Dynamic routing optimization method and system based on ad hoc network

Abstract

The invention provides a dynamic routing optimization method and system based on an ad hoc network. The method comprises the following steps: constructing a state space of the ad hoc network in routing switching through performance characteristics of each routing node in the ad hoc network and interaction density characteristics in neighbor node information; the method comprises the following steps: acquiring response time delay information of a route switching request in a route switching process in an ad hoc network, determining path stability of each route node in the ad hoc network in the route switching process through the response time delay information, and further determining a route working condition index of the ad hoc network in a current network according to all the path stability; when the routing working condition index is lower than a preset working condition threshold value, real-time updating of a routing table in the ad hoc network is triggered, and then incremental updating is carried out on the routing table in the ad hoc network based on the reward function in the state space. Based on the above scheme, topology dynamic sensing and intelligent routing optimization in the ad hoc network can be realized, so that the routing switching stability in the ad hoc network can be improved.

Description

Technical Field

[0001] This application relates to the field of routing communication technologies. More specifically, this application relates to a dynamic routing optimization method and system based on an ad-hoc network. Background Art

[0002] With the development of 5G and 6G communication technologies, the ad-hoc network technology has also been continuously improving its communication rate, capacity, and coverage. The ad-hoc network technology is in a stage of rapid development and has been widely applied in both military and civilian fields. In the military field, the unmanned aerial vehicle ad-hoc network technology has become a research hotspot. In the civilian aspect, due to its flexibility and self-healing characteristics, the wireless ad-hoc network system has been widely used in fields such as emergency communication and the Internet of Things, especially showing unique advantages in scenarios such as disaster rescue and field operations.

[0003] Traditional ad-hoc network routing protocols have obvious defects in static routing maintenance. The core problem lies in the use of a passive routing update mechanism, which cannot respond to network topology changes in real time. This traditional ad-hoc network routing protocol usually only establishes a routing path when a communication requirement occurs, or relies on the synchronization of the entire network routing information at fixed intervals, resulting in the network being unable to timely perceive the topological changes brought about by node movement. At the same time, using fixed parameters to determine the link state is difficult to adapt to the dynamic changes of the wireless channel environment, and misjudgments often occur. More seriously, such protocols generally adopt simple path selection criteria, only considering a single factor such as the number of hops, while ignoring key indicators such as node energy and network load, which easily causes uneven distribution of network resources and seriously affects the overall performance. Therefore, how to achieve dynamic topology perception and intelligent routing optimization in an ad-hoc network, thereby improving the routing switching stability in an ad-hoc network, has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides a dynamic routing optimization method and system based on an ad-hoc network, which can achieve dynamic topology perception and intelligent routing optimization in an ad-hoc network, thereby improving the routing switching stability in an ad-hoc network.

[0005] In a first aspect, this application provides a dynamic routing optimization method based on an ad-hoc network, including: Abstracting the routing nodes of the ad-hoc network into a graph structure to obtain the routing topology graph of the ad-hoc network, and then collecting the neighbor node information in the routing topology graph; Extracting the performance characteristics of each routing node in the routing topology graph and the interaction density characteristics in the neighbor node information, and constructing the state space of the ad-hoc network in routing switching through the performance characteristics of each routing node and the interaction density characteristics; During the routing handover process in the ad hoc network, collect the response delay information of the routing handover request, determine the path stability of each routing node in the ad hoc network during this routing handover through the response delay information, and then determine the routing working condition index of the ad hoc network in the current network according to all the path stabilities; When the routing working condition index is lower than the preset working condition threshold, trigger the real-time update of the routing table in the ad hoc network, and then perform incremental update on the routing table in the ad hoc network based on the reward function in the state space.

[0006] In some embodiments, extracting the performance characteristics of each routing node in the routing topology graph and the interaction density characteristics in the neighbor node information specifically includes: For each routing node in the routing topology graph, extract the historical performance mean of each performance parameter in the routing node from the pre-collected historical performance data; Determine the performance characteristics of the routing node through all the historical performance means, and then obtain the performance characteristics of each routing node in the routing topology graph; For each group of neighbor nodes in the neighbor node information, obtain all the interaction intervals between the neighbor nodes within a specified time period; Determine the interaction density value of the neighbor nodes through all the interaction intervals, and then obtain the interaction density value of each group of neighbor nodes in the neighbor node information; Determine the interaction density characteristics in the neighbor node information according to all the interaction density values.

[0007] In some embodiments, the performance parameters include the routing node location, remaining energy, and link quality of the routing node.

[0008] In some embodiments, constructing the state space of the ad hoc network during routing handover through the performance characteristics of each routing node and the interaction density characteristics specifically includes: Convert the node locations of each routing node into a relative distance matrix; Normalize the remaining energy and link quality of each performance characteristic and integrate them into the relative distance matrix, and then obtain the multi-dimensional matrix of the performance characteristics of the ad hoc network during routing handover; Generate an interaction density matrix of the ad hoc network during routing handover through the interaction density characteristics; Fuse the performance matrix and the interaction density matrix into the state space of the ad hoc network during routing handover.

[0009] In some embodiments, determining the path stability of each routing node in the ad hoc network during this routing handover through the response delay information specifically includes: For each routing node in the ad hoc network, obtain the response delay and the number of path hops of the switching path of the routing node in the current routing switch from the response delay information; Determine the path stability of the routing node in the current routing switch based on the response delay and the number of path hops, and further obtain the path stability of each routing node in the ad hoc network in the current routing switch.

[0010] In some embodiments, determining the routing working condition index of the ad hoc network in the current network according to all the path stabilities specifically includes: Obtain the adjustment coefficient of the network stability of the ad hoc network in the current network; Determine the first stability score and the second stability score of the ad hoc network according to all the path stabilities; Determine the routing working condition index of the ad hoc network in the current network based on the adjustment coefficient, the first stability score, and the second stability score.

[0011] In some embodiments, incrementally updating the routing table in the ad hoc network based on the reward function in the state space specifically includes: For each routing node in the routing table of the ad hoc network, extract the incremental reward value of the number of path hops in the routing node from the reward function in the state space; Perform greedy reward on the transmission path of the routing node based on the incremental reward value, and further perform greedy reward on the transmission paths of all routing nodes in the routing table of the ad hoc network to complete the incremental update of the routing table in the ad hoc network.

[0012] In a second aspect, the present application provides a dynamic routing optimization system based on an ad hoc network, including a routing update unit, and the routing update unit includes: An acquisition module, configured to abstract the routing nodes of the ad hoc network into a graph structure to obtain a routing topology graph of the ad hoc network, and further acquire neighbor node information in the routing topology graph; A processing module, configured to extract the performance characteristics of each routing node in the routing topology graph and the interaction density characteristics in the neighbor node information, and construct a state space of the ad hoc network in the routing switch based on the performance characteristics of each routing node and the interaction density characteristics; The processing module is further configured to collect response delay information of a routing switch request during the routing switch in the ad hoc network, determine the path stability of each routing node in the ad hoc network in the current routing switch based on the response delay information, and further determine the routing working condition index of the ad hoc network in the current network according to all the path stabilities; An execution module, configured to trigger real-time update of the routing table in the ad hoc network when the routing working condition index is lower than a preset working condition threshold, and further incrementally update the routing table in the ad hoc network based on the reward function in the state space.

[0013] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned dynamic routing optimization method based on an ad hoc network.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes run on a computer, the computer is enabled to execute the above-mentioned dynamic routing optimization method based on an ad hoc network.

[0015] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects: In a dynamic routing optimization method and system based on an ad hoc network provided by the present application, the routing nodes of the ad hoc network are abstracted into a graph structure to obtain a routing topology graph of the ad hoc network, and then the neighbor node information in the routing topology graph is collected; the performance characteristics of each routing node in the routing topology graph and the interaction density characteristics in the neighbor node information are extracted, and a state space of the ad hoc network in routing switching is constructed through the performance characteristics of each routing node and the interaction density characteristics; during the routing switching process in the ad hoc network, the response delay information of the routing switching request is collected, and the path stability of each routing node in the ad hoc network during this routing switching is determined through the response delay information, and then the routing working condition index of the ad hoc network in the current network is determined according to all the path stabilities; when the routing working condition index is lower than a preset working condition threshold, the real-time update of the routing table in the ad hoc network is triggered, and then the routing table in the ad hoc network is incrementally updated based on the reward function in the state space.

[0016] It can be seen that in this application, when the routing condition index is lower than the preset condition threshold, the real-time update of the routing table in the ad hoc network is triggered, and then the routing table in the ad hoc network is incrementally updated based on the reward function in the state space. First, by determining the state space, the real-time dynamic performance profile of all network nodes can be obtained, thus significantly improving the accuracy of routing decisions. By abstracting routing nodes into a graph structure and collecting neighbor node information, the ad hoc network can completely depict the network topology relationship. After extracting node performance characteristics and interaction density characteristics, the constructed multi-dimensional state space not only includes traditional static parameters such as location and energy, but also incorporates an interaction density index that reflects the dynamic characteristics of the network. The comprehensive state representation enables the ad hoc network to perceive the subtle changes in the network topology in real time. Based on the refined state-aware routing algorithm, more accurate path selection can be made, avoiding misjudgments caused by incomplete information in traditional protocols and fundamentally improving the stability of routing switching. Then, by determining the routing condition index, a quantitative evaluation of the overall network operation state can be obtained, thus realizing intelligent routing adjustment. By collecting the routing switching response delay and calculating the stability scores of each path, the ad hoc network can accurately evaluate the current health status of the network. After integrating the stability of all paths into a unified routing condition index, the ad hoc network has an objective standard for judging whether routing optimization is required. The incremental update mechanism triggered when the index is lower than the preset threshold can not only ensure timely response to network state changes but also avoid unnecessary frequent routing reconstruction. The intelligent trigger mechanism based on the quantitative index, combined with the detailed network information provided by the state space, enables the ad hoc network to quickly adapt to network changes while maintaining a low control overhead, significantly improving the stability and reliability of routing switching. In summary, based on the above solutions, dynamic topology perception and intelligent routing optimization in the ad hoc network can be realized, thereby improving the stability of routing switching in the ad hoc network. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained without creative efforts.

[0018] Figure 1 is an exemplary flowchart of a dynamic routing optimization method based on an ad hoc network shown in some embodiments of the present application; Figure 2 is a schematic flowchart of incremental update shown in some embodiments of the present application; Figure 3 is a schematic structural diagram of a routing update unit shown in some embodiments of the present application; Figure 4It is a schematic structural diagram of a computer device for implementing a dynamic routing optimization method based on an ad hoc network as shown in some embodiments of the present application. Detailed implementation manners

[0019] To better understand the technical solutions of the present application, the technical solutions of the present application will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0020] Refer to Figure 1 , which is an exemplary flowchart of a dynamic routing optimization method based on an ad hoc network as shown in some embodiments of the present application. The dynamic routing optimization method based on an ad hoc network mainly includes the following steps: In step 101, the routing nodes of the ad hoc network are abstracted into a graph structure to obtain a routing topology graph of the ad hoc network, and then the neighbor node information in the routing topology graph is collected.

[0021] It should be noted that in the present application, the neighbor node information represents a set of attribute data of all adjacent nodes of the current node; in specific implementation, each routing node in the ad hoc network periodically sends lightweight beacon messages containing its own ID, location, power, etc. The receiving node determines the neighbor relationship through the signal strength and records the link quality parameters. Each routing node maintains a dynamic neighbor table, and after summarization, a weighted topology graph is formed as the routing topology graph of the ad hoc network. The nodes in this routing topology graph represent devices, and the connections are marked with routing metrics such as delay and stability; by dynamically adjusting the beacon frequency (faster sending when moving fast) and the three-time timeout determination mechanism, it is ensured that the topology graph is updated in real time, and the set of all neighbor nodes in the routing topology graph is used as the neighbor node information in the routing topology graph.

[0022] In step 102, the performance characteristics of each routing node in the routing topology graph and the interaction density characteristics in the neighbor node information are extracted, and a state space of the ad hoc network in routing switching is constructed through the performance characteristics of each routing node and the interaction density characteristics.

[0023] In some embodiments, the extraction of the performance characteristics of each routing node in the routing topology graph and the interaction density characteristics in the neighbor node information can be implemented by the following steps: For each routing node in the routing topology graph, the historical performance mean of each performance parameter in the routing node is extracted from the pre-collected historical performance data; The performance characteristics of the routing node are determined through all the historical performance means, and then the performance characteristics of each routing node in the routing topology graph are obtained; For each group of neighbor nodes in the neighbor node information, all interaction intervals between the neighbor nodes within a specified time period are obtained; Determine the interaction density values of neighbor nodes through all interaction intervals, and then obtain the interaction density values of each group of neighbor nodes in the neighbor node information; Determine the interaction density feature in the neighbor node information according to all the interaction density values.

[0024] It should be noted that in this application, the interaction density feature represents the topological dynamic characteristics of the data interaction frequency and intensity between nodes per unit time; the interaction interval represents the minimum time interval between two adjacent valid data interactions; the interaction density value is a normalized numerical index quantifying the communication activity degree between nodes; the performance feature represents the set of operating state parameters of the routing node in terms of energy, load, and link quality; the historical performance mean represents the average level value of the performance feature of the node within a specific time window; the performance parameters include the routing node location, remaining energy, and link quality of the routing node.

[0025] When specifically implemented, first, collect the historical performance data of each routing node in the ad hoc network within a specified time period. Among them, the historical performance data contains the parameter values of each performance parameter. For each routing node in the routing topology graph, obtain the parameter values of each performance parameter in the routing node from the historical performance data. For each performance parameter in the routing node, the mean value of all parameter values of the performance parameter can be used as the historical performance mean of the performance parameter in the routing node. In this way, the historical performance means of each performance parameter in the routing node can be obtained; second, the set of all historical performance means can be used as the performance feature of the routing node. In this way, the performance features of each routing node in the routing topology graph can be obtained.

[0026] Then, for each group of neighbor nodes in the neighbor node information, obtaining all the interaction intervals between neighbor nodes within a specified time period can be implemented in the following manner, that is: for each group of neighbor nodes in the neighbor node information, obtain all the interaction intervals between neighbor nodes within a specified time period from the console of the ad hoc network; furthermore, the reciprocal of the mean value of all the interaction intervals can be used as the interaction density value of the neighbor node. In this way, the interaction density values of each group of neighbor nodes in the neighbor node information can be obtained; finally, the set of all the interaction density values can be used as the interaction density feature in the neighbor node information.

[0027] In some embodiments, constructing the state space of the ad hoc network in route switching through the performance features of each routing node and the interaction density feature can be implemented by the following steps: Convert the node positions of each routing node into a relative distance matrix; Normalize the remaining energy and link quality of each performance feature and integrate them into the relative distance matrix, and then obtain the multi-dimensional matrix of the performance feature of the ad hoc network in route switching; Generate an interaction density matrix for the ad hoc network during route switching based on the interaction density feature; Fuse the performance matrix and the interaction density matrix into a state space for the ad hoc network during route switching.

[0028] When specifically implemented, first, obtain the node positions of the corresponding routing nodes from the performance characteristics of each routing node, and then calculate the Euclidean distance between any two routing nodes as the relative distance, so as to matrixize all the relative distances as the relative distance matrix; second, use the normalization algorithm to normalize the remaining energy and link quality of each performance characteristic, so as to use the normalized remaining energy and link quality as new column vectors, and use the dimension concatenation algorithm (for example: vertical concatenation) to concatenate the new column vectors with the relative distance matrix, and then use the concatenated matrix as the multi-dimensional matrix of the performance characteristics of the ad hoc network during route switching; then, use the sliding window counting method to count the number of data packet interactions of all interaction density values in the interaction density feature within a set time window (default is 5s), so as to construct all the data packet interaction times as an asymmetric matrix as the interaction density matrix of the ad hoc network during route switching; finally, use the feature concatenation algorithm (for example: the multi-modal fusion algorithm in machine learning) to unify the routing node indexes in the performance matrix and the interaction density matrix to generate the state vector of the ad hoc network as the state space of the ad hoc network during route switching.

[0029] It should be noted that in this application, the state space represents a multi-dimensional feature set of the dynamic performance and topological relationship of all nodes in the ad hoc network; the relative distance matrix represents a symmetric distance quantization table of the physical connection relationship between nodes; the multi-dimensional matrix; the interaction density matrix represents a comprehensive feature matrix that fuses multiple indicators such as distance, energy, and link quality.

[0030] In step 103, during the route switching process in the ad hoc network, collect the response delay information of the route switching request, determine the path stability of each routing node in the ad hoc network during this route switching through the response delay information, and then determine the route working condition index of the ad hoc network in the current network according to all the path stabilities.

[0031] In some embodiments, collecting the response delay information of the route switching request during the route switching process in the ad hoc network can be implemented in the following manner, that is: during the route switching process in the ad hoc network, obtain the response delay and the number of path hops of each route switching request from the console of the ad hoc network, so as to use the set of all response delays and the number of path hops as the response delay information of the route switching request, where the response delay information represents the set of time delay data for the entire process from the sending to the receiving of the route request; the response delay represents the end-to-end transmission time consumption of a single route request; the number of path hops represents the number of relay nodes that the data packet needs to pass through from the source node to the target node.

[0032] In some embodiments, determining the path stability of each routing node in the ad hoc network during the current routing switch based on the response delay information can be achieved by the following steps: For each routing node in the ad hoc network, obtain the response delay and the number of path hops of the switched path of the routing node during the current routing switch from the response delay information; Determine the path stability of the routing node during the current routing switch based on the response delay and the number of path hops, thereby obtaining the path stability of each routing node in the ad hoc network during the current routing switch.

[0033] It should be noted that in this application, the path stability represents a comprehensive reliability quantification index of the transmission path under the constraints of delay, link quality, and node energy; specifically, first, for each routing node in the ad hoc network, obtain the response delay and the number of path hops of the switched path of the routing node during the current routing switch from the response delay information; then, use the product of the response delay and the natural logarithm of the number of path hops as the adjustment weight of the response delay, obtain the average path link quality of the routing node and the minimum remaining energy of the nodes in the path from the console of the ad hoc network, and thus preset the weight coefficients of the average path link quality and the minimum remaining energy in combination with historical experience, and then calculate the result of dividing the weighted sum of the average path link quality and the minimum remaining energy by the adjustment weight as the path stability of the routing node during the current routing switch. In this way, the path stability of each routing node in the ad hoc network during the current routing switch can be obtained.

[0034] In some embodiments, determining the routing working condition index of the ad hoc network in the current network based on all the path stabilities can be achieved by the following steps: Obtain the adjustment coefficient of the network stability of the ad hoc network in the current network; Determine the first stability score and the second stability score of the ad hoc network based on all the path stabilities; Determine the routing working condition index of the ad hoc network in the current network based on the adjustment coefficient, the first stability score, and the second stability score.

[0035] It should be noted that in this application, the adjustment coefficient is a dynamic weight parameter used to balance the influence degrees of the path stability mean and variance on the routing working condition index; the first stability score is used to quantify the overall level of the reliability of the entire network path; the second stability score is used to reflect the fluctuation degree of the path performance and the robustness of the network topology.

[0036] In specific implementation, first, obtain the adjustment coefficient of the network stability of the ad hoc network from the console of the ad hoc network; then, take the mean value of the stabilities of all paths as the first stability score of the ad hoc network, and take the variance of the stabilities of all paths as the first stability score of the ad hoc network; finally, the routing working condition index = the first stability score + the adjustment coefficient * the second stability score, and the routing working condition index of the ad hoc network in the current network can be obtained through the above formula.

[0037] In step 104, when the routing working condition index is lower than the preset working condition threshold, trigger the real-time update of the routing table in the ad hoc network, and then incrementally update the routing table in the ad hoc network based on the reward function in the state space.

[0038] It should be noted that in this application, the working condition threshold represents the quantization index of the critical state of network performance that triggers routing update. In specific implementation, the working condition threshold can be obtained from the console of the ad hoc network. In order to improve the accuracy of judgment, it can also be manually modified in combination with historical experience.

[0039] In some embodiments, incrementally update the routing table in the ad hoc network based on the reward function in the state space. Refer to Figure 2 As shown, this figure is a schematic flow diagram of incremental update in some embodiments of this application. In this embodiment, the incremental update can be implemented by the following steps: In step 1041, for each routing node in the routing table of the ad hoc network, extract the incremental reward value of the path hop count in the routing node from the reward function in the state space. In step 1042, perform greedy reward on the transmission path of the routing node through the incremental reward value, and then perform greedy reward on the transmission paths of each routing node in the routing table of the ad hoc network to complete the incremental update of the routing table in the ad hoc network.

[0040] In specific implementation, first, for each routing node in the routing table of the ad hoc network, obtain the reward value of the reward function in the state space as the incremental reward value of the path hop count in the routing node. This incremental reward value represents the quantization value of the hop count efficiency improvement of the new path relative to the old path; then, when the incremental reward value is greater than 0, use the greedy selection algorithm to select the path with the highest comprehensive reward value from the candidate paths to update and replace the routing table entry of the routing node. Through the above method, greedy reward can be performed on the transmission paths of each routing node in the routing table of the ad hoc network, thereby completing the incremental update of the routing table in the ad hoc network.

[0041] In addition, on the other hand of this application, in some embodiments, this application provides a dynamic routing optimization system based on an ad hoc network. The dynamic routing optimization system based on an ad hoc network includes a routing update unit. Refer to Figure 3, This figure is a schematic structural diagram of a routing update unit according to some embodiments of the present application. The routing update unit includes: a collection module 201, a processing module 202, and an execution module 203, which are described as follows: Collection module 201. In the present application, the collection module 201 is mainly used to abstract the routing nodes of the ad hoc network into a graph structure to obtain the routing topology graph of the ad hoc network, and then collect the neighbor node information in the routing topology graph; Processing module 202. In the present application, the processing module 202 is used to extract the performance characteristics of each routing node in the routing topology graph and the interaction density characteristics in the neighbor node information, and construct the state space of the ad hoc network in routing switching through the performance characteristics of each routing node and the interaction density characteristics; It should be noted that the processing module 202 is also used to collect the response delay information of the routing switch request during the routing switching process in the ad hoc network, determine the path stability of each routing node in the ad hoc network in this routing switch through the response delay information, and then determine the routing working condition index of the ad hoc network in the current network according to all the path stabilities; Execution module 203. In the present application, the execution module 203 is mainly used to trigger the real-time update of the routing table in the ad hoc network when the routing working condition index is lower than the preset working condition threshold, and then perform incremental update of the routing table in the ad hoc network based on the reward function in the state space.

[0042] The above has introduced in detail the examples of the dynamic routing optimization method and system based on the ad hoc network provided by the embodiments of the present application. It can be understood that, in order to implement the above functions, the corresponding device includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0043] In some embodiments, the present application also provides a computer device. The computer device includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned dynamic routing optimization method based on the ad hoc network.

[0044] In some embodiments, refer to Figure 4, the dashed lines in the figure indicate that the unit or module is optional. This figure is a schematic structural diagram of a computer device for implementing the method for optimizing dynamic routing based on an ad hoc network according to an embodiment of the present application. The method for optimizing dynamic routing based on an ad hoc network described in the above embodiment can be implemented by Figure 4 the computer device shown. The computer device includes at least one processor 301, a memory 302, and at least one communication unit 305. The computer device can be a terminal device, a server, or a chip.

[0045] The processor 301 can be a general-purpose processor or a dedicated processor. For example, the processor 301 can be a central processing unit (CPU). The CPU can be used to control the computer device, execute software programs, and process data of software programs. The computer device can also include a communication unit 305 for implementing signal input (reception) and output (transmission).

[0046] For example, the computer device can be a chip, and the communication unit 305 can be the input and / or output circuit of the chip, or the communication unit 305 can be the communication interface of the chip. The chip can be a component of a terminal device, a network device, or other devices.

[0047] Again, for example, the computer device can be a terminal device or a server, and the communication unit 305 can be the transceiver of the terminal device or the server, or the communication unit 305 can be the transceiver circuit of the terminal device or the server.

[0048] The computer device can include one or more memories 302 on which a program 304 is stored. The program 304 can be run by the processor 301 to generate instructions 303, so that the processor 301 executes the method described in the above method embodiment according to the instructions 303. Optionally, data (such as a target audit model) can also be stored in the memory 302. Optionally, the processor 301 can also read the data stored in the memory 302. The data can be stored at the same storage address as the program 304, or the data can be stored at a different storage address from the program 304.

[0049] The processor 301 and the memory 302 can be set separately or integrated together. For example, they can be integrated on a system on chip (SOC) of a terminal device.

[0050] It should be understood that each step of the above method embodiments can be completed by a logic circuit in the form of hardware or instructions in the form of software in the processor 301. The processor 301 can be a CPU, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, for example, discrete gates, transistor logic devices, or discrete hardware components.

[0051] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0052] For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or code are stored. When the instructions or code run on a computer, the computer is caused to execute the above-mentioned dynamic routing optimization method based on an ad hoc network.

[0053] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0054] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A dynamic routing optimization method based on ad hoc network, characterized in that: The steps include: Abstract the routing nodes of the ad hoc network into a graph structure, obtain the routing topology of the ad hoc network, and then collect the neighbor node information in the routing topology; Extracting the performance characteristics of each routing node in the routing topology and the interaction density characteristics in the neighbor node information, and constructing the state space of the ad hoc network in routing switching through the performance characteristics of each routing node and the interaction density characteristics; During the route switching process in the ad hoc network, the response delay information of the route switching request is collected, and the path stability of each routing node in the ad hoc network in this route switching is determined through the response delay information, and then the routing working condition index of the ad hoc network in the current network is determined according to all the path stabilities; When the routing operating condition indicator is lower than a preset operating condition threshold, the real-time update of the routing table in the ad hoc network is triggered, and then the routing table in the ad hoc network is incrementally updated based on the reward function in the state space.

2. The method according to claim 1, characterized in that Extracting the performance characteristics of each routing node in the routing topology graph and the interaction density characteristics in the neighbor node information specifically includes: For each routing node in the routing topology diagram, extracting the historical performance mean of each performance parameter in the routing node from the pre-collected historical performance data; Determine the performance characteristics of the routing nodes through all historical performance averages, and then obtain the performance characteristics of each routing node in the routing topology; For each group of neighbor nodes in the neighbor node information, obtaining all interaction intervals between the neighbor nodes within a specified time period; Determine the interaction density value of the neighbor nodes through all interaction intervals, and then obtain the interaction density value of each group of neighbor nodes in the neighbor node information; The interaction density feature in the neighbor node information is determined according to all the interaction density values.

3. The method according to claim 2, characterized in that The performance parameters include routing node location, remaining energy, and link quality of the routing node.

4. The method according to claim 1, characterized in that Constructing the state space of the ad hoc network in routing switching by using the performance characteristics of each routing node and the interaction density characteristics specifically includes: Convert the node positions of each routing node into a relative distance matrix; The residual energy and link quality of each performance characteristic are normalized and then integrated into the relative distance matrix, thereby obtaining a multi-dimensional matrix of performance characteristics of the ad hoc network in routing switching; Generate an interaction density matrix of the ad hoc network in routing switching through the interaction density feature; The multi-dimensional matrix of the performance characteristics and the interaction density matrix are merged into the state space of the ad hoc network in routing switching.

5. The method according to claim 1, characterized in that Determining the path stability of each routing node in the ad hoc network in this routing switch by using the response delay information specifically includes: For each routing node in the ad hoc network, obtaining the response delay and the number of path hops of the routing node in switching the path in this routing switch from the response delay information; The path stability of the routing node in this routing switch is determined by the response delay and the number of path hops, and then the path stability of each routing node in the ad hoc network in this routing switch is obtained.

6. The method according to claim 1, characterized in that The routing working condition indicators of the ad hoc network in the current network are determined based on the stability of all paths, including: Obtain the adjustment coefficient of the network stability of the ad hoc network in the current network; Determining a first stability score and a second stability score of the ad hoc network according to all path stabilities; The routing condition index of the ad hoc network in the current network is determined by the adjustment coefficient, the first stability score and the second stability score.

7. The method according to claim 1, characterized in that Incrementally updating the routing table in the ad hoc network based on the reward function in the state space specifically includes: For each routing node of the routing table in the ad hoc network, extracting an incremental reward value of the number of path hops in the routing node from the reward function in the state space; The transmission path of the routing node is greedily rewarded by the incremental reward value, and then the transmission path of each routing node in the routing table in the self-organizing network is greedily rewarded, so as to complete the incremental update of the routing table in the self-organizing network.

8. A dynamic routing optimization system based on a self-organizing network, the dynamic routing optimization system based on a self-organizing network includes a routing update unit, characterized in that: The routing update unit comprises: The collection module is used to abstract the routing nodes of the ad hoc network into a graph structure, obtain the routing topology of the ad hoc network, and then collect the neighbor node information in the routing topology; A processing module, used to extract the performance characteristics of each routing node in the routing topology diagram and the interaction density characteristics in the neighbor node information, and construct the state space of the ad hoc network in routing switching through the performance characteristics of each routing node and the interaction density characteristics; The processing module is also used to collect response delay information of the route switching request during the route switching process in the self-organizing network, determine the path stability of each routing node in the self-organizing network in this route switching through the response delay information, and then determine the routing working condition index of the self-organizing network in the current network according to all the path stabilities; The execution module is used to trigger the real-time update of the routing table in the self-organizing network when the routing condition indicator is lower than a preset condition threshold, and then incrementally update the routing table in the self-organizing network based on the reward function in the state space.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the dynamic routing optimization method based on a self-organizing network 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 instructions or codes, and when the instructions or codes are executed on a computer, the computer implements the dynamic routing optimization method based on a self-organizing network as described in any one of claims 1 to 7.

Images