Mobile routing planning methods, devices, equipment and storage media

Abstract

This invention belongs to the field of wireless communication technology and discloses a mobile routing planning method, apparatus, device, and storage medium. The invention obtains the overlap degree based on the network performance indicators of each mobile routing node in a wireless swarm intelligence system and the influence characteristics of routing planning; determines the target performance indicator based on the overlap degree; records the network connection status corresponding to the target performance indicator based on time series data; performs network slicing on the mobile routing nodes based on the difference and similarity of the network connection status to obtain target network slices; evaluates the service capabilities of each mobile node in the network slice to determine the target node; generates a service delay tree based on the service waiting time and service capabilities matched by neighboring nodes for the target node; and obtains the target routing plan based on the service delay tree. This invention solves the problems of high computational complexity, high resource consumption, insufficient resource allocation accuracy, long service response delays, and high bandwidth consumption in the computational process.

Description

Technical Field

[0001] This invention relates to the field of wireless communication technology, and in particular to a mobile routing planning method, apparatus, device, and storage medium. Background Technology

[0002] Under the constraints of highly dynamic, massive intelligent devices and multimodal scenarios, the complex and ever-changing nature of network information makes it difficult for existing technologies to meet the fully autonomous decision-making needs of mobile devices, making dynamic on-demand network design extremely challenging. Mobile nodes transmit multimedia information streams with quality-of-service requirements through dynamic routing and mobility management technologies. On-demand networking does not rely on pre-set infrastructure for temporary deployment; mobile nodes exchange information using their own devices, and can communicate with other nodes when they are out of range. In on-demand networking scenarios, due to the flexible mobility of networking devices and the complexity of the transmission environment, data transmission is unstable, leading to problems such as data errors and packet loss.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a mobile routing planning method, apparatus, device, and storage medium, aiming to solve the technical problems of existing technologies, such as high time complexity in the calculation process, consumption of large amounts of resources, insufficient accuracy in resource allocation, long service response delays, and high bandwidth consumption.

[0005] To achieve the above objectives, the present invention provides a mobile routing planning method applied to a wireless network swarm intelligence system, the wireless swarm intelligence system comprising a plurality of mobile routing nodes, the mobile routing planning method comprising:

[0006] The overlap is obtained based on the network performance indicators of each mobile routing node in the wireless swarm intelligence system and the influence characteristics of routing planning, and the target performance indicators are determined based on the overlap.

[0007] The network connection status corresponding to the target performance index is recorded according to the time series. The mobile routing node is then sliced ​​according to the difference and similarity of the network connection status to obtain the target network slice.

[0008] The service capabilities of each mobile node in the network slice are evaluated to determine the target node;

[0009] A service delay tree is generated based on the service wait time matched by neighboring nodes for the target node and the service capacity, and the target route plan is obtained based on the service delay tree.

[0010] Optionally, the step of obtaining the overlap degree based on the network performance indicators of each mobile routing node in the wireless swarm intelligence system and the influence characteristics of routing planning, and determining the target performance indicator based on the overlap degree, includes:

[0011] Based on the network performance indicators and the impact characteristics, a set of network performance indicators and a set of impact characteristics are obtained;

[0012] The probability density of network performance indicators is obtained based on the set of network performance indicators;

[0013] The probability density of the influencing features is obtained based on the influencing feature set;

[0014] The joint probability density of the network performance indicators and the influence features is obtained based on the network performance indicator set and the influence feature set.

[0015] The conditional entropy of the influence feature set on the network performance index set is obtained based on the network performance index set and the influence feature set.

[0016] Based on the probability density of the network performance index, the probability density of the influencing feature, the joint probability density of the network performance index and the influencing feature, the overlap degree of the influencing feature set with the conditional entropy of the network performance index set is obtained.

[0017] Based on the overlap, a corresponding set of network performance indicators is determined, and the network performance indicators in the corresponding set of network performance indicators are used as target performance indicators.

[0018] Optionally, the step of recording the network connection status corresponding to the target performance indicator according to the time series, and performing network slicing on the mobile routing node according to the difference and similarity of the network connection status to obtain the target network slice includes:

[0019] The adjacency period of the mobile routing node at any given time and the number of adjacency periods at any given time are obtained based on the network connection status.

[0020] When the number of adjacent time periods at any given time exceeds a preset threshold, the number of all connection edges that the mobile routing node has existed in both network connection states and the number of connection edges that have existed in both network connection states are obtained based on the adjacent time periods.

[0021] The difference in network connection states is obtained based on the number of all connection edges that the mobile routing node has existed in both network connection states, the number of connection edges that have existed in both network connection states, and the time period.

[0022] Several network slices are generated based on the difference, and a target network slice is selected from the network slices based on the similarity.

[0023] Optionally, the step of generating a plurality of network slices based on the difference and selecting a target network slice from the network slices based on the similarity includes:

[0024] Select one network slice from the plurality of network slices, and obtain the neighborhood set of the adjacent nodes in the network slice;

[0025] The number of nodes is obtained from the neighborhood set;

[0026] Based on the number of nodes, the neighborhood set obtains the similarity of the network slices;

[0027] Repeat the steps of selecting one network slice from the plurality of network slices and obtaining the neighborhood set of the adjacent nodes in the network slice until the similarity of all network slices is obtained;

[0028] The similarity scores are filtered to obtain the maximum similarity score;

[0029] The target network slice is determined based on the maximum similarity.

[0030] Optionally, the step of evaluating the service capabilities of each mobile node in the network slice and determining the target node includes:

[0031] Obtain the service speed and service response time of neighboring nodes;

[0032] Obtain the average number of services provided by neighboring nodes, the successful data packet transmission time, the probability of users consuming resources, the total resources of neighboring nodes, and the remaining resources of neighboring nodes.

[0033] The service delay is calculated based on the average number of services provided by the neighboring nodes, the successful transmission time of the data packet, the probability of the user occupying resources, the total resources of the neighboring nodes, and the remaining resources of the neighboring nodes.

[0034] Effective service time is determined based on service feedback time and service delay.

[0035] The evaluation results are obtained based on the service speed and the effective service time.

[0036] The target node is determined based on the evaluation results.

[0037] Optionally, generating a service latency tree based on the service wait time matched by neighboring nodes for the target node and the service capability includes:

[0038] The available service quantity of a neighboring node is obtained based on the available service quantity of the neighboring node, the quantified value of the transmission distance, the quantified value of the service waiting time, the quantified value of the service capacity, and the weight ratio.

[0039] The neighboring nodes are sorted according to their available service capacity to obtain the sorting result;

[0040] The service delay tree is generated based on the available service capacity of the target node, the available service capacity of the neighboring nodes, and the sorting result.

[0041] Optionally, generating a service delay tree based on the available service volume of the target node, the available service volume of the neighboring nodes, and the sorting result includes:

[0042] The target node is used as the starting node of the service delay tree, and the number of nodes in the next layer of the service delay tree is determined according to the available service capacity of the target node.

[0043] Based on the sorting result and the number of nodes in the next layer, determine the neighboring nodes of the next layer;

[0044] Based on the available service quantity corresponding to the neighbor node of the next layer, and based on the sorting result and the available service quantity corresponding to the neighbor node of the next layer, determine the next layer neighbor node of the next layer neighbor node, and repeat the steps of determining the next layer neighbor node of the next layer neighbor node based on the available service quantity corresponding to the neighbor node of the next layer and based on the sorting result and the available service quantity corresponding to the neighbor node of the next layer, until the middle node in the sorting result is selected, and the neighbor nodes of each layer are obtained.

[0045] The service delay tree is generated based on the neighbor nodes at each layer.

[0046] Furthermore, to achieve the above objectives, the present invention also proposes a mobile route planning device, the mobile route planning device comprising:

[0047] The performance determination module is used to obtain the overlap degree based on the network performance indicators of each mobile routing node in the wireless swarm intelligence system and the influence characteristics of routing planning, and to determine the target performance indicator based on the overlap.

[0048] The network slicing module is used to record the network connection status corresponding to the target performance index according to the time series, and to perform network slicing on the mobile routing node according to the difference and similarity of the network connection status to obtain the target network slice;

[0049] The node evaluation module is used to evaluate the service capabilities of each mobile node in the network slice and determine the target node.

[0050] The routing planning module is used to generate a service delay tree based on the service waiting time matched by neighboring nodes for the target node and the service capacity, and to obtain the target routing plan based on the service delay tree.

[0051] Furthermore, to achieve the above objectives, the present invention also proposes a mobile routing planning device, which includes: a memory, a processor, and a mobile routing planning program stored in the memory and executable on the processor, the mobile routing planning program being configured to implement the steps of the mobile routing planning method described above.

[0052] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a mobile routing planning program, which, when executed by a processor, implements the steps of the mobile routing planning method as described above.

[0053] This invention addresses the problems of high computational complexity, resource consumption, insufficient resource allocation accuracy, long service response delays, and high bandwidth consumption by determining the overlap between network performance indicators and routing planning characteristics of each mobile routing node in a wireless swarm intelligence system. It then records the network connection status corresponding to the target performance indicators based on time series data and performs network slicing on the mobile routing nodes according to the differences and similarities in network connection status. The service capabilities of each mobile node in the network slice are evaluated to determine the target node. A service delay tree is generated based on the service waiting time and service capabilities matched by neighboring nodes for the target node. The target routing plan is then obtained from the service delay tree. By determining the overlap between nodes based on the network performance indicators and routing planning characteristics of each mobile routing node in the wireless swarm intelligence system, slicing the network according to the differences in network connection status, evaluating the capabilities of each network slice, selecting the optimal target node, and performing routing planning, this invention solves the problems of high computational complexity, high resource consumption, insufficient resource allocation accuracy, long service response delays, and high bandwidth consumption in traditional methods. Attached Figure Description

[0054] Figure 1 This is a schematic diagram of the structure of a mobile routing planning device in the hardware operating environment involved in the embodiments of the present invention;

[0055] Figure 2 This is a flowchart illustrating the first embodiment of the mobile routing planning method of the present invention;

[0056] Figure 3 This is a flowchart illustrating the second embodiment of the mobile routing planning method of the present invention;

[0057] Figure 4 This is a schematic diagram of a service delay tree, representing an embodiment of the mobile routing planning method of the present invention.

[0058] Figure 5 This is a structural block diagram of the first embodiment of the mobile routing planning device of the present invention.

[0059] 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

[0060] 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.

[0061] Reference Figure 1 , Figure 1 This is a schematic diagram of the mobile routing planning device structure in the hardware operating environment involved in the embodiments of the present invention.

[0062] like Figure 1 As shown, the mobile routing planning 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 and 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 a high-speed random access memory (RAM) or a 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.

[0063] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the mobile routing planning device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0064] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a mobile routing planning program.

[0065] exist Figure 1In the mobile routing planning 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 the memory 1005 in the mobile routing planning device of the present invention can be set in the mobile routing planning device, and the mobile routing planning device calls the mobile routing planning program stored in the memory 1005 through the processor 1001 and executes the mobile routing planning method provided in the embodiment of the present invention.

[0066] This invention provides a mobile route planning method, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of a mobile routing planning method according to the present invention.

[0067] In this embodiment, the mobile route planning method includes the following steps:

[0068] Step S10: Obtain the overlap degree based on the network performance indicators of each mobile routing node in the wireless swarm intelligence system and the influence characteristics of routing planning, and determine the target performance indicator based on the overlap degree.

[0069] It should be noted that the execution subject of this embodiment is a mobile routing planning device, which has functions such as data processing, data communication and program execution. The mobile routing planning device can be an integrated controller, a control computer or other devices, or other devices with similar functions. This embodiment does not limit the scope of the embodiments.

[0070] It should be understood that a crowdsourcing system is a distributed, decentralized communication system capable of adapting to the current network environment. Overlap rate refers to the rate of overlap between network performance metrics and the influence characteristics of mobile routing node planning, calculated using probability density. Network performance metrics are indicators that measure network performance, including speed, bandwidth, throughput, latency, latency-bandwidth product, round-trip time, and utilization. These can be viewed using commands like `ifconfig` or `ip` to check the network configuration and status. Target performance metrics are those that significantly impact mobile routing node planning.

[0071] In its implementation, the wireless swarm intelligence system comprises several mobile routing nodes, which are connected via a wireless network, preferably a 5G network. When planning the mobile routing nodes, it is necessary to determine the network performance indicators for each node. Therefore, the network performance of each node needs to be tested to obtain its network performance indicators. The probability density is then calculated based on the network performance indicators of each node and their impact on the mobile node network planning. The overlap between these network performance indicators and the impact characteristics of the mobile node network planning is obtained, and the set of network performance indicators with the highest overlap is selected. The network performance indicators in the current set are used as the seed to select the target performance indicators that have a significant impact on the mobile node planning.

[0072] Step S20: Record the network connection status corresponding to the target performance index according to the time series, and perform network slicing on the mobile routing node according to the difference and similarity of the network connection status to obtain the target network slice.

[0073] It should be noted that network slicing is an on-demand networking method that allows operators to separate multiple virtual end-to-end networks on a unified infrastructure. Each network slice is logically isolated from the radio access network to the bearer network and then to the core network to adapt to various types of applications. The degree of difference in network status reflects the topology changes of the entire network.

[0074] In the specific implementation, the current time and the network state corresponding to the target network performance index at that time are recorded. The difference between network states is calculated based on the corresponding network connection states, and network slicing is performed based on the difference, resulting in several network slices. Each network slice is an isolated end-to-end network with its own unique latency, throughput, security, and throughput characteristics, capable of flexibly responding to different needs and services. After obtaining several network slices, the similarity between each network slice is calculated, and the target network slice is selected from the numerous network slices based on the similarity and difference.

[0075] Step S30: Evaluate the service capabilities of each mobile node in the network slice and determine the target node.

[0076] It should be noted that the target node is the mobile node with the most outstanding service capabilities in the network slice. This mobile node is used as the starting node for route planning, and service rights are granted to the target node. Service tasks are sent to the target node, including services such as forwarding data packets and calculation.

[0077] Step S40: Generate a service delay tree based on the service waiting time matched by neighboring nodes for the target node and the service capacity, and obtain the target route plan based on the service delay tree.

[0078] It should be noted that the service delay tree refers to a tree-like communication network constructed according to the service capabilities of each mobile node. The service delay tree can be used as a basis for path planning.

[0079] In the implementation, the service latency and service capacity of each node are determined based on neighboring nodes and the target node. The target node is used as the starting node of the service latency tree. Neighboring nodes are sorted according to their service latency and service capacity. Based on the sorting result, the service latency tree is constructed layer by layer, using the target node as the foundation. The service latency tree includes one target node, one terminal node, and several intermediate neighbor nodes. After the service latency tree is generated, route planning for mobile routing nodes can be performed based on it.

[0080] This embodiment determines the overlap degree by considering the network performance indicators of each mobile routing node in the wireless swarm intelligence system and the influence characteristics of routing planning. Based on this overlap degree, it determines the target performance indicator. It records the network connection status corresponding to the target performance indicator based on time series data, and performs network slicing on the mobile routing nodes according to the differences and similarities in network connection status to obtain target network slices. It evaluates the service capabilities of each mobile node in the network slice to determine the target node. It generates a service delay tree based on the service waiting time and service capabilities matched to the target node by neighboring nodes, and obtains the target routing plan based on the service delay tree. By determining the overlap degree between nodes based on the network performance indicators of each mobile routing node in the wireless swarm intelligence system and the influence characteristics of routing planning, and by slicing the network according to the differences in network connection status and evaluating the capabilities of each network slice, the best target node is selected and routing is planned. This approach solves the problems of high computational complexity, high resource consumption, insufficient resource allocation accuracy, long service response delays, and high bandwidth consumption in the computational process.

[0081] refer to Figure 3 , Figure 3 This is a flowchart illustrating a second embodiment of a mobile routing planning method according to the present invention.

[0082] Based on the first embodiment described above, step S10 of the mobile routing planning method in this embodiment further includes:

[0083] Step S101: Obtain the network performance index set and the influence feature set based on the network performance index and the influence feature;

[0084] Step S102: Obtain the probability density of network performance indicators based on the network performance indicator set;

[0085] Step S103: Obtain the probability density of the influencing features based on the influencing feature set;

[0086] Step S104: Obtain the joint probability density of the network performance indicators and the influence features based on the network performance indicator set and the influence feature set;

[0087] Step S105: Obtain the conditional entropy of the influence feature set on the network performance index set based on the network performance index set and the influence feature set;

[0088] Step S106: Based on the probability density of the network performance index, the probability density of the influencing feature, the joint probability density of the network performance index and the influencing feature, the conditional entropy of the influencing feature set to the network performance index set is obtained to obtain the degree of overlap.

[0089] Step S107: Determine the corresponding set of network performance indicators based on the overlap, and use the network performance indicators in the corresponding set of network performance indicators as the target performance indicators.

[0090] In practical implementation, the network performance metrics of mobile routing nodes are combined into a set to form a network performance metric set, which can be represented as X = {x1, x2, ..., x...} n}, where n represents the total number of network performance metrics. Performance metrics that have a significant impact on mobile routing node planning are selected from the network performance metrics to reduce the time complexity of subsequent calculations. Similarly, the image features of the mobile node network are also combined into a set to form an influence feature set, which can be represented as Y = {y1, y2, ..., y}. m}, where m represents the total number of influencing features. The overlap between X and Y is calculated using the probability density distribution function, and the formula is:

[0091]

[0092] Where H(X,Y) represents the overlap between X and Y, and p(x j ,y i ) represents x j ,y i The joint probability distribution of x j Let y represent the j-th element in set X. i Let p(x) represent the i-th element in set Y. j ) represents x j Marginal probability density, p(y i ) represents y iThe marginal probability density, E(Y|X), represents the conditional entropy of set Y with respect to set X. The categories of network performance indicators in the set X are adjusted to obtain the overlap between sets X and Y containing different network performance indicators. The set of network performance indicators with the highest overlap is selected. The network performance indicators contained in the current set are the final selected performance indicators that have a significant impact on mobile routing node planning, and these performance indicators with a significant impact on mobile routing node planning are taken as target performance indicators.

[0093] Further, the step of recording the network connection status corresponding to the target performance indicator according to the time series, and performing network slicing on the mobile routing node according to the difference and similarity of the network connection status to obtain the target network slice includes:

[0094] The adjacency period of the mobile routing node at any given time and the number of adjacency periods at any given time are obtained based on the network connection status.

[0095] When the number of adjacent time periods at any given time exceeds a preset threshold, the number of all connection edges that the mobile routing node has existed in both network connection states and the number of connection edges that have existed in both network connection states are obtained based on the adjacent time periods.

[0096] The difference in network connection states is obtained based on the number of all connection edges that the mobile routing node has existed in both network connection states, the number of connection edges that have existed in both network connection states, and the time period.

[0097] Several network slices are generated based on the difference, and a target network slice is selected from the network slices based on the similarity.

[0098] In the specific implementation, the difference degree of the current network state is calculated based on the network state. At this point, time information is needed to determine the adjacent time periods, and the number of all existing connection edges in the two network connection states is determined based on the adjacent time periods. The formula for calculating the difference degree is:

[0099]

[0100] Where D represents the degree of difference in network connection state, t∈[1,T], t′ represents the adjacent time interval selected at time t. This represents the number of adjacent time intervals selected at time t. N(E t′ ∪E t′+1 N(E) represents the number of all existing edges in two adjacent network connection states. t′ ∩E t′+1The number of connection edges that have existed in both network connection states at adjacent times is represented by . Based on the network connection states, the adjacency time period of the mobile routing node at any given time is obtained, and the number of adjacency time periods at any given time is determined. If the number of adjacency time periods at any given time is greater than a preset threshold (preferably 2), then the relationship between the current connection edges is obtained. This includes the number of all connection edges that have existed in both network connection states at adjacent times and the number of connection edges that exist in both network connection states. The difference in network states is obtained based on the number of all connection edges that have existed in both network connection states at adjacent times, the number of connection edges that exist in both network connection states, and the time period. Finally, based on the current difference and similarity, a target network slice is selected from several network slices.

[0101] Further, the step of generating several network slices based on the difference and selecting a target network slice from the network slices based on the similarity includes:

[0102] Select one network slice from the plurality of network slices, and obtain the neighborhood set of the adjacent nodes in the network slice;

[0103] The number of nodes is obtained from the neighborhood set;

[0104] Based on the number of nodes, the neighborhood set obtains the similarity of the network slices;

[0105] Repeat the steps of selecting one network slice from the plurality of network slices and obtaining the neighborhood set of the adjacent nodes in the network slice until the similarity of all network slices is obtained;

[0106] The similarity scores are filtered to obtain the maximum similarity score;

[0107] The target network slice is determined based on the maximum similarity.

[0108] In practical implementation, after slicing the network according to the degree of difference, several different network slices are formed. Each network slice contains its own unique network performance. In order to determine the optimal network slice, it is necessary to calculate the degree of difference and similarity of the network connection states corresponding to different network slices. When calculating the similarity, the formula can be used:

[0109]

[0110] Where S represents the similarity of network connection states, Let represent the neighborhood set of the u-th node in the t-th network connection state, where the neighborhood set refers to the set of nodes connected to the current node. Represents the neighborhood set The number of nodes in U represents the total number of nodes, u∈[1,U] This represents the number of nodes in the intersection of the neighborhood set of the u-th node and the neighborhood sets of its neighbors in the t-th network connection state. When calculating similarity, a network slice can be selected from numerous network slices. The neighborhood sets of the adjacent nodes in the current network slice are obtained, along with the number of nodes in each neighborhood set. Based on the number of nodes and the neighborhood sets, the similarity of the current network slice is calculated. This similarity calculation is repeated for each network slice to obtain the similarity for each slice. All similarities are then filtered, and the highest similarity is selected, determining its corresponding network slice. The network slice with the highest similarity is then chosen as the target network slice.

[0111] Furthermore, the step of evaluating the service capabilities of each mobile node in the network slice and determining the target node includes:

[0112] Obtain the service speed and service response time of neighboring nodes;

[0113] Obtain the average number of services provided by neighboring nodes, the successful data packet transmission time, the probability of users consuming resources, the total resources of neighboring nodes, and the remaining resources of neighboring nodes.

[0114] The service delay is calculated based on the average number of services provided by the neighboring nodes, the successful transmission time of the data packet, the probability of the user occupying resources, the total resources of the neighboring nodes, and the remaining resources of the neighboring nodes.

[0115] Effective service time is determined based on service feedback time and service delay.

[0116] The evaluation results are obtained based on the service speed and the effective service time.

[0117] The target node is determined based on the evaluation results.

[0118] In practical implementation, when determining the target node, it is necessary to calculate the service capabilities of each mobile node in the network slice. Before the calculation, it is necessary to obtain the service speed, service response time, average number of services, data packet successful transmission time, user resource occupancy probability, total resources of neighboring nodes, and remaining resources of neighboring nodes for each mobile node. The service capability is then calculated using the following formula:

[0119] sc=r×Γ

[0120] Γ = max{(τ-θ), 0}

[0121]

[0122] Where sc represents the service capacity function of the neighboring node, Γ represents the effective service time, r represents the service speed of the neighboring node, τ represents the service feedback time, i.e., the time period from when the mobile node sends a data packet to when it receives the feedback from the neighboring node after processing is complete, θ represents the service delay, and N U τ represents the average number of users served by neighboring nodes. se The time for successful data packet transmission is represented by tp, the probability of a user consuming resources is represented by tr, the total resources of neighboring nodes are represented by rs, and the remaining resources of neighboring nodes are represented by rs. After calculating the service capabilities of each mobile node, the service capabilities of each mobile node can be sorted by size, and the mobile node with the largest service capability can be selected as the target node.

[0123] Further, the step of generating a service latency tree based on the service wait time matched by neighboring nodes for the target node and the service capability includes:

[0124] The available service quantity of a neighboring node is obtained based on the available service quantity of the neighboring node, the quantified value of the transmission distance, the quantified value of the service waiting time, the quantified value of the service capacity, and the weight ratio.

[0125] The neighboring nodes are sorted according to their available service capacity to obtain the sorting result;

[0126] The service delay tree is generated based on the available service capacity of the target node, the available service capacity of the neighboring nodes, and the sorting result.

[0127] In the specific implementation, refer to Figure 4 , Figure 4 This is a schematic diagram of a service delay tree. A service delay tree is constructed based on the service wait time and service capabilities matched by neighboring nodes for the mobile node. Network resources are then allocated on demand according to this service delay tree. The specific construction process of the service delay tree involves the neighboring nodes allocating or modifying the priority of data packets according to mapping rules, serving queue scheduling and congestion control. The priority mapping function determines the priority of data packets based on the priority field carried by the data packets; higher-priority data packets have priority processing rights. The service wait time required for the data packets sent by the mobile node to the neighboring nodes is determined based on the priority, i.e., the waiting time before the current data packet can begin processing. The transmission distance, service wait time, and service capabilities of the neighboring nodes for the mobile node are used as the basis for constructing the service delay tree, with the mobile node as the root node. Transmission distance, service wait time, and service capabilities are quantified and assigned values ​​based on experiments or expert experience, and weighted ratios are matched. Each neighboring node is ranked for service availability based on the weighted average value, specifically calculated as follows:

[0128]

[0129] Where Afs represents the available service quantity of neighboring nodes, td represents the quantized value of transmission distance, swt represents the quantized value of service latency, sc represents the quantized value of service capacity, and ω1, ω2, and ω3 are all weight ratios. The available service quantities Afs are arranged in descending order to generate a service latency tree.

[0130] Further, generating a service delay tree based on the available service volume of the target node, the available service volume of the neighboring nodes, and the sorting result includes:

[0131] The target node is used as the starting node of the service delay tree, and the number of nodes in the next layer of the service delay tree is determined according to the available service capacity of the target node.

[0132] Based on the sorting result and the number of nodes in the next layer, determine the neighboring nodes of the next layer;

[0133] Based on the available service quantity corresponding to the neighbor node of the next layer, and based on the sorting result and the available service quantity corresponding to the neighbor node of the next layer, determine the next layer neighbor node of the next layer neighbor node, and repeat the steps of determining the next layer neighbor node of the next layer neighbor node based on the available service quantity corresponding to the neighbor node of the next layer and based on the sorting result and the available service quantity corresponding to the neighbor node of the next layer, until the middle node in the sorting result is selected, and the neighbor nodes of each layer are obtained.

[0134] The service delay tree is generated based on the neighbor nodes at each layer.

[0135] In the specific implementation, the available service quantity (Afs) is arranged in descending order. Neighbor nodes whose available service quantity meets the threshold condition are selected as leaf nodes of the second layer of the service latency tree. The available service quantity of the neighbor nodes of the second-layer leaf nodes is calculated according to the available service quantity calculation method, thus obtaining the third-layer leaf nodes. This calculation is iteratively performed until the data packet is transmitted to the terminal node. The resource consumption of all routes from the root node to the terminal node in the service latency tree is used as the service allocation value. The route with short service response latency and low bandwidth consumption is selected as the final routing plan.

[0136] This embodiment improves the accuracy of resource allocation and supports routing decisions for mobile nodes by analyzing the differences and similarities in network connection state changes and the impact of different slice sizes on these differences and similarities. It calculates the service capabilities of neighboring nodes by constructing a service capability model, calculates the available service quantity based on the service waiting time and service capabilities matched by neighboring nodes for mobile nodes, constructs a service latency tree for neighboring nodes based on the available service quantity, and calculates the service allocation value of the service latency tree. This results in routing plans with short service response latency and low bandwidth consumption, solving the problem that traditional cluster server methods cannot adapt to the ever-increasing network service demands and alleviating the issues of long service response latency and high bandwidth consumption.

[0137] Furthermore, embodiments of the present invention also propose a storage medium storing a mobile routing planning program, which, when executed by a processor, implements the steps of the mobile routing planning method described above.

[0138] Reference Figure 5 , Figure 5 This is a structural block diagram of the first embodiment of the mobile routing planning device of the present invention.

[0139] like Figure 5 As shown, the mobile routing planning device proposed in this embodiment of the invention includes:

[0140] The performance determination module 10 is used to obtain the overlap degree based on the network performance indicators of each mobile routing node in the wireless swarm intelligence system and the influence characteristics of routing planning, and to determine the target performance indicator based on the overlap.

[0141] Network slicing module 20 is used to record the network connection status corresponding to the target performance index according to the time series, and to perform network slicing on the mobile routing node according to the difference and similarity of the network connection status to obtain the target network slice;

[0142] The node evaluation module 30 is used to evaluate the service capabilities of each mobile node in the network slice and determine the target node.

[0143] The routing planning module 40 is used to generate a service delay tree based on the service waiting time matched by neighboring nodes for the target node and the service capacity, and to obtain the target routing plan based on the service delay tree.

[0144] This embodiment determines the overlap degree by considering the network performance indicators of each mobile routing node in the wireless swarm intelligence system and the influence characteristics of routing planning. Based on this overlap degree, it determines the target performance indicator. It records the network connection status corresponding to the target performance indicator based on time series data, and performs network slicing on the mobile routing nodes according to the differences and similarities in network connection status to obtain target network slices. It evaluates the service capabilities of each mobile node in the network slice to determine the target node. It generates a service delay tree based on the service waiting time and service capabilities matched to the target node by neighboring nodes, and obtains the target routing plan based on the service delay tree. By determining the overlap degree between nodes based on the network performance indicators of each mobile routing node in the wireless swarm intelligence system and the influence characteristics of routing planning, and by slicing the network according to the differences in network connection status and evaluating the capabilities of each network slice, the best target node is selected and routing is planned. This approach solves the problems of high computational complexity, high resource consumption, insufficient resource allocation accuracy, long service response delays, and high bandwidth consumption in the computational process.

[0145] In one embodiment, the performance determination module 10 is further configured to: obtain a set of network performance indicators and a set of influence features based on the network performance indicators and the influence features; obtain the probability density of network performance indicators based on the set of network performance indicators; obtain the probability density of influence features based on the set of influence features; obtain the joint probability density of the network performance indicators and the influence features based on the set of network performance indicators and the set of influence features; obtain the conditional entropy of the influence feature set on the set of network performance indicators based on the set of network performance indicators and the set of influence features; obtain the overlap degree based on the probability density of the network performance indicators, the probability density of the influence features, the joint probability density of the network performance indicators and the influence features, and the conditional entropy of the influence feature set on the set of network performance indicators; determine the corresponding set of network performance indicators based on the overlap degree; and use the network performance indicators in the corresponding set of network performance indicators as the target performance indicators.

[0146] In one embodiment, the network slicing module 20 is further configured to: obtain the adjacency time period of the mobile routing node at any given time and the number of adjacency time periods at any given time based on the network connection state; when the number of adjacency time periods at any given time is greater than a preset threshold, obtain the number of all connection edges that the mobile routing node has existed in two network connection states and the number of connection edges that have existed in both network connection states based on adjacent times; obtain the difference degree of the network connection state based on the number of all connection edges that the mobile routing node has existed in two network connection states, the number of connection edges that have existed in both network connection states, and the time period; generate a plurality of network slices based on the difference degree; and select a target network slice from the network slices based on the similarity degree.

[0147] In one embodiment, the network slicing module 20 is further configured to select one of the network slices from the plurality of network slices and obtain the neighborhood set of the adjacent nodes in the network slice;

[0148] The number of nodes is obtained from the neighborhood set; based on the number of nodes, the similarity of the network slice is obtained from the neighborhood set; the steps of selecting one network slice from the plurality of network slices and obtaining the neighborhood set of the adjacent nodes in the network slice are repeated until the similarity of all network slices is obtained; the similarity is filtered to obtain the maximum similarity; the target network slice is determined based on the maximum similarity.

[0149] In one embodiment, the node evaluation module 30 is further configured to obtain the service speed and service feedback time of neighboring nodes; obtain the average number of services provided by neighboring nodes, the successful transmission time of data packets, the probability of users occupying resources, the total resources of neighboring nodes, and the remaining resources of neighboring nodes; and obtain the service delay based on the average number of services provided by neighboring nodes, the successful transmission time of data packets, the probability of users occupying resources, the total resources of neighboring nodes, and the remaining resources of neighboring nodes.

[0150] The effective service time is obtained based on the service feedback time and service delay; the evaluation result is obtained based on the service speed and the effective service time; and the target node is determined based on the evaluation result.

[0151] In one embodiment, the routing planning module 40 is further configured to obtain the available service quantity of neighboring nodes based on the available service quantity of neighboring nodes, the quantized value of transmission distance, the quantized value of service waiting time, the quantized value of service capacity, and the weight ratio; sort the neighboring nodes according to their available service quantity to obtain a sorting result; and generate the service delay tree based on the available service quantity of the target node, the available service quantity of the neighboring nodes, and the sorting result.

[0152] In one embodiment, the routing planning module 40 is further configured to: use the target node as the starting node of the service delay tree; determine the number of nodes in the next layer of the service delay tree based on the available service capacity of the target node; determine the neighbor nodes of the next layer based on the sorting result and the number of nodes in the next layer; determine the next-layer neighbor nodes of the next-layer neighbor nodes based on the available service capacity corresponding to the next-layer neighbor nodes, and repeat the steps of determining the next-layer neighbor nodes of the next-layer neighbor nodes based on the available service capacity corresponding to the next-layer neighbor nodes, and repeating the steps of determining the next-layer neighbor nodes of the next-layer neighbor nodes based on the available service capacity corresponding to the next-layer neighbor nodes, until a middle node in the sorting result is selected, thus obtaining the neighbor nodes of each layer; and generate the service delay tree based on the neighbor nodes of each layer.

[0153] 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.

[0154] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0155] 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.

[0156] Furthermore, 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.

[0157] 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.

[0158] 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 (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0159] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A mobile route planning method, characterized in that, The mobile routing planning method is applied to a wireless network swarm intelligence system, which includes several mobile routing nodes. The mobile routing planning method includes: The overlap is obtained based on the network performance indicators of each mobile routing node in the wireless network swarm intelligence system and the influence characteristics of routing planning, and the target performance indicators are determined based on the overlap. The network connection status corresponding to the target performance index is recorded according to the time series. The mobile routing node is then sliced ​​according to the difference and similarity of the network connection status to obtain the target network slice. The service capabilities of each mobile node in the network slice are evaluated to determine the target node; A service delay tree is generated based on the service waiting time matched by neighboring nodes for the target node and the service capabilities. A target route plan is obtained based on the service delay tree. The service delay tree refers to a tree-like communication network constructed according to the service capabilities of each mobile node. The service delay tree can serve as the basis for path planning. The step of recording the network connection status corresponding to the target performance index according to the time series, and performing network slicing on the mobile routing node according to the difference and similarity of the network connection status to obtain the target network slice includes: The adjacency period of the mobile routing node at any given time and the number of adjacency periods at any given time are obtained based on the network connection status. When the number of adjacent time periods at any given time exceeds a preset threshold, the number of all connection edges that the mobile routing node has existed in both network connection states and the number of connection edges that have existed in both network connection states are obtained based on the adjacent time periods. The difference in network connection states is obtained based on the number of all connection edges that the mobile routing node has existed in both network connection states, the number of connection edges that have existed in both network connection states, and the time period. The formula for calculating the difference is as follows: in, Indicates the degree of difference in network connectivity status. , , This represents the adjacent time interval selected at time t. This represents the number of adjacent time intervals selected at time t. , This represents the number of all existing connection edges in two adjacent network connection states. This represents the number of connection edges that exist in both network connection states at adjacent time points; Several network slices are generated based on the difference, and a target network slice is selected from the network slices based on the similarity. The step of generating several network slices based on the difference and selecting a target network slice from the network slices based on the similarity includes: Select one network slice from the plurality of network slices, and obtain the neighborhood set of the adjacent nodes in the network slice; The number of nodes is obtained from the neighborhood set; Based on the number of nodes, the neighborhood set obtains the similarity of the network slice, and the formula for calculating the similarity is: in, Indicates the similarity of network connection states. Let represent the neighborhood set of the u-th node in the t-th network connection state, where the neighborhood set refers to the set of nodes connected to the current node. Represents the neighborhood set The number of nodes in , This represents the total number of all nodes. , This represents the number of nodes in the intersection of the neighborhood set of the u-th node and the neighborhood sets of its neighbors in the t-th network connection state. Repeat the steps of selecting one network slice from the plurality of network slices and obtaining the neighborhood set of the adjacent nodes in the network slice until the similarity of all network slices is obtained; The similarity scores are filtered to obtain the maximum similarity score; The target network slice is determined based on the maximum similarity. The step of generating a service latency tree based on the service wait time matched by neighboring nodes for the target node and the service capability includes: The available service quantity of a neighboring node is obtained based on the available service quantity of the neighboring node, the quantified value of the transmission distance, the quantified value of the service waiting time, the quantified value of the service capacity, and the weight ratio. The neighboring nodes are sorted according to their available service capacity to obtain the sorting result; The service delay tree is generated based on the available service capacity of the target node, the available service capacity of the neighboring nodes, and the sorting result. The step of generating a service delay tree based on the available service capacity of the target node, the available service capacity of the neighboring nodes, and the sorting result includes: The target node is used as the starting node of the service delay tree, and the number of nodes in the next layer of the service delay tree is determined according to the available service capacity of the target node. Based on the sorting result and the number of nodes in the next layer, determine the neighboring nodes of the next layer; Based on the available service quantity corresponding to the neighbor node of the next layer, and based on the sorting result and the available service quantity corresponding to the neighbor node of the next layer, determine the next layer neighbor node of the next layer neighbor node, and repeat the steps of determining the next layer neighbor node of the next layer neighbor node based on the available service quantity corresponding to the neighbor node of the next layer and based on the sorting result and the available service quantity corresponding to the neighbor node of the next layer, until the middle node in the sorting result is selected, and the neighbor nodes of each layer are obtained. The service delay tree is generated based on the neighbor nodes at each layer.

2. The method as described in claim 1, characterized in that, The process of obtaining the overlap degree based on the network performance indicators of each mobile routing node in the wireless network swarm intelligence system and the impact characteristics of routing planning, and determining the target performance indicator based on the overlap degree, includes: Based on the network performance indicators and the impact characteristics, a set of network performance indicators and a set of impact characteristics are obtained; The probability density of network performance indicators is obtained based on the set of network performance indicators; The probability density of the influencing features is obtained based on the influencing feature set; The joint probability density of the network performance indicators and the influence features is obtained based on the network performance indicator set and the influence feature set. The conditional entropy of the influence feature set on the network performance index set is obtained based on the network performance index set and the influence feature set. Based on the probability density of the network performance index, the probability density of the influencing feature, the joint probability density of the network performance index and the influencing feature, the overlap degree of the influencing feature set with the conditional entropy of the network performance index set is obtained. Based on the overlap, a corresponding set of network performance indicators is determined, and the network performance indicators in the corresponding set of network performance indicators are used as target performance indicators.

3. The method as described in claim 1, characterized in that, The step of evaluating the service capabilities of each mobile node in the network slice and determining the target node includes: Obtain the service speed and service response time of neighboring nodes; Obtain the average number of services provided by neighboring nodes, the successful data packet transmission time, the probability of users consuming resources, the total resources of neighboring nodes, and the remaining resources of neighboring nodes. The service delay is calculated based on the average number of services provided by the neighboring nodes, the successful transmission time of the data packet, the probability of the user occupying resources, the total resources of the neighboring nodes, and the remaining resources of the neighboring nodes. Effective service time is determined based on service feedback time and service delay. The evaluation results are obtained based on the service speed and the effective service time. The target node is determined based on the evaluation results.

4. A mobile route planning device, characterized in that, The mobile routing planning device includes: The performance determination module is used to obtain the overlap degree based on the network performance indicators of each mobile routing node in the wireless network swarm intelligence system and the influence characteristics of routing planning, and to determine the target performance indicator based on the overlap. The network slicing module is used to record the network connection status corresponding to the target performance index according to the time series, and to perform network slicing on the mobile routing node according to the difference and similarity of the network connection status to obtain the target network slice; The node evaluation module is used to evaluate the service capabilities of each mobile node in the network slice and determine the target node. The routing planning module is used to generate a service delay tree based on the service waiting time matched by neighboring nodes for the target node and the service capabilities, and to obtain the target route plan based on the service delay tree. The service delay tree refers to a tree-like communication network for network communication constructed according to the service capabilities of each mobile node, and the service delay tree can be used as the basis for path planning. The step of recording the network connection status corresponding to the target performance index according to the time series, and performing network slicing on the mobile routing node according to the difference and similarity of the network connection status to obtain the target network slice includes: The adjacency period of the mobile routing node at any given time and the number of adjacency periods at any given time are obtained based on the network connection status. When the number of adjacent time periods at any given time exceeds a preset threshold, the number of all connection edges that the mobile routing node has existed in both network connection states and the number of connection edges that have existed in both network connection states are obtained based on the adjacent time periods. The difference in network connection states is obtained based on the number of all connection edges that the mobile routing node has existed in both network connection states, the number of connection edges that have existed in both network connection states, and the time period. The formula for calculating the difference is as follows: in, Indicates the degree of difference in network connectivity status. , , This represents the adjacent time interval selected at time t. This represents the number of adjacent time intervals selected at time t. , This represents the number of all existing connection edges in two adjacent network connection states. This represents the number of connection edges that exist in both network connection states at adjacent time points; Several network slices are generated based on the difference, and a target network slice is selected from the network slices based on the similarity. The step of generating several network slices based on the difference and selecting a target network slice from the network slices based on the similarity includes: Select one network slice from the plurality of network slices, and obtain the neighborhood set of the adjacent nodes in the network slice; The number of nodes is obtained from the neighborhood set; Based on the number of nodes, the neighborhood set obtains the similarity of the network slice, and the formula for calculating the similarity is: in, Indicates the similarity of network connection states. Let represent the neighborhood set of the u-th node in the t-th network connection state, where the neighborhood set refers to the set of nodes connected to the current node. Represents the neighborhood set The number of nodes in , This represents the total number of all nodes. , This represents the number of nodes in the intersection of the neighborhood set of the u-th node and the neighborhood sets of its neighbors in the t-th network connection state. Repeat the steps of selecting one network slice from the plurality of network slices and obtaining the neighborhood set of the adjacent nodes in the network slice until the similarity of all network slices is obtained; The similarity scores are filtered to obtain the maximum similarity score; The target network slice is determined based on the maximum similarity. The step of generating a service latency tree based on the service wait time matched by neighboring nodes for the target node and the service capability includes: The available service quantity of a neighboring node is obtained based on the available service quantity of the neighboring node, the quantified value of the transmission distance, the quantified value of the service waiting time, the quantified value of the service capacity, and the weight ratio. The neighboring nodes are sorted according to their available service capacity to obtain the sorting result; The service delay tree is generated based on the available service capacity of the target node, the available service capacity of the neighboring nodes, and the sorting result. The step of generating a service delay tree based on the available service capacity of the target node, the available service capacity of the neighboring nodes, and the sorting result includes: The target node is used as the starting node of the service delay tree, and the number of nodes in the next layer of the service delay tree is determined according to the available service capacity of the target node. Based on the sorting result and the number of nodes in the next layer, determine the neighboring nodes of the next layer; Based on the available service quantity corresponding to the neighbor node of the next layer, and based on the sorting result and the available service quantity corresponding to the neighbor node of the next layer, determine the next layer neighbor node of the next layer neighbor node, and repeat the steps of determining the next layer neighbor node of the next layer neighbor node based on the available service quantity corresponding to the neighbor node of the next layer and based on the sorting result and the available service quantity corresponding to the neighbor node of the next layer, until the middle node in the sorting result is selected, and the neighbor nodes of each layer are obtained. The service delay tree is generated based on the neighbor nodes at each layer.

5. A mobile route planning device, characterized in that, The device includes: a memory, a processor, and a mobile routing planning program stored in the memory and executable on the processor, the mobile routing planning program being configured to implement the steps of the mobile routing planning method as described in any one of claims 1 to 3.

6. A storage medium, characterized in that, The storage medium stores a mobile routing planning program, which, when executed by a processor, implements the steps of the mobile routing planning method as described in any one of claims 1 to 3.

Images