Satellite network flow sensing method based on space-time diagram neural network

Abstract

The invention provides a satellite network flow sensing method based on a space-time diagram neural network, and the method comprises the following steps: calculating the telemetering time delay Li, j, the telemetering overhead Ci, j and the path reliability Ri, j from a node i to a node j along a path # imgabs0 # according to the satellite network topology and the node link flow; dividing the satellite network into K sub-networks GS (VS, ES) = {C1, C2,..., CK} based on a spectral clustering method; a Hamiltonian loop-based telemetering path with the minimum weighted sum of telemetering delay and telemetering overhead is searched in the sub-network k, and a flow telemetering threshold Ttr is set; acquiring a space-time dependency relationship between the network topology and the service traffic by using the space-time diagram neural network, and predicting traffic data at the next moment; according to the collected flow data and the predicted flow data, a satellite network flow state view is obtained through analysis, and satellite network flow perception is achieved. According to the method, the telemetering overhead in the satellite network is reduced, the traffic prediction accuracy is improved, and the problems of high perception overhead and low accuracy caused by space-time coupling and random burst of the satellite network service traffic are solved.

Description

Technical Field

[0001] The present invention relates to the field of satellite communication and network technology, and in particular to a satellite network traffic perception method based on spatiotemporal graph neural network. Background Art

[0002] Satellite network is a complex system that uses satellite platforms as carriers and combines ground gateways, data centers, etc. to realize information collection, processing, and transmission. It has the characteristics of wide-area coverage and ubiquitous access. It plays an increasingly important role in the fields of ocean navigation and emergency communications. It is an important part of the future space communication infrastructure and has become the forefront of current research. However, with the rapid development of the Internet, the amount of data in satellite networks has increased exponentially. The centralized control method of the system control segment lacks flexibility in business management and cannot handle network failures in real time. Software-defined satellite network (SDSN) decouples the control plane and the data plane. The satellite switching node only needs to complete simple data forwarding and hardware configuration. The control plane is programmable and can realize intelligent network control in a logically centralized controller without affecting the data flow, providing a technical basis for flexible control of satellite networks.

[0003] Network traffic perception is the basis for research on network performance detection, resource management and fault diagnosis, but active and passive measurement methods can no longer meet the low latency and high reliability performance requirements of satellite networks. In-band network telemetry (INT) has become a research hotspot in industry and academia. It combines packet forwarding and network measurement, collects status information of the network nodes it passes through and inserts telemetry packets. It has the characteristics of real-time, flexibility and fine-grainedness. It is necessary to study the telemetry method of INT in satellite networks to achieve real-time collection of satellite network traffic with the lowest possible overhead and relatively small latency.

[0004] The business traffic and network topology in satellite networks are tightly coupled and have strong spatiotemporal correlation and heterogeneity, making it difficult to predict business traffic. The network traffic prediction method based on spatiotemporal graph neural network (STGNN) has been applied to ground traffic prediction, weather forecasting and other fields. Compared with traditional statistical and deep learning methods, it can more efficiently and accurately extract complex spatiotemporal dependencies and provide a data basis for intelligent network management and control.

[0005] Telemetry delay, overhead and reliability are important factors affecting telemetry path planning. Network delay affects the efficiency and real-time performance of telemetry data transmission. Satellite network resources are limited, and the bandwidth and other resources occupied by telemetry data increase linearly with the information collected. The dynamic nature of satellite networks makes it easy for inter-satellite links to be interrupted, and the reliability of telemetry paths affects the time for error-free transmission of telemetry data. Unlike ground network traffic perception, satellite networks are susceptible to the space environment and are highly dynamic. In addition, onboard resources are limited, making existing research not applicable to satellite networks. The implementation of traffic perception in satellite networks has the problems of excessive telemetry overhead and low accuracy. Summary of the invention

[0006] In order to solve the technical problems existing in the above-mentioned prior art, the purpose of the present invention is to provide a satellite network traffic perception method based on spatiotemporal graph neural network, which reduces the telemetry overhead in the satellite network and improves the accuracy of traffic prediction, and solves the problems of large perception overhead and low accuracy caused by spatiotemporal coupling and random bursts of satellite network business traffic.

[0007] To achieve the above-mentioned purpose, the present invention provides a satellite network traffic perception method based on spatiotemporal graph neural network, comprising the following steps:

[0008] Step S1: Calculate the path based on the satellite network topology and node link traffic. The telemetry delay L from node i to node j i,j , telemetry overhead C i,j and path reliability R i,j ;

[0009] Step S2: Divide the satellite network into K sub-networks G based on the spectral clustering method S (V S ,E S )={C1,C2,...,C K};

[0010] Step S3: Find a telemetry path based on a Hamiltonian circuit with the minimum weighted sum of telemetry delay and telemetry overhead in subnetwork k, and set the flow telemetry threshold T tr ;

[0011] Step S4: Use the spatiotemporal graph neural network to obtain the spatiotemporal dependency of network topology and business traffic, and predict the traffic data at the next moment;

[0012] Step S5: Analyze and obtain a satellite network traffic status view based on the collected traffic data and the predicted traffic data to achieve satellite network traffic perception.

[0013] According to a technical solution of the present invention, in step S1, the propagation delay between the adjacent node a and the node b is Among them, dis a,b is the distance between node a and node b, and c is the speed of light;

[0014] D a,b represents the amount of data sent between adjacent node a and node b, B a,b represents the data transmission rate, then the transmission delay from adjacent node a to node b is

[0015] The queue processing delay of node a is L a represents the queue length of node a, λ is the arrival rate, and defines the The delay from node i to node j is L i,j The expression is:

[0016]

[0017] in, Indicates that (a,b) is a path The number of links on the Link , Indicates that node a is a path The number of nodes on the Sat .

[0018] According to a technical solution of the present invention, in step S1, the network along the path The telemetry cost C from node i to node j i,j It is expressed as:

[0019]

[0020] in, is the amount of data collected by node a, C header is the telemetry packet header overhead, C data For a single telemetry data overhead.

[0021] According to a technical solution of the present invention, in step S1, the path reliability consists of node reliability and link reliability. The reliability of the path from node i to node j is R i,j It is expressed as:

[0022]

[0023] Among them, the failure probability of node a is Failure probability of link (a,b)

[0024] According to a technical solution of the present invention, step S3 includes the following steps:

[0025] Step S31, determining the path repetition and coverage;

[0026] Step S32, constructing an objective function;

[0027] Step S33: Setting the flow telemetry threshold T tr ,Telemetry path planning based on Hamiltonian circuits.

[0028] According to a technical solution of the present invention, in step S31, sub-network C k Total nodes, telemetry path The number of nodes included is n INT , then the telemetry path duplication of the sub-network is ovl k It is expressed as:

[0029]

[0030] In subnetwork C k The path from node i to node j in The coverage is expressed as:

[0031]

[0032] According to a technical solution of the present invention, in step S32, the objective function x i,j is the comprehensive optimization function of telemetry delay and telemetry overhead, expressed as:

[0033]

[0034] in, represents the normalized telemetry overhead, represents the normalized telemetry delay, α and β are the weight coefficients of the normalized overhead and delay, and α+β=1; constraint C1 ensures the reliability of the telemetry path R INT Greater than or equal to the threshold reliability R th ; Constraint C2 ensures the coverage rate η of each subnetwork k is 1 and the coverage of the entire network; the normalized path delay is expressed as:

[0035]

[0036] Among them, L MAX =max{L i,j} is the maximum telemetry delay of the network;

[0037] The normalized path cost is expressed as:

[0038]

[0039] Among them, C MAX =max{C i,j} represents the maximum telemetry overhead of the network.

[0040] According to a technical solution of the present invention, in the step S4, it specifically includes:

[0041] The spatiotemporal convolutional layer consists of 2 GCNs and 2 TCNs connected alternately in series, and the spatiotemporal graph learning module consists of 2 spatiotemporal convolutional layers and 1 output layer;

[0042] According to the network topology characteristics and business traffic characteristics, a spatiotemporal graph based on spatial similarity is constructed, and the spatiotemporal dependency of network topology characteristics and business traffic characteristics in satellite networks is analyzed;

[0043] The historical business traffic data is input into the space-time graph learning module, the space-time dependency is mapped to the next time period, and the future satellite network traffic changes are predicted.

[0044] According to a technical solution of the present invention, the flow telemetry threshold T is set tr , only when the traffic flow of node i is T i Compared with the benchmark traffic T base When the difference between the service flow rate and the threshold service flow rate is greater than the threshold service flow rate, the service flow data of node i is collected and the reference service flow rate T is updated. base =T i ;

[0045] Otherwise, the node traffic is considered to be consistent with the previous moment.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The present invention proposes a satellite network traffic perception method based on spatiotemporal graph neural network, which reduces the telemetry overhead in the satellite network and improves the accuracy of traffic prediction, and solves the problems of large perception overhead and low accuracy caused by spatiotemporal coupling and random bursts of satellite network business traffic.

[0048] The present invention aims to solve the problem of difficulty in sensing satellite network service traffic. By planning a satellite network telemetry path with set thresholds to collect traffic data and constructing a spatiotemporal graph neural network to predict service traffic changes, the present invention can achieve low-overhead and high-accuracy satellite network traffic perception, thus providing a data basis for real-time and flexible satellite network management and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 It is a schematic diagram of the flow of a satellite network traffic perception method based on a spatiotemporal graph neural network in one embodiment of the present invention;

[0051] Figure 2 A schematic diagram of a satellite network scenario simulation in one embodiment of the present invention;

[0052] Figure 3 An in-band network telemetry data collection process in one embodiment of the present invention;

[0053] Figure 4 is a threshold in-band network telemetry in one embodiment of the present invention;

[0054] Figure 5 A spatiotemporal graph neural network traffic prediction process in one embodiment of the present invention;

[0055] Figure 6 A comparison of satellite network telemetry overhead and latency in one embodiment of the present invention;

[0056] Figure 7 An actual satellite network service flow diagram in one embodiment of the present invention;

[0057] Figure 8 This is a diagram of predicting satellite network service traffic in one embodiment of the present invention. DETAILED DESCRIPTION

[0058] Reference will now be made in detail to various embodiments of the present invention, examples of which are illustrated in the accompanying drawings and described below. Although the present invention will be described in conjunction with exemplary embodiments of the present invention, it should be understood that this specification is not intended to limit the present invention to those exemplary embodiments. On the other hand, the present invention is intended to cover not only the exemplary embodiments of the present invention, but also various alternatives, modifiers, equivalents and other embodiments, which may be included in the spirit and scope of the present invention as defined by the appended claims.

[0059] Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. The specific structures and functions described in the exemplary embodiments of the present invention are for illustrative purposes only. Embodiments according to the concepts of the present invention can be implemented in various forms, and it should be understood that they should not be interpreted as being limited to the exemplary embodiments described in the exemplary embodiments, but include all modifications, equivalents or substitutes included in the spirit and scope of the present invention.

[0060] Throughout the specification, the professional terms used herein are only for describing various exemplary embodiments and are not intended to be limiting. It will be further understood that the terms "include", "comprising", "having", etc., when used in the exemplary embodiments, specifically refer to the presence of the stated parts, steps, operations or elements, but do not exclude the presence or addition of one or more other parts, steps, operations or elements.

[0061] The satellite network traffic perception method based on the spatiotemporal graph neural network of the present invention involves a satellite network scenario based on a software defined network (SDN) G(V, E)=G S ∪G T , including the space segment network G S (V S ,E S ) and ground segment network G T (V T ,E T ), the two are connected by a satellite-to-ground link, such as Figure 2 The ground segment includes satellite gateways, switch nodes, and user nodes. The switch nodes are connected through ground links, and users are connected to switch nodes through user ground links. Satellite gateway deploys the main controller N docon Formulate satellite network forwarding strategy and upload it to the slave controller N in the space segment sercon At the same time, the user node transmits data to the satellite network through the satellite gateway.

[0062] Satellite Network G S (V S ,E S ) is composed of a mixture of polar orbit and inclined orbit low earth orbit (LEO) satellites. Adjacent satellites are connected by inter-satellite links, which are divided into K sub-networks G S (V S ,E S )={C1,C2,...,C K}, and deploy the slave controller in subnetwork k At the same time, telemetry paths are planned in the subnetwork, and data of the nodes passed through are collected and reported to the controller. Time-varying traffic and network topology features are extracted to build a spatiotemporal graph, predict the trend of business traffic changes, and analyze the local traffic status view. Telemetry paths are planned in subnetwork k. The information collection of the data plane does not need to interact with the control plane, and can realize real-time, fine-grained collection and reporting of device ports, data volume, and queue information.

[0063] The telemetry process used in this patent is as follows Figure 3 As shown in the figure, switch 1 inserts an INTheader into the data packet, which contains instructions to collect metadata, and encapsulates it into an INTpacket after obtaining telemetry information. The telemetry data packet obtains data through switches 2 and 3 and reaches switch 4, which sends the metadata to the controller through an INTreport message. In the controller, telemetry data and network topology features are extracted to construct a spatiotemporal graph, predict the trend of business traffic changes, and obtain a network status view.

[0064] like Figures 1 to 3 As shown, the present invention provides a satellite network traffic perception method based on a spatiotemporal graph neural network, comprising the following steps:

[0065] Step S1: Calculate the path based on the satellite network topology and node link traffic. The telemetry delay L from node i to node j i,j , telemetry overhead C i,j and path reliability R i,j ;

[0066] Step S2: Divide the satellite network into K sub-networks G based on the spectral clustering method S (V S ,E S )={C1,C2,...,C K};

[0067] Step S3: Find a telemetry path based on a Hamiltonian circuit with the minimum weighted sum of telemetry delay and telemetry overhead in subnetwork k, and set the flow telemetry threshold T tr ;

[0068] Step S4: Use the spatiotemporal graph neural network to obtain the spatiotemporal dependency of network topology and business traffic, and predict the traffic data at the next moment;

[0069] Step S5: Analyze and obtain a satellite network traffic status view based on the collected traffic data and the predicted traffic data to achieve satellite network traffic perception.

[0070] STGNN consists of a data processing module, a spatiotemporal graph learning module, and a task-aware prediction module, such as Figure 5As shown in the figure, the telemetry data is processed and input into the spatiotemporal graph learning module to obtain the spatiotemporal relationship between network topology and business traffic, and predict future network traffic. First, the satellite network traffic information collected by the telemetry path is input into the data processing module, and a spatiotemporal graph based on spatial similarity is constructed according to the satellite network topology and business traffic characteristics. The spatiotemporal graph learning module consists of two spatiotemporal convolutional layers and one output layer, which analyzes the dependency between business traffic and network topology in complex satellite networks according to the spatiotemporal graph. In the spatiotemporal convolutional layer, GCN captures the spatial correlation of satellite network topology, TCN captures the temporal correlation of business traffic, and spatial learning and temporal learning are coupled through the factor neural architecture to obtain the spatial characteristics of time-varying satellite network traffic. Finally, the perception prediction module maps the spatiotemporal dependency of satellite network business traffic obtained by spatiotemporal graph learning to the business traffic prediction for the next time period, and analyzes and obtains the satellite network traffic status view.

[0071] According to a technical solution of the present invention, in step S1, the propagation delay between the adjacent node a and the node b is Among them, dis a,b is the distance between node a and node b, and c is the speed of light;

[0072] D a,b represents the amount of data sent between adjacent node a and node b, B a,b represents the data transmission rate, then the transmission delay from adjacent node a to node b is

[0073] The queue processing delay of node a is L a represents the queue length of node a, λ is the arrival rate, and defines the The delay from node i to node j is L i,j The expression is:

[0074]

[0075] in, Indicates that (a,b) is a path The number of links on the Link , Indicates that node a is a path The number of nodes on the Sat .

[0076] As for telemetry delay, network telemetry needs to complete data collection and transmission with low latency and report it to the controller node to meet the satellite network's real-time perception needs for traffic data. Therefore, this paper considers the impact of propagation delay, transmission delay and queuing processing delay on the real-time performance of telemetry perception.

[0077] According to a technical solution of the present invention, in step S1, the network along the path The telemetry cost C from node i to node j i,j It is expressed as:

[0078]

[0079] in, is the amount of data collected by node a, C header is the telemetry packet header overhead, C data For a single telemetry data overhead.

[0080] For telemetry overhead, the more nodes and links the INT data packet passes through, the greater the overhead. The bandwidth and other resources it occupies increase linearly with the information collected by the data packet. In INT, the INT header occupies 8 bytes, and each telemetry data occupies 4 bytes. For a data packet of 2000 bytes, the bandwidth occupancy increases sharply with the number of nodes on the telemetry path. If two data of each node are collected through 10 hops, it occupies 4.4%, and the bandwidth overhead increases linearly with the growth of telemetry demand. Therefore, it is necessary to optimize the INT overhead to reduce bandwidth occupancy.

[0081] According to a technical solution of the present invention, in step S1, the path reliability consists of node reliability and link reliability. The reliability of the path from node i to node j is R i,j It is expressed as:

[0082]

[0083] Among them, the failure probability of node a is Failure probability of link (a,b)

[0084] As for path reliability, the higher the path reliability, the longer the time for error-free transmission of telemetry data between network nodes. Therefore, the telemetry path should choose a path with higher reliability to ensure the accurate collection of telemetry data. Path reliability consists of node reliability and link reliability.

[0085] According to a technical solution of the present invention, step S3 includes the following steps:

[0086] Step S31, determining the path repetition and coverage;

[0087] Step S32, constructing an objective function;

[0088] Step S33: Setting the flow telemetry threshold T tr ,Telemetry path planning based on Hamiltonian circuits.

[0089] The satellite network is divided into K sub-networks by using a spectral clustering-based method. The algorithm design complexity is reduced by dividing the complex global solution problem into multiple relatively simple local solution problems. In sub-network k, a backtracking pruning-based method is used to recursively search the solution space in a limited depth manner to reduce the number of invalid traversals. If there is no Hamiltonian circuit in the sub-network, the number of nodes that can be passed through the same node in the sub-network is gradually increased to continue the backtracking pruning search.

[0090] Set the flow telemetry threshold T tr ,like Figure 4 As shown, if and only if the service flow of node i is T i Compared with the benchmark traffic T base When the difference between the service flow rate and the service flow rate of node i is greater than the threshold service flow rate, the service flow data of node i is collected, and the current benchmark service flow rate is updated to the service flow rate of the current node i, that is, T base =T i If the difference between the two is less than the threshold value, the service flow data is not collected, that is, the node flow is considered to be consistent with the previous moment. The above-mentioned planning of telemetry paths and setting of threshold mechanisms can effectively reduce the redundancy of telemetry data and realize lightweight network service flow data acquisition.

[0091] According to a technical solution of the present invention, in step S31, sub-network C k Total nodes, telemetry path The number of nodes included is n INT , then the telemetry path duplication of the sub-network It is expressed as:

[0092]

[0093] In subnetwork C k The path from node i to node j in The coverage is expressed as:

[0094]

[0095] For path repetition and coverage, the telemetry path may collect node information through the same node multiple times. Repeated collection of node data leads to information redundancy and increased telemetry overhead. Coverage is the ratio of the number of nodes passed by the path in the network to the total number of nodes, reflecting the capacity of the satellite network covered by the telemetry path.

[0096] According to a technical solution of the present invention, in step S32, the objective function x i,j It is a comprehensive optimization function of telemetry delay and telemetry overhead, aiming to minimize the weighted sum of the two, expressed as:

[0097]

[0098] in, represents the normalized telemetry overhead, represents the normalized telemetry delay, α and β are the weight coefficients of the normalized overhead and delay, and α+β=1; constraint C1 ensures the reliability of the telemetry path R INT Greater than or equal to the threshold reliability R th ; Constraint C2 ensures the coverage rate η of each subnetwork k is 1 and the coverage of the entire network; the normalized path delay is expressed as:

[0099]

[0100] Among them, L MAX =max{L i,j} is the maximum telemetry delay of the network;

[0101] The normalized path cost is expressed as:

[0102]

[0103] Among them, C MAX =max{C i,j} represents the maximum telemetry overhead of the network.

[0104] According to a technical solution of the present invention, in the step S4, it specifically includes:

[0105] The spatiotemporal convolutional layer for traffic prediction consists of 2 GCNs and 2 TCNs connected alternately in series. It uses fewer parameters to achieve faster training and easier convergence, and has certain flexibility and scalability. The spatiotemporal graph learning module consists of 2 spatiotemporal convolutional layers and 1 output layer.

[0106] According to the network topology characteristics and business traffic characteristics, a spatiotemporal graph based on spatial similarity is constructed, and the spatiotemporal dependency of network topology characteristics and business traffic characteristics in satellite networks is analyzed;

[0107] The historical business traffic data is input into the space-time graph learning module, the space-time dependency is mapped to the next time period, and the future satellite network traffic changes are predicted.

[0108] For a network G(V,E) with N nodes, its node set is V = {v1,v2,...,v N}. If nodes i and j are connected, then w ij =1, otherwise w ij =0, the adjacency matrix is: W = (w ij );i,j=1,...,N. The degree of node i is The degree matrix of the graph is:

[0109]

[0110] In this application, the satellite network adjacency matrix A based on spatial similarity is ij );i,j=1,...,N, and a ij The definition is as follows,

[0111]

[0112] Among them, σ is a hyperparameter that controls the distribution. Spatial learning uses GCN, and the expression is approximately written as

[0113]

[0114] Among them, Θ is the graph convolution kernel, θ is the learnable parameter, I N is the identity matrix, D is the degree matrix, A is the adjacency matrix, and The temporal learning of spatiotemporal graph neural network adopts TCN, whose causal convolution is expressed as

[0115]

[0116] Among them, Γ is the temporal convolution kernel, d is the scaling factor, and k is the filter f in TCN. i The size of , s is the time series input.

[0117] The spatiotemporal convolution layer of this application is composed of 2 GCNs and 2 TCNs connected in series alternately. For the spatiotemporal convolution layer l, its input x l After the graph convolution kernel Temporal Convolution Kernel Graph convolution kernel and temporal convolution kernel Output x l+1 , the mapping relationship can be expressed as

[0118]

[0119] Among them, ReLU{·} is the rectified linear unit function.

[0120] According to a technical solution of the present invention, the flow telemetry threshold T is set tr , only when the traffic flow of node i is T i Compared with the benchmark traffic T base When the difference between the service flow rate and the threshold service flow rate is greater than the threshold service flow rate, the service flow data of node i is collected and the reference service flow rate T is updated. base =T i ;

[0121] Otherwise, the node traffic is considered to be consistent with the previous moment.

[0122] The following is a simulation analysis of the satellite network traffic perception method based on spatiotemporal graph neural network involved in the present invention.

[0123] The satellite network used in the simulation analysis refers to the constellation configuration of "Iridium" and "Starlink", which is composed of a mixture of inclined orbit and polar orbit satellites, with 293 LEO satellites, to verify the feasibility and effectiveness of the satellite network traffic perception algorithm based on STGNN. The data set used for STGNN training, verification and testing is the business traffic of a backbone network collected based on the WIDE Project. The traffic data is loaded into the satellite network and the traffic information of the nodes is collected to form a satellite network business traffic data set, which is divided into training, test and verification sets according to 0.7:0.15:0.15.

[0124] The comparison method of telemetry delay and overhead is the telemetry path planning method based on the Euler circuit, which starts from a node, passes through all the edges in the network once, and then returns to the starting point. The telemetry path based on the Hamiltonian circuit is a path that starts from a node, passes through all the nodes in the network only once, and finally returns to the starting point. The Euler method will repeatedly collect data from the same node multiple times, resulting in a sharp increase in overhead, while the Hamiltonian method only aims to pass through each node, which can reduce the redundancy of information collection to a certain extent and reduce telemetry overhead. Figure 6 As shown in the figure, the blue dotted line is the telemetry overhead of the Euler method, and the orange dotted line is the telemetry overhead of the Hamilton method. The proposed method reduces the overhead by more than 20% compared with the Euler method. The blue bar graph is the telemetry delay of the Euler method, and the orange bar graph is the telemetry delay of the Hamilton method. The delay of the proposed method is reduced by more than 40%, that is, the proposed Hamiltonian-based telemetry path achieves satellite network node traffic data acquisition with lower telemetry delay and overhead.

[0125] The comparison method of network traffic prediction is the LSTM-based method. The accuracy of the business traffic prediction results of the two methods is shown in Table 1. The root mean square error (RMSE) and mean absolute error (MAE) of LSTM are 1.9654 and 1.3438 respectively, while the RMSE and MAE of STGNN are 0.7893 and 0.2846. The two indicators of satellite network business traffic prediction based on STGNN adopted in this paper are better than those based on LSTM method, with an improvement of 59.8% and 78.8% respectively, which can more accurately predict the business traffic of satellite network nodes in subsequent time slices.

[0126] Table 1 Comparison of prediction accuracy

[0127]

[0128] The global status view includes the current network traffic and network topology, and can obtain the satellite network traffic distribution. Each block represents a satellite point. The more yellow the color, the greater the node traffic, and the smaller the color block, the smaller the node load. Figure 7 This is the actual satellite network traffic view. Figure 8 For the predicted traffic view, the predicted satellite traffic distribution is consistent with the actual one, and for satellite nodes without business traffic, the proposed basic algorithm still performs micro-traffic prediction, which can effectively deal with the impact of micro-burst traffic on the real-time perception of network and improve the adaptability of satellite networks.

[0129] The satellite network service flow perception method based on spatiotemporal graph neural network of the present invention proposes a satellite network telemetry path based on Hamiltonian circuit, and sets up flow control node data collection; constructs a spatiotemporal graph model based on spatial similarity according to satellite network topology and service flow characteristics, adopts GCN and TCN series coupling to construct STGNN to obtain spatiotemporal dependency, and predicts the satellite network service flow in the next time period; according to current and future flow data, analyzes and obtains the satellite network flow state view, and realizes satellite network flow perception. Therefore, in order to solve the problem of high overhead and low accuracy of satellite network service flow perception, the telemetry and telemetry delay are reduced by planning the satellite network telemetry path, and at the same time, the STGNN-based method is adopted according to the telemetry data to realize high-accuracy satellite network flow prediction, and realize satellite network flow perception.

[0130] The foregoing description of specific exemplary embodiments of the present invention has been presented for the purpose of illustration and description. It is not intended to exclude or limit the present invention to the precise form disclosed, and it is obvious that many modifications and changes are feasible in view of the above teachings. Exemplary embodiments are selected and described to explain certain principles of the present invention and their practical application, so that other technicians in the field can make or use various exemplary embodiments of the present invention, and various alternatives and modifications thereof. It is intended that the scope of the present invention will be defined by the claims attached hereto and their equivalents.

[0131] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the present invention. It can also be a reasonable combination of the features recorded in the above embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A satellite network traffic perception method based on spatiotemporal graph neural network, characterized in that: The following steps are involved: Step S1: Calculate the path based on the satellite network topology and node link traffic. The telemetry delay L from node i to node j i,j , telemetry overhead C i,j and path reliability R i,j ; Step S2: Divide the satellite network into K sub-networks G based on the spectral clustering method S (V S ,E S )={C1,C2,...,C K }; Step S3: Find a telemetry path based on a Hamiltonian circuit with the minimum weighted sum of telemetry delay and telemetry overhead in subnetwork k, and set the flow telemetry threshold T tr ; Step S4: Use the spatiotemporal graph neural network to obtain the spatiotemporal dependency of network topology and business traffic, and predict the traffic data at the next moment; Step S5: Analyze and obtain a satellite network traffic status view based on the collected traffic data and the predicted traffic data to achieve satellite network traffic perception.

2. The satellite network traffic perception method based on spatiotemporal graph neural network according to claim 1 is characterized in that: In step S1, the propagation delay between the adjacent node a and the node b is Among them, dis a,b is the distance between node a and node b, and c is the speed of light; D a,b represents the amount of data sent between adjacent node a and node b, B a,b represents the data transmission rate, then the transmission delay from adjacent node a to node b is The queue processing delay of node a is L a represents the queue length of node a, λ is the arrival rate, and defines the The delay from node i to node j is L i,j The expression is: in, Indicates that (a,b) is a path The number of links on the Link , Indicates that node a is a path The number of nodes on the Sat .

3. The satellite network traffic perception method based on spatiotemporal graph neural network according to claim 1 is characterized in that: In step S1, the network along the path The telemetry cost C from node i to node j i,j It is expressed as: in, is the amount of data collected by node a, C header is the telemetry header overhead, C data For a single telemetry data overhead.

4. The satellite network traffic perception method based on spatiotemporal graph neural network according to claim 1 is characterized in that: In step S1, path reliability consists of node reliability and link reliability. The reliability of the path from node i to node j is R i,j It is expressed as: Among them, the failure probability of node a is Failure probability of link (a,b) 5. The satellite network traffic perception method based on spatiotemporal graph neural network according to claim 1 is characterized in that: The step S3 includes the following steps: Step S31, determining the path repetition and coverage; Step S32, constructing an objective function; Step S33: Setting the flow telemetry threshold T tr ,Telemetry path planning based on Hamiltonian circuits.

6. The satellite network traffic perception method based on spatiotemporal graph neural network according to claim 5 is characterized in that: In step S31, sub-network C k Total nodes, telemetry path The number of nodes included is n INT , then the telemetry path duplication of the sub-network It is expressed as: In subnetwork C k The path from node i to node j in The coverage is expressed as:

7. The satellite network traffic perception method based on spatiotemporal graph neural network according to claim 5 is characterized in that: In step S32, the objective function x i,j is the comprehensive optimization function of telemetry delay and telemetry overhead, expressed as: subject to:C1:R INT ≥R th C2:∑η k =K&h k =1 in, represents the normalized telemetry overhead, represents the normalized telemetry delay, a and β are the weight coefficients of the normalized overhead and delay, and α+β=1; constraint C1 ensures the reliability of the telemetry path R INT Greater than or equal to the threshold reliability R th ; Constraint C2 ensures the coverage rate η of each subnetwork k is 1 and the coverage of the entire network; the normalized path delay is expressed as: Among them, L MAX =max{L i,j } is the maximum telemetry delay of the network; The normalized path cost is expressed as: Among them, C MAX =max{C i,j } represents the maximum telemetry overhead of the network.

8. The satellite network traffic perception method based on spatiotemporal graph neural network according to claim 1 is characterized in that: In the step S4, it specifically includes: The spatiotemporal convolutional layer consists of 2 GCNs and 2 TCNs connected alternately in series, and the spatiotemporal graph learning module consists of 2 spatiotemporal convolutional layers and 1 output layer; According to the network topology characteristics and business traffic characteristics, a spatiotemporal graph based on spatial similarity is constructed, and the spatiotemporal dependency of network topology characteristics and business traffic characteristics in satellite networks is analyzed; The historical business traffic data is input into the space-time graph learning module, the space-time dependency is mapped to the next time period, and the future satellite network traffic changes are predicted.

9. The satellite network traffic perception method based on spatiotemporal graph neural network according to claim 1 is characterized in that: The flow telemetry threshold T is set tr , only when the traffic flow of node i is T i Compared with the benchmark traffic T base When the difference between the traffic flow rate and the traffic flow rate of node i is greater than the threshold traffic flow rate, the traffic flow data of node i is collected and the reference traffic flow rate T is updated. base =T i ; Otherwise, the node traffic is considered to be consistent with the previous moment.

Images