the position matrix of the satellite or ground base station node at time T0 (for example, 9 satellite nodes), Pplane = (τplane, φplane, hplane) is the position matrix of the aircraft node at time T0 (for example, an aircraft node), τ represents longitude, φ represents latitude, all angles are expressed in radians, h represents altitude, α is the major radius of the earth ellipsoid, e is the first eccentricity, α = 6378137 meters = 6378 kilometers, e2 = 0.00669437999014.

[0137]

[0138] P plane =[-149.0927658°,64.9961215°,10]

[0139] Use the distance formula in three-dimensional space to calculate the distance (km) between each satellite (base station) node and the aircraft node, and obtain d(sat, plane)t0 at time T0;

[0140]

[0141] Through the collection of open source data (global flight route open source data, Starlink orbit files), the geographic location coordinates of satellite (base station) nodes and aircraft nodes are drawn. sat ,P plane , slice the flight time at 10-minute intervals to obtain the satellite or ground base station node location data from takeoff to landing (P sat t0 ,P sat t1 ,Psat t2 ,...,P sat tn ), aircraft node position data (P plane t0 ,P plane t1 ,P plane t2 ,...,P plane tn ), calculate D according to the above algorithm (sat,plane) =(d (sat,plane) t0 ,d (sat,plane) t1 ,d (sat,plane) t2 ,...,d (sat,plane) tn ), as shown in the following table:

[0142]

[0143]

[0144] If the straight-line distance between the aircraft node and the satellite or ground base station node is less than the maximum visible distance ε, then a connection line is added between the aircraft and the satellite or ground base station nodes in the hypergraph Gt. In addition, a connection line is added between adjacent satellite or ground base station nodes. All nodes are marked by time. Assuming there are N nodes and T time, there are NT new nodes. Based on this new node, a graph is constructed. Each point may be connected (considering the time lag principle, etc.), thus obtaining a super-element graph Gt. An example of a hyper-variable graph is shown in FIG. Figure 5 shown.

[0145] In some optional implementations, the hypervariable graph is input into the prediction model to obtain a link prediction result list, including:

[0146] The multivariate time series window at the preset time point is used as input data and embedded into the hypervariable graph as the feature of each node;

[0147] Perform discrete Fourier transform on node features to obtain frequency output;

[0148] Based on the frequency output, an inverse discrete Fourier transform is performed on the node features;

[0149] Perform feature extraction and nonlinear transformation on node features to obtain transformation results;

[0150] Generate a list of link prediction results based on the transformation results.

[0151] Specifically, a multivariate time series window Xt∈RN×T of N variables at a given timestamp T is taken as input data, and a fully connected hypervariable graph gt=(Xgt,Agt) with NT nodes is constructed. Each element of Xt is regarded as a node of Gt, where Xgt∈RNT×1 represents the node feature and Agt∈RNT×NT is the adjacency matrix. Therefore, the multivariate time series prediction task can be reformulated as the prediction of the hypervariable graph, where θg represents the network parameters of the hypervariable graph:

[0152]

[0153] The prediction model specifically includes:

[0154] DFT module: Discrete Fourier Transform, mainly responsible for performing discrete Fourier transform (DFT) on each embedded discrete space-time dimension to obtain frequency output.

[0155] FGO module: Fourier Graph Operator, is a learnable network layer in Fourier space, which mainly captures richer graph structure information by converting the node features on the graph into the frequency domain for operation and then converting it back to the spatial domain.

[0156] IDFT module: Inverse discrete Fourier transform, which is mainly responsible for converting the features processed in the frequency domain back to the spatial domain.

[0157] FFN module: Feedforward neural network, which mainly provides deeper feature extraction and nonlinear transformation capabilities in the spatial domain, and is used to process and transform node features.

[0158] In some optional implementations, the registration reply for the continuous communication service includes a cache success rate; the cache success rate is calculated based on the reply of the cache result sent by the ground base station after receiving the broadcast message.

[0159] AMF receives replies for each cache result and calculates the cache success rate SCache. SCache is used as one of the indicators in the user experience mechanism to ensure the continuous communication experience of onboard users. AMF sends a reply to the airport's RAN for continuous communication service registration, including SCache.

[0160] In some optional embodiments, the method also includes monitoring QoE indicators throughout the flight and adjusting network resources and service strategies based on the QoE indicators, where the QoE indicators include freeze rate, end-to-end delay, and continuous service time.

[0161] The QoE indicators cover the entire process of the in-flight user's Internet behavior, and are defined with the minimum behavior granularity and the minimum threshold user experience. The access registration of a single service is the behavior granularity, and the access success rate is the QoE indicator of the behavior granularity. The same is true for the others. It is worth noting that there are multiple QoE indicators for the service process: freeze rate, end-to-end delay, and continuous service duration. These indicators are measured by plug-ins installed in the user-side application. The QoE indicator diagram of the in-flight user service behavior is shown in the figure below. Figure 6 shown.

[0162] Specifically, data is collected by installing detectors on each link. Figure 7 As shown, the probe is used to monitor the traffic from one or more source stations to one or more destinations. When checking in or online, the onboard user chooses to subscribe to the onboard communication package and the corresponding QoS requirements. If the user does not provide relevant QoS requirements, the network side can provide default QoS requirements.

[0163] QoS indicators of onboard user service behavior: link throughput, delay, bit rate, jitter, packet loss, and availability.

[0164] According to an embodiment of the present invention, an aviation networking system is provided. Figure 8 As shown, the system includes:

[0165] The airborne terminal is used to send a continuous communication service registration request, wherein the continuous communication service registration request includes an estimated departure time, an estimated arrival time, and an estimated route information and registration information of the airborne terminal;

[0166] The satellite space segment includes at least one satellite for providing a wireless communication link between the onboard terminal and the ground base station;

[0167] The ground base station is used to receive signals from the satellite space segment and forward them to the corresponding network node;

[0168] The Internet of Things gateway is used to receive the service data of the ground base station, perform data transparent transmission and distribution, and allocate IPv6 addresses to the connected airborne terminals;

[0169] A traffic control center, used to connect the airborne terminal to the network;

[0170] The air traffic control business service center includes several local air traffic control centers, which are used to provide aviation traffic business and Internet of Things business services.

[0171] The aviation networking system includes airborne terminals (aircraft), satellite space segments, ground base stations / gateways, Internet of Things gateways, traffic control centers, and air traffic control business service centers. Specifically: Traffic Control Center: Mainly responsible for authorizing airborne terminals to access the network; Internet of Things Gateway: Mainly responsible for transparent transmission and distribution of business data, and converting the aircraft's IPv6 data with the Internet's IPv6 data to achieve network interoperability, support IP protocol specifications, and assign IPv6 addresses to terminals; Internet of Things Comprehensive Management and Control Center: Responsible for operating multiple Internet of Things gateways to achieve centralized management, resource planning, routing interoperability and other functions; Local Air Traffic Control Center: Mainly responsible for providing aviation traffic services and Internet of Things business services; Data Network: Mainly responsible for the network that realizes data communication by transmitting, exchanging and storing data.

[0172] The embodiment of the present invention also provides a computer device, see Fig. 9 , Fig. 9 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Fig. 9 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig. 9 A processor 10 is taken as an example.

[0173] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0174] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0175] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0176] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0177] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0178] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0179] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0180] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A system for ensuring continuous communication services for aircraft, characterized in that: The system comprises: The airborne terminal is used to send a continuous communication service registration request, wherein the continuous communication service registration request includes an estimated departure time, an estimated arrival time, an estimated route information, and registration information of the airborne terminal; A radio access network, configured to receive and forward the continuous communication service registration request to an access and mobility management function; The access and mobility management function is used to receive the continuous communication service registration request and send a registration information query request to the unified data management; The unified data management is used to receive the registration information query request and send a prediction request to the network data analysis function; The network data analysis function is used to receive the prediction request, generate a link prediction result list, and send a prediction request response including the link prediction result list to the unified data management; the link prediction linked list is used to characterize the expected link status of the aircraft with other nodes during the entire flight process; The access and mobility management function is also used to send a broadcast message of pre-cached registration information and session information to the corresponding satellite nodes and ground base station nodes according to the link prediction result list, and send a continuous communication service registration reply to the wireless access network.

2. The system according to claim 1, characterized in that The access and mobility management function is also used to receive cache result replies from the satellite node and the ground base station node, and calculate the cache success rate based on the received cache result replies.

3. The system according to claim 1 or 2, characterized in that: A prediction model is deployed on the network data analysis function, and the prediction model is used to generate the link prediction result list based on a hypervariable graph; the hypervariable graph is obtained based on the estimated departure time, the estimated arrival time and the estimated route information.

4. A method for continuous aircraft communication service, characterized in that: The method is applied to the system for ensuring continuous communication services for aircraft according to any one of claims 1 to 3, and the method comprises: receiving a continuous communication service registration request, the continuous communication service registration request including an estimated departure time, an estimated arrival time, an estimated route information, and registration information of the airborne terminal; Generate a prediction request based on the continuous communication service registration request; the prediction request includes the estimated departure time, the estimated arrival time and the estimated route information; Based on the prediction request, a link prediction result list is generated, wherein the link prediction linked list is used to characterize the expected link status between the aircraft and other nodes during the entire flight process; Sending a broadcast message of registration information and session information corresponding to the registration request to the satellite node and the ground base station node in the link prediction linked list respectively; After receiving the broadcast message, the ground base station node sends a registration reply for the continuous communication service.

5. The method according to claim 4, characterized in that The step of generating a link prediction result list based on the prediction request includes: constructing a hypervariable graph based on the estimated departure time, the estimated arrival time, and the estimated route information; The hypervariable graph is input into a prediction model to obtain the link prediction result list.

6. The method according to claim 5, characterized in that The constructing a hypervariable graph based on the estimated departure time, the estimated arrival time and the estimated route information includes: Obtaining the longitude and latitude coordinates of the aircraft, each satellite node and ground base station node; Converting the latitude and longitude coordinates into Earth-centered Earth-fixed coordinates; Calculating the straight-line distance between the aircraft and each satellite node and the ground base station node based on the aircraft, each satellite node and the ground base station node; If the straight-line distance between the aircraft and the target node is less than the maximum visible distance, adding a connecting line between the aircraft and the target node; Add connections between adjacent nodes to obtain a fully connected hypervariable graph.

7. The method according to claim 6, characterized in that The step of inputting the hypervariable graph into a prediction model to obtain the link prediction result list includes: The multivariate time series window at a preset time point is used as input data and embedded into the hypervariable graph as each node feature; Performing discrete Fourier transform on the node features to obtain frequency output; Based on the frequency output, performing an inverse discrete Fourier transform on the node features; Performing feature extraction and nonlinear transformation on the node features to obtain transformation results; The link prediction result list is generated based on the transformation result.

8. The method according to any one of claims 4 to 7, characterized in that The registration reply of the continuous communication service includes a cache success rate; the cache success rate is calculated based on the reply of the cache result sent by the ground base station after receiving the broadcast message.

9. The method according to claim 8, characterized in that The method also includes monitoring QoE indicators throughout the flight and adjusting network resources and service strategies according to the QoE indicators, wherein the QoE indicators include freeze rate, end-to-end delay, and continuous service duration.

10. An aviation networking system, characterized in that: The system comprises: The airborne terminal is used to send a continuous communication service registration request, wherein the continuous communication service registration request includes an estimated departure time, an estimated arrival time, an estimated route information, and registration information of the airborne terminal; The satellite space segment includes at least one satellite for providing a wireless communication link between the onboard terminal and the ground base station; The ground base station is used to receive signals from the satellite space segment and forward them to the corresponding network node; The Internet of Things gateway is used to receive the service data of the ground base station, perform data transparent transmission and distribution, and allocate IPv6 addresses to the connected airborne terminals; A traffic control center, used to connect the airborne terminal to the network; The air traffic control business service center includes several local air traffic control centers, which are used to provide aviation traffic business and Internet of Things business services.

Images