Smart networking linkage system and method based on Internet of Things technology

Abstract

This invention belongs to the field of smart networking, specifically to a smart networking linkage system and method based on Internet of Things technology. The method includes current networking scoring, target initialization, generation of an initial set of candidate solutions, iterative updates, selection of the optimal solution, and network optimization. This solution uses a heuristic algorithm to evaluate the location and number of terminal devices requiring service to determine the deployment plan for gateway nodes, effectively meeting the coverage requirements of smart gateways at a low cost. This solution creatively proposes a smart gateway optimization method that combines Pareto frontier technology to find the optimal balance between system cost and coverage quality, resulting in a networking linkage solution that reduces system cost while ensuring a high bit rate.

Description

Technical Field

[0001] The present invention belongs to the field of smart networking, and specifically relates to a smart networking linkage system and method based on Internet of Things technology. Background Art

[0002] The Internet of Things technology has greatly promoted the interconnection and interoperability between intelligent devices. The intelligent networking linkage system and method based on the Internet of Things technology is a method that uses the Internet of Things technology to calculate and optimize the network structure and improve the information transmission and processing capabilities of node devices in the network.

[0003] Among the existing similar solutions, for example, CN113543046B is an intelligent control system for BLEmesh networking of power grids. This solution addresses the technical problems of existing IoT network technologies such as high power consumption, poor mobility, complex protocols, and inability to connect directly to smartphones. This solution uses BLE multicast technology to reduce power consumption, establishes a BLE connection between Bluetooth devices and smartphones, communicates with each other through the GATT protocol, and simultaneously issues commands to smartphones and associated devices without the need for relaying messages from other nodes. This achieves the technical effect of supporting intelligent linkage and 5G real-time transmission of high-definition video on site. However, there is a technical problem that the Bluetooth coverage is still affected by obstacles such as terrain and buildings, and more relay points need to be deployed to achieve full coverage.

[0004] Furthermore, there is often a conflict between system cost and bit rate: reducing system cost may reduce the number of smart gateways, thereby reducing the bit rate, while increasing the bit rate may require increasing the number of smart gateways, thereby increasing system cost. For example, CN115499282B proposes a method and system for constructing flexible networking linkage management based on native IPv6. This solution addresses the technical issues that existing technologies cannot achieve scenario-based customization based on differentiated network service requirements and the relatively complex operation and maintenance of edge routers. By using a controller to issue edge router configurations, with the controller's northbound interface responsible for customizing network service requirements and its southbound interface controlling edge routers, it achieves a technical approach that integrates network and application, meets scenario-based network requirements, enables unified management and control of edge routers, effectively shields differences in edge router devices, and enhances scalability and compatibility. However, the cost of LoRa smart gateways is higher than that of other low-power wide-area network smart gateways, and the technical issue of network deployment costs is not considered. Summary of the Invention

[0005] In response to the above situation and to overcome the shortcomings of the existing technology, the present invention provides a smart networking linkage system and method based on Internet of Things technology. In response to the technical problem that the Bluetooth coverage range of the existing technology is still affected by obstacles such as terrain and buildings, and more relay points need to be deployed to achieve complete coverage, this solution uses a heuristic algorithm to evaluate the location and number of terminal devices that need to be served to determine the deployment plan of the gateway node, effectively meeting the coverage range of the smart gateway at a low cost. In response to the technical problem that the cost of LoRa smart gateways is higher than that of other low-power wide-area network smart gateways in the existing technology, and the network deployment cost is not taken into account, this solution creatively proposes a smart gateway optimization method that combines Pareto frontier technology to find the optimal balance between system cost and coverage quality, and finds a networking linkage solution that can both reduce system cost and ensure a high bit rate.

[0006] The technical solution adopted by the present invention is as follows: The present invention provides an intelligent networking linkage system based on Internet of Things technology, which includes a current networking scoring module, a target initialization module, an initial candidate solution set generation module, an iterative update module, an optimal solution screening module and a networking optimization module;

[0007] The current networking scoring module evaluates the current networking quality;

[0008] The target initialization module determines a deployment cost minimization objective function and a bit rate maximization objective function;

[0009] The initial candidate solution set generation module generates candidate solutions to obtain an initial candidate solution set;

[0010] The iterative update module optimizes the candidate solution set;

[0011] The optimal solution screening module screens all candidate solutions to obtain non-dominated solutions, and then screens the non-dominated solutions to obtain the optimal solution;

[0012] The networking optimization module generates a networking linkage solution based on the best solution.

[0013] The present invention also provides a smart networking linkage method based on Internet of Things technology, which includes the following steps:

[0014] Step S1: Current network scoring, used to evaluate the signal quality of the current network. Specifically, the LoRa wide area network is composed of node devices, including terminal nodes, smart gateways, network cover devices, and application cover devices. The distance between the current smart gateway and the terminal node in the LoRa wide area network is calculated. According to the distance, the signal quality is divided into different levels and a corresponding bit rate performance score is assigned. The bit rate performance score represents the signal quality between the smart gateway and the terminal node. The closer the distance between the smart gateway and the terminal node, the higher the bit rate performance score. The terminal node outside the coverage range of the smart gateway has a bit rate performance score of 0:

[0015] Step S2: target initialization;

[0016] Step S3: generating an initial set of candidate solutions, which is used to provide an initial set of solutions for selecting the location of the smart gateway in the LoRa wide area network. Specifically, candidate solutions are randomly generated based on the location and number of the current smart gateway and terminal nodes to obtain an initial set of candidate solutions. The values ​​in the candidate solutions represent the priority of the smart gateway location that can cover any terminal node.

[0017] Step S4: Iterative update, specifically, optimizing the candidate solution set under the conditions of ensuring that each terminal node is covered by at least one intelligent gateway and ensuring that the number of terminal nodes covered by each intelligent gateway does not exceed the maximum capacity of the intelligent gateway:

[0018] Step S5: Screening the best solution;

[0019] Step S6: Network optimization, specifically, generating a network linkage solution based on the optimal solution, optimizing the number and location of smart gateways in the LoRa wide area network, dynamically adjusting the network topology, and realizing intelligent linkage between node devices.

[0020] Furthermore, in step S2, the target is initialized, which specifically includes the following steps:

[0021] Step S21: Cost minimization, specifically, defining a first decision variable, which indicates whether to deploy an intelligent gateway at location r. If the intelligent gateway is deployed at location r, the first decision variable is 1, otherwise the first decision variable is 0. The deployment cost minimization objective function is calculated. The formula used is as follows:

[0022] ;

[0023] Where, represents the deployment cost minimization objective function, represents the operating cost of deploying a smart gateway at location r, represents the first decision variable for deploying the smart gateway at location r, represents the candidate location set of the smart gateway;

[0024] Step S22: Bit rate maximization is used to optimize the signal coverage quality in the deployment of the intelligent gateway. Specifically, a second decision variable is defined. The second decision variable indicates whether the intelligent gateway at position r provides coverage for the terminal node. T1 is preset. T1 indicates the maximum distance that the intelligent gateway can cover. If the intelligent gateway at position r can cover the terminal node and the distance between the intelligent gateway and the terminal node is less than or equal to T1, the second decision variable is 1; otherwise, the second decision variable is 0. The bit rate maximization objective function is calculated. The formula used is as follows:

[0025] ;

[0026] Where, represents the bit rate maximization objective function, represents the total number of terminal nodes, represents the terminal node index, represents the second decision variable, represents the bitrate performance score;

[0027] Step S23: Target synthesis, specifically, using the Pareto frontier technology to construct a comprehensive target function based on the deployment cost minimization target function and the bit rate maximization target function.

[0028] Furthermore, in step S4, iterative updating specifically includes the following steps:

[0029] Step S41: Update the black box probability, which is used to dynamically adjust the weight of the black box method in each iteration based on the historical performance of the black box method. Specifically, determine M candidate solution improvement methods, record the candidate solution improvement methods as black box methods, and form a black box operation set. The probability of any black box method being selected is calculated using the following formula:

[0030] ;

[0031] ;

[0032] Where, Indicates the In the iteration, select The probability of a black box method, represents the index of the black box method, Indicates the The number of times a black-box method is chosen, Indicates the The black box method The average value of the comprehensive objective function of all candidate solutions in the round iteration, is the reward factor, indicating the The black box method Whether a non-dominated solution is found in the first iteration, A black box method finds a non-dominated solution, and the reward factor increases by 1. Indicates in The comprehensive objective function of the non-dominated solution found in the round iteration, Indicates a temporary variable. represents the control weight, represents the scaling factor, Indicates the total number of black box methods;

[0033] Step S42: black box application, specifically, selecting a black box method from the black box operation set according to the selection probability, and using the selected black box method to update the candidate solution to obtain a new candidate solution;

[0034] Step S43: Candidate solution update, used to select the candidate solution for the next iteration. Specifically, by comparing the current candidate solution with the new candidate solution improved by the black box method, it is decided whether to update the candidate solution. If the comprehensive objective function of the new candidate solution improved by the black box method is better than the comprehensive objective function of the current candidate solution, the candidate solution is updated to the new candidate solution improved by the black box method. Otherwise, the candidate solution remains unchanged. The formula used is as follows:

[0035] ;

[0036] Where, Indicates the The candidate solution The element in The value in the iteration, Indicates the The candidate solution The element in The value in the iteration, Indicates in The first iteration improved by the black box method The candidate solution The value of the element, Denotes the comprehensive objective function.

[0037] Furthermore, in step S5, the optimal solution is screened, which specifically includes the following steps:

[0038] Step S51: Filter and obtain non-dominated solutions from all candidate solutions, and record all non-dominated solutions as the Pareto optimal solution set;

[0039] The non-dominated solution refers to a candidate solution that is better than other candidate solutions in at least one objective function and is not inferior to other candidate solutions in other objective functions;

[0040] Step S52: constructing a decision matrix, specifically, constructing a decision matrix of the Pareto optimal solution set with the number of non-dominated solutions as rows and the number of objective functions as columns;

[0041] Step S53: Standardization, specifically, standardizing the decision matrix to a dimensionless form;

[0042] Step S54: Matrix weighting, specifically, assigning weights to the decision matrix according to the importance of the objective function and constructing a weighted normalized matrix;

[0043] Step S55: determining a positive ideal solution and a negative ideal solution, wherein the positive ideal solution is a solution consisting of the maximum value of each objective function of all non-dominated solutions in the Pareto optimal solution set, and the negative ideal solution is a solution consisting of the minimum value of each objective function of all non-dominated solutions in the Pareto optimal solution set;

[0044] Step S56: Positive ideal distance, calculating the Euclidean distance between each non-dominated solution and the positive ideal solution;

[0045] Step S57: Negative ideal distance, calculating the Euclidean distance between each non-dominated solution and the negative ideal solution;

[0046] Step S58: Calculate the relative proximity using the following formula:

[0047] ;

[0048] Where, Indicates relative proximity, represents the Euclidean distance between the non-dominated solution and the positive ideal solution, Shows the Euclidean distance between the non-dominated solution and the negative ideal solution;

[0049] Step S59: selecting the best solution, specifically, sorting the non-dominated solutions in the Pareto optimal solution set according to the relative proximity, and recording the non-dominated solution with the highest relative proximity as the best solution.

[0050] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0051] (1) In view of the technical problem that the coverage of Bluetooth in existing technologies is still affected by obstacles such as terrain and buildings, and more relay points need to be deployed to achieve full coverage, this solution uses a heuristic algorithm to evaluate the location and number of terminal devices that need to be served, and determines the deployment plan of the gateway node. This effectively meets the coverage of the smart gateway at a lower cost.

[0052] (2) In view of the fact that the cost of LoRa smart gateway is higher than that of other low-power wide-area network smart gateways in existing technologies and the technical problem of network deployment cost is not taken into account, this solution creatively proposes a smart gateway optimization method that combines Pareto frontier technology to find the best balance between system cost and coverage quality, and to find a network linkage solution that can reduce system cost while ensuring a higher bit rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A schematic diagram of the modules of the campus network security emergency management system based on public opinion monitoring provided by the present invention;

[0054] Figure 2 A flow chart of the campus network security emergency management method based on public opinion monitoring provided by the present invention;

[0055] Figure 3 is a schematic diagram of step S2;

[0056] Figure 4 is a schematic diagram of step S4;

[0057] Figure 5 is a schematic diagram of step S5.

[0058] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0060] In the description of the present invention, it should be understood that terms such as "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0061] Example 1, see Figure 1,This embodiment provides a smart networking linkage system based on Internet of Things technology, the system includes a current networking scoring module, a target initialization module, an initial candidate solution set generation module, an iterative update module, an optimal solution screening module and a networking optimization module;

[0062] The current networking scoring module evaluates the current networking quality;

[0063] The target initialization module determines a deployment cost minimization objective function and a bit rate maximization objective function;

[0064] The initial candidate solution set generation module generates candidate solutions to obtain an initial candidate solution set;

[0065] The iterative update module optimizes the candidate solution set;

[0066] The optimal solution screening module screens all candidate solutions to obtain non-dominated solutions, and then screens the non-dominated solutions to obtain the optimal solution;

[0067] The networking optimization module generates a networking linkage solution based on the best solution.

[0068] Example 2, see Figure 1 and Figure 2 Based on the above embodiment, this embodiment provides a smart networking linkage method based on Internet of Things technology, which includes the following steps:

[0069] Step S1: Current network scoring is used to evaluate the current network quality. Specifically, the LoRa wide area network is composed of node devices, which include terminal nodes, smart gateways, network cover devices, and application cover devices. The distance between the current smart gateway and the terminal node in the LoRa wide area network is calculated. According to the distance, the signal quality is divided into different levels and a corresponding bit rate performance score is assigned. The bit rate performance score represents the signal quality between the smart gateway and the terminal node. The closer the distance between the smart gateway and the terminal node, the higher the bit rate performance score. The terminal node outside the coverage range of the smart gateway has a bit rate performance score of 0:

[0070] Step S2: target initialization;

[0071] Step S3: generating an initial set of candidate solutions, which is used to provide an initial set of solutions for selecting the location of the smart gateway in the LoRa wide area network. Specifically, candidate solutions are randomly generated based on the location and number of the current smart gateway and terminal nodes to obtain an initial set of candidate solutions. The values ​​in the candidate solutions represent the priority of the smart gateway location that can cover any terminal node.

[0072] Step S4: Iterative update, specifically, optimizing the candidate solution set under the conditions of ensuring that each terminal node is covered by at least one intelligent gateway and ensuring that the number of terminal nodes covered by each intelligent gateway does not exceed the maximum capacity of the intelligent gateway:

[0073] Step S5: Screening the best solution;

[0074] Step S6: Network optimization, specifically, generating a network linkage solution based on the optimal solution, optimizing the number and location of smart gateways in the LoRa wide area network, dynamically adjusting the network topology, and realizing intelligent linkage between node devices.

[0075] Example 3, see Figures 1 to 3 This embodiment is based on the above embodiment. In step S2, the target is initialized, specifically including the following steps:

[0076] Step S21: Cost minimization, specifically, defining a first decision variable, which indicates whether to deploy an intelligent gateway at location r. If the intelligent gateway is deployed at location r, the first decision variable is 1, otherwise the first decision variable is 0. The deployment cost minimization objective function is calculated. The formula used is as follows:

[0077] ;

[0078] Where, represents the deployment cost minimization objective function, represents the operating cost of deploying a smart gateway at location r, represents the first decision variable, represents the candidate location set of the smart gateway;

[0079] Step S22: Bit rate maximization is used to optimize the signal coverage quality in the deployment of the intelligent gateway. Specifically, a second decision variable is defined. The second decision variable indicates whether the intelligent gateway at position r provides coverage for the terminal node. T1 is preset. T1 indicates the maximum distance that the intelligent gateway can cover. If the intelligent gateway at position r can cover the terminal node and the distance between the intelligent gateway and the terminal node is less than or equal to T1, the second decision variable is 1; otherwise, the second decision variable is 0. The bit rate maximization objective function is calculated. The formula used is as follows:

[0080] ;

[0081] Where, represents the bit rate maximization objective function, represents the total number of terminal nodes, represents the terminal node index, represents the second decision variable, represents the bitrate performance score;

[0082] Step S23: Target synthesis, specifically, using the Pareto frontier technology to construct a comprehensive target function based on the deployment cost minimization target function and the bit rate maximization target function.

[0083] Example 4, see Figures 1 to 4 This embodiment is based on the above embodiment. In step S4, iterative updating specifically includes the following steps:

[0084] Step S41: Update the black box probability; this is used to dynamically adjust the weight of the black box method in each iteration based on the historical performance of the black box method. Specifically, M candidate solution improvement methods are determined, each of which is recorded as a black box method. All black box methods constitute a black box operation set, and the probability of any black box method being selected is calculated using the following formula:

[0085] ;

[0086] ;

[0087] Where, Indicates the In the iteration, select The probability of a black box method, represents the index of the black box method, Indicates the The number of times a black-box method is chosen, Indicates the The black box method The average value of the comprehensive objective function of all candidate solutions in the round iteration, is the reward factor, indicating the The black box method Whether a non-dominated solution is found in the first iteration, A black box method finds a non-dominated solution, and the reward factor increases by 1. Indicates in The comprehensive objective function of the non-dominated solution found in the round iteration, Indicates a temporary variable. represents the control weight, represents the scaling factor, Indicates the total number of black box methods;

[0088] Step S42: black box application, specifically, selecting a black box method from the black box operation set according to the selection probability, and using the selected black box method to update the candidate solution to obtain a new candidate solution;

[0089] Step S43: Candidate solution update, used to select the candidate solution for the next iteration. Specifically, by comparing the current candidate solution with the new candidate solution improved by the black box method, it is decided whether to update the candidate solution. If the comprehensive objective function of the new candidate solution improved by the black box method is better than the comprehensive objective function of the current candidate solution, the candidate solution is updated to the new candidate solution improved by the black box method. Otherwise, the candidate solution remains unchanged. The formula used is as follows:

[0090] ;

[0091] Where, Indicates the The candidate solution The element in The value in the iteration, Indicates the The candidate solution The element in The value in the iteration, Indicates in The first iteration improved by the black box method The candidate solution The value of the element, Denotes the comprehensive objective function.

[0092] Example 5, see Figures 1 to 5 This embodiment is based on the above embodiment. In step S5, the optimal solution is screened, specifically including the following steps:

[0093] Step S51: Filter and obtain non-dominated solutions from all candidate solutions, and record all non-dominated solutions as the Pareto optimal solution set;

[0094] The non-dominated solution refers to a candidate solution that is better than other candidate solutions in at least one objective function and is not inferior to other candidate solutions in other objective functions;

[0095] Step S52: constructing a decision matrix, specifically, constructing a decision matrix of the Pareto optimal solution set with the number of non-dominated solutions as rows and the number of objective functions as columns;

[0096] Step S53: Standardization, specifically, standardizing the decision matrix to a dimensionless form;

[0097] Step S54: Matrix weighting, specifically, assigning weights to the decision matrix according to the importance of the objective function and constructing a weighted normalized matrix;

[0098] Step S55: determining a positive ideal solution and a negative ideal solution, wherein the positive ideal solution is a solution consisting of the maximum value of each objective function of all non-dominated solutions in the Pareto optimal solution set, and the negative ideal solution is a solution consisting of the minimum value of each objective function of all non-dominated solutions in the Pareto optimal solution set;

[0099] Step S56: Positive ideal distance, calculating the Euclidean distance between each non-dominated solution and the positive ideal solution;

[0100] Step S57: Negative ideal distance, calculating the Euclidean distance between each non-dominated solution and the negative ideal solution;

[0101] Step S58: Calculate the relative proximity using the following formula:

[0102] ;

[0103] Where, Indicates relative proximity, represents the Euclidean distance between the non-dominated solution and the positive ideal solution, Shows the Euclidean distance between the non-dominated solution and the negative ideal solution;

[0104] Step S59: selecting the best solution, specifically, sorting the non-dominated solutions in the Pareto optimal solution set according to the relative proximity, and recording the non-dominated solution with the highest relative proximity as the best solution.

[0105] Example 6, see Figures 1 to 5 This embodiment is based on the above embodiment. In step S1, the signal quality is divided into different levels according to the distance and a corresponding bit rate performance score is assigned. Specifically, when the distance is 0-2 kilometers, the bit rate performance score is 4 points; when the distance is 3-4 kilometers, the bit rate performance score is 3 points; when the distance is 5-6 kilometers, the bit rate performance score is 2 points; and when the distance is 7-8 kilometers, the bit rate performance score is 1 point.

[0106] Example 7, see Figures 1 to 5 This embodiment is based on the above embodiment. In step S3, the dimension of the candidate solution is 1×D, where D is the terminal node.

[0107] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0108] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

[0109] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. A smart networking linkage method based on Internet of Things technology, characterized by: The method comprises the following steps: Step S1: Current network scoring, used to evaluate the signal quality of the current network. Specifically, the LoRa wide area network is composed of node devices, including terminal nodes, smart gateways, network cover devices, and application cover devices. The distance between the current smart gateway and the terminal node in the LoRa wide area network is calculated. According to the distance, the signal quality is divided into different levels and a corresponding bit rate performance score is assigned. The bit rate performance score represents the signal quality between the smart gateway and the terminal node. The closer the distance between the smart gateway and the terminal node, the higher the bit rate performance score. The terminal node outside the coverage range of the smart gateway has a bit rate performance score of 0: Step S2: target initialization; Step S3: generating an initial set of candidate solutions, which is used to provide an initial set of solutions for selecting the location of the smart gateway in the LoRa wide area network. Specifically, candidate solutions are randomly generated based on the location and number of the current smart gateway and terminal nodes to obtain an initial set of candidate solutions. The values ​​in the candidate solutions represent the priority of the smart gateway location that can cover any terminal node. Step S4: Iterative update, specifically, optimizing the candidate solution set under the conditions of ensuring that each terminal node is covered by at least one intelligent gateway and ensuring that the number of terminal nodes covered by each intelligent gateway does not exceed the maximum capacity of the intelligent gateway: Step S5: Screening the best solution; Step S6: Network optimization, specifically, generating a network linkage solution based on the optimal solution, optimizing the number and location of smart gateways in the LoRa wide area network, dynamically adjusting the network topology, and realizing intelligent linkage between node devices.

2. The method for intelligent networking based on Internet of Things technology according to claim 1, characterized in that: In step S2, the target is initialized, which specifically includes the following steps: Step S21: Cost minimization, specifically, defining a first decision variable, which indicates whether to deploy an intelligent gateway at location r. If the intelligent gateway is deployed at location r, the first decision variable is 1, otherwise the first decision variable is 0. The deployment cost minimization objective function is calculated. The formula used is as follows: ； Where, represents the deployment cost minimization objective function, represents the operating cost of deploying a smart gateway at location r, represents the first decision variable, represents the candidate location set of the smart gateway; Step S22: Bit rate maximization is used to optimize the signal coverage quality in the deployment of the intelligent gateway. Specifically, a second decision variable is defined. The second decision variable indicates whether the intelligent gateway at position r provides coverage for the terminal node. T1 is preset. T1 indicates the maximum distance that the intelligent gateway can cover. If the intelligent gateway at position r can cover the terminal node and the distance between the intelligent gateway and the terminal node is less than or equal to T1, the second decision variable is 1; otherwise, the second decision variable is 0. The bit rate maximization objective function is calculated. The formula used is as follows: ； Where, represents the bit rate maximization objective function, represents the total number of terminal nodes, represents the terminal node index, represents the second decision variable, represents the bitrate performance score; Step S23: Target synthesis, specifically, using the Pareto frontier technology to construct a comprehensive target function based on the deployment cost minimization target function and the bit rate maximization target function.

3. The method for intelligent networking based on Internet of Things technology according to claim 2, characterized in that: In step S4, iterative updating specifically includes the following steps: Step S41: Update the black box probability, which is used to dynamically adjust the weight of the black box method in each iteration based on the historical performance of the black box method. Specifically, determine M candidate solution improvement methods, record the candidate solution improvement methods as black box methods, and form a black box operation set. The probability of any black box method being selected is calculated using the following formula: ； ； Where, Indicates the In the iteration, select The probability of a black box method, represents the index of the black box method, Indicates the The number of times a black-box method is chosen, Indicates the The black box method The average value of the comprehensive objective function of all candidate solutions in the round iteration, is the reward factor, indicating the The black box method Whether a non-dominated solution is found in the first iteration, A black box method finds a non-dominated solution, and the reward factor increases by 1. Indicates in The comprehensive objective function of the non-dominated solution found in the round iteration, Indicates a temporary variable. represents the control weight, represents the scaling factor, Indicates the total number of black box methods; Step S42: black box application, specifically, selecting a black box method from the black box operation set according to the selection probability, and using the selected black box method to update the candidate solution to obtain a new candidate solution; Step S43: Candidate solution update, used to select the candidate solution for the next iteration. Specifically, by comparing the current candidate solution with the new candidate solution improved by the black box method, it is decided whether to update the candidate solution. If the comprehensive objective function of the new candidate solution improved by the black box method is better than the comprehensive objective function of the current candidate solution, the candidate solution is updated to the new candidate solution improved by the black box method. Otherwise, the candidate solution remains unchanged. The formula used is as follows: ； Where, Indicates the The candidate solution The element in The value in the iteration, Indicates the The candidate solution The element in The value in the iteration, Indicates in The first iteration improved by the black box method The candidate solution The value of the element, Denotes the comprehensive objective function.

4. The method for intelligent networking based on Internet of Things technology according to claim 3 is characterized in that: In step S5, the optimal solution is selected, which specifically includes the following steps: Step S51: Filter and obtain non-dominated solutions from all candidate solutions, and record all non-dominated solutions as the Pareto optimal solution set; The non-dominated solution refers to a candidate solution that is better than other candidate solutions in at least one objective function and is not inferior to other candidate solutions in other objective functions; Step S52: constructing a decision matrix, specifically, constructing a decision matrix of the Pareto optimal solution set with the number of non-dominated solutions as rows and the number of objective functions as columns; Step S53: Standardization, specifically, standardizing the decision matrix to a dimensionless form; Step S54: Matrix weighting, specifically, assigning weights to the decision matrix according to the importance of the objective function and constructing a weighted normalized matrix; Step S55: determining a positive ideal solution and a negative ideal solution, wherein the positive ideal solution is a solution consisting of the maximum value of each objective function of all non-dominated solutions in the Pareto optimal solution set, and the negative ideal solution is a solution consisting of the minimum value of each objective function of all non-dominated solutions in the Pareto optimal solution set; Step S56: Positive ideal distance, calculating the Euclidean distance between each non-dominated solution and the positive ideal solution; Step S57: Negative ideal distance, calculating the Euclidean distance between each non-dominated solution and the negative ideal solution; Step S58: Calculate the relative proximity using the following formula: ； Where, Indicates relative proximity, represents the Euclidean distance between the non-dominated solution and the positive ideal solution, Shows the Euclidean distance between the non-dominated solution and the negative ideal solution; Step S59: selecting the best solution, specifically, sorting the non-dominated solutions in the Pareto optimal solution set according to the relative proximity, and recording the non-dominated solution with the highest relative proximity as the best solution.

5. An intelligent networking linkage system based on Internet of Things technology, for implementing the intelligent networking linkage method based on Internet of Things technology according to any one of claims 1 to 4, characterized in that: The system includes a current networking scoring module, a target initialization module, an initial candidate solution set generation module, an iterative update module, an optimal solution screening module and a networking optimization module; The current networking scoring module evaluates the current networking quality; The target initialization module determines a deployment cost minimization objective function and a bit rate maximization objective function; The initial candidate solution set generation module generates candidate solutions to obtain an initial candidate solution set; The iterative update module optimizes the candidate solution set; The optimal solution screening module screens all candidate solutions to obtain non-dominated solutions, and then screens the non-dominated solutions to obtain the optimal solution; The networking optimization module generates a networking linkage solution based on the best solution.

Images