A low-orbit satellite network task offloading and routing planning joint scheduling method based on a time-expanded graph and related devices

Abstract

This invention provides a method and related apparatus for joint scheduling of task offloading and routing planning in low-Earth orbit (LEO) satellite networks based on time-spreading graphs, belonging to the field of wireless communication technology. The method constructs a dynamically time-varying LEO satellite network; represents the constructed network as a directed network topology graph based on time series using a time-spreading graph; constructs a joint scheduling model using the time-series directed network topology graph; sets constraints on the joint scheduling model; solves the objective function of the constructed model based on the set constraints to obtain the optimal result; and performs joint scheduling of task offloading and routing planning on the LEO satellite network based on the obtained optimal result to obtain the joint scheduling result. This invention solves the problem of poor global performance optimization caused by not fully considering the coupling relationship between task offloading and routing planning in dynamically time-varying network scenarios.

Description

Technical Field

[0001] This invention belongs to the field of wireless communication technology, specifically relating to a joint scheduling method and related apparatus for task offloading and routing planning in low-Earth orbit satellite networks based on time spread graphs. Background Technology

[0002] In recent years, with the full deployment and commercialization of fifth-generation mobile communication technology, many countries and regions around the world are actively promoting research and development for sixth-generation mobile communication systems (6G). The world's first 6G white paper points out that the key to the 6G vision is ubiquitous wireless intelligence. Ubiquity refers to the ability to provide seamless services to users anywhere. In other words, in the future, an information network will be laid that seamlessly covers all users in the air, space, land, and sea, thereby achieving integrated air, space, and sea communication.

[0003] Low Earth Orbit (LEO) satellites are typically deployed at altitudes between 500km and 2000km above the Earth's surface. Compared to medium and high Earth orbit satellites, they offer lower transmission latency and less link loss. Deploying multiple LEO satellites can achieve global coverage without being limited by terrain. For example, for communication needs in remote areas or extreme regions such as oceans and deserts, the application of LEO satellite networks is sufficient to overcome the challenge of lacking effective terrestrial mobile communication coverage in these areas. LEO satellite networks have become an important component of 6G.

[0004] On the other hand, an increasing number of new application services are emerging, such as real-time remote sensing data processing, large-scale IoT information aggregation, and intelligent disaster monitoring. These emerging services provide diversified offerings, greatly enhancing the user experience. However, these computationally intensive applications place high demands on resource-constrained servers (such as low-Earth orbit remote sensing satellites), making it difficult to handle the massive amounts of task data using only their own limited computing power and storage resources.

[0005] Against this backdrop, mobile edge computing has become a key solution for optimizing resource utilization. By offloading computationally intensive or latency-sensitive tasks to computing devices with richer computing resources and larger data storage, such as edge computing satellites deploying edge servers, the limitations of multi-satellite computing power can be addressed, avoiding performance bottlenecks of a single satellite. Typically, after collecting observation data, low-computing-power remote sensing satellites need to segment complex and computationally intensive tasks to ensure the integrity and orderliness of each task flow. Appropriate segments are selected as the task data to be offloaded, and strategies determine whether to offload tasks and which tasks to offload to which edge computing satellite. Based on the current network topology, considering data transmission security and efficiency, feasible communication links are established. After receiving task requests, the target edge computing satellite queues and schedules tasks based on priority and other factors, then executes the computation instructions. Finally, the processed data is transmitted back to the remote sensing satellite, and the edge computing satellite releases the allocated task computing resources. As can be seen from the above, the complete task offloading process requires careful planning and scheduling of the entire network system for task segmentation decisions, task offloading decisions, edge computing satellite selection decisions, and resource allocation decisions. These decisions collectively determine the quality of service of a computing network.

[0006] Chen et al. proposed an adaptive particle swarm optimization algorithm based on genetic algorithm operators. This algorithm effectively formulates an offloading strategy for deep neural network layers through layer partitioning operations, and simulation experiments verify that the algorithm strategy can significantly reduce energy consumption. Wu et al. decoupled the power and computational resource allocation problems by establishing an analytical model, solved the KKT (Karush-Kuhn-Tucker) stable point for each subproblem separately, and optimized system power consumption through a heuristic algorithm. Li et al. studied the task offloading problem with statistical QoS guarantees, formulating it as a mixed-integer nonlinear programming problem with constraints on CPU cycle number and latency exponent, and solved it using the Gibbs sampling method. Tang et al. established a dynamic scheduling model for task queues, decoupled the joint optimization problem of all time slots into computational resource allocation and power bandwidth subproblems using Lyapunov optimization theory, and solved them separately. Simulation results verified the algorithm's superiority. Gang et al. proposed an efficient inter-satellite collaborative computation offloading algorithm for LEO satellite networks to reduce latency and energy consumption, and solved the subproblems using the Lagrange multiplier method and binary particle swarm optimization algorithm respectively.

[0007] In recent years, a large number of related documents and results have emerged in the field of task offloading technology research. Although new technologies are emerging one after another, the following two problems still exist:

[0008] 1. There is a lack of attention to the joint optimization of task offloading and offloading route planning. Task offloading not only needs to consider how to offload computing tasks from low-performance nodes to edge nodes or the cloud, but also needs to optimize offloading routes to ensure efficient and stable data transmission in complex network environments. During task offloading, the choice of offloading route directly determines the path and efficiency of task transmission. Inappropriate selection may lead to link congestion, transmission delays, or even data loss. Most current research focuses on the single decision of task offloading, neglecting the inherent coupling between task offloading and route selection. Even when considering route optimization, most studies adopt a separate approach, first planning task offloading and then independently selecting transmission paths, lacking means to model the interaction between the two simultaneously.

[0009] 2. Ignoring the dynamic changes in the actual network environment. Current research generally assumes that the topology of low-Earth orbit (LEO) satellite networks is fixed and that communication links always exist between satellites. This simplification ignores the complexity of the actual dynamic environment. In real-world LEO satellite networks, high-speed satellite movement, link discontinuity, and changes in channel states make traditional models ill-suited to the characteristics of dynamic topologies. They cannot effectively address real-world problems such as link interruptions and resource contention, thus limiting the practicality and reliability of task scheduling and resource allocation strategies.

[0010] In summary, current technologies mainly focus on task offloading decisions or route planning optimization, without fully considering the coupling relationship between task offloading and route planning in dynamic time-varying network scenarios, resulting in poor global performance optimization. Summary of the Invention

[0011] The purpose of this invention is to provide a joint scheduling method and related apparatus for task offloading and route planning in low-Earth orbit satellite networks based on time-spreading graphs, which solves the problem that the existing technology does not fully consider the coupling relationship between task offloading and route planning in dynamic time-varying network scenarios, resulting in poor global performance optimization.

[0012] To achieve the above objectives, the present invention adopts the following technical solution:

[0013] In a first aspect, the present invention provides a joint scheduling method for low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs, comprising the following steps:

[0014] Construct a dynamic, time-varying low-Earth orbit satellite network;

[0015] The constructed dynamic time-varying low-Earth orbit satellite network is represented as a directed network topology graph based on time series using a time-extended graph.

[0016] A joint scheduling model is constructed using a time-series-based directed network topology graph, with the objective function being to minimize total energy consumption.

[0017] Set constraints for the joint scheduling model;

[0018] Based on the constraints of the joint scheduling model, the objective function of the constructed joint scheduling model is solved to obtain the optimal result;

[0019] Based on the optimal results obtained, a joint scheduling of task offloading and route planning is performed on the low-Earth orbit satellite network to obtain the joint scheduling results of task offloading and route planning.

[0020] A further improvement of this invention is that the expression for the objective function of minimizing total energy consumption is:

[0021]

[0022] in, For remote sensing satellites, For edge computing satellites, For time slot set, To minimize the total energy consumption objective function, For time slots Energy consumption for local calculations by domestic remote sensing satellites For remote sensing satellites in time slots Internal transmission energy consumption For time slots The energy consumed by inner edge computing satellites in processing remote sensing data. For time slots Total energy consumption of inner edge computing satellites participating in transmission relay.

[0023] A further improvement of this invention is that the constraints of the joint scheduling model include the following formula:

[0024]

[0025]

[0026]

[0027]

[0028]

[0029]

[0030] in, k For time slots, For remote sensing satellites, For edge computing satellites, For task unloading strategy, Choose a strategy for the uninstallation target. This represents the total amount of data waiting to be processed locally by remote sensing satellites. This represents the maximum computing and storage capacity for remote sensing satellites. This represents the total amount of data awaiting computation by edge computing satellites. This represents the maximum computing and storage capacity for edge computing satellites. It is a constant. .

[0031] A further improvement of this invention is that, after constructing a joint scheduling model using a directed network topology graph, the objective function of the constructed joint scheduling model is first decoupled to obtain the objective function of the decoupled joint scheduling model, and then the objective function of the decoupled joint scheduling model is solved.

[0032] A further improvement of this invention lies in the specific steps for decoupling the objective function of the constructed joint scheduling model, which include:

[0033] Build a route planning model;

[0034] In the constructed routing planning model, Dijkstra's algorithm is used to find the optimal offloading path from each remote sensing satellite node to the edge computing satellite node at different times;

[0035] The offloading path loss is obtained based on the optimal offloading path from each remote sensing satellite node to the edge computing satellite node at different times.

[0036] The objective function of the decoupled joint scheduling model is obtained by multiplying the path loss by the amount of unloaded data and then summing the results.

[0037] A further improvement of the present invention is that,

[0038] The objective function of the decoupled joint scheduling model is expressed as:

[0039]

[0040] in, For time slots Energy consumption for local calculations by domestic remote sensing satellites For time slots The energy consumed by inner edge computing satellites in processing remote sensing data. This represents the total energy consumption of the entire transmission process.

[0041] Total energy consumption of the entire transmission process The calculation formula is:

[0042]

[0043] in, Choose a strategy for the uninstallation target. For the amount of data that needs to be unloaded and processed, This is the basic overhead of offloading routes.

[0044] A further improvement of the present invention is that, in the step of solving the objective function of the established joint scheduling model based on the constraints of the set joint scheduling model to obtain the optimal result, the alternating optimization algorithm is specifically used to solve the objective function of the established joint scheduling model to obtain the optimal result.

[0045] Secondly, the present invention provides a joint scheduling system for low-Earth orbit satellite network task offloading and route planning based on time spread graph, including a satellite network construction module, a directed network topology graph acquisition module, a joint scheduling model construction module, a constraint setting module, an objective function solving module, and a joint scheduling module;

[0046] The satellite network construction module is used to construct a dynamic, time-varying low-Earth orbit satellite network;

[0047] The directed network topology graph acquisition module is used to represent the constructed dynamic time-varying low-orbit satellite network as a time-series-based directed network topology graph using a time-extended graph.

[0048] The joint scheduling model construction module is used to construct a joint scheduling model using a time-series-based directed network topology graph. The joint scheduling model takes minimizing total energy consumption as its objective function.

[0049] The constraint setting module is used to set the constraints of the joint scheduling model;

[0050] The objective function solving module is used to solve the objective function of the constructed joint scheduling model based on the constraints of the set joint scheduling model, and obtain the optimal result;

[0051] The joint scheduling module is used to perform joint scheduling of task offloading and route planning for the low-orbit satellite network based on the obtained optimal results, and to obtain the joint scheduling results of task offloading and route planning.

[0052] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method for joint scheduling of low-Earth orbit satellite network task offloading and routing planning based on time-spreading graphs.

[0053] Fourthly, the present invention provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described method for joint scheduling of low-Earth orbit satellite network task offloading and routing planning based on time-spreading graphs.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] This invention is an improved version. Compared with existing low-Earth orbit (LEO) satellite network task offloading and route planning scheduling methods, this invention comprehensively considers the close coupling relationship between task offloading decisions and route planning, proposing a joint optimization scheduling method. Specifically, task offloading decisions directly affect the distribution of offloading routes and link transmission status, while the status of offloading routes, in turn, restricts the feasibility and performance of optional offloading schemes. Therefore, this invention, while making task offloading decisions, comprehensively considers the dynamic changes in link status and network topology in real time, and collaboratively optimizes task offloading and offloading route strategies to achieve optimal global performance. This effectively solves the problem in existing technologies where the coupling relationship between task offloading and route planning in dynamic time-varying network scenarios is not fully considered, resulting in poor global performance optimization. On the other hand, this invention can achieve efficient coordination of computing and communication resources in dynamically changing LEO satellite network environments. It can not only avoid computing node overload or communication path congestion that may occur due to individual optimization, but also significantly improve the overall task processing efficiency and resource utilization of the system, ultimately achieving better energy consumption performance.

[0056] Secondly, this invention utilizes a directed network topology graph to construct a joint scheduling model. Specifically, it constructs a joint scheduling model by building a time-varying network state time-series model (based on a time-series directed network topology graph), which effectively solves the topology time-varying problem caused by the high-speed movement of nodes in low-Earth orbit satellite networks, thereby enabling more accurate scheduling decisions.

[0057] Furthermore, this invention discloses an expression for the objective function of minimizing total energy consumption. Based on the objective function of minimizing total energy consumption, it can be seen that this invention considers a variety of factors when establishing a joint scheduling model.

[0058] Furthermore, this invention discloses six constraints for the joint scheduling model. It is evident that this invention comprehensively considers multiple constraints, which can more fully reflect the actual situation of the joint scheduling problem of task offloading and routing planning.

[0059] Furthermore, this invention discloses that after constructing a joint scheduling model using a directed network topology graph, the objective function of the constructed joint scheduling model is first decoupled to obtain the objective function of the decoupled joint scheduling model, and then the objective function of the decoupled joint scheduling model is solved. By decomposing the complex objective function of the joint scheduling model into multiple relatively simple sub-models (the objective function of the decoupled joint scheduling model), the computational complexity of each sub-model can be significantly reduced, thereby improving the solution efficiency of the subsequent model. Attached Figure Description

[0060] Figure 1 This is a flowchart of the joint scheduling method for low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs according to the present invention.

[0061] Figure 2 This is a schematic diagram of the joint scheduling system for low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs according to the present invention.

[0062] Figure 3 This is an architecture diagram of the low-Earth orbit satellite network of the present invention;

[0063] Figure 4 This is a directed network topology diagram based on time series data, as presented in this invention.

[0064] Figure 5 This is a comparison chart of the total energy consumption of the joint scheduling method of this invention and the other two algorithm systems with the number of remote sensing satellites;

[0065] Figure 6 A schematic diagram showing the relationship between the optimal energy consumption value obtained by the joint scheduling method of this invention and the number of remote sensing satellites under different edge computing satellite numbers;

[0066] Figure 7 This is a schematic diagram of the structure of the electronic device of the present invention. Detailed Implementation

[0067] To further understand the content of this invention, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments are merely illustrative and not limiting of the invention.

[0068] This invention proposes a joint scheduling method for task offloading and route planning in low-Earth orbit (LEO) satellite networks based on time-spreading graphs. Based on the constraints of a set joint scheduling model, the objective function of the constructed joint scheduling model is solved to obtain the optimal result. The optimal result is then used to perform joint scheduling of task offloading and route planning on the LEO satellite network, yielding the joint scheduling result. Compared to existing technologies, this invention effectively solves the problem of poor global performance optimization caused by the failure to fully consider the coupling relationship between task offloading and route planning in dynamically time-varying network scenarios.

[0069] Example 1:

[0070] The flowchart of the joint scheduling method for low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs of this invention is as follows: Figure 1 As shown, the joint scheduling method for low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs of the present invention includes the following steps:

[0071] S1. Construct a dynamic, time-varying low-Earth orbit satellite network.

[0072] S2. The constructed dynamic time-varying low-Earth orbit satellite network is represented as a directed network topology graph based on time series using a time-extended graph.

[0073] S3. Construct a joint scheduling model using a time-series-based directed network topology graph, wherein the joint scheduling model takes minimizing total energy consumption as its objective function.

[0074] S4. Set the constraints for the joint scheduling model.

[0075] S5. Based on the constraints of the joint scheduling model, solve the objective function of the constructed joint scheduling model to obtain the optimal result.

[0076] S6. Based on the obtained optimal results, perform joint scheduling of task offloading and route planning for the low-Earth orbit satellite network to obtain the joint scheduling results of task offloading and route planning.

[0077] Example 2:

[0078] A schematic diagram of the joint scheduling system for low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs of this invention is shown below. Figure 2 As shown, the joint scheduling system for low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs of the present invention includes a satellite network construction module, a directed network topology graph acquisition module, a joint scheduling model construction module, a constraint setting module, an objective function solving module, and a joint scheduling module.

[0079] The satellite network construction module is used to build a dynamic, time-varying low-Earth orbit satellite network.

[0080] The directed network topology graph acquisition module is used to represent the constructed dynamic time-varying low-Earth orbit satellite network as a time-series-based directed network topology graph using a time-extended graph.

[0081] The joint scheduling model construction module is used to construct a joint scheduling model using a time-series-based directed network topology graph. The joint scheduling model takes minimizing total energy consumption as its objective function.

[0082] The constraint setting module is used to set the constraints of the joint scheduling model.

[0083] The objective function solving module is used to solve the objective function of the constructed joint scheduling model based on the constraints set in the joint scheduling model, and obtain the optimal result.

[0084] The joint scheduling module is used to perform joint scheduling of task offloading and route planning for the low-Earth orbit satellite network based on the obtained optimal results, and obtain the joint scheduling results of task offloading and route planning.

[0085] Example 3:

[0086] The present invention provides a joint scheduling method for low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs, comprising the following steps:

[0087] S1. Construct a dynamic, time-varying low-Earth orbit satellite network.

[0088] First, a dynamically time-varying low-Earth orbit (LEO) satellite network is constructed. The architecture of the dynamically time-varying LEO satellite network is as follows: Figure 3 As shown, the low-Earth orbit satellite network comprises three main functional layers: the user layer, the observation layer, and the access layer. These layers communicate with each other via communication links to exchange task requirements and data. A detailed description of each layer follows:

[0089] The core of the user layer is that the ground center gathers the mission requirements of ground users, which involve multiple fields, such as emergency rescue and environmental monitoring, and organizes them into a standardized set of tasks. These tasks are uploaded to the low-Earth orbit satellite network through specific interfaces for remote sensing satellites to execute.

[0090] The observation layer consists of several remote sensing satellites operating in low Earth orbit. Each satellite carries a high-resolution remote sensing camera to acquire real-time images of the Earth's surface or information on moving targets. Due to their high coverage and short revisit cycles, remote sensing satellites offer significant flexibility in space observation missions. However, their computing and storage capabilities are limited by power consumption and hardware configuration. To further process the data, remote sensing satellites can utilize their own computing power to perform basic tasks, or they can choose to offload the data to edge computing satellites in the access layer via inter-satellite links for computation.

[0091] The access layer consists of edge computing satellites distributed in higher orbits. These satellites are equipped with powerful computing modules and large-capacity storage systems to support computationally intensive tasks. Although fewer in number than remote sensing satellites, edge computing satellites have significantly greater computing power. Through dynamic links with remote sensing satellites, the access layer can receive offloaded task requests and return processing results promptly after completing computations, significantly reducing overall task response time.

[0092] S2. The constructed dynamic time-varying low-Earth orbit satellite network is represented as a directed network topology graph based on time series using a time-extended graph.

[0093] The constructed dynamically time-varying low-Earth orbit satellite network is represented as a time-series-based directed network topology using a Time-Expanded Graph (TEG). The time-series-based directed network topology is shown below. Figure 4 As shown. Assume the entire task processing time is divided into... There are discrete time slots, each with a length of [missing information]. Within the same time slot, the network topology is assumed to remain fixed, while the link connection status between adjacent time slots may change with satellite movement, thus dynamically reflecting the evolution of the entire network over time.

[0094] node( Figure 4 (Black circles represent nodes) Time Extension: Assuming the satellite network contains two types of nodes: remote sensing satellites and edge computing satellites, the use of a time extension graph adds a temporal dimension. Each node is replicated at different time points, extending into multiple twin nodes, representing the different states of the same node at different time points. This effectively captures the dynamic characteristics of nodes changing over time and reflects the state evolution of nodes in different time slots.

[0095] Specifically, Represents the set of all satellite nodes. ,in and These represent the sets of remote sensing satellites and edge computing satellites, respectively. For each vertex in the set... or In the time-extended graph, nodes expand according to the evolution over time. Twin nodes or Therefore, a static set of nodes. This can be further transformed into representing a set of nodes based on different times. ,in .

[0096] Spatiotemporal extension link ( Figure 4 (Each arrow in the image represents a spatiotemporal extension link) generation: Figure 4 Midlink This includes cached links and transmission links. A cached link represents a directed edge connecting the same satellite between two consecutive time slots, using... This indicates that the cache link represents the internal storage of mission data within the satellite, including incomplete computational tasks and mission data awaiting offloading. In reality, the cache link does not exist in the actual network; it simply means that data is stored on the nodes. To avoid data processing chaos, the mission data in the cache link is divided into two independent queues, used to store mission data awaiting computation and mission data awaiting transmission, respectively. The transmission link represents the directed edge connecting different satellites between two consecutive time slots, formed by... This includes inter-satellite links within the edge computing satellite layer, inter-satellite links between remote sensing satellites, and cross-layer inter-satellite links between remote sensing satellites and edge computing satellites. Ultimately, the buffer links and transmission links between nodes at adjacent time points together constitute a fixed network topology within a unit time slot, thereby effectively capturing the changing patterns of satellite communication links and providing support for optimal path selection for computation offloading tasks.

[0097] S3. Construct a joint scheduling model using a time-series-based directed network topology graph.

[0098] A joint scheduling model is constructed using a time-series-based directed network topology graph, where the objective function of the joint scheduling model is to minimize the total energy consumption.

[0099] Minimize the total energy consumption objective function (also called The expression for ) is:

[0100]

[0101] in, For remote sensing satellites, For edge computing satellites, For time slot set, The objective function is to minimize the total energy consumption (specifically, to minimize the total energy consumption of two types of satellites, including remote sensing satellites and edge computing satellites). For time slots Energy consumption for local calculations by domestic remote sensing satellites For remote sensing satellites in time slots Internal transmission energy consumption For time slots The energy consumed by inner edge computing satellites in processing remote sensing data. For time slots The total energy consumption of the inner edge computing satellite participating in the transmission relay is calculated below. The parameters are as follows (…). , , and ) will be explained in detail:

[0102] A. Energy consumption for local computing on remote sensing satellites

[0103] Assuming in time slot Inside, remote sensing satellites The original remote sensing data to be processed (i.e., the task) is generated independently and identically distributed. Let the average task generation rate be... The amount of newly generated data per unit time slot is ,satisfy Each remote sensing satellite can choose to perform calculations locally or offload them to edge computing satellites for processing. This indicates the task unloading strategy, specifying which tasks to unload and which to replace newly generated tasks. proportion, The calculation formula is:

[0104]

[0105] in, The amount of data processed locally. The amount of data that needs to be unloaded and processed.

[0106] Assuming a computation task input of 1 bit requires, One CPU cycle, remote sensing satellite The CPU cycle frequency is The remote sensing satellite will then be responsible for the mission. Local computing speed The calculation formula is:

[0107]

[0108] The amount of data that can be processed locally within a unit time slot Represented as:

[0109]

[0110] The amount of unprocessed data remaining after the time slot ends It will wait in the computation queue for processing in the next time slot. The calculation formula is as follows:

[0111]

[0112] Therefore, remote sensing satellites The amount of data waiting in the queue per time slot The calculation formula has been updated to:

[0113]

[0114] According to circuit theory, the power consumption of a CPU is mainly determined by dynamic power consumption, which originates from the switching activities of the CPU's internal logic gates and is related to the circuit voltage in the CMOS circuit. and CPU cycle frequency It is proportional to the square of the voltage. Furthermore, during low-voltage operation, the CPU cycle frequency is approximately linearly related to the chip voltage. Therefore, the local computing power consumption of remote sensing satellites... The calculation formula is:

[0115]

[0116] in, This is a constant energy consumption coefficient related to the internal structure of the equipment.

[0117] Therefore, time slot Energy consumption calculated locally The calculation formula is:

[0118]

[0119] B. Energy consumption for remote sensing satellite transmission

[0120] make This indicates the offloading target selection strategy for edge computing satellites. Among them, Indicates remote sensing satellite Select edge computing satellite The task offloading computation is performed on the target. It is stipulated that a remote sensing satellite can select at most one edge computing satellite as its offloading target node, and choose an appropriate transmission route for offloading. The task is to satisfy Each edge computing satellite can receive offloaded tasks from multiple remote sensing satellites and process them in parallel.

[0121] For tasks to be unloaded, remote sensing satellites Multiple routes are available, each capable of transmitting data to the target edge computing node. Define the set of transmission routes. ,in It refers to a set of routes that start from different remote sensing satellite nodes and end at different edge computing satellite nodes, and is listed by enumeration. , These are the routing numbers for satellites unloaded from the same initial point to the same edge computing satellite node at different times. (Binary variable) judge Time slot and (Time interval) satellite Corresponding node Uninstall the router? Among them , . express In transmission routing middle, This indicates that it does not exist.

[0122] Remote sensing satellite Data transmission rate to the next node of the route The calculation formula is:

[0123]

[0124] in, For satellite The transmission power, considering Rayleigh fading environment, , The inter-satellite channel fading coefficient, Let Variance be the variance of Gaussian white noise. For remote sensing satellites The transmission bandwidth is also constrained. Simultaneously, the transmission latency (the amount of data that needs to be offloaded for processing) is also limited. The duration is no greater than the duration of each time slot, meaning that any amount of data can be transmitted within one time slot.

[0125] and Let represent the initial remote sensing satellite node and the edge computing satellite node selected as the offloading target, respectively. Then, the remote sensing satellite... Energy consumption for data transmission The calculation formula is:

[0126]

[0127] Therefore, remote sensing satellites in time slots Internal transmission power consumption The calculation formula is:

[0128]

[0129] C. Energy consumption of edge computing satellites

[0130] Define the CPU clock frequency of the edge computing satellite as follows: The unit is cycle / s, and the calculated intensity is... (Number of CPU cycles required to process a 1-bit task), the unit is cycle / bit. Therefore, in the time slot Inner edge computing satellite Unload task processing speed The calculation formula is:

[0131]

[0132] in, This represents the loss coefficient related to the internal architecture of the edge computing satellite, thus calculating energy consumption. The expression is:

[0133]

[0134] For each edge computing satellite There is multi-task offloading due to the access of multiple remote sensing satellites. If the edge computing terminal receives an offloading task before a certain time, it is automatically added to the computing queue to await processing in subsequent time slots. For binary parameters... ,like This means that the current edge computing satellite is the final target satellite node to be unloaded. Therefore, time slots Received data volume of tasks to be computed The calculation formula is:

[0135]

[0136] Time slot The total amount of data waiting to be processed in the queue The calculation formula is:

[0137]

[0138] The remaining task volume that was not calculated in the previous time slot The calculation formula is:

[0139]

[0140] in, For time slots The maximum amount of task data that can be processed within the system is calculated using the following formula:

[0141]

[0142] Therefore, time slot Inner edge computing satellite Computational energy consumption The expression is:

[0143]

[0144] D. Total energy consumption of edge computing satellite transmission relay

[0145] The formula for calculating the satellite transmission rate of edge computing is as follows: :

[0146]

[0147] in, and These represent the transmission bandwidth and transmission power of the edge computing satellite, respectively.

[0148] Edge computing satellite Towards Transmission energy consumption The calculation formula is:

[0149]

[0150] Therefore, time slot Total energy consumption of inner edge computing satellites participating in transmission relay The calculation formula is:

[0151]

[0152] S4. Set the constraints for the joint scheduling model.

[0153] The constraints of the joint scheduling model include the following formulas:

[0154] C1:

[0155] C2:

[0156] C3:

[0157] C4:

[0158] C5:

[0159] C6:

[0160] in, k For time slots, For remote sensing satellites, For edge computing satellites, For task unloading strategy, Choose a strategy for the uninstallation target. This represents the total amount of data waiting to be processed locally by remote sensing satellites. This represents the maximum computing and storage capacity for remote sensing satellites. This represents the total amount of data awaiting computation by edge computing satellites. This represents the maximum computing and storage capacity for edge computing satellites. It is a constant. .

[0161] The constraints are explained in detail below:

[0162] Specifically, C1 is the task unloading strategy. The upper and lower bound constraints. C2 represents the unloading target selection strategy. It is a binary variable. C3 ensures that each remote sensing satellite offloads its task to at most one edge computing satellite. C4 indicates... and The relationship of mutual restraint between them, that is, when ,but Conversely, if Then there must exist a Make C5 and C6 respectively indicate that the total number of tasks waiting to be computed in the two types of satellite queues before the start of any time slot does not exceed their respective computing storage limits.

[0163] S5. Based on the constraints of the joint scheduling model, solve the objective function of the constructed joint scheduling model to obtain the optimal result.

[0164] In this step, the alternating optimization algorithm is used to solve the objective function of the established joint scheduling model to obtain the optimal result.

[0165] S6. Based on the obtained optimal results, perform joint scheduling of task offloading and route planning for the low-Earth orbit satellite network to obtain the joint scheduling results of task offloading and route planning.

[0166] Example 4:

[0167] In this embodiment, after constructing the joint scheduling model using the directed network topology graph in step S3, the objective function of the constructed joint scheduling model is first decoupled to obtain the objective function of the decoupled joint scheduling model. In step S4, the objective function of the decoupled joint scheduling model is solved (specifically, the alternating optimization algorithm is used to solve the objective function of the decoupled joint scheduling model to obtain the optimal result).

[0168] Build a route planning model;

[0169] In the constructed routing planning model, Dijkstra's algorithm is used to find the optimal offloading path from each remote sensing satellite node to the edge computing satellite node at different times;

[0170] The offloading path loss is obtained based on the optimal offloading path from each remote sensing satellite node to the edge computing satellite node at different times.

[0171] The objective function of the decoupled joint scheduling model is obtained by multiplying the path loss by the amount of unloaded data and then summing the results.

[0172] The objective function of the constructed joint scheduling model is decoupled and explained in detail below:

[0173] Due to the existence of data transmission This assumption implies that parallel data transmission from both remote sensing satellites and edge computing satellites acting as relays can be completed within a unit time slot. Furthermore, according to... and It can be seen that the transmission rate of remote sensing satellite communication and edge computing satellite communication transmission rate These are variables only related to the current node and the node to which the transmission is directed, and are unrelated to time slots. A directed network topology graph is as follows: Figure 4 As shown, the routing problem can be extracted and optimized separately. The energy consumption of each path segment can be determined by... Indicates variables and These are coefficients related to the nodes, and generally have definite numerical values. Therefore, we can assume... This represents the basic loss cost for each link. Specifically, the cost of an inter-satellite link with a remote sensing satellite as the transmitter is expressed as: The cost of using edge computing satellites as transmitters is expressed as Such as The communication and storage cost within a node is set to 0, while the cost between two nodes is set to infinity if no communication link exists. Therefore, for each remote sensing satellite's data to be unloaded within each time slot, a unique unloading route can be independently found. Defined as the time slot of a remote sensing satellite node. Newly generated unloaded task It needs to be transmitted to edge satellites. The collection of all satellite nodes traversed. Simultaneously, introducing... Indicates unloading the route The basic energy consumption is the total basic cost of the corresponding route.

[0174] because The binary variables that are difficult to determine and simultaneously control for computation and transmission energy consumption It can be transformed into an independent transmission energy consumption problem, and the computational energy consumption is no longer affected by the division problem. and The third variable outside of control.

[0175] For variables The determination of this can be summarized as finding the least costly path for each remote sensing satellite to offload and transfer the new task to the target computing satellite in each time slot. The set of paths is defined as follows: The cost set is The two correspond to each other. Each remote sensing satellite has nodes in each time slot. They are all considered as the starting point of the path, that is The endpoint is different edge computing satellites at different times. , represented as Therefore, a total of exist. Save the optimal transmission route as ,in In fact, For edge computing satellite nodes The state at different times, and its role in the network is to offload computational processing tasks; therefore, it is only necessary to... Choose the route with the lowest cost, which represents the remote sensing satellite. The task Uninstall to the target uninstall node Optimal transmission route Corresponding cost ,generate 1-th order matrix and This invention calculates using Dijkstra's algorithm. (Also known as the optimal offloading path from each remote sensing satellite node to the edge computing satellite node at different times) and The matrix (also called the unloading path loss) is calculated using the following steps:

[0176] a. Assignment

[0177] Based on all parameters to the starting node of the path The base cost of each link in the TEG is assigned sequentially;

[0178] b. Route finding

[0179] respectively indivual Starting from this point, we will search for... indivual Optimal path to destination and minimum cost ;

[0180] c. Determining the optimal route

[0181] exist Choose the unload point with the lowest cost. ,Sure and ,generate and matrix.

[0182] The basic loss value of the path to be optimized has been determined. Based on the analysis described above, the basic loss... Data volume unloaded on the current road segment The product of path loss and unloaded data (also called path loss multiplied by unloaded data volume) is the transmission energy consumption. Therefore, considering all time slots and all remote sensing satellites unloading to possible computational edges, the total energy consumption of the overall transmission process can be transformed into the following expression:

[0183]

[0184] For edge computing satellites A judgment variable is introduced for the time slot when the mission unloads and arrives at the target satellite. To determine remote sensing satellites In the time slot Are newly generated unloadable tasks in the time slot? Reach the current node after completion If the requirements are met, the variable is assigned a value of 1; otherwise, it is assigned a value of 0. (Time slot) Total amount of data waiting to be processed in the queue The calculation formula is:

[0185]

[0186] The objective function of the decoupled joint scheduling model (also called ), The expression is:

[0187]

[0188] in, For time slots Energy consumption for local calculations by domestic remote sensing satellites For time slots The energy consumed by inner edge computing satellites in processing remote sensing data. This represents the total energy consumption of the entire transmission process.

[0189] In this embodiment, step S4 involves solving the objective function of the decoupled joint scheduling model using an alternating optimization algorithm. The specific steps include:

[0190] A. Initialization

[0191] First, set the upper limit for the two nested loops. and and the initial loop number Set according to the constraint relationship of C1-C4 and The initial value;

[0192] B. Fixed Solve about The single-objective optimization problem is to find and update the optimal solution. .according to Computing system energy consumption ;

[0193] C. Fixed Solve about The single-objective optimization problem is to find and update the optimal solution. .according to Computing system energy consumption ;

[0194] D. Check the inner loop convergence condition.

[0195] Compare the changes in alternating optimization; if the convergence condition is met... Or reach the maximum number of iterations of the inner loop. When the inner iteration loop stops, the optimal value of the inner loop is output. Otherwise, Return to step B and continue the iteration;

[0196] E. Check the outer loop convergence condition.

[0197] Compare the change in the current iteration result with the result in the previous iteration. If the convergence condition is met... Or reach the maximum number of iterations of the outer loop. Then stop the outer iteration loop and output the optimal solution. and and optimal value Otherwise, Return to step B and continue the iteration.

[0198] The other steps in this embodiment (steps S1, S2, S5 and S6) are the same as in embodiment 3.

[0199] To verify the effectiveness of the proposed joint scheduling method for low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs, this embodiment uses MATLAB 2019 software for simulation experiments. The specific simulation parameters are configured as follows: the remote sensing satellite constellation includes... The edge satellite constellation contains remote sensing satellites. Edge satellites. Transmission power of communication between remote sensing satellites and edge computing satellites. The size ranges are 1~5W and 5~10W respectively, bandwidth The clock speeds are 10MHz and 20MHz respectively. The computing power of the two types of satellites is 1~2GHz and 2~4GHz respectively, with a CPU clock frequency of 737.5 cycles / bit and a capacitor loss factor of [missing information]. The noise power spectral density is specified as -174 dBm / Hz. Simulation and optimization are performed concurrently. Each time slot is [number] time slots, and each time slot is [number]. s.

[0200] To evaluate the superiority of the proposed joint scheduling method for task offloading and route planning in low-Earth orbit satellite networks based on time-spreading graphs, this invention designs comparative methods: a single-timeslot offloading algorithm and a random offloading algorithm. Specifically, the single-timeslot offloading algorithm optimizes the offloading ratio and transmission route only for newly generated tasks within the current timeslot, while keeping the network topology fixed within a unit timeslot. For example, in Figure 4 In China, for Newly generated If offloading is considered, the decision is made based on the inter-satellite link diagram within that time slot. Only edge computing nodes with valid time windows can be selected. As the final unloading point, the random unloading algorithm will randomly generate the unloading ratio for each remote sensing satellite in each time slot. Then calculate the optimal uninstallation option. The simulation results are as follows Figure 5 As shown, the total energy consumption of the system gradually increases with the increase in the number of remote sensing satellites. However, due to the lack of connectivity between two nodes during offloading route selection, the base cost is infinite, and this situation cannot be avoided in the random offloading algorithm. Therefore, its total energy consumption is much higher than the other two algorithms, exceeding the value by several orders of magnitude. The proposed algorithm (also called the method proposed in this invention) and the single-slot offloading algorithm consider the connectivity between nodes, thereby limiting the offloading ratio and keeping the total energy consumption of the system at a lower level. Figure 5 The trend of the curves shows that the energy consumption of the proposed algorithm is generally lower than that of the single-slot offloading algorithm, but the difference is small. This is because the main difference between the two algorithms lies in the transmission routing stage, and the percentage of transmission energy consumption in the total energy consumption is low, so the difference is negligible. If the running time and the number of running slots are increased, the energy consumption disadvantage of the single-slot offloading algorithm compared to the proposed algorithm will gradually become more prominent.

[0201] To assess the impact of the number of edge computing satellites on the performance of low-Earth orbit satellite networks. Figure 6 This demonstrates the trend of total system energy consumption varying with the number of remote sensing satellites under different configurations of edge satellites. From Figure 6 It is evident that as the number of available edge satellites increases, the total energy consumption decreases. Specifically, firstly, the increased number of edge satellites expands the range of task offloading options, thereby improving the flexibility of the offloading process and enhancing the system's adaptability to handling various tasks. This allows for a wider range of optimal offloading target satellites to be selected based on task requirements and network conditions. Secondly, in the time-spread graph-based network topology, the increased number of edge satellite nodes introduces more offloading routes with lower transmission costs. Therefore, routing further reduces the system's total energy consumption by optimizing data transmission paths and reducing energy-intensive long-distance communications. Furthermore, in... and In both cases, the curves almost overlap, the energy consumption is very similar, and the optimization and improvement effect is not significant, possibly because the system is already close to its energy efficiency limit.

[0202] Example 5:

[0203] Please see Figure 7 As shown, the present invention also provides an electronic device 100 for a joint scheduling method of low-Earth orbit satellite network task offloading and routing planning based on time-spreading graphs; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0204] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the joint scheduling method for low-Earth orbit satellite network task offloading and routing planning based on time-spreading graphs as described in Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0205] The at least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, 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, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor. The processor 102 is the control center of the electronic device 100, connecting various parts of the electronic device 100 via various interfaces and lines.

[0206] The memory 101 in the electronic device 100 stores multiple instructions to implement a joint scheduling method for low-Earth orbit satellite network task offloading and routing planning based on a time-spreading graph. The processor 102 can execute the multiple instructions to achieve the following:

[0207] Construct a dynamic, time-varying low-Earth orbit satellite network;

[0208] The constructed dynamic time-varying low-Earth orbit satellite network is represented as a directed network topology graph based on time series using a time-extended graph.

[0209] A joint scheduling model is constructed using a time-series-based directed network topology graph, with the objective function being to minimize total energy consumption.

[0210] Set constraints for the joint scheduling model;

[0211] Based on the constraints of the joint scheduling model, the objective function of the constructed joint scheduling model is solved to obtain the optimal result;

[0212] Based on the optimal results obtained, a joint scheduling of task offloading and route planning is performed on the low-Earth orbit satellite network to obtain the joint scheduling results of task offloading and route planning.

[0213] Example 6:

[0214] If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0215] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0216] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0217] 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.

[0218] 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.

[0219] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A time-expanded graph based low earth orbit satellite network task offloading and routing planning joint scheduling method, characterized in that, Includes the following steps: Construct a dynamic, time-varying low-Earth orbit satellite network; The constructed dynamic time-varying low-Earth orbit satellite network is represented as a directed network topology graph based on time series using a time-extended graph. A joint scheduling model is constructed using a time-series-based directed network topology graph. The objective function of the joint scheduling model is to minimize the total energy consumption. The objective function of the constructed joint scheduling model is decoupled to obtain the objective function of the decoupled joint scheduling model. The objective function for minimizing total energy consumption is expressed as: in, For remote sensing satellites, For edge computing satellites, For time slot set, To minimize the total energy consumption objective function, For time slots Energy consumption for local calculations by domestic remote sensing satellites For remote sensing satellites in time slots Internal transmission energy consumption For time slots The energy consumed by inner edge computing satellites in processing remote sensing data. For time slots Total energy consumption of inner edge computing satellites participating in transmission relay; Set constraints for the joint scheduling model; The constraints of the joint scheduling model include the following formulas: in, k For time slots, For remote sensing satellites, For edge computing satellites, For task unloading strategy, Choose a strategy for the uninstallation target. This represents the total amount of data waiting to be processed locally by remote sensing satellites. This represents the maximum computing and storage capacity for remote sensing satellites. This represents the total amount of data awaiting computation by edge computing satellites. This represents the maximum computing and storage capacity for edge computing satellites. It is a constant. ; Based on the constraints of the joint scheduling model, the objective function of the decoupled joint scheduling model is solved to obtain the optimal result; Based on the optimal results obtained, a joint scheduling of task offloading and route planning is performed on the low-Earth orbit satellite network to obtain the joint scheduling results of task offloading and route planning.

2. The method for joint scheduling of low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs according to claim 1, characterized in that, The specific steps for decoupling the objective function of the constructed joint scheduling model include: Build a route planning model; In the constructed routing planning model, Dijkstra's algorithm is used to find the optimal offloading path from each remote sensing satellite node to the edge computing satellite node at different times; The offloading path loss is obtained based on the optimal offloading path from each remote sensing satellite node to the edge computing satellite node at different times. The objective function of the decoupled joint scheduling model is obtained by multiplying the path loss by the amount of unloaded data and then summing the results.

3. The method for joint scheduling of low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs according to claim 2, characterized in that, The objective function of the decoupled joint scheduling model is expressed as: in, For time slots Energy consumption for local calculations by domestic remote sensing satellites For time slots The energy consumed by inner edge computing satellites in processing remote sensing data. This represents the total energy consumption of the entire transmission process. Total energy consumption of the entire transmission process The calculation formula is: in, Choose a strategy for the uninstallation target. For the amount of data that needs to be unloaded and processed, This is the basic overhead of offloading routes.

4. The method for joint scheduling of low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs according to claim 1, characterized in that, In the step of solving the objective function of the decoupled joint scheduling model based on the constraints of the set joint scheduling model to obtain the optimal result, the alternating optimization algorithm is specifically used to solve the objective function of the decoupled joint scheduling model to obtain the optimal result.

5. A joint scheduling system for mission offloading and route planning in low-Earth orbit satellite networks based on time-spreading graphs, characterized in that, It includes a satellite network construction module, a directed network topology graph acquisition module, a joint scheduling model construction module, a constraint setting module, an objective function solving module, and a joint scheduling module; The satellite network construction module is used to construct a dynamic, time-varying low-Earth orbit satellite network; The directed network topology graph acquisition module is used to represent the constructed dynamic time-varying low-orbit satellite network as a time-series-based directed network topology graph using a time-extended graph. The joint scheduling model construction module is used to construct a joint scheduling model using a time-series-based directed network topology graph. The joint scheduling model takes minimizing total energy consumption as its objective function. The objective function of the constructed joint scheduling model is decoupled to obtain the objective function of the decoupled joint scheduling model. The objective function for minimizing total energy consumption is expressed as: in, For remote sensing satellites, For edge computing satellites, For time slot set, To minimize the total energy consumption objective function, For time slots Energy consumption for local calculations by domestic remote sensing satellites For remote sensing satellites in time slots Internal transmission energy consumption For time slots The energy consumed by inner edge computing satellites in processing remote sensing data. For time slots Total energy consumption of inner edge computing satellites participating in transmission relay; The constraint setting module is used to set the constraints of the joint scheduling model; The constraints of the joint scheduling model include the following formulas: in, k For time slots, For remote sensing satellites, For edge computing satellites, For task unloading strategy, Choose a strategy for the uninstallation target. This represents the total amount of data waiting to be processed locally by remote sensing satellites. This represents the maximum computing and storage capacity for remote sensing satellites. This represents the total amount of data awaiting computation by edge computing satellites. This represents the maximum computing and storage capacity for edge computing satellites. It is a constant. ; The objective function solving module is used to solve the objective function of the decoupled joint scheduling model based on the set constraints of the joint scheduling model, and obtain the optimal result; The joint scheduling module is used to perform joint scheduling of task offloading and route planning for the low-orbit satellite network based on the obtained optimal results, and to obtain the joint scheduling results of task offloading and route planning.

6. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the joint scheduling method for low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs as described in any one of claims 1 to 4.

7. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the joint scheduling method for low-Earth orbit satellite network task offloading and route planning based on time-spreading graphs as described in any one of claims 1 to 4.

Images