Cross-domain multi-system networking measurement and control topology optimization method based on group switching and related equipment

Abstract

The embodiment of the invention provides a cross-domain multi-system networking measurement and control topology optimization method based on group switching and related equipment, and relates to the technical field of heterogeneous measurement and control network topology optimization, and the method comprises the steps: sensing the prior information of each heterogeneous node, and carrying out the grouping processing of the heterogeneous nodes based on the prior information, a plurality of heterogeneous node groups are obtained; performing node screening on each heterogeneous node group; determining an initial topological configuration based on a node screening result; in each time slice, judging whether the connectivity among the nodes in each heterogeneous node group is changed or not; if yes, node screening is carried out again, and group switching is carried out; and converting the initial topological configuration based on a group switching result until an optimal topological configuration meeting the measurement and control precision requirement is obtained. According to the technical scheme, topological optimization of the heterogeneous measurement and control network can be realized, the power consumption of each heterogeneous node is reduced, and the operation efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of heterogeneous measurement and control network topology optimization, and in particular to a cross-domain multi-system networking measurement and control topology optimization method based on group switching and related equipment. Background Art

[0002] With the widespread use of heterogeneous unmanned platforms with different measurement and control systems and communication capabilities, such as collaboration between satellites, drones, unmanned vehicles, and unmanned ships, the integrated heterogeneous network of air, land, and sea will profoundly change the application mode of unmanned platforms in the future. The topological structure of heterogeneous networks is affected by many factors, some of which are controllable, such as the transmission power and antenna direction of the node, and others, such as terrain, weather, noise, and movement trajectory, are uncontrollable factors.

[0003] The complex and changeable environment makes heterogeneous nodes susceptible to external interference. In addition, mobility or node damage and failure will affect the change of network connectivity. When using traditional topology optimization technology for topology reconstruction, there will be the following problems and defects:

[0004] (1) Due to the different mobility characteristics, measurement and control systems, and antenna fields of view of nodes in heterogeneous networks, large-scale nodes will not be able to successfully establish links due to mismatches when establishing and dismantling links, resulting in huge signaling overhead and unnecessary signaling loss.

[0005] (2) The locations of some dynamic heterogeneous nodes are constantly changing. Methods such as introducing additional relay nodes or controlling the movement of nodes to ensure network connectivity are not well suited to this scenario, and thus the positioning accuracy of the heterogeneous measurement and control network cannot be guaranteed.

[0006] (3) Due to the special constraints of heterogeneous measurement and control networks, traditional large-scale link switching technologies, including switching schemes based on received signal strength (RSS), switching schemes based on QoS, and switching schemes based on graph theory, cannot fully meet the requirements. Summary of the invention

[0007] The embodiments of the present application provide a cross-domain multi-system networking measurement and control topology optimization method and related equipment based on group switching to solve the technical problems existing in the prior art.

[0008] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0009] According to a first aspect of an embodiment of the present application, a cross-domain multi-system networking measurement and control topology optimization method based on group switching is provided, which is applied to a dynamic heterogeneous measurement and control network, and is characterized in that the method includes:

[0010] Perceiving the prior information of each heterogeneous node, the prior information includes: heterogeneous node location, antenna field of view, node mobility, node remaining energy resources and measurement and control system;

[0011] Based on the prior information, the heterogeneous nodes are grouped to obtain a plurality of heterogeneous node groups;

[0012] Perform node screening on each heterogeneous node group;

[0013] Determine the initial topology configuration based on the node screening result;

[0014] In each time slice, determine whether the connectivity between nodes in each heterogeneous node group has changed;

[0015] If yes, the nodes are screened again and group switching is performed;

[0016] The initial topology configuration is transformed based on the group switching result until an optimal topology configuration that meets the measurement and control accuracy requirement is obtained.

[0017] In some embodiments of the present application, based on the above solution, the heterogeneous nodes are grouped based on the prior information to obtain multiple heterogeneous node groups, including:

[0018] Divide nodes with the same measurement and control system into the same heterogeneous node group;

[0019] The heterogeneous node with the largest number of node remaining energy resources and neighboring nodes that can be linked is selected as the leader node of the heterogeneous node group.

[0020] In some embodiments of the present application, based on the above solution, the confirmation process of the group leader node further includes:

[0021] The remaining energy of the node and the number of neighboring nodes that the node can link to are normalized and weighted;

[0022] The weights of the nodes in each group are calculated and sorted in descending order, with the first-ranked node being the group leader node and the second-ranked node being the backup group leader node.

[0023] In some embodiments of the present application, based on the above solution, the node screening of each heterogeneous node group includes:

[0024] Make judgments based on the measurement and control system of the nodes in the current heterogeneous node group, the antenna field of view, and the remaining energy resources of the nodes;

[0025] If two heterogeneous nodes have the same measurement and control system and can be matched, their antenna fields of view are interoperable, and the energy resources of the remaining nodes meet the requirements for link building, then these two heterogeneous nodes are selected as nodes in the group that can be linked;

[0026] Make judgments based on the current measurement and control system of each cluster leader node, antenna field of view, and remaining energy resources of the node;

[0027] If two cluster head nodes have the same measurement and control system and can achieve matching, their antenna fields of view are interoperable, and the energy resources of the remaining nodes meet the requirements for link building, then these two cluster head nodes will be selected as cluster head nodes that can build a link.

[0028] In some embodiments of the present application, based on the above solution, the determining of the initial topology configuration based on the node screening result includes:

[0029] Introducing an intelligent decision-making model into the dynamic heterogeneous measurement and control network;

[0030] According to the state S of the current node, action A is set as the next node set that can establish a link with the node, where the state S of the current node includes: the intersection of the measurement and control systems between the node and its candidate link-building nodes, the intersection with the antenna field of view, the current energy state of the node, the target node temporarily linking with the node, and the connectivity of the current node;

[0031] Set a reward function r determined by the energy consumption between links, the connectivity of nodes and the geometric reduction of precision factor GDOP to jointly determine the operation of the intelligent decision-making model;

[0032] The intelligent agent of the intelligent decision-making model interacts with the global information of the dynamic heterogeneous measurement and control network nodes and trains the decision-making model, and finally outputs the initial topology configuration.

[0033] In some embodiments of the present application, based on the above solution, the group switching includes:

[0034] If the connectivity of the current heterogeneous node changes, the current heterogeneous node sends a switching request to the destination node based on node screening again;

[0035] The destination node confirms the acceptance of the switching request and sends a confirmation message back to the current heterogeneous node that initiated the switching request;

[0036] After receiving the confirmation message, the current heterogeneous node encapsulates the relevant access information in the switching command, and the group node members execute the switching according to the information in the switching command.

[0037] In some embodiments of the present application, based on the above solution, it also includes:

[0038] The dynamic heterogeneous measurement and control network establishes a tree-like logical transmission topology with the cluster head as the root node and the nodes within the cluster as leaves and intermediate nodes;

[0039] The cluster head node collects the prior information collected by the nodes in the cluster in real time, and places the decision of network link group switching in the cluster head node for centralized processing;

[0040] The group leader node sends the decision result to the nodes in the group, instructing the nodes in the group to perform the group switching operation according to the instructions;

[0041] Each node in the group adjusts the antenna power settings and antenna angles of each node according to the received instructions for distributed processing and performs group switching.

[0042] According to a second aspect of an embodiment of the present application, a cross-domain multi-system networking measurement and control topology optimization device based on group switching is provided, comprising:

[0043] A sensing unit, used to sense the prior information of each heterogeneous node, the prior information including: heterogeneous node location, antenna field of view, node mobility, node remaining energy resources and measurement and control system;

[0044] A processing unit, configured to perform grouping processing on the heterogeneous nodes based on the prior information to obtain a plurality of heterogeneous node groups;

[0045] A screening unit, used for performing node screening;

[0046] A determination unit, used for determining an initial topology configuration based on a node screening result;

[0047] A judgment unit, used to judge whether the connectivity between nodes in each heterogeneous node group has changed in each time slice;

[0048] A switching unit, used for performing group switching;

[0049] The transformation unit is used to transform the initial topology configuration based on the group switching result until an optimal topology configuration that meets the measurement and control accuracy requirement is obtained.

[0050] According to a third aspect of an embodiment of the present application, a computer-readable storage medium is provided, wherein the storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer executes the method according to the first aspect above.

[0051] According to a fourth aspect of the embodiments of the present application, there is provided an electronic device, including: a memory and a processor;

[0052] The memory is used to store computer instructions;

[0053] The processor is used to call the computer instructions stored in the memory so that the electronic device executes the method as described in the first aspect above.

[0054] The technical solution of the present application utilizes the idea of ​​cluster processing and group switching in group switching, and through reasonable topology link building planning, transforms the traditional situation where there is no constraint on the geographical location characteristics, mobility characteristics, measurement and control system and antenna field of view of clustered heterogeneous nodes to a situation where only sparse link switching within the specified group range is required to complete the reconstruction of the measurement and control network topology, thereby improving the success rate of link building, reducing the number of link building attempts and unnecessary signaling consumption, and ensuring the normal operation of system measurement and control.

[0055] The technical solution of the present application, by making full use of the intelligent analysis and decision-making capabilities of the cluster leader node and the real-time data collection and execution capabilities of the nodes within the cluster, this center + edge distributed deployment method significantly accelerates the model distribution process, improves computing power and reduces the system burden, and realizes intelligent optimization management of the measurement and control network topology.

[0056] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0058] Figure 1 A schematic diagram of a process of a cross-domain multi-system networking measurement and control topology optimization method based on group switching according to an embodiment of the present application is shown;

[0059] Figure 2 A flowchart of a cross-domain multi-system networking measurement and control topology optimization method based on group switching in Example 1 of the present application is shown;

[0060] Figure 3 A flowchart showing an implementation method of steps 1031 to 1033 in Embodiment 1 of the present application is shown;

[0061] Figure 4 A flowchart showing an implementation method of steps 1034 to 1036 in Embodiment 1 of the present application is shown;

[0062] Figure 5 A flowchart showing an implementation method of step 105 in embodiment 1 of the present application is shown;

[0063] Figure 6 A flowchart showing an implementation method of step 106 in embodiment 1 of the present application is shown;

[0064] Figure 7 A schematic diagram of a theoretical model of a cross-domain multi-system networking measurement and control system according to Example 1 of the present application is shown;

[0065] Figure 8 A schematic diagram of group head selection in the grouping process according to step 102 in embodiment 1 of the present application is shown;

[0066] Fig. 9 A schematic diagram of switching the measurement and control network group according to step 105 in embodiment 1 of the present application is shown;

[0067] Fig.10 A schematic diagram of a deep reinforcement learning model according to steps 210-215 in Example 2 of the present application is shown;

[0068] Fig.11 A schematic diagram of a centralized-distributed tree aggregation model of measurement and control network computing power in Example 3 of the present application is shown;

[0069] Fig.12 A block diagram of a cross-domain multi-system networking measurement and control topology optimization device based on group switching according to an embodiment of the present application is shown;

[0070] Fig.13 A block diagram of an electronic device according to an embodiment of the present application is shown;

[0071] Fig.14 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0072] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0073] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0074] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0075] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0076] It should be noted that the “plurality” mentioned in this article refers to two or more.

[0077] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0078] Some embodiments of the present application will be described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments may be combined with each other.

[0079] In view of the problem that the network positioning accuracy cannot be guaranteed in a heterogeneous measurement and control network system with a satellite communication network as the core and integrated air, ground and sea networks due to external interference, mobility, or changes in network connectivity caused by node damage and failure, the present application proposes a cross-domain multi-system networking measurement and control topology optimization method based on group switching. The method uses the characteristics of group processing and group switching to plan topology reconstruction and realize a fast group switching process of link establishment and dismantling, while ensuring the measurement and control accuracy and reasonable consumption of resources, and divides the functions of the topology decision and execution process, and deploys them in a "center + edge distributed" manner to achieve low power consumption and efficient computing of each node.

[0080] See also Figure 1 , shows a flow chart of a method for optimizing cross-domain multi-system networking measurement and control topology based on group switching according to an embodiment of the present application.

[0081] like Figure 1 As shown, a cross-domain multi-system networking measurement and control topology optimization method based on group switching is demonstrated, which is applied to a dynamic heterogeneous measurement and control network. The method includes steps S100 to S700.

[0082] It should be noted that the dynamic heterogeneous measurement and control network is an integrated air-space-ground-sea network for the battlefield, composed of different types of heterogeneous nodes such as satellites, drone clusters, unmanned vehicles, and unmanned ships.

[0083] Step S100, sensing the prior information of each heterogeneous node, the prior information includes: heterogeneous node location, antenna field of view, node mobility, node remaining energy resources and measurement and control system.

[0084] Continue to refer Figure 1 , step S200, clustering the heterogeneous nodes based on the prior information to obtain multiple heterogeneous node groups.

[0085] In some feasible embodiments, based on the above solution, the heterogeneous nodes are grouped based on the prior information to obtain multiple heterogeneous node groups, including:

[0086] Divide nodes with the same measurement and control system into the same heterogeneous node group;

[0087] The heterogeneous node with the largest number of node remaining energy resources and neighboring nodes that can be linked is selected as the leader node of the heterogeneous node group.

[0088] In some embodiments of the present application, based on the above solution, in order to prevent the cluster head node from malfunctioning or being damaged due to external interference, the cluster head node confirmation process further includes:

[0089] The remaining energy of the node and the number of neighboring nodes that the node can link to are normalized and weighted;

[0090] The weights of the nodes in each group are calculated and sorted in descending order, with the first-ranked node being the group leader node and the second-ranked node being the backup group leader node.

[0091] When the group leader node is not damaged, the backup group leader will be regarded as a common node in the group and interconnected with other nodes. Only when the group leader node is damaged, the backup group leader will play a role.

[0092] At this moment, the remaining nodes immediately establish a connection with the group leader based on the selection of nodes that can be linked, to avoid the entire network being paralyzed due to network interference.

[0093] Continue to refer Figure 1 , step S300, performing node screening on each heterogeneous node group.

[0094] It can be understood that this step is to screen out nodes that can build a chain.

[0095] In some feasible embodiments, based on the above solution, the node screening of each heterogeneous node group includes:

[0096] Make judgments based on the measurement and control system of the nodes in the current heterogeneous node group, the antenna field of view, and the remaining energy resources of the nodes;

[0097] If two heterogeneous nodes have the same measurement and control system and can be matched, their antenna fields of view are interoperable, and the energy resources of the remaining nodes meet the requirements for link building, then these two heterogeneous nodes are selected as nodes in the group that can be linked;

[0098] Make judgments based on the current measurement and control system of each cluster leader node, antenna field of view, and remaining energy resources of the node;

[0099] If two cluster head nodes have the same measurement and control system and can achieve matching, their antenna fields of view are interoperable, and the energy resources of the remaining nodes meet the requirements for link building, then these two cluster head nodes will be selected as cluster head nodes that can build a link.

[0100] Continue to refer Figure 1 , step S400, determining an initial topology configuration based on the node screening result.

[0101] In some feasible embodiments, based on the above solution, determining the initial topology configuration based on the node screening result includes:

[0102] Introducing an intelligent decision-making model into the dynamic heterogeneous measurement and control network;

[0103] According to the state S of the current node, action A is set as the next node set that can establish a link with the node, where the state S of the current node includes: the intersection of the measurement and control systems between the node and its candidate link-building nodes, the intersection with the antenna field of view, the current energy state of the node, the target node temporarily linking with the node, and the connectivity of the current node;

[0104] Set a reward function r determined by the energy consumption between links, the connectivity of nodes and the geometric reduction of precision factor GDOP to jointly determine the operation of the intelligent decision-making model;

[0105] The intelligent agent of the intelligent decision-making model interacts with the global information of the dynamic heterogeneous measurement and control network nodes and trains the decision-making model, and finally outputs the initial topology configuration.

[0106] Continue to refer Figure 1 , step S500, in each time slice, determining whether the connectivity between nodes in each heterogeneous node group changes.

[0107] It is understandable that the connectivity between nodes in each heterogeneous node group should meet the minimum connectivity requirement.

[0108] Continue to refer Figure 1 , step S600, if yes, perform node screening again and perform group switching.

[0109] It can be understood that the node screening method performed in this step is the same as the node screening method performed in step S300.

[0110] In some feasible embodiments, based on the above solution, the group switching includes:

[0111] If the connectivity of the current heterogeneous node changes, the current heterogeneous node sends a switching request to the destination node based on node screening again;

[0112] The destination node confirms the acceptance of the switching request and sends a confirmation message back to the current heterogeneous node that initiated the switching request;

[0113] After receiving the confirmation message, the current heterogeneous node encapsulates the relevant access information in the switching command, and the group node members execute the switching according to the information in the switching command.

[0114] It can be understood that when all nodes are switched to a new connection state, it indicates that the group switching is completed.

[0115] It is understandable that if the connectivity does not change, the link between the nodes is maintained and no switching is performed.

[0116] Continue to refer Figure 1 , step S700, transforming the initial topology configuration based on the group switching result until an optimal topology configuration that meets the measurement and control accuracy requirement is obtained.

[0117] In some feasible embodiments, based on the above-mentioned solution, this embodiment provides a topology decision and execution process function segmentation and deployment solution, specifically:

[0118] The dynamic heterogeneous measurement and control network establishes a tree-like logical transmission topology with the cluster head as the root node and the nodes within the cluster as leaves and intermediate nodes;

[0119] The cluster head node collects the prior information collected by the nodes in the cluster in real time, and places the decision of network link group switching in the cluster head node for centralized processing;

[0120] The group leader node sends the decision result to the nodes in the group, instructing the nodes in the group to perform the group switching operation according to the instructions;

[0121] Each node in the group adjusts the antenna power settings and antenna angles of each node according to the received instructions for distributed processing and performs group switching.

[0122] Some examples are provided below.

[0123] Example 1

[0124] This embodiment provides a cross-domain multi-system networking measurement and control topology optimization method based on group switching, which is applied to battlefield-oriented scenarios of air-space-ground-sea heterogeneous node networking measurement and control topology, such as Figure 2 As shown, the measurement and control topology optimization method includes:

[0125] Step 101, the heterogeneous network perceives the prior information of each node;

[0126] Step 102: Grouping heterogeneous nodes;

[0127] Step 103: Screen nodes that can be chained;

[0128] Step 104: Switch application condition determination;

[0129] Step 105: When the switching condition is met, group switching is performed;

[0130] Step 106: Output the optimal topological configuration result.

[0131] In this embodiment, if step 104 determines that the switching application condition is not satisfied, step 105 is not executed, and step 106 is necessary.

[0132] In this embodiment, the current optimal topological configuration result is output in step 106, and it is necessary to periodically return to step 103 to continue screening and judging.

[0133] In this embodiment, in order to fully screen the nodes that can be linked, Figure 3 and Figure 4 As shown, step 103 specifically includes:

[0134] Step 1031: determine whether the measurement and control systems and antenna fields of view of the nodes in each group are matched, and whether the remaining energy resources of the nodes meet the requirements for link establishment;

[0135] Step 1032: If the nodes in two groups have the same measurement and control system, their antenna fields of view are interoperable, and the energy resources of the remaining nodes meet the requirements for link establishment, the nodes in the group that can establish a link are selected;

[0136] Step 1033: If any of the measurement and control system, antenna field of view and remaining energy resources between the nodes in the two groups do not meet the requirements, they will not be included in the screening range of the nodes that can be linked.

[0137] Step 1034: determine whether the measurement and control systems and antenna fields of view of each cluster leader node are matched, and whether the remaining energy resources of the node meet the link establishment requirements;

[0138] Step 1035: If the two cluster head nodes have the same measurement and control system, their antenna fields of view are interoperable, and the energy resources of the remaining nodes meet the requirements for link establishment, the cluster head node that can establish a link is selected;

[0139] Step 1036: If any of the measurement and control system, antenna field of view and remaining energy resources between the two cluster head nodes do not meet the requirements, they will not be included in the screening range of the nodes that can be linked.

[0140] Among them, step 1032 and step 1033 are in an either-or relationship. If step 1032 is executed, step 1033 is optional. If step 1033 is not executed, step 1033 is required.

[0141] Among them, step 1035 and step 1036 are in an either-or relationship. If step 1035 is executed, step 1036 is optional. If step 1035 is not executed, step 1036 is required.

[0142] In this embodiment, in order to ensure the normal switching of the measurement and control network group, Figure 5 As shown, step 105 specifically includes:

[0143] Step 1051: determine whether the connectivity of the node has changed;

[0144] Step 1052: If the connectivity has changed, the current node sends a switching request to the destination node;

[0145] Step 1053: The destination node confirms acceptance of the switching request and sends a confirmation message to the node that initiated the switching request, indicating that it is ready to receive the switching;

[0146] Step 1054: After receiving the switching reply information, the destination node encapsulates the related access information in the switching command, and the group node members execute the switching according to the information in the switching command;

[0147] Step 1055: When all nodes are switched to the new connection state, the group switching is completed;

[0148] Step 1056: If the connectivity has not changed, the link between the nodes is maintained.

[0149] Among them, when it is determined in step 1051 that the connectivity of the node has changed, steps 1052, 1053, 1054, and 1055 are required, and step 1056 is not required. When it is determined in step 1051 that the connectivity of the node has not changed, step 1056 is required, and steps 1052, 1053, 1054, and 1055 are not required.

[0150] In this embodiment, in order to ensure the measurement and control accuracy and low energy consumption of the reconstructed measurement and control network topology, Figure 6 As shown, step 106 specifically includes:

[0151] Step 1061, setting the state S of the current node, including: the intersection of the measurement and control systems between the node and its candidate link-building nodes, the intersection with the antenna field of view, the current energy state of the node, the target node for temporarily linking with the node, and the connectivity of the node;

[0152] Step 1062, set action A as the next node set that can establish a link with the node;

[0153] Step 1063: Set a reward function r determined by the energy consumption between links, the connectivity of the nodes and the geometric reduction of precision factor GDOP.

[0154] Step 1064: operate the intelligent decision-making model and output the optimal topology.

[0155] In this embodiment, there are 6 types of heterogeneous nodes included in the integrated heterogeneous measurement and control network of air, land, and sea, namely: drones, airships, unmanned vehicles, unmanned ships, high-altitude balloon clusters, and satellite networks. In the initial state, the same measurement and control system is divided into the same unmanned cluster for group processing. The head of each group is a multi-mode node, and the nodes of the satellite network are all regarded as the head node. The measurement and control system, antenna field of view, and node residual energy resources of the group and the head node are screened and linked respectively, and the initial state of the constructed topology is as follows: Figure 7 shown.

[0156] In this embodiment, in order to prevent the cluster head node from malfunctioning or being damaged due to external interference, the cluster head is selected as follows: Figure 8 As shown, the specific steps are as follows:

[0157] The remaining energy of the node and the number of neighboring nodes that the node can link to are normalized and weighted.

[0158] The weights of the nodes in each group are calculated and sorted from large to small. The first two group heads are selected as multi-mode nodes, and one of them is used as a backup group head.

[0159] When the group leader node is not damaged, the backup group leader will be regarded as a common node in the group and interconnected with other nodes. Only when the group leader node is damaged, the backup group leader will play a role.

[0160] At this moment, the remaining nodes immediately establish a connection with the group leader based on the selection of nodes that can be linked, to avoid the entire network being paralyzed due to network interference.

[0161] In this embodiment, step 105 monitors and controls the group switching process caused by the change in the connectivity of the nodes in the network, such as Fig. 9 As shown, the details are as follows:

[0162] In the current group A, during the movement of nodes A1 and A2, the link-building field of view between A2 and the group leader A3 does not match, resulting in the inability to build a link, and the connectivity of the nodes changes;

[0163] In order to ensure the accuracy of node measurement and control, the minimum connectivity is set to 2, and considering the energy consumption of the node, the optimal topology configuration of group A is reconstructed based on the current linkable nodes;

[0164] During this process, the connection between nodes A4 and A3 is switched to A1, the connection between A5 and A3 is disconnected, and a link is re-established between A3 and A1 to ensure the measurement, control and positioning;

[0165] The nodes in group B do not meet the switching application decision conditions, the links between the nodes remain unchanged, and no switching occurs.

[0166] Example 2

[0167] This embodiment shows how to introduce specific parameters into the process for calculation and representation. This embodiment provides a specific case of implementing a cross-domain multi-system networking measurement and control topology optimization method based on group switching, and further illustrates the method of the present invention. The case of an integrated heterogeneous measurement and control network with six types of heterogeneous nodes is still used. The topology configuration is as follows: Figure 7 As shown, the details are as follows:

[0168] Step 201: Nodes of different heterogeneous networks are distributed in different spaces. The network topology of each time slice t can be considered as an undirected connected graph G = (V, E t ), where V includes all heterogeneous nodes, E t Including all connections in the current time slice. First, perceive the prior information of each arbitrary node u in the heterogeneous network, including the node type N u 、Position of heterogeneous nodes u 、Antenna field of view θ u Node mobility: moving speed V u With angle ψ u , node remaining energy resources E res , Measurement and control system category M u .

[0169] Step 202: Group the heterogeneous network and divide the homogeneous platforms with the same measurement and control system into the same unmanned cluster, using group N. i (i=1,2,…,6) represents.

[0170] Step 203: Any node u in each group transmits with maximum transmission power P max Determine the number of neighbor nodes within the communication rangeu , and combined with the node residual energy E u , calculate W according to the weighted method u =w1×Num u +w2×Num u Sort the nodes and select W u The node with the largest value is the group leader, and the node with the second-best value is the backup relay node. The group leaders are all multi-mode nodes, which means that the node supports multiple measurement and control systems, namely: u |>1.

[0171] Step 204: First, in each time slice t, determine whether the measurement and control system and antenna field of view of each group of nodes intersect, that is, M u ∩M u ≠Φ,θ u ∩θ u ≠Φ, if there is an intersection, the nodes that can be linked can be screened.

[0172] Step 205: At the same time, determine whether the remaining energy resources of the node meet the link building requirements. The total energy consumption E of any node u in the tth time slot u It mainly consists of three parts: data transmission energy consumption E tr , link switching energy consumption E s , and other inherent energy consumption E c , that is, satisfying: E u =E tr +E s +E c , filter the remaining energy resource E of node u res ≥E u The set of nodes that can be linked is Set u .

[0173] Step 206: Data transmission energy consumption E tr Affected by signal attenuation, the link e between any nodes u and v uv The data transmission energy consumption can be simplified as: E tr =(P t +P r )×t uv , where P t With P r Respectively represent the transmit power and receive power of the node, t uv =B uv / R(u,v) represents the data transmission delay, B uv is the size of the data packet transmitted between links, and R(u, v) is the maximum transmission rate of the channel. At the same time, the free space propagation model can be used to obtain the relationship between the transmission power and the receiving power: P r =P t Gt G r λ 2 / (4πd) 2 L, where G t Transmitter antenna gain, G r is the antenna gain of the receiver, λ is the wavelength, d is the distance between the transmitter antenna and the receiver antenna, and L is the system loss.

[0174] Step 207: Energy consumption E when the link between nodes switches in time slice t s It is mainly affected by the antenna steering angle, expressed as: E s =αθ uv , α represents the energy consumption of a single antenna steering angle, θ uv Antenna steering angle for re-establishing the link from node u to node v.

[0175] Step 208: Finally, other energy consumptions such as node attitude adjustment, GPS navigation, and measurement and control can be regarded as a constant. Other inherent energy consumption is expressed as E c .

[0176] Step 209: Determine the switching application condition in the current time slice, that is, whether the connectivity of the current node has changed. If the connectivity has not changed, the link between the nodes is maintained; if the connectivity has changed and is less than the minimum connectivity k u <k min , at this time the current node is based on the linkable node set Set u Send a switching request to the destination node.

[0177] Step 210: In order to ensure the measurement and control accuracy and low energy consumption of the reconstructed measurement and control network topology, a deep Q network algorithm is used to solve the problem. The specific rules are as follows: Fig.10 As shown. First, observe the environment of the heterogeneous measurement and control network, and the state space of each node i is set to: S i ={Node i ,K i ,t},Node i is the current sequence number of node i, K i A represents the target node that temporarily links with node i (reflecting the connectivity of the current node), t is the index of the time slice; the action space of each node i is set to: A i = {V i}, where V i It is the next set of nodes that can build a link with node i.

[0178] Step 211: The agent strengthens the exploration of the environment according to the ε-greedy algorithm to decide whether to randomly select an action at a position or take the action with the greatest value among the existing actions according to the Q function. t In the early stage of training, we hope to explore the environment more, and in the later stage, we use the environment as much as possible to make better choices, which can be expressed as: Among them, i is the number of iterations, ε0 is the initial value, and ε f is the decay rate.

[0179] Step 212: The agent performs action a t You will get a reward t and the next new state s t+1 The reward r is determined by the energy consumption E between links. ia , the connectivity k of the node i Geometric Dilution of Precision GDOP i Jointly determined reward function: a∈V i ,k i ≥k min ,in The geometrical dilution of precision factor GDOP is a weighting factor. i The volume of the space cube V is inversely proportional to the volume formed by node i and its neighboring link nodes. i The larger the GDOP i The smaller the value, the higher the accuracy of measurement and control. In order to simplify the model, let GDOP i ≈1 / V i .

[0180] Step 213: Store a large number of excessive samples (s t ,a t ,r t ,s t+1 ), the agent randomly selects a batch of small transition samples before updating the Q network and calculates its loss Where Q * is the target q value, θ - is the parameter of the target q value, and the discount rate γ∈[0,1). The parameters are updated using the stochastic gradient descent method (SGD). The gradient is calculated as follows:

[0181] Step 214: Update network parameters Where α>0 is the learning rate.

[0182] Step 215: Update the Q network every C steps until the end.

[0183] Step 216, the optimal action determined by the deep Q network algorithm is to establish a link with lower energy consumption and higher measurement and control accuracy with neighboring nodes to ensure the normal operation of cross-domain multi-body network measurement and control positioning. When the destination node confirms that it accepts the switching request and sends a confirmation message to the node that initiated the switching request, it indicates that it is ready to receive the switching; after receiving the switching reply information, the destination node encapsulates the relevant access information in the switching command, and the group node members execute the switching according to the information in the switching command.

[0184] Step 216: When all nodes are switched to the new connection state, the group switching is completed.

[0185] Example 3

[0186] This embodiment describes the process of the above-mentioned intelligent decision-making training.

[0187] With known motion trajectories, node configurations, and communication capabilities, the model can be trained in advance to cope well with group switching environments caused by various emergencies, including interference, node damage, high mobility, etc., and deployed on each node. The above functions can be implemented by centralized-distributed deployment of computing power in the measurement and control network, which can significantly accelerate the training process. Distributed processing can use a distributed machine learning transmission optimization model based on dynamic tree topology, such as Fig.11 As shown, the specific steps are as follows:

[0188] Step 311: The measurement and control network collects information of visible nodes in the field of view. Each node only calculates the topology related to itself, and establishes a tree-like logical transmission topology with the group head as the root node and the homogeneous nodes in the group as leaves and intermediate nodes.

[0189] Step 312: The cluster leader node is responsible for collecting prior information from nodes in the cluster and determining the switching application condition, that is, whether the connectivity of the node is lower than the minimum connectivity k of the system. min .

[0190] Step 313: The decision of link group switching within the system is placed in the cluster head with high computing power and abundant resources for centralized processing. According to the judgment result, the cluster head node sends instructions to the nodes within the cluster to guide the nodes within the cluster to perform the group switching operation according to the instructions.

[0191] Step 314: Each node in the group adjusts the antenna power setting and antenna angle of each node according to the received instructions to perform distributed processing and execute group switching operations to optimize the network topology and achieve optimization of cross-domain multi-system networking measurement and control topology reconstruction.

[0192] Step 315: The server only needs to receive and send very little data to complete the model update of all nodes in the training system.

[0193] Because different nodes have different computing resources (the cluster leader has more computing resources and the nodes have less computing resources), this embodiment can accelerate the training process of the above-mentioned intelligent decision-making algorithm to find the optimal topology and save computing resources by deploying the node computing power.

[0194] In summary, the technical solution provided by this application can fully utilize the intelligent analysis and decision-making capabilities of the cluster leader node through this center + edge distributed deployment method, combined with the real-time data collection and execution capabilities of the nodes in the cluster, to achieve optimized management of the measurement and control network topology. This deployment method can significantly accelerate the distribution process of the model, improve computing power and reduce the burden on the system.

[0195] The following describes an embodiment of the device of the present application, which can be used to execute a cross-domain multi-system networking measurement and control topology optimization method based on group switching in the above embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the above method of the present application.

[0196] Reference Fig.12 As shown, according to an embodiment of the present application, a cross-domain multi-system networking measurement and control topology optimization device 1200 based on group switching includes:

[0197] A sensing unit 1201 is used to sense the prior information of each heterogeneous node, wherein the prior information includes: heterogeneous node location, antenna field of view, node mobility, node remaining energy resources and measurement and control system;

[0198] A processing unit 1202 is used to perform grouping processing on the heterogeneous nodes based on the prior information to obtain multiple heterogeneous node groups;

[0199] A screening unit 1203, used for performing node screening;

[0200] A determining unit 1204 is used to determine an initial topology configuration based on the node screening result;

[0201] A determination unit 1205 is used to determine whether the connectivity between nodes in each heterogeneous node group has changed in each time slice;

[0202] A switching unit 1206, configured to perform group switching;

[0203] The transformation unit 1207 is used to transform the initial topology configuration based on the group switching result until an optimal topology configuration that meets the measurement and control accuracy requirement is obtained.

[0204] like Fig.13As shown, an embodiment of the present application also provides an electronic device 1300, including a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor. When the processor 1320 executes the computer program 1311, the steps of the above-mentioned cross-domain multi-system networking measurement and control topology optimization method based on group switching are implemented.

[0205] Since the electronic device introduced in this embodiment is a device used to implement a cross-domain multi-system networking measurement and control topology optimization device based on group switching in the embodiment of the present application, based on the method introduced in the embodiment of the present application, the technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment adopted by the technical personnel in this field to implement the method in the embodiment of the present application, it belongs to the scope of protection of this application.

[0206] During the specific implementation process, when the computer program 1311 is executed by a processor, any implementation method in the embodiments corresponding to the first aspect can be implemented.

[0207] Fig.14 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0208] It should be noted that Fig.14 The computer system 1400 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0209] like Fig.14 As shown, the computer system 1400 includes a central processing unit (CPU) 1401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1402 or the program loaded from the storage part 1408 to the random access memory (RAM) 1403, such as executing the method described in the above embodiment. In the RAM 1403, various programs and data required for system operation are also stored. The CPU 1401, the ROM 1402 and the RAM 1403 are connected to each other through the bus 1404. The input / output (I / O) interface 1405 is also connected to the bus 1404.

[0210] The following components are connected to the I / O interface 1405: an input section 1406 including a keyboard, a mouse, etc.; an output section 1407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1408 including a hard disk, etc.; and a communication section 1409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 1409 performs communication processing via a network such as the Internet. A drive 1410 is also connected to the I / O interface 1405 as needed. A removable medium 1411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1410 as needed so that a computer program read therefrom is installed into the storage section 1408 as needed.

[0211] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 1409, and / or installed from a removable medium 1411. When the computer program is executed by a central processing unit (CPU) 1401, various functions defined in the system of the present application are executed.

[0212] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0213] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0214] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0215] As another aspect, the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes a cross-domain multi-system networking measurement and control topology optimization method based on group switching described in the above embodiment.

[0216] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements a cross-domain multi-system networking measurement and control topology optimization method based on group switching described in the above embodiment.

[0217] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0218] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0219] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary techniques in the art that are not disclosed in the present application. It should be understood that the present application is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A cross-domain multi-system network measurement and control topology optimization method based on group switching, applied to dynamic heterogeneous measurement and control networks, characterized in that: The method comprises: Perceiving the prior information of each heterogeneous node, the prior information includes: heterogeneous node location, antenna field of view, node mobility, node remaining energy resources and measurement and control system; Based on the prior information, the heterogeneous nodes are grouped to obtain a plurality of heterogeneous node groups; Perform node screening on each heterogeneous node group; Determine the initial topology configuration based on the node screening result; In each time slice, determine whether the connectivity between nodes in each heterogeneous node group has changed; If yes, the nodes are screened again and group switching is performed; The initial topology configuration is transformed based on the group switching result until an optimal topology configuration that meets the measurement and control accuracy requirement is obtained.

2. The method according to claim 1, characterized in that The grouping of heterogeneous nodes based on the prior information to obtain multiple heterogeneous node groups includes: Divide nodes with the same measurement and control system into the same heterogeneous node group; The heterogeneous node with the largest number of node remaining energy resources and neighboring nodes that can be linked is selected as the leader node of the heterogeneous node group.

3. The method according to claim 2, characterized in that The confirmation process of the leader node also includes: The remaining energy of the node and the number of neighboring nodes that the node can link to are normalized and weighted; The weights of the nodes in each group are calculated and sorted in descending order, with the first-ranked node being the group leader node and the second-ranked node being the backup group leader node.

4. The method according to claim 2, characterized in that: The node screening of each heterogeneous node group includes: Make judgments based on the measurement and control system of the nodes in the current heterogeneous node group, the antenna field of view, and the remaining energy resources of the nodes; If two heterogeneous nodes have the same measurement and control system and can be matched, their antenna fields of view are interoperable, and the energy resources of the remaining nodes meet the requirements for link building, then these two heterogeneous nodes are selected as nodes in the group that can be linked; Make judgments based on the current measurement and control system of each cluster leader node, antenna field of view, and remaining energy resources of the node; If two cluster head nodes have the same measurement and control system and can achieve matching, their antenna fields of view are interoperable, and the energy resources of the remaining nodes meet the requirements for link building, then these two cluster head nodes will be selected as cluster head nodes that can build a link.

5. The method according to claim 4, characterized in that The determining of the initial topology configuration based on the node screening result includes: Introducing an intelligent decision-making model into the dynamic heterogeneous measurement and control network; According to the state S of the current node, action A is set as the next node set that can establish a link with the node, where the state S of the current node includes: the intersection of the measurement and control systems between the node and its candidate link-building nodes, the intersection with the antenna field of view, the current energy state of the node, the target node temporarily linking with the node, and the connectivity of the current node; Set a reward function r determined by the energy consumption between links, the connectivity of nodes and the geometric reduction of precision factor GDOP to jointly determine the operation of the intelligent decision-making model; The intelligent agent of the intelligent decision-making model interacts with the global information of the dynamic heterogeneous measurement and control network nodes and trains the decision-making model, and finally outputs the initial topology configuration.

6. The method according to claim 5, characterized in that The group switching includes: If the connectivity of the current heterogeneous node changes, the current heterogeneous node sends a switching request to the destination node based on node screening again; The destination node confirms the acceptance of the switching request and sends a confirmation message back to the current heterogeneous node that initiated the switching request; After receiving the confirmation message, the current heterogeneous node encapsulates the relevant access information in the switching command, and the group node members execute the switching according to the information in the switching command.

7. The method according to any one of claims 1 to 6, characterized in that: Also includes: The dynamic heterogeneous measurement and control network establishes a tree-like logical transmission topology with the cluster head as the root node and the nodes within the cluster as leaves and intermediate nodes; The cluster head node collects the prior information collected by the nodes in the cluster in real time, and places the decision of network link group switching in the cluster head node for centralized processing; The group leader node sends the decision result to the nodes in the group, instructing the nodes in the group to perform the group switching operation according to the instructions; Each node in the group adjusts the antenna power settings and antenna angles of each node according to the received instructions for distributed processing and performs group switching.

8. A cross-domain multi-system networking measurement and control topology optimization device based on group switching, characterized in that: include: A sensing unit, used to sense the prior information of each heterogeneous node, the prior information including: heterogeneous node location, antenna field of view, node mobility, node remaining energy resources and measurement and control system; A processing unit, configured to perform grouping processing on the heterogeneous nodes based on the prior information to obtain a plurality of heterogeneous node groups; A screening unit, used for performing node screening; A determination unit, used for determining an initial topology configuration based on a node screening result; A judgment unit, used to judge whether the connectivity between nodes in each heterogeneous node group has changed in each time slice; A switching unit, used for performing group switching; The transformation unit is used to transform the initial topology configuration based on the group switching result until an optimal topology configuration that meets the measurement and control accuracy requirement is obtained.

9. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer is enabled to execute the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer instructions; The processor is used to call the computer instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

Images