A dynamic network representation and resource optimization method and device based on space-time attributes

Abstract

This application relates to the field of resource allocation technology and provides a method and apparatus for dynamic network representation and resource optimization based on spatiotemporal attributes. The method receives service requests sent by ground station nodes / user nodes in a terrestrial network at the current time, takes the source node as the current node, and uses a configured joint objective function to calculate the resource optimization value for the amount of service to be processed on the corresponding network link. The network link corresponding to the maximum resource optimization value is taken as a sub-transmission processing path. The target node is taken as the new current node, and the execution steps are returned: calculating the resource optimization value for the amount of service to be processed on the corresponding network link until all other nodes are traversed; if the target node calculated during the traversal is the destination node, then the optimized transmission path composed of the sub-transmission processing paths starting from the source node and ending at the destination node is obtained. This method realizes the resource allocation between application service transmission processing paths and satellite nodes.

Description

Technical Field

[0001] This application relates to the field of resource allocation technology, and more specifically, to a dynamic network representation and resource optimization method and apparatus based on spatiotemporal attributes. Background Technology

[0002] With the development of satellite internet technology, space wireless communication networks such as satellite communication and near-space platform communication are further merging with various traditional terrestrial wireless and wired networks, forming an integrated space-air-ground network that is ubiquitous and omnipresent, covering the ground, sea, air, and space. As one of the national public infrastructures of the information age, the main task of the integrated space-air-ground network is to achieve seamless global coverage, efficient data transmission, and flexible network access by comprehensively utilizing various communication resources in space, air, and ground.

[0003] To meet the ever-growing, dynamic, and diversified business demands and improve the utilization rate of limited satellite resources, researchers have proposed numerous satellite resource scheduling algorithms to address resource allocation and decision-making problems in satellite communication systems. Space information networks contain various types of satellite nodes, such as relay satellites, communication satellites, and remote sensing satellites. These satellites possess different functions, enabling the real-time acquisition, transmission, processing, and distribution of massive amounts of data. The satellites in the network exhibit highly dynamic characteristics, and the satellite links and onboard resource information processing capabilities are also dynamically changing; therefore, the network utility of space information networks is time-varying.

[0004] However, due to the dynamic changes in the nodes and topology of spatial information networks, resource scheduling algorithms often cannot keep pace with resource status information in real time. Resource allocation results lag behind resource status updates, failing to guarantee the service continuity of dynamic services in the network. Therefore, static resource scheduling strategies cannot meet the needs of time-varying and discrete spatial information networks. Summary of the Invention

[0005] The purpose of this application is to provide a dynamic network representation and resource optimization method and apparatus based on spatiotemporal attributes. This method is designed to address the highly dynamic changes in network topology and the time-varying nature of network resources under large spatiotemporal scales in spatial information networks. It can describe networks and their resources in different spatiotemporal dimensions, assign spatiotemporal attributes to networks and network resources, and establish a dynamic transmission optimization model based on the dynamic network to achieve the best application service transmission processing path and satellite node resource allocation, thereby improving network resource utilization.

[0006] Firstly, a dynamic network representation and resource optimization method based on spatiotemporal attributes is provided, applicable to a space information network including multiple satellite nodes. This method may include:

[0007] Receive service requests sent by ground station nodes / user nodes in the terrestrial network at the current moment. The service requests include source nodes, destination nodes, and the amount of service to be processed. The links between satellite nodes are collectively referred to as network links.

[0008] Using the source node as the current node, and employing the configured joint objective function, calculate the resource optimization value for transmitting the amount of traffic to be processed through the network links between the current satellite node and each of the other nodes; the other nodes are any nodes other than the current node and the nodes whose resource optimization values ​​have been calculated; the joint objective function is a function that characterizes the total transmission time and network capacity of the network links as they change over time, and satisfies the preset resource optimization objective.

[0009] The network link between the target node corresponding to the maximum resource optimization value and the current node is taken as the sub-transmission processing path; then, the target node is taken as the new current node, and the execution steps are returned: using the configured joint objective function, the resource optimization value of the network link between the current node and each other node is calculated to transmit the amount of business to be processed, until each other node is traversed;

[0010] If the target node calculated during the traversal is the destination node, then the traversal ends, and an optimized transmission path is obtained, consisting of the sub-transmission processing paths starting from the source node and ending at the destination node.

[0011] In one possible implementation, the preset resource optimization objective is to minimize the total transmission time and maximize the network capacity.

[0012] Using the configured joint objective function, the resource optimization values ​​for transmitting the pending service volume through network links between the current node and each other node are calculated, including:

[0013] For any other node, calculate the total transmission time and network capacity of the network link between the current node and that other node at the current moment;

[0014] The configured joint objective function is used to process the total transmission time and network capacity of the network link to obtain the resource optimization value Z for transmitting the traffic to be processed on the network link.

[0015] In one possible implementation, the calculation process for the network capacity includes:

[0016] If there are no historical tasks being transmitted on the network link at the current moment, then the total bandwidth of the network link is determined as the network capacity of the network link.

[0017] If there are historical tasks being transmitted on the network link at the current moment, the difference between the total bandwidth of the network link and the bandwidth occupied by the historical tasks being transmitted is determined as the network capacity of the network link.

[0018] In one possible implementation, the calculation of the total transmission time includes:

[0019] Calculate the propagation delay of the network link based on the length of the network link and the speed of light at the current moment;

[0020] The ratio of the amount of traffic to be processed to the network capacity is determined as the link transmission delay of the network link.

[0021] Based on the transmission rate of the network link, the amount of traffic to be processed, and the number of data packets in the current satellite node that are queued for the traffic to be processed from the current moment, the queuing delay of the traffic to be processed is determined.

[0022] The sum of the propagation delay, link transmission delay, and queuing delay is determined as the total transmission time of the network link.

[0023] In one possible implementation, the configuration process of the joint objective function includes:

[0024] The basic attribute information of the space information network is obtained. The basic attribute information includes different types of satellite nodes, different types of links between satellites, and the node resource function and link resource function that vary with time and space for each satellite node and each network link. Among them, the links between satellites, user links and ground station links are collectively referred to as network links.

[0025] Based on the node resource function corresponding to each satellite node and the link resource function corresponding to each network link, a dynamic function for network resources is constructed.

[0026] A dynamic satellite network is established based on network resource dynamic functions, as well as network links between different types of satellite nodes and different types of satellites; the dynamic satellite network includes a link model, a network transmission path model, and a residual network model.

[0027] Based on the link model, determine the total bandwidth function of each network link as it changes over time;

[0028] Based on the network transmission path model, the node paths between different nodes determined by the shortest distance route are determined, as well as the total transmission time function of each network link over time.

[0029] Based on the remaining network model and the total bandwidth function of each network link over time, the network capacity function of each network link over time is determined.

[0030] Based on the node path, network traffic parameters, total transmission time function, and network capacity function, a joint objective function that satisfies the resource optimization objective is constructed.

[0031] In one possible implementation, the joint objective function is expressed as:

[0032]

[0033] Where Z is the calculated resource optimization value of the network link between node i and node j. Indicates task information The total transmission time function between node i and node j This represents the information of the k-th task in the task set. Data packet size, Let be the network capacity function of the network link between node i and node j, which varies with time t. , Here, E represents the weighting coefficient, and E represents the set of links.

[0034] In one possible implementation, different types of satellite nodes include satellite sensing nodes and satellite transmission computing nodes;

[0035] Links between different types of satellites include intra-orbit links within the same orbital layer, inter-satellite links between satellites in different orbits within the same orbital layer, and inter-layer links between different orbital layers.

[0036] Secondly, a dynamic network representation and resource optimization device based on spatiotemporal attributes is provided, which is applied in a space information network including multiple satellite nodes. The device may include:

[0037] The receiving unit is used to receive service requests sent by ground station nodes / user nodes in the terrestrial network at the current moment. The service request includes the source node, the destination node, and the amount of service to be processed. The links between satellite nodes are collectively referred to as network links.

[0038] The calculation unit is used to take the source node as the current node and use a configured joint objective function to calculate the resource optimization value of the network link transmission of the service to be processed between the current satellite node and each other node; the other nodes are any nodes other than the current node and the nodes whose resource optimization values ​​have been calculated; the joint objective function is a function that characterizes the total transmission time and network capacity of the network link changing with time and satisfying the preset resource optimization objective.

[0039] The return unit is used to take the network link between the target node corresponding to the maximum resource optimization value and the current node as the sub-transmission processing path; then, the target node is taken as the new current node, and the execution steps are returned: using the configured joint objective function, the resource optimization value of the network link between the current node and each other node is calculated to transmit the amount of business to be processed, until each other node is traversed;

[0040] The acquisition unit is used to end the traversal if the target node calculated during the traversal is the destination node, and to acquire the optimized transmission path composed of each sub-transmission processing path starting from the source node and ending at the destination node.

[0041] Thirdly, an electronic device is provided, which includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0042] Memory, used to store computer programs;

[0043] When a processor executes a program stored in memory, it implements any of the steps described in the first aspect above.

[0044] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the steps of any of the methods described in the first aspect above.

[0045] In the spatiotemporal attribute-based dynamic network representation and resource optimization method provided in this application, after receiving a service request sent by a ground station node / user node in a terrestrial information network at the current moment, the service request includes a source node, a destination node, and the amount of service to be processed; the space information network also includes multiple satellite nodes; the links between satellite nodes are collectively referred to as network links; the source node is taken as the current node, and a configured joint objective function is used to calculate the resource optimization value of the amount of service to be processed transmitted between the current satellite node and each of the other nodes; the other nodes are any nodes other than the current node and the nodes whose resource optimization values ​​have been calculated; the joint objective function is a representation of the network The total transmission time and network capacity of the link change over time and satisfy a function of a preset resource optimization objective. The network link between the target node corresponding to the maximum resource optimization value and the current node is taken as a sub-transmission processing path. This target node is taken as the new current node, and the execution steps are returned: using the configured joint objective function, the resource optimization value of the network link between the current node and each other node is calculated to transmit the amount of business to be processed, until all other nodes are traversed; if the target node calculated during the traversal is the destination node, the traversal ends, and the optimized transmission path composed of each sub-transmission processing path starting from the source node and ending at the destination node is obtained. This method addresses the highly dynamic changes in network topology and the time-varying characteristics of network resources under the large spatiotemporal scale of spatial information networks. It can describe the network and its resources in different spatiotemporal dimensions, assign spatiotemporal attributes to the network and network resources, and establish a dynamic transmission optimization model based on this dynamic network to achieve the best application business transmission processing path and satellite node resource allocation, thereby improving network resource utilization. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 A flowchart illustrating a dynamic network representation and resource optimization method based on spatiotemporal attributes provided in this application embodiment;

[0048] Figure 2 A schematic diagram of a dynamic network representation and resource optimization device based on spatiotemporal attributes provided in an embodiment of this application;

[0049] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0050] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by those skilled in the art. The words "first," "second," and similar terms used in this application do not indicate any order, quantity, or importance, but are only used to distinguish different components. The words "comprising" or "including," etc., mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, but do not exclude other elements or objects. The words "connected," "coupled," or "connected," etc., are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up," "down," "left," "right," etc., are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0051] Space information networks comprise various types of satellite nodes, such as relay satellites, communication satellites, and remote sensing satellites. These satellites possess different functions, enabling the real-time acquisition, transmission, processing, and distribution of massive amounts of data. The satellites within the network exhibit highly dynamic characteristics, and the satellite links and onboard resource information processing capabilities are also dynamically changing. Therefore, the network utility of space information networks is time-varying. When handling application services arising from sensing and communication tasks, considering the highly dynamic changes in network topology and the time-varying characteristics of network resources across large spatiotemporal scales, it is possible to describe the network and its resources at different spatiotemporal scales, assigning spatiotemporal attributes to the network and its resources. Based on this dynamic network, a dynamic transmission optimization model can be established to achieve the optimal application service transmission processing path and satellite node resource allocation.

[0052] Currently, time-varying graphs are commonly used to describe spatial information networks, and their representation is as follows: Triples, which describe network nodes, links, and time, reflect the dynamic changes in network structure, but to some extent ignore the dynamic changes in network resources, especially network utility or ability, as the network structure changes. For highly dynamic networks like spatial information networks, where network resources are closely related to network structure, time-varying graph representations cannot accurately characterize spatial information networks, affecting the acquisition, processing, transmission, and application of network information, and limiting the performance and resource utilization of spatial information networks. Spatial information network transmission models based on time-varying graphs, using static graph theory as their design basis, treat time-varying networks as segmented static networks. They lack consideration of the spatiotemporal attributes of resources and the correlation between resources at different times, leading to the inability to coordinate and utilize multi-dimensional network resources and difficulty in scheduling them according to time. This results in low resource utilization and difficulty in ensuring Quality of Service (QoS) and Quality of Experience (QoE) in time-varying networks.

[0053] The existing spatial information network representation methods and transmission models mainly include the following schemes:

[0054] Existing spatial information networks mainly rely on time-varying maps. The representation of time-varying networks includes: snapshot graphs, time-extended graphs, and time-aggregated graphs. Snapshot graphs primarily describe the changes in network topology over different time periods. Through discretization in the time dimension, each snapshot graph (equivalent to a static graph) can depict the network state that remains unchanged within each time period, thus achieving a static representation of time-varying networks. However, snapshot subgraphs are relatively independent, severing the correlation of network resources and failing to achieve accurate modeling of network resources, resulting in a waste of time-varying resources. Time-extended graphs introduce storage links on top of snapshots, interconnecting identical nodes in adjacent snapshot subgraphs and using storage link weights to represent the storage capacity of nodes, achieving a joint characterization of storage and link resources in time-varying networks with high representation accuracy. However, when the network scale is large and the time range is large (with many snapshot subgraphs), time-extended graphs also suffer from high complexity in storage space and routing calculations. Therefore, to reduce the space complexity of the graph model, time-aggregated graphs aggregate snapshot subgraphs and represent the link weights of each time period as a link weight sequence. For example, when the link weight is the link capacity, the link weight sequence represents the link capacity of each time period. Because time-aggregated graphs do not require multiple replications of nodes, graph model storage is more efficient. However, time-aggregated graphs lack characterization of storage resources, cannot guarantee the constraints between time-segmented links and caches, and have low graph model accuracy.

[0055] Transmission models based on time-varying graph models struggle to accurately represent and utilize the relationships between time-varying resources. Furthermore, the diverse and complex task types within the network, coupled with varying QoS requirements for different tasks, present numerous challenges for representing and designing routes for multidimensional time-varying resources in spatial information networks. Some studies utilize snapshots to model the dynamic topology of spatial information networks and propose dynamic routing algorithms aimed at minimizing path costs. However, these algorithms only calculate paths within each snapshot, neglecting the network resource utility existing between snapshots. Transmission modeling based on time-aggregated graphs reduces the storage complexity of graph models by aggregating and representing time-varying link resources, and proposes a shortest path algorithm based on time-aggregated graphs. However, time-aggregated graphs lack representation of the constraints between time-segmented link resources and multidimensional network resources, resulting in low model accuracy and an inability to solve for maximum network flow. Existing transmission models pre-determine and maintain the spatial tasks and transmission processes, failing to reflect the relationships between network dynamics, service characteristics, and transmission modes, and also neglecting to fully consider the temporal attributes of resources and the relationships between multidimensional resources.

[0056] However, the inventors have discovered the following problems with the existing spatial information network representation methods described above:

[0057] (1) Existing spatial network structure representation methods mainly rely on traditional static graphs and snapshot graphs based on time-varying graphs. Static graphs and snapshot graphs are difficult to fully describe and represent the highly dynamic structural features of spatial information networks. In particular, snapshot graphs lack descriptions of the interdependence, correlation and evolution relationships between different snapshot graphs.

[0058] (2) Although the time extension graph and time aggregation graph established based on the time-varying graph reflect the change process of the network dynamic structure, they do not dynamically represent and describe the multidimensional network resources involved in the network, and do not have a relatively complete representation of the relationship and dynamic characteristics of the changes in multidimensional network resources and network structure. In particular, they lack a description of the dynamic utility and capability changes of network resources with the network structure, making it difficult to accurately link the network structure and network application services to provide users with optimized transmission and application services.

[0059] (3) Most studies on network resource management based on time-varying graphs discuss the allocation, management and optimization of network resources based on the relatively static network structure. They mainly treat network resources as static resources for allocation, and pay little attention to the relationship between network resources and the spatiotemporal changes of the network dynamic structure. However, they ignore the dynamic changes of network resources, especially the network utility or ability, with the network structure to a certain extent. This results in a relatively small optimization space for network resources and limited improvement in network resource utilization. The characteristics of highly dynamic changes in networks and resources in spatial information networks are not fully explored and utilized.

[0060] To address the aforementioned issues, this application presents a dynamic network representation and resource optimization method based on spatiotemporal attributes. It proposes a novel network representation and resource description model, G=(V,E,R,t,p), based on time-varying graphs. This model endows network structure and resources with spatiotemporal attributes, describing and characterizing the dynamic changes of network resources with the network structure across five dimensions: nodes, links, resources, time, and space. It fully considers the spatiotemporal attributes of resources and the correlations of multi-dimensional resources to construct a more accurate dynamic satellite network. Furthermore, a service transmission model is established based on the dynamic satellite network. With network capacity and transmission latency as objectives, modeling and optimization are performed at three levels: network topology, network routing transmission, and node resource management. By optimizing the transmission processing paths of network application services and the resource allocation of nodes, it better adapts to dynamic network transmission scenarios and improves network resource utilization.

[0061] The dynamic network representation and resource optimization method based on spatiotemporal attributes provided in this application can be applied to spatial information networks. These networks can be jointly represented by their basic attribute information (nodes, links, resources, time, and space), and can be represented as quintuples. ;

[0062] This represents a set of nodes. It includes satellite sensing nodes and satellite transmission computing nodes. Satellite sensing nodes include optical, SAR, and electronic spectrum types. Satellite transmission computing nodes include communication satellites, broadcast satellites, and relay satellites. The terrestrial network includes ground station nodes and user nodes. User nodes include mobile terminals, vehicle-mounted terminals, and airborne terminals. Ground station nodes include ground processing centers and ground receiving stations.

[0063] This represents a set of links. There are four main types of links: intra-orbit links (ISL) within the same orbital layer, inter-satellite links (IOL) between satellites in different orbits within the same orbital layer, inter-layer links (IOL) between different orbital layers, and user links and ground station links between the user / ground station and the satellite orbit. User links include user uplinks and user downlinks; ground station links include feeder uplinks and feeder downlinks. Links between satellite nodes are collectively referred to as network links.

[0064] Represents a resource set, describing the time- and space-varying node resource functions corresponding to each node and network link in a spatial information network. and link resource functions .

[0065] Indicates time; Indicates spatial location (e.g., latitude and longitude, orbital position).

[0066] (1) Node resource functions Node resources include computing resources, storage resources, sensing resources, and transmission resources. Among these, computing and storage resources are the resources of the onboard computer system, and they can be represented as functions that vary with time and space.

[0067] Computational resource dynamic functions: ,in, This is the initial calculation of the total amount of resources. It is in time and the position of the corresponding node Next The computing resources consumed by each task;

[0068] Storage resource dynamic functions: ,in It is the initial total amount of storage resources. It is in time and location Next Storage resources consumed by each task.

[0069] (2) Link resource function Link resources mainly involve bandwidth, latency, and packet loss rate. Considering these metrics, construct link performance functions, including a dynamic bandwidth function, a dynamic latency function, and a link reliability function.

[0070] The bandwidth dynamic function is expressed as: ,in, It is the initial bandwidth. It is a spatiotemporal influencing factor;

[0071] The delayed dynamic function is expressed as: ,in, It is the base latency. This is an additional delay caused by satellite movement or load changes;

[0072] Link reliability function: ,in, It is initial reliability. These are factors that vary with time and space, such as link status and interference.

[0073] Then, based on the node resource function corresponding to each node and the link resource function corresponding to each network link, a dynamic network resource function is constructed. For example, the total dynamic network resource at a certain moment can be expressed as: ,in, It is the first The resource dynamic function of each node. It is the first The resource dynamic function of each link. N represents the number of network nodes, and E represents the number of network links.

[0074] Based on spatiotemporal benchmarks, the relationship between networks and network resources is characterized. This represents the changing relationships of network nodes, links, and resources over time and space, in order to construct a dynamic network resource graph with spatiotemporal attributes.

[0075] It should be noted that in real-world applications, the dynamic changes of resources are often influenced by numerous constraints, which need to be reflected in the dynamic function. These include: capacity constraints. , ,in, and Maximum available resources for nodes and links; latency and real-time constraints: This indicates that the link delay must not exceed a certain maximum value. .

[0076] Then, based on the network resource dynamic function, and the network links between different types of satellite nodes, user nodes, ground station nodes, and different types of satellites, a dynamic satellite network can be established; this dynamic satellite network can include a link model, a network transmission path model, a mission model, and a residual network model.

[0077] (1) The network links in the link model can include: Inter-satellite links in the same orbital layer: the connection relationship is basically fixed. Inter-satellite links between satellites in different orbital layers: the connection relationship is dynamic and there are relatively fixed link establishment rules. Inter-satellite links between layers, inter-satellite links between satellites at different altitude layers such as high orbit, medium orbit, and low orbit: the connection relationship is dynamic and linked dynamically according to the requirements of the transmission mission.

[0078] Based on this link model, the total bandwidth function of each network link over time and the bandwidth allocated to task service resources can be determined. Specifically, It is a network link The bandwidth time series of the total link bandwidth, where, This indicates that the ij link is within the time period Total link bandwidth Then it means Link bandwidth; Indicates that link ij is within the time period Medium-duty business resources The allocated bandwidth.

[0079] (2) Network transmission path model describes the transmission path of a certain service in the network. It can be transmitted according to the routing protocol or by specifying the path.

[0080] Based on this network transmission path model, the node paths between different nodes determined by the shortest distance routing, as well as the total transmission time function of each network link over time, can be determined. Specifically, path selection is achieved using shortest distance routing; the propagation delay function varies with time t. Link transmission delay function Queuing delay function This refers to the time it takes for data to be cached at the satellite node and await retransmission, including the time it takes for the data packet to arrive at the satellite, for the data packet to be processed, and the waiting time for the data packet to be transmitted from the satellite to the next hop. Indicates satellite In time Initial number of data packets, Indicates the data packet size. For the link between node i and node j The length of the distance between nodes, i.e., the path between nodes, where c is the speed of light. Indicates link Transmission rate. Total transmission time function. + .

[0081] (3) Task Model

[0082] For any time , Each ground station / user node will generate a batch of business requests, defined Showing time The task set, This belongs to the information of the k-th task in the task set, where k is any value from 1 to n. It is a four-tuple containing the source node, destination node, packet size, and service type of the data packet, represented as: , representing the k-th business information; based on business type, it can be divided into three categories. Category A Services: Deterministic Latency Services. These services have high requirements for latency and packet loss rate, needing to ensure data can be transmitted quickly from source to destination while maintaining a low packet loss rate to prevent significant latency jitter caused by packet loss and retransmission, thus ensuring real-time application performance. Audio and video conferencing and real-time monitoring fall into this category. Category B Services: High Bandwidth Requirement Services. These services have high requirements for bandwidth and packet loss rate. File transfer, backup, and data synchronization fall into this category. Category C Services: General Services. These services do not have particularly strict limitations on performance indicators such as latency and bandwidth. Email and fax fall into this category.

[0083] (4) Residual network model

[0084] Based on the remaining network model and the time-varying total bandwidth function of each network link, the time-varying network capacity function of each network link is determined. Specifically, for ease of subsequent calculations, the tasks in the task model can be described in time-series form. , This represents the i-th data quantity transmitted from the source link to the destination link. Simultaneously, it defines... For the task During the period Time flow through the link The amount of data. After the task flow consumes network links and link resources, the corresponding remaining resources constitute the remaining network. Therefore, it has a task flow... The link bandwidth, and its remaining network bandwidth capacity (or "network capacity function"). It can be represented as: .in Indicates along network links All task data must not exceed the maximum capacity of the link.

[0085] (5) Establish a multi-objective transmission optimization model: The sum of the product of network traffic and transmission time is expressed as the network transmission delay weighted by the transmission traffic. The objective of this application is to optimize the transmission delay and network capacity (i.e., the bandwidth of the network connection).

[0086] Objective 1: Minimize total transmission time:

[0087]

[0088] Objective 2: Maximize network capacity:

[0089]

[0090] Joint objective function:

[0091]

[0092] Where Z is the calculated resource optimization value of the network link between node i and node j. Representing task information The total transmission time is minimized (i.e., the product of transmission time and the amount of data transmitted is minimized). Indicates task information Total transmission time between node i and node j This represents the information of the kth task. The size of the data packet (i.e., the amount of data). , The weighting coefficients are used to balance the relative importance of the two objective functions. The joint objective function is defined as follows: when network link ij has no historical task transmissions, and when network link ij has historical task transmissions.

[0093] If the formula is... Replace with The difference between the bandwidth occupied by the current task flow and the historical task volume being transmitted can be used to obtain the current network capacity, expressed as:

[0094]

[0095] The constraints are as follows:

[0096]

[0097] Where n represents the nth satellite; This indicates the establishment of an inter-satellite link relationship; This indicates that the communication coverage area and the antenna elevation angle are greater than the minimum allowable elevation angle θ of the antenna; This indicates that the link bandwidth is less than the maximum bandwidth; This indicates a transmission path constraint, where the total delay from the source link to the destination link is less than the maximum allowable delay. This indicates that the satellite node resources do not exceed its total resources; This indicates that the link resources do not exceed its total resources.

[0098] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0099] Figure 1 This is a flowchart illustrating a dynamic network representation and resource optimization method based on spatiotemporal attributes, provided in an embodiment of this application. Figure 1 As shown, the method may include:

[0100] Step S110: Receive the service request sent by the ground station node / user node in the ground network at the current time.

[0101] A business request may include a source node, a destination node, and the amount of business to be processed.

[0102] Step S120: Using the source node as the current node, and employing the configured joint objective function, calculate the resource optimization value for the amount of business to be processed transmitted through the network links between the current node and each of the other nodes.

[0103] Among them, other nodes are any nodes other than the current node and the nodes that have calculated the resource optimization value; the joint objective function is a function that characterizes the total transmission time and network capacity of the network link changing with time and satisfying the preset resource optimization objective.

[0104] The configured joint objective function can be expressed as:

[0105]

[0106] For any network link, calculate the total transmission time and network capacity of the network link between the current node and other nodes at the current moment;

[0107] Specifically, regarding network capacity: if there are no historical tasks being transmitted on the network link at the current moment, then the total bandwidth of the network link is determined as the network capacity of the network link; if there are historical tasks being transmitted on the network link at the current moment, then the difference between the total bandwidth of the network link and the bandwidth occupied by the historical tasks being transmitted is determined as the network capacity of the network link.

[0108] For the total transmission time: Based on the length of the network link and the speed of light at the current moment, calculate the propagation delay of the network link; determine the link transmission delay of the network link by the ratio of the amount of traffic to be processed to the network capacity; determine the queuing delay of the traffic to be processed by the transmission rate of the network link, the amount of traffic to be processed, and the number of data packets in the current satellite node that are in the queue of traffic to be processed from the current moment; and determine the total transmission time of the network link by the sum of the propagation delay, the link transmission delay, and the queuing delay.

[0109] Then, the configured joint objective function is used to process the total transmission time and network capacity of the network link to obtain the resource optimization value Z for the amount of traffic to be processed on the network link.

[0110] Step S130: Take the network link between the target node corresponding to the maximum resource optimization value and the current node as the sub-transmission processing path; take the target node as the new current node, and return to execute step S120 until all other nodes are traversed.

[0111] In steps S120-S130, the initial current node is the first satellite node that receives the service request sent by the ground station node / user node, and the other nodes are other satellite nodes besides the first satellite node.

[0112] Step S140: If the target node calculated during the traversal is the destination node, then the traversal ends, and an optimized transmission path is obtained, consisting of each sub-transmission processing path starting from the source satellite node and ending at the destination node, so as to transmit the data to be processed through the optimized transmission path.

[0113] In some embodiments, if the data packet carrying the amount of business to be processed in the service request received in step S110 is 1, then steps S120-S140 can be executed directly.

[0114] If the service request received in step S110 contains multiple data packets carrying the amount of service to be processed, they need to be sorted according to the size of the amount of service to be processed carried in the data packets, and the data packets with smaller amounts of service should be transmitted first. The transmission process is as follows: steps S120-S140.

[0115] Specifically, the solution strategies for the network dynamic transmission optimization model include:

[0116] (1) Initialize satellite positions and calculate the set of satellites that each satellite can establish a communication link with. , … (i.e., other nodes).

[0117] (2) Initialize network node resources and network link resources .

[0118] (3) Application traffic Sort by size, prioritizing smaller traffic volumes for transmission or processing.

[0119] (4) For the application service transmission processing path, the current node The solution involves joint optimization from three levels: network topology, node resources, and transmission paths, to calculate the node and its satellite set. objective function in .

[0120] (5) Select the objective function of the current satellite node. The largest satellite node is added to the transmission processing path.

[0121] (6) After the current node resource allocation and transmission processing path is completed, update the satellite resource quantity and node allocation record, and continue to cycle until the last satellite node service is allocated.

[0122] (7) After all node services are processed, output the optimized transmission processing path and resource allocation for the application services.

[0123] Corresponding to the above method, embodiments of this application also provide a dynamic network representation and resource optimization device based on spatiotemporal attributes, such as... Figure 2 As shown, the device includes:

[0124] The receiving unit 210 is used to receive service requests sent by ground station nodes / user nodes in the terrestrial network at the current time. The service request includes a source node, a destination node, and the amount of service to be processed. The links between satellite nodes are collectively referred to as network links.

[0125] The calculation unit 220 is used to take the source node as the current node and use a configured joint objective function to calculate the resource optimization value of the network link transmission of the service to be processed between the current satellite node and each other node; the other nodes are any nodes other than the current node and the nodes whose resource optimization values ​​have been calculated; the joint objective function is a function that characterizes the total transmission time and network capacity of the network link changing with time and satisfying the preset resource optimization objective.

[0126] Return unit 230 is used to take the network link between the target node corresponding to the maximum resource optimization value and the current node as the sub-transmission processing path; then, the target node is taken as the new current node, and the execution steps are returned: using the configured joint objective function, the resource optimization value of the network link between the current node and each other node is calculated to transmit the amount of business to be processed, until each other node is traversed;

[0127] The acquisition unit 240 is used to end the traversal if the target node calculated during the traversal is the destination node, and to acquire the optimized transmission path composed of each sub-transmission processing path starting from the source node and ending at the destination node.

[0128] The functions of each functional unit of the dynamic network representation and resource optimization device based on spatiotemporal attributes provided in the above embodiments of this application can be implemented through the above method steps. Therefore, the specific working process and beneficial effects of each unit in the dynamic network representation and resource optimization device based on spatiotemporal attributes provided in the embodiments of this application will not be repeated here.

[0129] This application also provides an electronic device, such as... Figure 3 As shown, it includes a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340.

[0130] Memory 330 is used to store computer programs;

[0131] When the processor 310 executes the program stored in the memory 330, it performs the following steps:

[0132] Receive service requests sent by ground station nodes / user nodes in the terrestrial network at the current moment. The service requests include source nodes, destination nodes, and the amount of service to be processed. The links between satellite nodes are collectively referred to as network links.

[0133] Using the source node as the current node, and employing the configured joint objective function, calculate the resource optimization value for transmitting the amount of traffic to be processed through the network links between the current satellite node and each of the other nodes; the other nodes are any nodes other than the current node and the nodes whose resource optimization values ​​have been calculated; the joint objective function is a function that characterizes the total transmission time and network capacity of the network links as they change over time, and satisfies the preset resource optimization objective.

[0134] The network link between the target node corresponding to the maximum resource optimization value and the current node is taken as the sub-transmission processing path; then, the target node is taken as the new current node, and the execution steps are returned: using the configured joint objective function, the resource optimization value of the network link between the current node and each other node is calculated to transmit the amount of business to be processed, until each other node is traversed;

[0135] If the target node calculated during the traversal is the destination node, then the traversal ends, and an optimized transmission path is obtained, consisting of the sub-transmission processing paths starting from the source node and ending at the destination node.

[0136] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0137] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0138] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0139] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0140] The implementation methods and beneficial effects of the various components of the electronic device in the above embodiments for solving the problem can be found in [reference needed]. Figure 1 The steps in the illustrated embodiments are used to implement the electronic device. Therefore, the specific working process and beneficial effects of the electronic device provided in this application will not be repeated here.

[0141] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform any of the spatiotemporal attribute-based dynamic network representation and resource optimization methods described in the above embodiments.

[0142] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the spatiotemporal attribute-based dynamic network representation and resource optimization methods described in the above embodiments.

[0143] Those skilled in the art will understand that the embodiments in this application can be provided as methods, systems, or computer program products. Therefore, the embodiments in this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments in this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] This application describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this application with reference to flowchart illustrations and / or block diagrams. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0145] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0146] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0147] Although preferred embodiments have been described in this application, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of this application.

[0148] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the claims in this application and their equivalents, then this application also intends to include these modifications and variations.

Claims

1. A dynamic network representation and resource optimization method based on spatiotemporal attributes, characterized in that, When applied in a space information network comprising multiple satellite nodes, the method includes: Receive service requests sent by ground station nodes / user nodes in the terrestrial network at the current moment. The service requests include source nodes, destination nodes, and the amount of service to be processed. The links between satellite nodes are collectively referred to as network links. Using the source node as the current node, and employing the configured joint objective function, calculate the resource optimization value for transmitting the amount of business to be processed through the network links between the current node and each of the other nodes; the other nodes are any nodes other than the current node and the nodes whose resource optimization values ​​have been calculated; the joint objective function is a function that characterizes the total transmission time and network capacity of the network links changing over time and satisfying the preset resource optimization objective; The network link between the target node corresponding to the maximum resource optimization value and the current node is taken as the sub-transmission processing path; then, the target node is taken as the new current node, and the execution steps are returned: using the configured joint objective function, the resource optimization value of the network link between the current node and each other node is calculated to transmit the amount of business to be processed, until each other node is traversed; If the target node calculated during the traversal is the destination node, then the traversal ends, and an optimized transmission path is obtained, consisting of the sub-transmission processing paths starting from the source node and ending at the destination node.

2. The method as described in claim 1, characterized in that, The preset resource optimization objective is to minimize total transmission time and maximize network capacity. Using the configured joint objective function, the resource optimization values ​​for transmitting the pending service volume through network links between the current node and each other node are calculated, including: For any other node, calculate the total transmission time and network capacity of the network link between the current node and that other node at the current moment; The configured joint objective function is used to process the total transmission time and network capacity of the network link to obtain the resource optimization value for transmitting the amount of service to be processed on the network link.

3. The method as described in claim 2, characterized in that, The calculation process for the network capacity includes: If there are no historical tasks being transmitted on the network link at the current moment, then the total bandwidth of the network link is determined as the network capacity of the network link. If there are historical tasks being transmitted on the network link at the current moment, the difference between the total bandwidth of the network link and the bandwidth occupied by the historical tasks being transmitted is determined as the network capacity of the network link.

4. The method as described in claim 3, characterized in that, The calculation process for the total transmission time includes: Calculate the propagation delay of the network link based on the length of the network link and the speed of light at the current moment; The ratio of the amount of traffic to be processed to the network capacity is determined as the link transmission delay of the network link. Based on the transmission rate of the network link, the amount of traffic to be processed, and the number of data packets in the current node that are ahead of the amount of traffic to be processed from the current moment, the queuing delay of the traffic to be processed is determined. The sum of the propagation delay, link transmission delay, and queuing delay is determined as the total transmission time of the network link.

5. The method as described in claim 1 or 2, characterized in that, The configuration process of the joint objective function includes: Obtain the basic attribute information of the space information network, which includes different types of satellite nodes, network links between different types of satellite nodes, and node resource functions and link resource functions that vary with time and space for each satellite node and each network link; Based on the node resource function corresponding to each satellite node and the link resource function corresponding to each network link, a dynamic function for network resources is constructed. A dynamic satellite network is established based on network resource dynamic functions, different types of satellite nodes, and network links between different types of satellite nodes; the dynamic satellite network includes a link model, a network transmission path model, and a residual network model. Based on the link model, determine the total bandwidth function of each network link as it changes over time; Based on the network transmission path model, the node paths between different nodes determined by the shortest distance route are determined, as well as the total transmission time function of each network link over time. Based on the remaining network model and the total bandwidth function of each network link over time, the network capacity function of each network link over time is determined. Based on the node path, network traffic parameters, total transmission time function, and network capacity function, a joint objective function that satisfies the resource optimization objective is constructed.

6. The method as described in claim 5, characterized in that, The formula for the joint objective function is expressed as: Where Z is the calculated resource optimization value of the network link between node i and node j. Indicates task information The total transmission time function between node i and node j This represents the information of the kth task. Data packet size, Let be the network capacity function of the network link between node i and node j, which varies with time t. , Here, E represents the weighting coefficient, and E represents the set of links.

7. The method as described in claim 5, characterized in that, Different types of satellite nodes include satellite sensing nodes and satellite transmission computing nodes; Network links between different types of satellite nodes include intra-orbit links within the same orbital layer, inter-satellite links between satellites in different orbits within the same orbital layer, and inter-layer links between different orbital layers.

8. A dynamic network representation and resource optimization device based on spatiotemporal attributes, characterized in that, The device, used in a space information network comprising multiple satellite nodes, includes: The receiving unit is used to receive service requests sent by ground station nodes / user nodes in the terrestrial network at the current moment. The service request includes the source node, the destination node, and the amount of service to be processed. The links between satellite nodes are collectively referred to as network links. The calculation unit is used to take the source node as the current node and use a configured joint objective function to calculate the resource optimization value of the network link transmission of the service to be processed between the current node and each other node; the other nodes are any nodes other than the current node and the nodes whose resource optimization values ​​have been calculated; the joint objective function is a function that characterizes the total transmission time and network capacity of the network link changing with time and satisfying the preset resource optimization objective. The return unit is used to take the network link between the target node corresponding to the maximum resource optimization value and the current node as the sub-transmission processing path; then, the target node is taken as the new current node, and the execution steps are returned: using the configured joint objective function, the resource optimization value of the network link between the current node and each other node is calculated to transmit the amount of business to be processed, until each other node is traversed; The acquisition unit is used to end the traversal if the target node calculated during the traversal is the destination node, and to acquire the optimized transmission path composed of each sub-transmission processing path starting from the source node and ending at the destination node.

9. An electronic device, characterized in that, The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images