Satellite-ground fusion hybrid ad hoc network routing protocol and fault self-healing method and device, equipment and storage medium

Abstract

The invention discloses a satellite-ground fusion hybrid ad hoc network routing protocol and fault self-healing method, device and equipment and a storage medium, and the method comprises the steps: building a satellite-ground fusion network model based on the global routing information of a target region, and when a task request is received, sending the task request to a satellite-ground fusion network; generating a target routing strategy based on the task priority of the task request and the satellite-ground fusion network model, calling each node of the communication link based on the target routing strategy to carry out communication response on the task request, monitoring the communication response process of the communication link, and when the communication link has a fault, sending the fault to the satellite-ground fusion network model; according to the method, fault self-healing analysis is carried out through the target fault self-healing analysis model, a fault self-healing link is generated, and each node in the fault self-healing link is called to carry out communication response on the task request, so that communication fault self-healing in the communication response process is realized, the link stability and the fault-tolerant capability of the self-networking network in the unmanned area are effectively improved, and the self-healing efficiency of the self-networking network in the unmanned area is improved. The multi-target balance in the communication response process is realized, and the fault self-healing speed during the communication response fault is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication, in particular to a kind of star-ground fusion hybrid ad hoc network routing protocol and fault self-healing method, device, equipment and storage medium. BACKGROUND

[0002] With the continuous development of various communication network technologies, global communication conditions are increasingly perfect, but there are still problems of insufficient communication area coverage in large areas of uninhabited areas. The communication blind area of uninhabited area needs reliable coverage to ensure the diversity of communication scenarios in uninhabited area. Uninhabited area communication scenarios include border uninhabited area safety control, communication blind area online monitoring, field exploration and resource exploitation, post-disaster emergency response and rescue, environmental monitoring and protection, intelligent agriculture and precision agriculture monitoring, and unmanned aerial vehicle inspection and monitoring. In the above uninhabited area communication scenarios, communication can be realized through star-ground fusion hybrid ad hoc network, but reliable communication guarantee is often lacking in actual communication environment.

[0003] Star-ground fusion hybrid ad hoc network faces problems such as short endurance time, high delay, poor link stability, and easy data loss in actual application. Especially in the dynamic and complex environment of uninhabited area and the changing network conditions, the communication system is difficult to ensure the stable return of data, and lacks sufficient flexibility, stability and fault tolerance. The optimization target of current communication optimization and fault processing research for star-ground fusion hybrid ad hoc network is single, and there is lack of effective mechanism for flexible balance between energy consumption and delay. Conventional routing protocols or algorithms usually only judge whether the link is available according to the current measurement value, and the link stability is less considered in future changes. In the network with fast actual environment change, it is easy to appear chain break or continuous packet loss in the middle, which reduces the communication stability. Traditional ad hoc network has problems of high energy consumption, long delay, unstable link and insufficient fault self-healing ability, which leads to short network endurance time and unstable communication quality in uninhabited area information monitoring, and network paralysis caused by node failure. SUMMARY

[0004] The main purpose of the present application is to provide a kind of star-ground fusion hybrid ad hoc network routing protocol and fault self-healing method, device, equipment and storage medium, to solve the problems of high energy consumption, long delay, unstable link and insufficient fault self-healing ability of traditional ad hoc network in prior art, which leads to short network endurance time and unstable communication quality in uninhabited area information monitoring, and network paralysis caused by node failure.

[0005] To achieve the above purpose, the present application provides a kind of star-ground fusion hybrid ad hoc network routing protocol and fault self-healing method, the method comprises the following steps: construct a star-ground fusion network model based on global routing information of a target region, the global routing information comprising network topology information of the target region, the star-ground fusion network model being composed of a plurality of nodes in the target region and a communication topology between the nodes, the nodes comprising ad hoc network nodes and gateway nodes, the gateway nodes being connected with a plurality of ad hoc network nodes, and the ad hoc network nodes being connected with at least one ad hoc network node; generate a routing strategy according to the star-ground fusion network model, the routing strategy comprising a reactive routing strategy and a proactive routing strategy; when a task request is received, generate a target routing strategy based on a task priority of the task request and the routing strategy, the target routing strategy comprising a communication link for responding to the task request; respond to the task request by nodes in the communication link based on the target routing strategy, and monitor a communication response process of the communication link; when a fault is detected in the communication link, input the network topology information, node characteristics of the nodes in the communication link, and link characteristics of the communication link into a target fault self-healing analysis model for fault self-healing analysis, generate a fault self-healing link, and respond to the task request by nodes in the fault self-healing link to realize communication fault self-healing in the communication process.

[0006] Optionally, when a task request is received, generating a target routing strategy based on a task priority of the task request and the routing strategy comprises: when a task request is received, obtain a task state and a task priority of the task request; if the task state of the task request is a routine state or the task priority of the task request is lower than a priority threshold, use the reactive routing strategy as the target routing strategy; if the task state of the task request is an emergency state or the task priority of the task request is not lower than the priority threshold, use the proactive routing strategy as the target routing strategy, and monitor whether the task request is restored from the emergency state to the routine state; if the task request is restored from the emergency state to the routine state, use the reactive routing strategy as the target routing strategy; wherein the reactive routing strategy comprises generating a plurality of candidate paths based on the star-ground fusion network model, and using a path with the lowest data transmission energy consumption in the candidate paths as the communication link for responding to the task request; the proactive routing strategy comprises generating a plurality of candidate paths based on the star-ground fusion network model, and using a path with the optimal comprehensive evaluation result of link stability in the candidate paths as the communication link for responding to the task request.

[0007] Optionally, the generating the routing strategy according to the star-ground fusion network model comprises: generating a plurality of candidate paths based on the star-ground fusion network model, and determining an energy consumption receiving degree of each node in the candidate paths: wherein, represents the energy consumption receiving degree of a node , represents the residual energy of a node , represents the initial energy of a node ; determining the sending energy consumption of the sending node data of each node in the candidate paths: wherein, represents the sending energy consumption of the sending node data between a node and a node , represents an energy consumption coefficient, represents the amount of data to be transmitted, represents a time coefficient, the time coefficient representing the activity of the node in the current time window; determining a path selection weight of each candidate path based on the energy consumption receiving degree and the sending energy consumption: wherein, represents the path selection weight; determining the path with the lowest data transmission energy consumption in the candidate paths based on the path selection weight, and taking the path with the lowest data transmission energy consumption as the communication link of the communication response, and generating a reactive routing strategy based on the communication link.

[0008] Optionally, the generating the routing strategy according to the star-ground fusion network model comprises: generating a plurality of candidate paths based on the star-ground fusion network model, and evaluating the current link quality of each candidate path to obtain a current link quality evaluation result: wherein, represents the current link quality evaluation result, represents a historical data weight, represents a historical link quality evaluation result, represents a current link quality comprehensive score, the current link quality comprehensive score being obtained by weighting based on the data packet receiving ratio, the smoothed data packet receiving rate, the stability factor and the signal-to-noise ratio of the candidate path; The transmission anti-interference capability of each node in the candidate path is evaluated to obtain the anti-interference security level: in, This indicates the level of security against interference in data transmission between nodes. This indicates the maximum level of interference that nodes can withstand. This indicates the degree of interference between nodes; Prediction factors are determined based on the rate of change in link quality for each candidate link: in, Indicates predictor factor, Indicates the rate of change in link quality. This indicates the fastest rate at which historical link quality changes. Indicates time The link quality assessment results Indicates time The link quality assessment results Indicates the time interval for calculating the rate of change; Based on the current link quality assessment results, anti-interference security level, and prediction factors of each candidate path, a comprehensive link stability assessment is performed on each candidate path to obtain the comprehensive link stability assessment result: in, This indicates the comprehensive evaluation result of link stability. , and Indicates the weighting factor; Based on the comprehensive evaluation results of the link stability, the path with the best comprehensive evaluation results among the candidate paths is selected as the communication link for the communication response, and an active routing strategy is generated based on the communication link.

[0009] Optionally, before inputting the network topology information, the node characteristics of each node in the communication link, and the link characteristics of the communication link into the target fault self-healing analysis model for fault self-healing analysis, the method further includes: Configure reinforcement learning parameters, which include state information, actions, and rewards. The state information includes the node's current neighbor node information, the comprehensive evaluation result of link stability, historical fault flags, and remaining energy. The actions include generating a fault self-healing link based on the state information. The rewards include providing positive or negative feedback based on the communication response results of the fault self-healing path. A value function is constructed based on the reinforcement learning parameters, the value function comprising: in, Indicates the learning rate. Indicates the discount factor. Indicates the state Take action below Instant rewards Indicates the state Take action below The optimal value Indicates the state Take action below The corresponding current value, Indicates the state Take action below The value of updating; Based on the aforementioned value function, an original fault self-healing analysis model is constructed. A loss function is constructed based on a time-series difference strategy, and the original fault self-healing analysis model is trained based on the loss function to obtain a target fault self-healing analysis model. The loss function includes: in, This represents the loss function, which iteratively updates the current network parameters through backpropagation and gradient descent. , This represents the current policy network during the training of the original fault self-healing analysis model. This represents the current network parameters of the current policy network. Represents the target policy network. This represents the target network parameters of the target policy network.

[0010] Optionally, constructing the value function based on the reinforcement learning parameters includes: A graph structure is generated based on network topology information, and the graph structure includes multiple nodes and edges connecting the nodes. The graph structure is configured with initial features based on the reinforcement learning parameters. The initial features include initial node features and initial edge features. The initial node features include the remaining energy and historical fault flags of the nodes. The edge features include the comprehensive evaluation results of link stability and link time delay information. An initial graph neural network is generated based on the initial features and the graph structure; The target graph neural network is obtained by updating the features of each node and edge in the initial graph neural network based on the message passing mechanism. in, Represents a node No. Layer node characteristics, Represents a node With nodes No. Layer edge features, Represents a node The set of neighboring nodes, Indicates the first Layer node weight matrix, This represents the activation function. Represents a node No. Layer node characteristics, Representing neighboring nodes No. Layer node characteristics, Represents a node With nodes In the Layer edge features, Indicates the first Layer edge weight matrix; The reinforcement learning parameters are transformed into embedding vectors by the target graph neural network to obtain reinforcement learning embedding vectors, and a value function is constructed based on the reinforcement learning embedding vectors.

[0011] Optionally, the process of monitoring the communication response of the communication link includes: Monitor the response status of neighboring nodes after each node in the communication link sends a communication request to the neighboring node during the communication response process; The comprehensive evaluation results of the link stability of the communication link during the monitoring communication response process; During the monitoring of the communication response process, the energy alarm information of each node in the communication link includes the remaining energy of the node being lower than a preset energy threshold.

[0012] Furthermore, to achieve the above objectives, this invention also proposes a satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing device, wherein the satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing device includes: The satellite-ground fusion model construction module is used to construct a satellite-ground fusion network model based on the global routing information of the target area. The global routing information includes the network topology information of the target area. The satellite-ground fusion network model consists of multiple nodes within the target area and the communication topology between the nodes. The nodes include ad hoc network nodes and gateway nodes. The gateway node is connected to multiple ad hoc network nodes, and the ad hoc network node is connected to at least one ad hoc network node. The routing policy generation module is used to generate routing policies based on the satellite-ground converged network model. The routing policies include reactive routing policies and proactive routing policies. A routing response module is used to generate a target routing policy based on the task priority of the task request and the routing policy when a task request is received. The target routing policy includes determining the communication link for the communication response. The communication response module is used to call each node of the communication link to respond to the task request based on the target routing strategy, and to monitor the communication response process of the communication link. The fault self-healing module is used to input the network topology information, the node characteristics of each node in the communication link, and the link characteristics of the communication link into the target fault self-healing analysis model to perform fault self-healing analysis, generate a fault self-healing link, and call each node in the fault self-healing link to respond to the task request, so as to realize communication fault self-healing during the communication process.

[0013] In addition, to achieve the above objectives, this application also proposes a satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method as described above.

[0014] In addition, to achieve the above objectives, this application also proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method described above.

[0015] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method described above.

[0016] This invention constructs a satellite-ground integrated network model based on global routing information of a target area. The global routing information includes network topology information of the target area. The satellite-ground integrated network model consists of multiple nodes within the target area and the communication topology between these nodes. The nodes include ad hoc network nodes and gateway nodes. Each gateway node connects to multiple ad hoc network nodes, and each ad hoc network node connects to at least one ad hoc network node. A routing strategy is generated based on the satellite-ground integrated network model. The routing strategy includes reactive and proactive routing strategies. Upon receiving a task request, a target routing strategy is generated based on the task priority of the task request and the routing strategy. The target routing strategy includes determining the communication link for the communication response. Based on the target routing strategy, each node on the communication link is invoked to respond to the task request, and the communication response process of the communication link is monitored. When a fault is detected in the communication link, the network topology information, the node characteristics of each node in the communication link, and the communication link itself are used to... The link characteristics are input into the target fault self-healing analysis model for fault self-healing analysis, generating fault self-healing links, and calling each node in the fault self-healing links to respond to the task request, thereby realizing communication fault self-healing during the communication response process. Since this invention constructs a satellite-ground integrated network model of the target area, and generates reactive and proactive routing strategies based on the satellite-ground integrated network model, it selects appropriate routing strategies for different task scenarios, realizes multi-objective optimization in the communication response process, significantly reduces end-to-end latency of sudden tasks while ensuring relatively low overall network energy consumption, and improves the network's adaptability to multiple types of services. By monitoring the communication response process, and performing fault self-healing analysis through the target fault self-healing analysis model when there is a fault in the communication link, and calling each node in the fault self-healing link to respond to the task request, it realizes rapid detection and self-healing decision-making for communication faults, and can promptly select backup paths and perform seamless switching when there is a link or node failure, improving the fault self-healing speed and processing efficiency of autonomous network communication in unmanned areas. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the structure of the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing device in the hardware operating environment involved in the embodiments of the present invention; Figure 2This is a flowchart illustrating the first embodiment of the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing method of the present invention; Figure 3 This is a schematic diagram of the topology of a satellite-ground integrated network model in one embodiment of the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing method of the present invention. Figure 4 This is a flowchart illustrating the comprehensive evaluation of link stability in one embodiment of the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing method of the present invention. Figure 5 This is a flowchart illustrating the second embodiment of the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing method of the present invention; Figure 6 This is a structural block diagram of the first embodiment of the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing device of the present invention.

[0019] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0021] Reference Figure 1 , Figure 1 This is a schematic diagram of the routing protocol and fault self-healing device structure of the satellite-ground integrated hybrid self-organizing network in the hardware operating environment involved in the embodiments of the present invention.

[0022] like Figure 1 As shown, the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0023] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the satellite-ground converged hybrid ad hoc network routing protocol and fault-healing device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0024] like Figure 1 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing program.

[0025] exist Figure 1 In the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing device of the present invention can be set in the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing device. The satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing device calls the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing program stored in the memory 1005 through the processor 1001, and executes the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing method provided in the embodiment of the present invention.

[0026] This invention provides a satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing method of the present invention.

[0027] In this embodiment, the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing method includes the following steps: Step S10: Construct a satellite-ground fusion network model based on the global routing information of the target area.

[0028] It should be noted that this embodiment addresses the problems of high energy consumption, long latency, link instability, and insufficient fault self-healing capabilities in traditional ad hoc networks in unmanned area communication scenarios, leading to short network endurance, unstable communication quality, and network paralysis caused by node failures in unmanned area information monitoring. It proposes a space-ground integrated hybrid ad hoc network high-reliability routing protocol and fault self-healing method. This scheme flexibly combines reactive and proactive routing to provide low-energy transmission methods for routine tasks and quickly switches to low-latency paths when sudden or high-priority tasks occur. Simultaneously, it incorporates multi-dimensional link stability assessment and prediction to identify and avoid potentially unstable links in real time, significantly improving communication reliability and efficiency.

[0029] The uninhabited area communication scenarios applied in this embodiment can include border uninhabited area security management, online monitoring of communication blind spots, field exploration and resource extraction, post-disaster emergency response and rescue, environmental monitoring and protection, smart agriculture and precision agriculture monitoring, and drone inspection and monitoring, etc.

[0030] It should be understood that the executing entity of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a terminal electronic device capable of performing the above functions. The following uses a satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing terminal device (hereinafter referred to as the terminal device) as an example to illustrate this embodiment and the following embodiments.

[0031] It should be noted that the global routing information includes the network topology information of the target area. The satellite-ground fusion network model consists of multiple nodes within the target area and the communication topology between the nodes. The nodes include ad hoc network nodes and gateway nodes. The gateway node is connected to multiple ad hoc network nodes, and the ad hoc network node is connected to at least one ad hoc network node.

[0032] It should be noted that the target area can be an uninhabited area, such as a desert or a primeval forest. Ad hoc network nodes can be sensor data acquisition nodes, whose main function is to aggregate data from surrounding sensors. Gateway nodes are central nodes deployed with wide area network terminals; their main function is to aggregate data from ad hoc network nodes over a large area and transmit the data back to the monitoring center via the public internet or low-Earth orbit satellite internet.

[0033] Understandably, since uninhabited areas require extensive communication coverage, this embodiment constructs a satellite-ground fusion network model based on the global routing information of the target area, referring to... Figure 3 , Figure 3 This is a schematic diagram of the topology of a satellite-ground integrated network model in one embodiment. The satellite-ground integrated network model may include three layers: the first layer is where self-organizing network nodes collect sensor data from the surrounding local area; the second layer is where self-organizing network nodes transmit the collected sensor data through multi-hop transmission to a gateway node equipped with a wide area network terminal, with one self-organizing network node placed at intervals of one unit distance, and the maximum transmission distance of the self-organizing network nodes is two unit distances; the third layer is where the gateway node performs preliminary preprocessing on the collected data and then transmits it back to the monitoring center.

[0034] In some embodiments, terminal devices can adopt a three-layer satellite-ground converged architecture (sensor layer, self-organizing network layer, and gateway center layer) to construct a satellite-ground converged network model. This can reduce the use of satellite links in local multi-hop transmission and achieve full coverage by relying on satellites at critical moments. It can achieve coverage of communication blind spots in uninhabited areas and rely on satellite connections when terrestrial networks are blocked or nodes are too sparse, further ensuring seamless data backhaul.

[0035] Step S20: Generate a routing strategy based on the satellite-ground fusion network model.

[0036] It should be noted that the routing strategies include reactive routing strategies and proactive routing strategies.

[0037] Reactive routing strategies can be applied to daily or routine tasks, achieving the lowest power consumption for self-organizing networks while meeting data transmission requirements.

[0038] Proactive routing strategies are suitable for bursty tasks, high-priority tasks, or urgent tasks that require prioritizing the reduction of transmission latency and ensuring link stability.

[0039] In some embodiments, the gateway nodes in the network are connected to a sustainable power supply without considering energy consumption. Each ad hoc network link can have a gateway device at both ends for data backhaul. Therefore, each ad hoc network node not located at either end of the chain network has at least four links to choose from. Thus, the terminal device can generate a reactive routing strategy based on the energy consumption of node data transmission and energy consumption acceptance, selecting the path with the lowest energy consumption for communication responses when handling daily tasks.

[0040] In some embodiments, when faced with urgent or high-priority tasks, the terminal device generates an active routing strategy based on link stability scores, estimated latency, and the remaining energy of nodes, thereby ensuring link stability during the communication response process and reducing transmission latency.

[0041] Furthermore, in order to effectively reduce the communication energy consumption during the response process of the reaction routing strategy, step S20 above may include: Step S201: Generate multiple candidate paths based on the satellite-ground fusion network model, and determine the energy reception of each node in the candidate paths; Step S202: Determine the transmission energy consumption of the transmitting node data of each node in the candidate path; Step S203: Determine the path selection weight of each candidate path based on the energy consumption reception rate and the transmission energy consumption; Step S204: Based on the path selection weight, determine the path with the lowest data transmission energy consumption among the candidate paths, and use the path with the lowest data transmission energy consumption as the communication link for the communication response, and generate a reactive routing strategy based on the communication link.

[0042] In some embodiments, the terminal device first performs network initialization, and the node's local node ID, energy, location and other information are transmitted back to the gateway in a hop-by-hop manner.

[0043] The specific process is as follows: The gateway sends access data packets to its neighboring nodes on both sides. These packets contain information such as the node's ID, energy status, and timestamp. Upon receiving the data, each node sends an acknowledgment and stores the information in its routing table. The next-hop neighboring node follows the same process to forward the data packets until all nodes have received the information. If there is a significant difference between the node's local information and the data in the data packet, the data is stored in the routing table; otherwise, it is discarded. Through this process, all nodes maintain information about their neighboring nodes within their maximum one-hop communication range, establishing a reverse path to the gateway.

[0044] Secondly, energy assessment is performed. Nodes select based on the energy status of each node in the routing table, trying to avoid low-energy nodes and choosing high-energy nodes for forwarding.

[0045] node i Send data to the node j Energy acceptability is defined as: in, Represents a node The energy consumption reception level indicates its suitability as a data receiving node; Represents a node The remaining energy reflects the node's current available resources in real time; Represents a node The initial energy is used for normalization calculations.

[0046] The energy consumption for transmitting data at this node is: in, Represents a node With nodes Energy consumption for transmitting data between nodes; The energy consumption coefficient is related to hardware characteristics (such as transmit power and antenna efficiency) and environmental factors (such as channel attenuation). In some embodiments, the terminal device can determine the energy consumption coefficient based on the hardware characteristics of the node and environmental factors. This indicates the amount of data to be transmitted, expressed in bits or data packets. The time coefficient represents the activity level of a node within the current time window, reflecting the node's activity level. i Activity level or channel occupancy time within the current time window.

[0047] Path selection weight is defined as: in, This represents the path selection weight; the larger the path selection weight, the easier it is to select that path.

[0048] Finally, the node's energy status will be updated. The reactive routing protocol stipulates that if a node's energy is below a threshold (e.g., 5% of the battery), the node will send an alarm message to its neighboring nodes. Upon receiving the alarm message, the neighboring nodes will promptly update the information in their routing tables.

[0049] Furthermore, in order to ensure communication stability and transmission timeliness during communication responses to urgent or high-priority tasks, step S20 may include: Step S211: Generate multiple candidate paths based on the satellite-ground fusion network model, evaluate the current link quality of each candidate path, and obtain the current link quality evaluation result; Step S212: Evaluate the transmission anti-interference capability of each node in the candidate path to obtain the anti-interference security level; Step S213: Determine the prediction factor based on the link quality change rate of each candidate link; Step S214: Based on the current link quality assessment results, anti-interference security level, and prediction factors of each candidate path, perform a comprehensive link stability assessment on each candidate path to obtain a comprehensive link stability assessment result; Step S215: Based on the comprehensive evaluation result of the link stability, the path with the best comprehensive evaluation result of the link stability among the candidate paths is taken as the communication link for the communication response, and an active routing strategy is generated based on the communication link.

[0050] It should be noted that when faced with sudden, urgent, or high-priority tasks, terminal devices can adopt proactive routing strategies for communication response, prioritizing the reduction of transmission latency and ensuring link stability.

[0051] In some embodiments, the terminal device first updates the global routing information. Network initialization in step 1 enables network topology awareness. In proactive routing, routing update messages are broadcast or propagated through multiple hops within the network at fixed time intervals or when significant network topology changes occur, allowing each node to monitor network topology changes in real time and promptly correct its global routing table.

[0052] Secondly, priority paths are calculated. Remaining node energy, link stability score, and estimated latency are incorporated into a weighted calculation to construct a cost function. Based on this cost function, Dijkstra's algorithm is used to calculate reachable paths across the entire network and mark them in the routing table. When a sudden task is detected, the system automatically finds and activates the corresponding "optimal path" entry, eliminating the need for an additional path discovery process like reactive routing, thus significantly reducing end-to-end latency.

[0053] Finally, a parallel design combining latency sensitivity and energy balance is adopted. When the burst workload is small, the remaining energy of nodes is considered while calculating the optimal path to avoid high-priority data occupying some low-energy nodes for a long time. When the burst workload is large, the weight of energy consideration is reduced, and the focus is on link stability and latency to ensure fast data return.

[0054] In some embodiments, refer to Figure 4 , Figure 4 This is a flowchart illustrating a comprehensive link stability assessment in one embodiment. The terminal device can perform a multi-dimensional time assessment of link stability by combining past, present, and future information, using the following steps: Step 1: Multi-dimensional link quality assessment: A link quality estimator based on fuzzy logic constructs a comprehensive link stability score. This index is used to predict link status and determine whether the link may be disconnected or unstable, providing a basis for subsequent route selection decisions.

[0055] First, a fuzzy logic-based link quality estimator is used to evaluate link quality. This includes four metrics: Packet Receiver Ratio (PRR), Smooth Packet Receiver Ratio (SPRR), Stability Factor (SF), and Signal-to-Noise Ratio (SNR). The specific formulas are as follows: The Packet Receive Ratio (PRR) is calculated using the following formula: The Smooth Packet Receive Rate (SPRR) is calculated using the following formula: in, Historical weighting factor The larger the value, the more significant the influence of historical data.

[0056] Stability Factor (SF): Reflects the degree of link fluctuation and is calculated as the reciprocal of the standard deviation of PRR. The signal-to-noise ratio is directly taken from the physical layer measurement and normalized to the range of 0 to 100.

[0057] The current link quality assessment formula is: in, This indicates the current link quality assessment result. Indicates the weight of historical data. This indicates the historical link quality assessment results. This represents the current link quality comprehensive score, which is obtained by weighting the candidate path's packet reception ratio, smooth packet reception rate, stability factor, and signal-to-noise ratio.

[0058] Secondly, the environment in uninhabited areas is complex and ever-changing, with long distances between nodes and constantly shifting interference in the channel. Therefore, we define the concept of security to assess the current transmission capability of a node. This assessment can be based on evaluating the anti-interference security of data transmission between nodes, as shown in the following formula: in, This indicates the level of security against interference in data transmission between nodes. This indicates the maximum level of interference that nodes can withstand. This indicates the level of interference between nodes. Interference resistance level indicates that connections between nodes will become more difficult; a higher level of resistance means that it will take longer for links between nodes to break down.

[0059] Step 2: Predicting Link Quality Changes The communication environment between nodes is constantly changing, but this change is often a continuous process. Therefore, the trend of change in the next time period can be predicted by calculating the instantaneous change trend of link quality. The formulas for calculating the instantaneous rate of change in link quality between nodes and the predictor factor are as follows: in, Indicates predictor factor, Indicates the rate of change in link quality. This indicates the fastest rate at which historical link quality changes. Indicates time The link quality assessment results Indicates time The link quality assessment results This indicates the time interval for calculating the rate of change.

[0060] The system dynamically adjusts routing based on this stability score, avoiding the use of unstable links and prioritizing reliable links to ensure efficient data transmission.

[0061] Step 3: Comprehensive link stability calculation. Link stability can be viewed as a comprehensive assessment of the link's past, present, and future quality. Refer to the following formula: in, This indicates the comprehensive evaluation result of link stability. , and This represents the weighting factor. Ultimately, stability depends on the minimum value of the link set; the larger the minimum value, the more stable the link.

[0062] Step S30: Upon receiving a task request, generate a target routing policy based on the task priority of the task request and the routing policy.

[0063] It should be noted that the target routing strategy includes determining the communication link for the communication response.

[0064] In some embodiments, the target routing strategy can be a hybrid routing strategy combining proactive and reactive routing strategies. The terminal device can dynamically select an appropriate routing strategy based on the type of task (routine task or emergency task). Reactive routing is used to reduce communication energy consumption for routine tasks, while proactive routing is used to handle emergency tasks, ensuring minimum latency and link stability. Therefore, after completing an emergency task, the proactive routing strategy can be switched to a reactive routing strategy to reduce communication energy consumption, thereby achieving multi-objective optimization.

[0065] In some embodiments, terminal devices can use an energy threshold mechanism to reduce the occupancy of low-power nodes by high-priority services in a timely manner; when a node comes back online, a small-scale testing and observation period management strategy is adopted to gradually increase its traffic sharing ratio. This can effectively extend the overall network lifespan and quickly integrate the node into the available topology after recovery, making full use of network resources.

[0066] Furthermore, in order to achieve multi-objective optimization in the communication response process and to realize adaptive routing response in dynamic communication scenarios, step S30 above may include: Step S301: Upon receiving a task request, obtain the task status and task priority of the task request; Step S302: If the task status of the task request is a normal state or the task priority of the task request is lower than the priority threshold, the reactive routing policy is used as the target routing policy. Step S303: If the task status of the task request is an emergency state or the task priority of the task request is not lower than the priority threshold, the proactive routing strategy is used as the target routing strategy, and the task request is monitored to see if it recovers from an emergency state to a normal state. Step S304: When it is detected that the task request has returned from an emergency state to a normal state, the reactive routing policy is used as the target routing policy; It should be noted that the reactive routing strategy includes generating multiple candidate paths based on the satellite-ground fusion network model, and using the path with the lowest data transmission energy consumption among the candidate paths as the communication link for communication response; the proactive routing strategy includes generating multiple candidate paths based on the satellite-ground fusion network model, and using the path with the best comprehensive link stability evaluation result among the candidate paths as the communication link for communication response.

[0067] In practical implementation, terminal devices can dynamically select appropriate routing strategies based on the type of task (routine tasks and sudden tasks). Reactive routing is used to reduce communication power consumption for routine tasks, while proactive routing is used to handle sudden tasks, ensuring minimum latency and link stability.

[0068] In some embodiments, the system first identifies and classifies tasks. Based on metadata such as business priority and data urgency, the system categorizes the data streams to be sent into corresponding types, thus identifying and labeling the task types.

[0069] Secondly, reactive and proactive routing are maintained. For routine tasks, routing requests are initiated only when data needs to be sent, completing path discovery and establishment, reducing the overhead of periodic topology updates across the entire network, thereby reducing node energy consumption. For high-priority or bursty tasks, global routing information is broadcast at fixed time intervals or through triggered broadcasts (or multi-hop transmissions), enabling each node to have a more comprehensive understanding of the network topology and quickly look up the optimal or suboptimal path when bursty tasks occur, reducing end-to-end latency.

[0070] It should be noted that this embodiment can adopt a hybrid routing response strategy, namely, a mechanism for switching between proactive and reactive routing. This includes: upon detecting a high-priority task or a sudden request, the system immediately activates the optimal path maintained by proactive routing to avoid the additional latency caused by re-flooding the path search in reactive routing; when the task ends or the network returns to its normal state, the system can revert to reactive routing as the primary mode, reducing the energy and bandwidth overhead of global updates. If the network topology changes are minor, the links are stable, and the volume of regular data is large, reactive routing can take the lead; if frequent link failures, rapid node energy decay, or multiple emergency data flows are detected, the system will temporarily increase the frequency of proactive route updates or switch to proactive priority to ensure timeliness and reliability. A threshold is set in the hybrid strategy; when the remaining energy of a local node or a critical forwarding node falls below a certain level, its usage in high-priority tasks is automatically reduced, and other nodes with more energy are prioritized for forwarding, extending the overall network lifespan.

[0071] Step S40: Based on the target routing policy, call each node of the communication link to respond to the task request, and monitor the communication response process of the communication link.

[0072] In practice, the terminal device generates one or more communication links based on the target routing strategy, calls each node in the communication link to respond to the task request, and monitors for faults in the communication response process.

[0073] For example, the target routing strategy is a hybrid routing strategy. Within the first task execution time window, if the task request is determined to be a routine task, a first communication link is generated based on a reactive routing strategy to reduce communication energy consumption, and each node of the first communication link is invoked to respond to the task request. Within the second task execution time window, if the task request is determined to be an urgent task, a second communication link is generated based on a proactive routing strategy to ensure link stability and transmission timeliness, and each node of the second communication link is invoked to respond to the task request. Within the third task execution time window, if the urgent task ends and the task is changed to a routine task, a third communication link is generated based on a reactive routing strategy to reduce communication energy consumption, and each node of the third communication link is invoked to respond to the task request.

[0074] Furthermore, in order to accurately detect faults and promptly perform fault self-healing when there is a risk of fault in the communication link, thereby improving the fault self-healing response capability, the above step S40 may include: Step S401: Monitor the response status of neighboring nodes after each node in the communication link sends a communication request to the neighboring node during the communication response process; Step S402: Monitor the comprehensive evaluation results of the link stability of the communication link during the communication response process; Step S403: Monitor the energy alarm information of each node in the communication link during the communication response process. The energy alarm information includes the remaining energy of the node being lower than a preset energy threshold.

[0075] In some embodiments, link failure detection involves a node sending a communication request to the communication link. If there is no response after three consecutive attempts, it indicates a link failure. The link stability comprehensive assessment result is then used to determine the link failure mechanism. If the energy level is below a threshold or an energy alarm message is received from a neighboring node, the terminal device determines that there is a potential fault in the link. Once the link is detected as faulty, a fault self-healing analysis is performed using the target fault self-healing analysis model to generate a fault self-healing link and quickly switch the communication link.

[0076] Step S50: When a fault is detected in the communication link, the network topology information, the node characteristics of each node in the communication link, and the link characteristics of the communication link are input into the target fault self-healing analysis model to perform fault self-healing analysis, generate a fault self-healing link, and call each node in the fault self-healing link to respond to the task request in order to realize communication fault self-healing during the communication process.

[0077] In some embodiments, the interruption device can input information such as network topology, node energy, and link status into a graph neural network for high-dimensional embedding, and combine it with reinforcement learning to achieve adaptive decision-making for fault switching strategies. This allows for rapid switching to the optimal alternative path when a node or link fails. In complex, large-scale networks with frequently changing environmental conditions, this significantly shortens route reconstruction time, enhances network fault tolerance and recovery capabilities, and enables self-healing within a short timeframe.

[0078] This embodiment constructs a satellite-ground integrated network model based on global routing information of the target area. The global routing information includes network topology information of the target area. The satellite-ground integrated network model consists of multiple nodes within the target area and the communication topology between these nodes. The nodes include ad hoc network nodes and gateway nodes. Each gateway node connects to multiple ad hoc network nodes, and each ad hoc network node connects to at least one ad hoc network node. A routing strategy is generated based on the satellite-ground integrated network model. The routing strategy includes reactive and proactive routing strategies. Upon receiving a task request, a target routing strategy is generated based on the task priority of the task request and the routing strategy. The target routing strategy includes determining the communication link for the communication response. Based on the target routing strategy, each node on the communication link is invoked to respond to the task request, and the communication response process of the communication link is monitored. When a fault is detected in the communication link, the network topology information, the node characteristics of each node in the communication link, and the communication link itself are used to... The link characteristics are input into the target fault self-healing analysis model for fault self-healing analysis, generating fault self-healing links, and calling each node in the fault self-healing links to respond to the task request, thereby realizing communication fault self-healing during the communication response process. Since this embodiment constructs a satellite-ground integrated network model of the target area, and generates reactive routing strategies and proactive routing strategies based on the satellite-ground integrated network model, it selects appropriate routing strategies for different task scenarios, realizes multi-objective optimization in the communication response process, significantly reduces end-to-end latency of sudden tasks while ensuring relatively low overall network energy consumption, and improves the network's adaptability to multiple types of services. By monitoring the communication response process, and performing fault self-healing analysis through the target fault self-healing analysis model when there is a fault in the communication link, and calling each node in the fault self-healing links to respond to the task request, it realizes rapid detection and self-healing decision-making for communication faults, and can promptly select backup paths and perform seamless switching when there is a link or node failure, thereby improving the fault self-healing speed and processing efficiency of autonomous network communication in unmanned areas.

[0079] refer to Figure 5 , Figure 5 This is a flowchart illustrating the second embodiment of the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing method of the present invention.

[0080] Based on the first embodiment described above, in this embodiment, before step S50, the method further includes: Step S501: Configure reinforcement learning parameters.

[0081] It should be noted that the reinforcement learning parameters include state information, actions, and rewards. The state information includes the node's current neighbor node information, the comprehensive evaluation result of link stability, historical fault flags, and remaining energy. The actions include generating a fault self-healing link based on the state information. The rewards include providing positive or negative feedback based on the communication response results of the fault self-healing path.

[0082] In some embodiments, the state may include information about the node's current neighbor nodes, link stability assessment, historical fault information, and the node's remaining capacity. Actions may be link decisions that the node can choose, with alternative paths updated in real time in the path database; rewards include positive feedback for successful communication after path switching and meeting requirements, and negative feedback for severe packet loss, faults, or timeouts.

[0083] Step S502: Construct a value function based on the reinforcement learning parameters.

[0084] It should be noted that the actions mainly implement short-term path switching. The action set may include: switching between the next-hop links available at the current node; selecting an alternative route from the backup path library; traffic redistribution or load adjustment; and maintaining the existing path (a retention action under fault-free or good performance conditions).

[0085] The reward refers to the value determined by detecting the link communication quality after performing path switching or fault repair actions. A positive reward is given if communication is normal and meets predetermined requirements after path switching; a negative reward is given for severe packet loss, worsening of the fault, or timeout. The reward mechanism can be represented as follows: in, and All parameters are adjustable, used to balance the need for timely recovery and stable operation.

[0086] It should be noted that this embodiment can achieve fault-healing path selection through reinforcement learning. For short-term path switching caused by node failures or link problems, a path selection strategy based on value function reinforcement learning is adopted. In the state Next action The overall return that can be obtained (e.g., switching to a candidate link or alternative path). The value function includes: in, Indicates the learning rate. Indicates the discount factor. Indicates the state Take action below Instant rewards Indicates the state Take action below The optimal value Indicates the state Take action below The corresponding current value, Indicates the state Take action below The value of updating.

[0087] Furthermore, in order to accurately encode the multidimensional state characteristics in the satellite-ground integrated self-organizing network, thereby efficiently constructing the value function and improving fault self-healing performance, step S502 above may include: Step S5021: Generate a graph structure based on network topology information; Step S5022: Configure initial features for the graph structure according to the reinforcement learning parameters; Step S5023: Generate an initial graph neural network based on the initial features and the graph structure; Step S5024: Update the features of each node and each edge in the initial graph neural network based on the message passing mechanism to obtain the target graph neural network; Step S5025: The reinforcement learning parameters are transformed into embedding vectors through the target graph neural network to obtain reinforcement learning embedding vectors, and a value function is constructed based on the reinforcement learning embedding vectors.

[0088] It should be noted that the graph structure includes multiple nodes and edges connecting the nodes. The initialization includes initial node features and initial edge features. The initial node features include the node's remaining energy and historical fault flags, and the edge features include the comprehensive link stability assessment results and link time delay information.

[0089] It should be noted that, since the state dimension in the ad hoc network may be large (with a large number of nodes and rich link features), this embodiment uses a graph neural network (GNN) to embed and encode the multidimensional state features in the satellite-ground integrated ad hoc network.

[0090] For time network topology The initial characteristics of a node, specifically including its remaining energy and fault indicators, can be represented as follows: The equilateral characteristics of link quality and time delay in a network can be denoted as: Through a series of message passing and update operations in the GNN layers, a high-dimensional vector of the nodes and the global vector can be obtained.

[0091] The output of the GNN is used as the state representation in reinforcement learning. Approximated by a trainable model The value, the formula is: in, This includes the parameters of the GNN itself, as well as the parameters of any additional decision layers (such as small MLPs). In graph neural networks, features of each node and edge are updated through a message-passing mechanism. in, Represents a node No. Layer node characteristics, Represents a node With nodes No. Layer edge features, Represents a node The set of neighboring nodes, Indicates the first Layer node weight matrix, This represents the activation function. Represents a node No. Layer node characteristics, Representing neighboring nodes No. Layer node characteristics, Represents a node With nodes In the Layer edge features, Indicates the first The edge weight matrix of the layer.

[0092] Step S503: Construct the original fault self-healing analysis model based on the value function.

[0093] It should be noted that the specific process of fault self-healing is as follows: fault detection – if a node energy alarm, link failure, or severe packet loss is detected, the reinforcement learning decision for fault self-healing is triggered; state acquisition – the current network graph structure is encoded to obtain a state vector. Action selection, based on The estimated value is used to select the optimal action (e.g., switching to an alternative path); a reward / penalty feedback system is implemented, providing positive / negative rewards based on the switching result, and then updating the algorithm. The value (i.e.) Value); continuous iteration: through multiple failure scenarios and path switching processes, the value function is continuously iterated. The value enables the system to converge to a better short-term switching strategy.

[0094] Step S504: Construct a loss function based on the time-series difference strategy, and train the original fault self-healing analysis model based on the loss function to obtain the target fault self-healing analysis model.

[0095] It should be noted that whenever an action is performed... And receive instant rewards and the next state Then, according to the temporal difference (TD) update principle, the following loss function is minimized, wherein the loss function includes: in, This represents the loss function, which iteratively updates the current network parameters through backpropagation and gradient descent. , This represents the current policy network during the training of the original fault self-healing analysis model. This represents the current network parameters of the current policy network. Represents the target policy network. The target network parameters, representing the target policy network, can be iteratively updated through backpropagation and gradient descent. This allows GNNs to gradually learn to select the optimal short-term switching action under different fault scenarios.

[0096] In some embodiments, the reinforcement learning path switching process is roughly as follows: fault information or low-energy alarms are written into the corresponding node / edge features for graph updating; the embedding vector of the current graph structure is extracted. And calculate the values ​​in each set of optional actions. The highest value is used for GNN forward inference; the highest value is selected. The value is executed; corresponding positive and negative rewards are given based on the data transmission results, and then updated. The network parameters are set and iterated continuously.

[0097] In some embodiments, link failure detection involves a node sending a communication request to the communication link. If there is no response after three consecutive attempts, it indicates a link failure. The link stability comprehensive assessment result is then used to determine the link failure mechanism. If the energy level is below a threshold or an energy alarm message is received from a neighboring node, the terminal device determines that there is a potential link failure. Once the link is detected as faulty, the corresponding action is considered unavailable in the reinforcement learning decision-making process and assigned a very low priority. Value. Simultaneously, the optimal next action is selected from the backup link, using the following formula: Flow table and group table updates: In the flow tables pre-installed on the gateway or local node, the primary path is updated to... The corresponding forwarding rules enable "one-click local switching," reducing the time spent on rerouting or flooding.

[0098] This embodiment also includes: fault switching feedback and experience playback. If data is successfully transmitted after the switch, the system provides a positive reward for updating. If packet loss persists, a negative reward is applied for reinforcement learning to guide subsequent iterations in selecting a better connection. The fault and switching process (state-action-reward-new state) is saved to the experience replay pool for batch sampling in the next round of training, improving the algorithm's continuous adaptability to fault scenarios.

[0099] This embodiment also proposes a backup path selection mechanism to address link communication failures caused by link interruptions between nodes or even damage to network nodes.

[0100] For each link, generate a corresponding backup path and then use the current link. Remove the topology network and use the shortest path algorithm to calculate the bypass. Select an alternative path The total cost of backup communication links shall not exceed twice that of the initial optimal path, that is: This embodiment also includes: loop prevention verification, which checks whether the backup path forms a loop. If a loop exists, the backup path is removed; if no loop exists, the backup path is retained, and the backup path library is updated.

[0101] This embodiment also includes the maintenance of a backup path table, which is sorted by cost and reinforcement learning score, and the backup path table is updated periodically.

[0102] This embodiment also includes: node failure determination, such as three consecutive communication failures of a node or link instability. Then the link is determined to be faulty, if the node If all links in the set fail, then the node is considered to be faulty, or the node... A node is considered to have insufficient energy to support any single communication link. Invalid.

[0103] This embodiment also includes: topology reconstruction after node failure. After a node fails, neighboring nodes first perform instantaneous switching according to the paths in the backup path table to ensure seamless communication, while the gateway broadcasts the node's information. Failure message, updating node Values ​​and neural network parameters.

[0104] This embodiment also includes a node self-healing mechanism, which uses an exponential smoothing coefficient when a node recovers from a fault and comes back online. To synthesize the most recent observations: When link stability is continuous If all windows are above the lower bound threshold for link stability, then the reinforcement learning function of the link should be improved. The value is used to revert to the available topological set.

[0105] At the node Preliminary assessment indicates recovery, but it is not yet fully confirmed whether it meets high-load reliability requirements. This invention can be verified using small-scale test traffic. in, For the target total amount of data, Indicates only allocation ×100% of the traffic goes to the node If the packet loss rate, latency, and other link stability metrics of the test traffic consistently meet expectations, the traffic share will be gradually increased. Based on the test verification results, the system can gradually increase the traffic share and adjust it within the Agent's... Update nodes in the value table The value of an action is determined until it is treated exactly the same as a normal node.

[0106] When node Once the network is confirmed to have recovered during the testing phase, it will switch back to the node, either by rerouting the original path or, in some scenarios, by sharing traffic with the node.

[0107] The gateway broadcasts a notification to re-add the mapping rules, ensuring that subsequent data can be successfully distributed to the nodes. To prevent nodes If a secondary failure occurs for unknown reasons, this embodiment can also set an observation period. The link is monitored based on the observation period. During this observation period, the gateway continuously monitors... Monitor the link metrics; if everything is normal, confirm a "full switchback"; if it deteriorates again, reduce its speed again. Value or undo the switchback.

[0108] This embodiment configures reinforcement learning parameters, constructs a value function based on the reinforcement learning parameters, constructs an original fault self-healing analysis model based on the value function, constructs a loss function according to the temporal difference strategy, and trains the original fault self-healing analysis model based on the loss function to obtain a target fault self-healing analysis model. Thus, it achieves fault self-healing in communication fault scenarios through reinforcement learning, realizes dynamic switching of communication links, significantly shortens route reconstruction time, enhances network fault tolerance and recovery capabilities, and achieves self-healing in a short time.

[0109] Furthermore, this embodiment of the invention also proposes a computer-readable storage medium storing a satellite-ground integrated hybrid ad hoc network routing protocol and a fault self-healing program. When the satellite-ground integrated hybrid ad hoc network routing protocol and the fault self-healing program are executed by a processor, they implement the steps of the satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method as described above.

[0110] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0111] The aforementioned computer-readable storage medium may be included in the satellite-ground converged hybrid ad hoc network routing protocol and fault self-healing device; or it may exist independently and not be assembled into the satellite-ground converged hybrid ad hoc network routing protocol and fault self-healing device.

[0112] Furthermore, this invention also proposes a computer program product, including a satellite-ground integrated hybrid ad hoc network routing protocol and a fault self-healing program, wherein when the satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing program are executed by a processor, the satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing program implement the steps of the satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method as described above.

[0113] The specific implementation of the computer program product of the present invention is basically the same as the embodiments of the above-mentioned satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing method, and will not be repeated here.

[0114] Reference Figure 6 , Figure 6This is a structural block diagram of the first embodiment of the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing device of the present invention.

[0115] like Figure 6 As shown, the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing device proposed in this embodiment of the invention include: The satellite-ground fusion model construction module 10 is used to construct a satellite-ground fusion network model based on the global routing information of the target area. The global routing information includes the network topology information of the target area. The satellite-ground fusion network model consists of multiple nodes within the target area and the communication topology between the nodes. The nodes include ad hoc network nodes and gateway nodes. The gateway node is connected to multiple ad hoc network nodes, and the ad hoc network node is connected to at least one ad hoc network node. The routing policy generation module 20 is used to generate routing policies based on the satellite-ground converged network model. The routing policies include reactive routing policies and proactive routing policies. The routing response module 30 is used to generate a target routing policy based on the task priority of the task request and the routing policy when a task request is received. The target routing policy includes determining the communication link for the communication response. The communication response module 40 is used to call each node of the communication link to respond to the task request based on the target routing strategy, and to monitor the communication response process of the communication link; The fault self-healing module 50 is used to input the network topology information, the node characteristics of each node in the communication link, and the link characteristics of the communication link into the target fault self-healing analysis model to perform fault self-healing analysis, generate a fault self-healing link, and call each node in the fault self-healing link to respond to the task request, so as to realize the communication fault self-healing during the communication response process.

[0116] This embodiment constructs a satellite-ground integrated network model based on global routing information of the target area. The global routing information includes network topology information of the target area. The satellite-ground integrated network model consists of multiple nodes within the target area and the communication topology between these nodes. The nodes include ad hoc network nodes and gateway nodes. Each gateway node connects to multiple ad hoc network nodes, and each ad hoc network node connects to at least one ad hoc network node. A routing strategy is generated based on the satellite-ground integrated network model. The routing strategy includes reactive and proactive routing strategies. Upon receiving a task request, a target routing strategy is generated based on the task priority of the task request and the routing strategy. The target routing strategy includes determining the communication link for the communication response. Based on the target routing strategy, each node on the communication link is invoked to respond to the task request, and the communication response process of the communication link is monitored. When a fault is detected in the communication link, the network topology information, the node characteristics of each node in the communication link, and the communication link itself are used to... The link characteristics are input into the target fault self-healing analysis model for fault self-healing analysis, generating fault self-healing links, and calling each node in the fault self-healing links to respond to the task request, thereby realizing communication fault self-healing during the communication response process. Since this embodiment constructs a satellite-ground integrated network model of the target area, and generates reactive routing strategies and proactive routing strategies based on the satellite-ground integrated network model, it selects appropriate routing strategies for different task scenarios, realizes multi-objective optimization in the communication response process, significantly reduces end-to-end latency of sudden tasks while ensuring relatively low overall network energy consumption, and improves the network's adaptability to multiple types of services. By monitoring the communication response process, and performing fault self-healing analysis through the target fault self-healing analysis model when there is a fault in the communication link, and calling each node in the fault self-healing links to respond to the task request, it realizes rapid detection and self-healing decision-making for communication faults, and can promptly select backup paths and perform seamless switching when there is a link or node failure, thereby improving the fault self-healing speed and processing efficiency of autonomous network communication in unmanned areas.

[0117] The satellite-ground converged hybrid ad hoc network routing protocol and fault self-healing device provided in this application, employing the satellite-ground converged hybrid ad hoc network routing protocol and fault self-healing method in the above embodiments, can solve the technical problems of satellite-ground converged hybrid ad hoc network routing protocol and fault self-healing. Compared with the prior art, the beneficial effects of the satellite-ground converged hybrid ad hoc network routing protocol and fault self-healing device provided in this application are the same as the beneficial effects of the satellite-ground converged hybrid ad hoc network routing protocol and fault self-healing method provided in the above embodiments, and other technical features in the satellite-ground converged hybrid ad hoc network routing protocol and fault self-healing device are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0118] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0119] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0120] In addition, for technical details not described in detail in this embodiment, please refer to the satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing method provided in any embodiment of the present invention, which will not be repeated here.

[0121] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0122] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0123] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0124] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method, characterized in that, The method includes: A satellite-ground converged network model is constructed based on the global routing information of the target area. The global routing information includes the network topology information of the target area. The satellite-ground converged network model consists of multiple nodes within the target area and the communication topology between the nodes. The nodes include ad hoc network nodes and gateway nodes. The gateway node is connected to multiple ad hoc network nodes, and the ad hoc network node is connected to at least one ad hoc network node. Routing strategies are generated based on the satellite-ground integrated network model, and the routing strategies include reactive routing strategies and proactive routing strategies. Upon receiving a task request, a target routing policy is generated based on the task priority of the task request and the routing policy. The target routing policy includes determining the communication link for the communication response. Based on the target routing strategy, each node of the communication link is invoked to respond to the task request, and the communication response process of the communication link is monitored. When a fault is detected in the communication link, the network topology information, the node characteristics of each node in the communication link, and the link characteristics of the communication link are input into the target fault self-healing analysis model to perform fault self-healing analysis, generate a fault self-healing link, and call each node in the fault self-healing link to respond to the task request, so as to realize the communication fault self-healing during the communication process.

2. The satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method as described in claim 1, characterized in that, Upon receiving a task request, generating a target routing policy based on the task priority of the task request and the routing policy includes: Upon receiving a task request, obtain the task status and task priority of the task request; If the task status of the task request is a normal state or the task priority of the task request is lower than the priority threshold, the reactive routing policy will be used as the target routing policy. If the task status of the task request is an emergency state or the task priority of the task request is not lower than the priority threshold, the proactive routing strategy is used as the target routing strategy, and the task request is monitored to see if it recovers from an emergency state to a normal state. When the task request is detected to have returned to normal from an emergency state, the reactive routing policy will be used as the target routing policy. The reactive routing strategy includes generating multiple candidate paths based on the satellite-ground fusion network model, and using the path with the lowest data transmission energy consumption among the candidate paths as the communication link for communication response. The proactive routing strategy includes generating multiple candidate paths based on the satellite-ground fusion network model, and using the path with the best comprehensive link stability evaluation result among the candidate paths as the communication link for the communication response.

3. The satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method as described in claim 2, characterized in that, The step of generating a routing strategy based on the satellite-ground fusion network model includes: Multiple candidate paths are generated based on the aforementioned satellite-ground fusion network model, and the energy reception of each node in the candidate paths is determined: in, Represents a node Energy consumption acceptance, Represents a node The remaining energy, Represents a node The initial energy; Determine the transmission energy consumption of the transmitting node data for each node in the candidate path: in, Represents a node With nodes Energy consumption for sending data between nodes Indicates the energy consumption coefficient. Indicates the amount of data to be transmitted. This represents the time coefficient, which indicates the activity level of a node within the current time window. The path selection weights for each candidate path are determined based on the energy consumption reception and the transmission energy consumption. in, Indicates the path selection weight; Based on the path selection weights, the path with the lowest data transmission energy consumption among the candidate paths is determined, and the path with the lowest data transmission energy consumption is used as the communication link for the communication response. A reactive routing strategy is then generated based on the communication link.

4. The satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method as described in claim 3, characterized in that, The step of generating a routing strategy based on the satellite-ground fusion network model includes: Multiple candidate paths are generated based on the aforementioned satellite-ground fusion network model, and the current link quality of each candidate path is evaluated to obtain the current link quality evaluation result: in, This indicates the current link quality assessment result. Indicates the weight of historical data. This indicates the historical link quality assessment results. This represents the current link quality comprehensive score, which is obtained by weighting the candidate path's packet reception ratio, smooth packet reception rate, stability factor, and signal-to-noise ratio. The transmission anti-interference capability of each node in the candidate path is evaluated to obtain the anti-interference security level: in, This indicates the level of security against interference in data transmission between nodes. This indicates the maximum level of interference that nodes can withstand. This indicates the degree of interference between nodes; Prediction factors are determined based on the rate of change in link quality for each candidate link: in, Indicates predictor factor, Indicates the rate of change in link quality. This indicates the fastest rate at which historical link quality changes. Indicates time The link quality assessment results Indicates time The link quality assessment results Indicates the time interval for calculating the rate of change; Based on the current link quality assessment results, anti-interference security level, and prediction factors of each candidate path, a comprehensive link stability assessment is performed on each candidate path to obtain the comprehensive link stability assessment result: in, This indicates the comprehensive evaluation result of link stability. , and Indicates the weighting factor; Based on the comprehensive evaluation results of the link stability, the path with the best comprehensive evaluation results among the candidate paths is taken as the communication link for the communication response, and an active routing strategy is generated based on the communication link.

5. The satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method as described in any one of claims 1 to 4, characterized in that, Before inputting the network topology information, the node characteristics of each node in the communication link, and the link characteristics of the communication link into the target fault self-healing analysis model for fault self-healing analysis, the method further includes: Configure reinforcement learning parameters, which include state information, actions, and rewards. The state information includes the node's current neighbor node information, the comprehensive evaluation result of link stability, historical fault flags, and remaining energy. The actions include generating a fault self-healing link based on the state information. The rewards include providing positive or negative feedback based on the communication response results of the fault self-healing path. A value function is constructed based on the reinforcement learning parameters, the value function comprising: in, Indicates the learning rate. Indicates the discount factor. Indicates the state Take action below Instant rewards Indicates the state Take action below The optimal value Indicates the state Take action below The corresponding current value, Indicates the state Take action below The value of updating; Based on the aforementioned value function, an original fault self-healing analysis model is constructed. A loss function is constructed based on a time-series difference strategy, and the original fault self-healing analysis model is trained based on the loss function to obtain a target fault self-healing analysis model. The loss function includes: in, This represents the loss function, which iteratively updates the current network parameters through backpropagation and gradient descent. , This represents the current policy network during the training of the original fault self-healing analysis model. This represents the current network parameters of the current policy network. Represents the target policy network. This represents the target network parameters of the target policy network.

6. The satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method as described in claim 5, characterized in that, The construction of the value function based on the reinforcement learning parameters includes: A graph structure is generated based on network topology information, and the graph structure includes multiple nodes and edges connecting the nodes. The graph structure is configured with initial features based on the reinforcement learning parameters. The initial features include initial node features and initial edge features. The initial node features include the remaining energy and historical fault flags of the nodes. The edge features include the comprehensive evaluation results of link stability and link time delay information. An initial graph neural network is generated based on the initial features and the graph structure; The target graph neural network is obtained by updating the features of each node and edge in the initial graph neural network based on the message passing mechanism. in, Represents a node No. Layer node characteristics, Represents a node With nodes No. Layer edge features, Represents a node The set of neighboring nodes, Indicates the first The node weight matrix of the layer, This represents the activation function. Represents a node No. Layer node characteristics, Representing neighboring nodes No. Layer node characteristics, Represents a node With nodes In the Layer edge features, Indicates the first The edge weight matrix of the layer; The reinforcement learning parameters are transformed into embedding vectors by the target graph neural network to obtain reinforcement learning embedding vectors, and a value function is constructed based on the reinforcement learning embedding vectors.

7. The satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method as described in any one of claims 1 to 4, characterized in that, The process of monitoring the communication response of the communication link includes: Monitor the response status of neighboring nodes after each node in the communication link sends a communication request to the neighboring node during the communication response process; The comprehensive evaluation results of the link stability of the communication link during the monitoring communication response process; During the monitoring of the communication response process, the energy alarm information of each node in the communication link includes the remaining energy of the node being lower than a preset energy threshold.

8. A satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing device, characterized in that, The satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing device include: The satellite-ground fusion model construction module is used to construct a satellite-ground fusion network model based on the global routing information of the target area. The global routing information includes the network topology information of the target area. The satellite-ground fusion network model consists of multiple nodes within the target area and the communication topology between the nodes. The nodes include ad hoc network nodes and gateway nodes. The gateway node is connected to multiple ad hoc network nodes, and the ad hoc network node is connected to at least one ad hoc network node. The routing policy generation module is used to generate routing policies based on the satellite-ground converged network model. The routing policies include reactive routing policies and proactive routing policies. A routing response module is used to generate a target routing policy based on the task priority of the task request and the routing policy when a task request is received. The target routing policy includes determining the communication link for the communication response. The communication response module is used to call each node of the communication link to respond to the task request based on the target routing strategy, and to monitor the communication response process of the communication link. The fault self-healing module is used to input the network topology information, the node characteristics of each node in the communication link, and the link characteristics of the communication link into the target fault self-healing analysis model when a fault is detected in the communication link, perform fault self-healing analysis, generate a fault self-healing link, and call each node in the fault self-healing link to respond to the task request, so as to realize communication fault self-healing during the communication process.

9. A satellite-ground integrated hybrid self-organizing network routing protocol and fault self-healing device, characterized in that, The satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing device includes: a memory, a processor, and a satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing program stored in the memory and executable on the processor. The satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing program is configured to implement the satellite-ground integrated hybrid ad hoc network routing protocol and fault self-healing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a satellite-ground converged hybrid ad hoc network routing protocol and a fault self-healing program, which, when executed by a processor, implements the satellite-ground converged hybrid ad hoc network routing protocol and fault self-healing method as described in any one of claims 1 to 7.

Images