Construction method of low earth orbit constellation transmission and computing fusion network and task offloading method

Abstract

The application relates to a construction method and a task unloading method of a low-orbit constellation transmission and calculation fusion network. After a low-orbit constellation is acquired and modeling is performed on the low-orbit constellation, a dynamic low-orbit constellation model is obtained, a virtual copy is constructed for the dynamic low-orbit constellation model, and the connection between the dynamic low-orbit constellation model and the virtual copy is established based on a meta graph, so that the low-orbit constellation transmission and calculation fusion network is obtained. Based on this, the organic combination of multiple types of networks is realized, and the task unloading path limitation of various tasks is broken. After the connection link of the dynamic low-orbit constellation model, the virtual copy and the task in the low-orbit constellation transmission and calculation fusion network is determined, the unloading path is determined according to the connection link, and the task unloading is performed according to the unloading path. Based on this, the task unloading path of various tasks can be enriched according to the low-orbit constellation transmission and calculation fusion network, and a more optimal path selection is provided for the unloading path.

Description

Technical Field

[0001] This invention relates to the field of communication network technology, and in particular to a method for constructing and offloading tasks in a low-Earth orbit constellation transmission and computing converged network. Background Technology

[0002] Low Earth Orbit (LEO) satellite networks are an important component of satellite internet. Due to their low latency, low loss, and low cost, they are considered the most promising satellite communication networks and have become the focus of a new round of global network technology development and space competition.

[0003] Existing low-Earth orbit (LEO) constellations all use a curved data transmission network, offloading massive amounts of raw data to powerful ground-based cloud centers for processing. However, this approach is limited by factors such as long-distance transmission and ionospheric interference, resulting in very limited satellite-to-ground transmission rates that are insufficient to meet the needs of latency-sensitive services and may even cause network congestion. Therefore, there is an urgent need to find new offloading targets. In recent years, on-orbit computing has received widespread attention. On-orbit computing based on LEO constellations directly offloads tasks to LEO satellite networks for computation, and then transmits the results to the ground. Since the results can be as small as a few bits, transmission latency can be effectively reduced. At the same time, the continuous development of high-performance onboard computing technology for LEO satellites has made it possible to use LEO satellite networks for on-orbit computing.

[0004] Despite the promising future of on-orbit computing on low-Earth orbit (LEO) satellite networks, existing on-orbit computing offloading schemes for visible LEO satellites are limited by the uneven network load in reality, resulting in resource shortages in hotspot areas. Current LEO satellite network on-orbit computing schemes offload tasks to nearby visible LEO satellites via a one-hop transfer. However, in reality, task generation is closely related to human activities, with a large number of tasks originating from a few hotspot areas (such as cities and ports), leading to an extremely uneven distribution of tasks globally. In this situation, visible satellites in hotspot areas often experience task overload and resource shortages. Summary of the Invention

[0005] Therefore, it is necessary to provide a method for constructing a low-Earth orbit constellation transmission and computing fusion network and a method for task offloading, which are limited by the unbalanced network load in actual operation, to address the shortcomings of low-Earth orbit satellite mission offloading.

[0006] A method for constructing a low-Earth orbit constellation fusion network includes the following steps:

[0007] The low-Earth orbit (LEO) constellation is obtained and modeled to obtain a dynamic LEO constellation model. The dynamic LEO constellation model includes virtual nodes and the first inter-satellite link between virtual nodes. The first inter-satellite link is related to the communication between virtual nodes.

[0008] A virtual replica is constructed for the dynamic low-Earth orbit constellation model; wherein, the virtual replica includes a virtual node replica corresponding to a virtual node and a second inter-satellite link between the virtual node replicas; the second inter-satellite link is related to the communication between the virtual node replicas;

[0009] A connection between a dynamic low-Earth orbit (LEO) constellation model and a virtual replica is established based on the metagraph, resulting in a fusion network for LEO constellation transmission and computation.

[0010] The aforementioned method for constructing a low-Earth orbit (LEO) constellation-based integrated transmission and computing network involves acquiring and modeling the LEO constellation to obtain a dynamic LEO constellation model. A virtual replica of this dynamic model is then constructed, and a connection between the dynamic LEO constellation model and the virtual replica is established based on a metagraph, resulting in the LEO constellation-based integrated transmission and computing network. This approach enables the organic combination of multiple network types, overcoming the limitations of task offloading paths for various tasks.

[0011] In one embodiment, the process of establishing a connection between a dynamic low-Earth orbit constellation model and a virtual replica based on a metagraph includes the following steps:

[0012] Virtual nodes and their replicas are connected one-to-one via virtual edges; the virtual edges are related to the communication between the virtual nodes and their replicas.

[0013] In one embodiment, the process of establishing a connection between a dynamic low-Earth orbit constellation model and a virtual replica based on a metagraph includes the following steps:

[0014] Communication is established with the source node of the mission through a dynamic low-Earth orbit constellation model, and with the target node of the mission through a virtual replica.

[0015] In one embodiment, the process of establishing a connection between a dynamic low-Earth orbit constellation model and a virtual replica based on a metagraph includes the following steps:

[0016] Communication is established between the source and target nodes of the mission through a dynamic low-Earth orbit constellation model.

[0017] In one embodiment, the process of establishing a connection between a dynamic low-Earth orbit constellation model and a virtual replica based on a metagraph includes the following steps:

[0018] Communication is established with the source node of the mission through a virtual replica, and with the target node of the mission through a dynamic low-Earth orbit constellation model.

[0019] In one embodiment, the first inter-satellite link, the second inter-satellite link, and the virtual edge are all used to characterize the corresponding communication-related transmission and computation processes.

[0020] In one embodiment, the step further includes:

[0021] The computation latency of the virtual node corresponding to the virtual node replica is used as the weight of the corresponding virtual edge.

[0022] In one embodiment, a dynamic low-orbit constellation model and a virtual copy constitute a metagraph.

[0023] In one embodiment, the virtual replica is a dynamic low-Earth orbit constellation model when the set of edges formed by the first inter-satellite links is empty.

[0024] A device for constructing a low-Earth orbit constellation transmission and computing converged network includes:

[0025] The model building module is used to acquire and model the low-Earth orbit constellation to obtain a dynamic low-Earth orbit constellation model. The dynamic low-Earth orbit constellation model includes virtual nodes and the first inter-satellite link between virtual nodes. The first inter-satellite link is related to the communication between virtual nodes.

[0026] The replica creation module is used to construct virtual replicas for the dynamic low-Earth orbit constellation model; wherein, the virtual replicas include virtual node replicas that correspond one-to-one with the virtual nodes and a second inter-satellite link between the virtual node replicas; the second inter-satellite link is related to the communication between the virtual node replicas;

[0027] The network establishment module is used to establish a connection between the dynamic low-Earth orbit constellation model and the virtual replica based on the metagraph, thereby obtaining a low-Earth orbit constellation transmission and computing fusion network.

[0028] The aforementioned constructing device for the low-Earth orbit (LEO) constellation transmission and computing fusion network acquires and models the LEO constellation to obtain a dynamic LEO constellation model. Then, it constructs a virtual copy of the dynamic LEO constellation model and establishes a connection between the dynamic LEO constellation model and the virtual copy based on a metagraph, thus obtaining the LEO constellation transmission and computing fusion network. Based on this, it achieves an organic combination of multiple network types, overcoming the limitations of task offloading paths for various tasks.

[0029] A computer storage medium storing computer instructions, which, when executed by a processor, implement a method for constructing a low-orbit constellation transmission and computing converged network according to any of the above embodiments.

[0030] The aforementioned computer storage medium, after acquiring and modeling the low-Earth orbit (LEO) constellation to obtain a dynamic LEO constellation model, constructs a virtual copy of the dynamic LEO constellation model and establishes a connection between the dynamic LEO constellation model and the virtual copy based on a metagraph, thus obtaining a converged LEO constellation transmission and computing network. Based on this, an organic combination of multiple network types is achieved, overcoming the limitations of task offloading paths for various tasks.

[0031] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements a method for constructing a low-Earth orbit constellation transmission and computing converged network according to any of the above embodiments.

[0032] The aforementioned computer equipment, after acquiring and modeling a low-Earth orbit (LEO) constellation to obtain a dynamic LEO constellation model, constructs a virtual copy of the dynamic LEO constellation model and establishes a connection between the dynamic LEO constellation model and the virtual copy based on a metagraph, thus obtaining a converged LEO constellation transmission and computing network. Based on this, an organic combination of multiple network types is achieved, overcoming the limitations of task offloading paths for various tasks.

[0033] A task offloading method for a low-Earth orbit constellation-integrated transmission and computing network includes the following steps:

[0034] Determine the connection links of the dynamic LEO constellation model, virtual replicas, and tasks in the LEO constellation transmission and computing converged network;

[0035] The uninstallation path is determined based on the connection link, and the uninstallation task is executed according to the uninstallation path.

[0036] The aforementioned task offloading method for a converged LEO constellation transmission and computing network determines the connection links between the dynamic LEO constellation model, virtual replicas, and tasks within the network. Based on these connection links, an offloading path is determined, and task offloading is executed according to the offloading path. Therefore, the converged LEO constellation transmission and computing network can enrich the task offloading paths for various tasks, providing a more optimized path selection.

[0037] A task offloading device for a low-Earth orbit constellation transmission and computing converged network includes:

[0038] The link determination module is used to determine the connection links of the dynamic LEO constellation model, virtual replicas, and tasks in the LEO constellation transmission and computing converged network.

[0039] The path determination module is used to determine the uninstallation path based on the connection link and to execute the uninstallation task according to the uninstallation path.

[0040] The aforementioned task offloading device for the LEO constellation transmission and computing converged network determines the offloading path based on the connection links of the dynamic LEO constellation model, virtual replicas, and tasks within the network, and then executes task offloading according to the offloading path. Based on this, the LEO constellation transmission and computing converged network can enrich the task offloading paths for various tasks, providing a more optimized path selection.

[0041] A computer storage medium storing computer instructions, which, when executed by a processor, implement the task offloading method for a low-orbit constellation transmission and computing converged network according to any of the above embodiments.

[0042] The aforementioned computer storage medium, after determining the connection links of the dynamic LEO constellation model, virtual replicas, and tasks in the LEO constellation transmission and computing converged network, determines the offloading path based on the connection links and executes task offloading according to the offloading path. Based on this, the LEO constellation transmission and computing converged network can enrich the task offloading paths for various tasks, providing better path selection for offloading.

[0043] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the task offloading method for the low-Earth orbit constellation transmission and computing converged network of any of the above embodiments.

[0044] The aforementioned computer equipment, after determining the connection links of the dynamic LEO constellation model, virtual replicas, and tasks in the LEO constellation transmission and computing converged network, determines the offloading path based on the connection links and executes task offloading according to the offloading path. Based on this, the LEO constellation transmission and computing converged network can enrich the task offloading paths for various tasks, providing better path selection for offloading. Attached Figure Description

[0045] Figure 1 A flowchart illustrating a method for constructing a low-Earth orbit constellation transmission and computing fusion network as one embodiment;

[0046] Figure 2 A schematic diagram illustrating the construction of a virtual copy as one implementation method;

[0047] Figure 3 A schematic diagram illustrating the construction of a virtual copy for another implementation method;

[0048] Figure 4 A schematic diagram illustrating the connection establishment in one implementation method;

[0049] Figure 5 A schematic diagram illustrating the connection setup for another implementation method;

[0050] Figure 6 A structural diagram of a construction device module for a low-Earth orbit constellation transmission and computing fusion network according to one embodiment;

[0051] Figure 7 Flowchart of a task offloading method for a low-Earth orbit constellation transmission and computing converged network as one embodiment;

[0052] Figure 8 A structural diagram of a task offloading device module for a low-Earth orbit constellation transmission and computing convergence network according to one embodiment;

[0053] Figure 9 This is a schematic diagram of the internal structure of a computer according to one embodiment. Detailed Implementation

[0054] To better understand the purpose, technical solution, and technical effects of this invention, the invention will be further explained and described below in conjunction with the accompanying drawings and embodiments. It should also be stated that the embodiments described below are only for explaining this invention and are not intended to limit this invention.

[0055] This invention provides a method for constructing a low-orbit constellation transmission and computing fusion network.

[0056] Figure 1 A flowchart illustrating a method for constructing a low-Earth orbit constellation transmission and computing converged network according to one embodiment is shown below. Figure 1 As shown, a method for constructing a low-Earth orbit constellation transmission and computing fusion network according to one embodiment includes steps S100 to S102:

[0057] S100, acquire the low-Earth orbit constellation and model the low-Earth orbit constellation to obtain a dynamic low-Earth orbit constellation model; wherein, the dynamic low-Earth orbit constellation model includes virtual nodes and the first inter-satellite link between virtual nodes; the first inter-satellite link is related to the communication between virtual nodes;

[0058] S101 constructs a virtual replica for the dynamic low-Earth orbit constellation model; wherein, the virtual replica includes a virtual node replica corresponding to a virtual node and a second inter-satellite link between the virtual node replicas; the second inter-satellite link is related to the communication between the virtual node replicas;

[0059] S102, establishes a connection between the dynamic low-Earth orbit constellation model and the virtual replica based on the metagraph, and obtains a low-Earth orbit constellation transmission and computing fusion network.

[0060] Among them, the method of determining and modeling the low-Earth orbit constellation can be achieved by using modeling methods such as virtual topology or virtual node replicas to obtain a dynamic low-Earth orbit constellation model. Figure 2 This is a schematic diagram illustrating the construction of a virtual copy in one implementation method, as shown below. Figure 2 As shown, a dynamic low-Earth orbit constellation model G(t) is constructed, which includes virtual nodes (a, b, ..., p) and the first inter-satellite link between the virtual nodes.

[0061] In this system, each virtual node represents communication-related aspects, including communication direction and capabilities, through a first inter-satellite link. In one embodiment, the first inter-satellite link is used to represent the corresponding communication-related transmission and computation processes. The corresponding communication-related aspect refers to the communication between virtual nodes connected by the first inter-satellite link. As a preferred implementation, edge weights are assigned to the first inter-satellite link to represent the transmission process. These edge weights represent the sum of the transmission delay and propagation delay of the corresponding communication link, achieving a unified representation of the transmission and computation processes based on the first inter-satellite link, thus intuitively reflecting transmission and computation resources.

[0062] A virtual replica is constructed based on a dynamic low-Earth orbit constellation model. For example... Figure 2 As shown, a virtual replica G'(t) is established for the dynamic low-Earth orbit constellation model G(t). The virtual replica G'(t) includes virtual node replicas (a, b, ..., p) that correspond one-to-one with the virtual nodes, as well as the second inter-satellite links between the virtual node replicas.

[0063] The second inter-satellite link relates to communication between virtual node replicas, including communication direction and capabilities. In one embodiment, the second inter-satellite link is used to characterize the corresponding communication-related transmission and computation processes. The corresponding communication-related aspects refer to the communication between virtual node replicas connected by the second inter-satellite link. As a preferred implementation, edge weights are assigned to the second inter-satellite link to characterize the transmission process. The edge weights represent the sum of the transmission delay and propagation delay of the corresponding communication link, achieving a unified characterization of the transmission and computation processes based on the second inter-satellite link, thus intuitively reflecting transmission and computation resources.

[0064] It should be noted that different types of virtual copies can be created depending on the different definitions of virtual copies. Figure 3 A schematic diagram illustrating the construction of a virtual copy for another implementation method, such as Figure 3 As shown, the virtual replica H(t) is the dynamic low-Earth orbit constellation model G(t) when the edge set formed by the first inter-satellite link is empty.

[0065] like Figure 2 As shown in Figure 3, the dynamic low-orbit constellation model and the virtual replica constitute a metagraph, and are connected by virtual edges. The virtual edges correspond one-to-one with the virtual node replica and the virtual node.

[0066] The second inter-satellite link is related to communication between virtual nodes and their replicas, including communication direction and capabilities. In one embodiment, the second inter-satellite link is used to characterize the transmission and computation processes related to the corresponding communication. The corresponding communication relationship refers to the communication between the virtual node replicas connected by the second inter-satellite link. As a preferred implementation, the computation latency of the virtual node corresponding to the virtual node replica is used as the weight of the corresponding virtual edge, thus achieving a characterization of the computation process based on the virtual edge.

[0067] Based on this, a unified representation of transmission and computing resources is achieved by establishing the first inter-satellite link, the second inter-satellite link, and virtual edges.

[0068] The task involves multiple network layers, including air, space, and ground, and the integration of transmission and computation is key to achieving full network offloading of the task. Typically, task offloading involves processing raw data from the source node to a virtual node, completing the computation, and then transmitting the computation results to the target node.

[0069] Based on this, in one embodiment, Figure 4 A schematic diagram illustrating the connection establishment in one implementation method, such as... Figure 4 As shown, step S102, which establishes the connection between the dynamic low-Earth orbit constellation model and the virtual replica based on the metagraph, includes the following steps:

[0070] Communication is established with the source node of the mission through a dynamic low-Earth orbit constellation model, and with the target node of the mission through a virtual replica.

[0071] like Figure 4 As shown, the source node of the task communicates with virtual nodes within the visible range on the dynamic low-Earth orbit constellation model, and the target node communicates with virtual node replicas within the visible range on the virtual replicas, thereby realizing the construction of the fused network.

[0072] In one embodiment, Figure 5 A schematic diagram illustrating the connection in another implementation method is shown, such as... Figure 5 As shown, step S102, which establishes the connection between the dynamic low-Earth orbit constellation model and the virtual replica based on the metagraph, includes the following steps:

[0073] Communication is established between the source and target nodes of the mission through a dynamic low-Earth orbit constellation model.

[0074] like Figure 5 As shown, the source node of the task communicates with virtual nodes within the visible range of the dynamic low-Earth orbit constellation model, and the target node communicates with replicas of virtual nodes within the visible range of the dynamic low-Earth orbit constellation model, thereby realizing the construction of the fused network.

[0075] In one embodiment, such as Figure 3As shown, the process of establishing a connection between the dynamic low-Earth orbit constellation model and the virtual replica based on the metagraph includes the following steps:

[0076] Communication is established with the source node of the mission through a virtual replica, and with the target node of the mission through a dynamic low-Earth orbit constellation model.

[0077] like Figure 3 As shown, the source node of the task communicates with virtual nodes within the visible range of the virtual replica, and the target node communicates with virtual node replicas within the visible range of the dynamic low-Earth orbit constellation model, thereby realizing the construction of the fused network.

[0078] The method for constructing a low-Earth orbit (LEO) constellation transmission and computing fusion network according to any of the above embodiments involves acquiring and modeling the LEO constellation to obtain a dynamic LEO constellation model. A virtual copy of the dynamic LEO constellation model is then constructed, and a connection between the dynamic LEO constellation model and the virtual copy is established based on a metagraph, thereby obtaining the LEO constellation transmission and computing fusion network. Based on this, an organic combination of multiple network types is achieved, overcoming the limitations of task offloading paths for various tasks.

[0079] This invention also provides a construction device for a low-orbit constellation transmission and computing fusion network.

[0080] Figure 6 This is a structural diagram of a construction device module for a low-Earth orbit constellation transmission and computing converged network according to one embodiment, as shown below. Figure 6 As shown, a construction apparatus for a low-Earth orbit constellation transmission and computing fusion network according to one embodiment includes:

[0081] The model building module 100 is used to acquire the low-Earth orbit constellation and model the low-Earth orbit constellation to obtain a dynamic low-Earth orbit constellation model; wherein, the dynamic low-Earth orbit constellation model includes virtual nodes and the first inter-satellite link between virtual nodes; the first inter-satellite link is related to the communication between virtual nodes;

[0082] The replica creation module 101 is used to construct virtual replicas for the dynamic low-Earth orbit constellation model; wherein, the virtual replicas include virtual node replicas that correspond one-to-one with the virtual nodes and a second inter-satellite link between the virtual node replicas; the second inter-satellite link is related to the communication between the virtual node replicas;

[0083] Network establishment module 102 is used to establish a connection between a dynamic low-Earth orbit constellation model and a virtual replica based on a metagraph, thereby obtaining a low-Earth orbit constellation transmission and computing fusion network.

[0084] The aforementioned constructing device for the low-Earth orbit (LEO) constellation transmission and computing fusion network acquires and models the LEO constellation to obtain a dynamic LEO constellation model. Then, it constructs a virtual copy of the dynamic LEO constellation model and establishes a connection between the dynamic LEO constellation model and the virtual copy based on a metagraph, thus obtaining the LEO constellation transmission and computing fusion network. Based on this, it achieves an organic combination of multiple network types, overcoming the limitations of task offloading paths for various tasks.

[0085] This invention also provides a task offloading method for a low-orbit constellation transmission and computing fusion network.

[0086] Figure 7 A flowchart illustrating a task offloading method for a low-Earth orbit constellation-based converged transmission and computing network, as described in one embodiment. Figure 7 As shown, a task offloading method for a low-Earth orbit constellation transmission and computing converged network according to one embodiment includes steps S200 and S201:

[0087] S200, determine the connection links of the dynamic LEO constellation model, virtual replicas and tasks in the LEO constellation transmission and computing converged network;

[0088] S201, determine the uninstallation path based on the connection link, and execute the uninstallation task according to the uninstallation path.

[0089] Taking the LEO constellation transmission and computing fusion network constructed by the construction method of any of the above embodiments as an example:

[0090] like Figure 2 As shown, the second aspect is the construction of a fusion network based on metagraphs. Task offloading across the entire network may involve multiple layers of networks, including air, space, and ground. For integrated space-ground networks containing multiple layers, achieving the fusion of transmission and computation is crucial for realizing task offloading. Metagraphs can not only represent the connection relationships between nodes within a graph but also the associations between graphs. Metagraphs can effectively describe the relationships between different network layers. Based on metagraphs, a combination of multiple networks, including a dynamic low-Earth orbit constellation model G(t) with time-varying weights, its virtual replica G′(t), and tasks, is performed.

[0091] like Figure 4 As shown, for a task Γ with source node u, destination node v and offloaded via a low-Earth orbit constellation, in a network with four subgraphs: source node u, destination node v, dynamic low-Earth orbit constellation model G(t), and virtual replica G′(t), the task can be offloaded to a low-Earth orbit satellite for computation, or it can be offloaded to a ground cloud center for computation.

[0092] Figure 4In one of the unloading paths shown, the original data of the task is unloaded from the source node u to the virtual node replica f in the low-Earth orbit constellation. Then, the original data of the task is routed to the virtual node replica k via the inter-satellite link f→j→k in G(t). The virtual edge k→k representing the computation completes the computation of the task. Then, the computation result of the task is routed from the computation node k to the visible virtual node replica p of the destination node via the inter-satellite link k→o→p in G′(t). Finally, the computation result is transmitted back to the ground via the satellite-to-ground transmission link p→v.

[0093] Figure 4 In the alternative unloading path shown, the original data of the mission is unloaded from the source node u to the virtual node replica g in the low-Earth orbit constellation. Then, the original data of the mission is routed to the visible virtual node replica l of the destination node through the inter-satellite link g→h→l in G(t). Finally, the original data of the mission is transmitted back to the ground for calculation by the satellite-to-ground transmission link l→v.

[0094] by Figure 4 As shown in the fused network diagram, tasks can be offloaded to any computing node across the entire network, which is beneficial for the rational use of the network's computing resources and alleviates the problem of local computing resource shortages caused by uneven network load.

[0095] In another embodiment, such as Figure 5 As shown, the raw data of the mission is transmitted from the source node u to the virtual node copy within its visible range, and then transmitted to the visible virtual node copy of the destination node v through the inter-satellite link of the low-orbit constellation model G(t), and then offloaded to the ground cloud center for calculation through the satellite-to-ground transmission link.

[0096] In another embodiment, such as Figure 3 As shown, the raw data of the mission is transmitted from the source node u to the virtual node replicas f, g, j and k within its visible range, and the satellite associated with the visible virtual node replicas of the source node u performs the mission calculations directly. Then, the virtual node replicas f, g, j and k in G(t) transmit the calculation results to the visible virtual node replicas of the destination node v via the inter-satellite link, and then the calculation results are unloaded to the ground via the satellite-to-ground transmission link.

[0097] As can be seen from the task offloading process based on any of the above implementation methods, the set of offloading paths for the ground offloading strategy and the visible low-Earth orbit (LEO) satellite offloading strategy is a subset of the offloading paths for the fusion network. That is, under the ground offloading strategy and the visible LEO satellite offloading strategy, the optimal offloading path that achieves the minimum latency must be included in the set of offloading paths for the LEO constellation transmission and computing fusion network. Therefore, for any offloading task, the latency of the optimal offloading path for the transmission and computing fusion task offloading is always less than or equal to the latency of the optimal offloading paths for ground offloading and LEO satellite offloading, and this overcomes the limitation of traditional task offloading mechanisms (such as offloading tasks to ground cloud centers or visible LEO satellites) in failing to jointly optimize transmission and computing issues during the offloading process.

[0098] In one embodiment, the optimal unloading path can be determined from the connection links using shortest path algorithms such as Dijkstra's algorithm. If the obtained optimal unloading path contains virtual edges, the current task is unloaded to the virtual node corresponding to the virtual edge for computation; otherwise, the task is unloaded to the ground server for computation, thereby improving the computational efficiency of the unloading path.

[0099] The task offloading method for the LEO constellation transmission and computing converged network in any of the above embodiments, after determining the connection links of the dynamic LEO constellation model, virtual replica, and tasks in the LEO constellation transmission and computing converged network, determines the offloading path based on the connection links and executes task offloading according to the offloading path. Based on this, the LEO constellation transmission and computing converged network can enrich the task offloading paths for various tasks, providing a better path selection for offloading paths.

[0100] This invention also provides a task offloading device for a low-orbit constellation transmission and computing converged network.

[0101] Figure 8 This is a structural diagram of a task offloading device module for a low-Earth orbit constellation transmission and computing converged network according to one embodiment, as shown below. Figure 8 As shown, a task offloading device for a low-Earth orbit constellation transmission and computing converged network according to one embodiment includes:

[0102] Link determination module 200 is used to determine the connection links of dynamic low-Earth orbit constellation model, virtual replica and mission in low-Earth orbit constellation transmission and computing converged network;

[0103] The path determination module 201 is used to determine the uninstallation path based on the connection link and to perform the uninstallation task based on the uninstallation path.

[0104] The aforementioned task offloading device for the LEO constellation transmission and computing converged network determines the offloading path based on the connection links of the dynamic LEO constellation model, virtual replicas, and tasks within the network, and then executes task offloading according to the offloading path. Based on this, the LEO constellation transmission and computing converged network can enrich the task offloading paths for various tasks, providing a more optimized path selection.

[0105] This invention also provides a computer storage medium storing computer instructions that, when executed by a processor, implement the construction method of the low-Earth orbit constellation transmission and computing converged network or the task offloading method of the low-Earth orbit constellation transmission and computing converged network of any of the above embodiments.

[0106] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0107] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, terminal, or network device, etc.) to execute all or part of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, RAM, ROM, magnetic disks, or optical disks.

[0108] Corresponding to the computer storage medium described above, one embodiment also provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements any of the construction methods or task offloading methods of the low-Earth orbit constellation transmission and computing converged network described in the above embodiments.

[0109] This computer device can be a terminal, and its internal structure diagram can be as follows: Figure 9 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for constructing a low-Earth orbit (LEO) constellation transmission and computing converged network or a task offloading method for such a network. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0110] The aforementioned computer equipment, after acquiring and modeling a low-Earth orbit (LEO) constellation to obtain a dynamic LEO constellation model, constructs a virtual copy of the dynamic LEO constellation model and establishes connections between the dynamic LEO constellation model and the virtual copy based on a metagraph, thus obtaining a converged LEO constellation transmission and computing network. Based on this, it achieves an organic combination of multiple network types, overcoming the limitations of task offloading paths for various tasks. Alternatively, after determining the connection links between the dynamic LEO constellation model, the virtual copy, and the tasks in the converged LEO constellation transmission and computing network, it determines the offloading path based on the connection links and executes task offloading according to the offloading path. Therefore, the converged LEO constellation transmission and computing network can enrich the task offloading paths for various tasks, providing better path selection for offloading.

[0111] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0112] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for constructing a low-Earth orbit constellation-integrated transmission and computing network, characterized in that, Including the following steps: A low-Earth orbit (LEO) constellation is obtained and modeled to obtain a dynamic LEO constellation model; wherein, the dynamic LEO constellation model includes virtual nodes and a first inter-satellite link between the virtual nodes; the first inter-satellite link is related to the communication between the virtual nodes; A virtual replica is constructed for the dynamic low-Earth orbit (LEO) constellation model; wherein, the virtual replica includes virtual node replicas corresponding one-to-one with the virtual nodes and a second inter-satellite link between the virtual node replicas; the second inter-satellite link is related to the communication between the virtual node replicas; wherein, the first inter-satellite link and the second inter-satellite link are used to characterize the corresponding communication-related transmission and calculation processes; the dynamic LEO constellation model and the virtual replica constitute a metagraph, and the virtual replica is the dynamic LEO constellation model when the edge set formed by the first inter-satellite link is an empty set; Based on the metagraph, a connection is established between the dynamic low-Earth orbit constellation model and the virtual replica to obtain a low-Earth orbit constellation transmission and computing fusion network.

2. The method for constructing a low-Earth orbit constellation transmission and computing fusion network according to claim 1, characterized in that, The process of establishing the connection between the dynamic low-orbit constellation model and the virtual replica based on the metagraph includes the following steps: The virtual node and the virtual node replica are connected in a one-to-one correspondence through virtual edges; wherein the virtual edges are related to the communication between the virtual node and the virtual node replica.

3. The method for constructing a low-orbit constellation transmission and computing fusion network according to claim 1, characterized in that, The process of establishing the connection between the dynamic low-orbit constellation model and the virtual replica based on the metagraph includes the following steps: The dynamic low-Earth orbit constellation model establishes a communication relationship with the source node of the mission, and the virtual replica establishes a communication relationship with the target node of the mission.

4. The method for constructing a low-Earth orbit constellation transmission and computing fusion network according to claim 1, characterized in that, The process of establishing the connection between the dynamic low-orbit constellation model and the virtual replica based on the metagraph includes the following steps: The dynamic low-Earth orbit constellation model establishes communication relationships with the source and target nodes of the mission.

5. The method for constructing a low-Earth orbit constellation transmission and computing fusion network according to claim 1, characterized in that, The process of establishing the connection between the dynamic low-orbit constellation model and the virtual replica based on the metagraph includes the following steps: The virtual replica establishes a communication relationship with the source node of the mission, and the dynamic low-Earth orbit constellation model establishes a communication relationship with the target node of the mission.

6. The method for constructing a low-orbit constellation transmission and computing fusion network according to claim 2, characterized in that, The virtual edges are used to represent the corresponding communication-related transmission and calculation processes.

7. The method for constructing a low-Earth orbit constellation transmission and computing fusion network according to claim 6, characterized in that, It also includes the following steps: The computation delay of the virtual node corresponding to the virtual node replica is used as the weight of the corresponding virtual edge.

8. A task offloading method for a low-Earth orbit (LEO) constellation transmission and computing fusion network constructed according to any one of claims 1 to 7, characterized in that, Including the following steps: Determine the connection links of the dynamic LEO constellation model, virtual replicas, and tasks in the LEO constellation transmission and computing converged network; The uninstallation path is determined based on the connection link, and the uninstallation task is executed based on the uninstallation path.

Images