A method and system for intelligent optimization deployment of wireless networks

Abstract

This invention discloses a method and system for intelligent optimization deployment of wireless networks. By distributing network deployment strategies to edge nodes, the computational load on the central controller is reduced, improving the optimization efficiency of network deployment strategies. Furthermore, by using a "double mutation mechanism" to evolve the strategy chromosome, dynamically changing gene mutation probabilities and environmental evolution ranges are introduced, enabling the algorithm to quickly escape local optima and dynamically track and adapt to changes in the network environment, significantly improving the convergence speed of the evolutionary algorithm. Finally, the strategy chromosome is analyzed based on network state data to determine the optimized deployment strategy. This invention significantly reduces the overall overhead and latency of network deployment strategies and improves efficiency.

Description

Technical Field

[0001] This invention relates to the field of wireless communication network technology, and more specifically, to a method and system for intelligent optimization deployment of wireless networks. Background Technology

[0002] In wireless sensor networks, nodes transmit monitoring information of sensed objects within their coverage area to the service terminal through collaborative sensing, thereby achieving an organic integration of the network world and the real world. In the traditional wireless network deployment process, all network deployment strategies are mainly controlled by the terminal, which increases the terminal's computing load and response time, causing problems such as sensor node lag. In addition, the lack of restrictions during network deployment adjustments increases the terminal's computing load.

[0003] Therefore, existing technologies have shortcomings and urgently need improvement. Summary of the Invention

[0004] To address at least one of the aforementioned technical problems, the present invention aims to provide a method and system for intelligent optimization deployment of wireless networks, which can reduce the overall overhead and latency of network deployment strategies and improve efficiency.

[0005] The first aspect of this invention provides a method for intelligent optimization deployment of a wireless network, comprising:

[0006] Obtain the sensor node location and store the edge nodes of the sensor node location within the corresponding area;

[0007] Edge nodes report the stored sensor node locations to the central controller;

[0008] Genetic algorithms are used to generate an initial policy set containing multiple network deployment strategies, and each deployment strategy is encoded as a policy chromosome.

[0009] Based on the sampling information, the edge nodes collect network status data from the sensor nodes;

[0010] When the deployment strategy is only within the scope of the corresponding edge node, the corresponding edge node evolves and optimizes the strategy chromosome based on network state data to obtain the optimized deployment strategy;

[0011] When a deployment strategy exists in multiple edge node ranges, the network status data is uploaded to the central controller. The central controller evolves and optimizes the strategy chromosome based on the network status data to obtain the optimized deployment strategy.

[0012] The optimized deployment strategy is sent to the corresponding edge nodes for execution;

[0013] The network status data includes link latency, network packet loss rate, network load, available bandwidth, and node energy consumption.

[0014] In this scheme, the step of generating the sampling information includes:

[0015] Based on a fixed frequency, edge nodes acquire the raw received signal strength or signal-to-noise ratio;

[0016] Arrange the original received signal strengths or signal-to-noise ratios in chronological order of acquisition to obtain the dataset. ;

[0017] Based on the set sliding time window, extract adjacent data within the corresponding sliding time window;

[0018] Calculate the difference between adjacent data within the sliding time window, take the absolute value, and obtain the difference between adjacent indicators.

[0019] By traversing the entire sliding time window, a set of differences between adjacent indicators is obtained. The average value of the values ​​in the set of differences between adjacent indicators is then calculated to obtain the stability index corresponding to the current sliding time window. ;

[0020] Set the current signal fluctuation value to Its formula is If the current signal fluctuation value is greater than the preset signal fluctuation threshold, sampling information is generated.

[0021] In this solution, the step of obtaining the preset signal fluctuation threshold specifically includes:

[0022] Acquire the environment in which the original received signal strength or signal-to-noise ratio is collected;

[0023] Determine the initial threshold for signal fluctuations based on the corresponding environment;

[0024] Extract the stability metrics from the previous sliding time window;

[0025] The initial threshold for signal fluctuation is optimized based on the stability index of the previous sliding time window to obtain the preset signal fluctuation threshold for the current sliding time window.

[0026] In this scheme, the evolution steps specifically include:

[0027] Extract the network load and available bandwidth from the network status data of the current time point and the previous time point;

[0028] By comparing and analyzing the network load at the current time point with the network load at the previous time point, the absolute value of the change in network load can be obtained.

[0029] By comparing and analyzing the available bandwidth at the current time point with the available bandwidth at the previous time point, the absolute value of the change in available bandwidth is obtained.

[0030] The current environmental change index is determined based on the absolute values ​​of the network load change rate and the available bandwidth change rate.

[0031] Based on the range within which the environmental change index falls, the evolutionary range of the corresponding strategy chromosome is determined;

[0032] Based on the evolutionary range, the values ​​of one or more gene positions in the strategy chromosome are randomly changed according to the preset gene mutation probability to obtain a new strategy chromosome.

[0033] This plan also includes:

[0034] The preset environmental sensitivity coefficient is optimized based on the environmental change index to obtain the gene mutation probability adjustment value;

[0035] Let the preset gene mutation probability be P, and its formula is: ,in denoted as the initial probability of gene mutation, and k represents the adjustment value of the gene mutation probability.

[0036] In this solution, the optimization steps specifically include:

[0037] Obtain the service to be transmitted;

[0038] Set the corresponding optimization weight parameters according to the service to be transmitted;

[0039] Based on the corresponding optimization weight parameters, set the strategy chromosome optimization function;

[0040] The network state data is divided according to the policy chromosome to obtain the network state data of the corresponding policy chromosome.

[0041] Send the network state data of the corresponding policy chromosome to the policy chromosome optimization function to obtain the optimization index of the corresponding policy chromosome;

[0042] If the optimization index of the strategy chromosome is greater than the optimization index of the strategy chromosome before evolution, then the evolved strategy chromosome will replace the previous strategy chromosome.

[0043] If the optimization index of the strategy chromosome is less than or equal to the optimization index of the strategy chromosome before evolution, then the strategy chromosome before evolution is restored, and the corresponding evolution path is recorded.

[0044] After a set number of evolutions, the optimized strategy chromosome is output.

[0045] This plan also includes:

[0046] Based on the established blockchain smart contract, the edge nodes periodically call out the names of the sensor nodes;

[0047] Extract the time points at which edge nodes mark sensor nodes and start a countdown for a set time.

[0048] If the countdown timer reaches zero and the sensor node has not yet reported data, the sensor node will be marked, and the marked sensor node will be obtained.

[0049] Replace the corresponding tagged sensor node with a preset backup sensor node and write it to the blockchain to broadcast to other edge nodes and the central controller.

[0050] A second aspect of the present invention provides a wireless network intelligent optimization deployment system, including a memory and a processor. The memory stores a wireless network intelligent optimization deployment method program, which, when executed by the processor, performs the following steps:

[0051] Obtain the sensor node location and store the edge nodes of the sensor node location within the corresponding area;

[0052] Edge nodes report the stored sensor node locations to the central controller;

[0053] Genetic algorithms are used to generate an initial policy set containing multiple network deployment strategies, and each deployment strategy is encoded as a policy chromosome.

[0054] Based on the sampling information, the edge nodes collect network status data from the sensor nodes;

[0055] When the deployment strategy is only within the scope of the corresponding edge node, the corresponding edge node evolves and optimizes the strategy chromosome based on network state data to obtain the optimized deployment strategy;

[0056] When a deployment strategy exists in multiple edge node ranges, the network status data is uploaded to the central controller. The central controller evolves and optimizes the strategy chromosome based on the network status data to obtain the optimized deployment strategy.

[0057] The optimized deployment strategy is sent to the corresponding edge nodes for execution;

[0058] The network status data includes link latency, network packet loss rate, network load, available bandwidth, and node energy consumption.

[0059] In this scheme, the step of generating the sampling information includes:

[0060] Based on a fixed frequency, edge nodes acquire the raw received signal strength or signal-to-noise ratio;

[0061] Arrange the original received signal strengths or signal-to-noise ratios in chronological order of acquisition to obtain the dataset. ;

[0062] Based on the set sliding time window, extract adjacent data within the corresponding sliding time window;

[0063] Calculate the difference between adjacent data within the sliding time window, take the absolute value, and obtain the difference between adjacent indicators.

[0064] By traversing the entire sliding time window, a set of differences between adjacent indicators is obtained. The average value of the values ​​in the set of differences between adjacent indicators is then calculated to obtain the stability index corresponding to the current sliding time window. ;

[0065] Set the current signal fluctuation value to Its formula is If the current signal fluctuation value is greater than the preset signal fluctuation threshold, sampling information is generated.

[0066] In this solution, the step of obtaining the preset signal fluctuation threshold specifically includes:

[0067] Acquire the environment in which the original received signal strength or signal-to-noise ratio is collected;

[0068] Determine the initial threshold for signal fluctuations based on the corresponding environment;

[0069] Extract the stability metrics from the previous sliding time window;

[0070] The initial threshold for signal fluctuation is optimized based on the stability index of the previous sliding time window to obtain the preset signal fluctuation threshold for the current sliding time window.

[0071] This invention discloses a method and system for intelligent optimization deployment of wireless networks. By distributing network deployment strategies to edge nodes, the computational load on the central controller is reduced, improving the optimization efficiency of network deployment strategies. Furthermore, by using a "double mutation mechanism" to evolve the strategy chromosome, dynamically changing gene mutation probabilities and environmental evolution ranges are introduced, enabling the algorithm to quickly escape local optima and dynamically track and adapt to changes in the network environment, significantly improving the convergence speed of the evolutionary algorithm. Finally, the strategy chromosome is analyzed based on network state data to determine the optimized deployment strategy. This invention significantly reduces the overall overhead and latency of network deployment strategies and improves efficiency. Attached Figure Description

[0072] Figure 1A flowchart of a wireless network intelligent optimization deployment method according to the present invention is shown;

[0073] Figure 2 A block diagram of a wireless network intelligent optimization deployment system according to the present invention is shown. Detailed Implementation

[0074] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0075] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0076] Figure 1 A flowchart of a wireless network intelligent optimization deployment method according to the present invention is shown.

[0077] S101, Obtain the sensor node location, and store the edge nodes of the sensor node location in the corresponding area;

[0078] S102, the edge node reports the stored sensor node locations to the central controller;

[0079] S103, Generate an initial policy set containing multiple network deployment strategies based on a genetic algorithm, and encode each deployment strategy as a policy chromosome;

[0080] S104, Based on the sampling information, the edge node collects network status data from the sensor node;

[0081] S105, When the deployment strategy is only within the scope of the corresponding edge node, the corresponding edge node evolves and optimizes the strategy chromosome based on the network state data to obtain the optimized deployment strategy;

[0082] S106, When the deployment strategy exists in multiple edge node ranges at the same time, the network status data is uploaded to the central controller. The central controller evolves and optimizes the strategy chromosome based on the network status data to obtain the optimized deployment strategy.

[0083] S107, the optimized deployment strategy is sent to the corresponding edge node for execution.

[0084] According to embodiments of the present invention, edge nodes are configured to collect and report the locations of sensor nodes within their jurisdiction to a centralized controller. The centralized controller then generates a diverse set of initial strategies using a built-in genetic algorithm. Each deployment strategy is encoded as a strategy chromosome, which transforms complex network configuration parameters (such as power, channel, and routing) into a data structure of gene strings that can be processed and optimized by a computer, laying the foundation for subsequent intelligent evolution. The deployment strategies are then distributed to each edge node (such as base stations and access points) for execution. Data collection at the edge nodes is triggered by sampling information, greatly reducing unnecessary data transmission and energy consumption. Network status data is only collected when the network status changes (such as signal mutations or service switching), ensuring the real-time nature and effectiveness of the data. Furthermore, when a deployment strategy involves only sensor nodes within one edge node, the corresponding edge node evolves and optimizes the deployment strategy. When a deployment strategy involves sensor nodes within two or more edge nodes, the centralized controller evolves and optimizes the deployment strategy. By using edge nodes, the computational load on the centralized controller and the data transmission between the edge nodes and the centralized controller are effectively reduced, further reducing channel occupancy. The network status data includes link latency, network packet loss rate, network load, available bandwidth, and node energy consumption. The node energy consumption refers to the energy consumption of sensor nodes, and the sensor nodes are wireless network sensor nodes.

[0085] It should be noted that in genetic algorithms, a chromosome represents a possible solution, i.e., a deployment strategy. In this embodiment, the chromosome is designed as a compact binary code containing multiple gene segments, each corresponding to a configurable network parameter; for example, it may consist of three gene segments: a power control segment, a channel allocation segment, and a routing segment. The power control segment represents the device's transmit power level; for example, if divided into 16 levels, then 1001 (binary) represents power level 9 (decimal). The channel allocation segment represents the selected wireless channel. The range includes channels 1-64, so 001010 represents channel 10; the routing segment represents the identifier of the next node, using the hash value of the node ID as the encoding to ensure uniqueness. For example, 01101001 represents a node with a hash value of 105. For example, the length of the policy chromosome is 4+6+8=18 (bits), the power control segment is 0101, the channel allocation segment is 001100, and the routing segment is 01101001. Then the corresponding policy chromosome represents power level 5, channel 12, and the hash value of the next sensor node ID is 105.

[0086] According to an embodiment of the present invention, the step of generating the sampling information includes:

[0087] Based on a fixed frequency, edge nodes acquire the raw received signal strength or signal-to-noise ratio;

[0088] Arrange the original received signal strengths or signal-to-noise ratios in chronological order of acquisition to obtain the dataset. ;

[0089] Based on the set sliding time window, extract adjacent data within the corresponding sliding time window;

[0090] Calculate the difference between adjacent data within the sliding time window, take the absolute value, and obtain the difference between adjacent indicators.

[0091] By traversing the entire sliding time window, a set of differences between adjacent indicators is obtained. The average value of the values ​​in the set of differences between adjacent indicators is then calculated to obtain the stability index corresponding to the current sliding time window. ;

[0092] Set the current signal fluctuation value to Its formula is If the current signal fluctuation value is greater than the preset signal fluctuation threshold, sampling information is generated.

[0093] It should be noted that, for example, if the sliding time window is set to 10 seconds, then the data within the previous 10 seconds will be extracted based on the current time point, and the data before 10 seconds will be deleted. This represents the stability index of the previous sliding time window.

[0094] According to an embodiment of the present invention, the step of obtaining the preset signal fluctuation threshold specifically includes:

[0095] Acquire the environment in which the original received signal strength or signal-to-noise ratio is collected;

[0096] Determine the initial threshold for signal fluctuations based on the corresponding environment;

[0097] Extract the stability metrics from the previous sliding time window;

[0098] The initial threshold for signal fluctuation is optimized based on the stability index of the previous sliding time window to obtain the preset signal fluctuation threshold for the current sliding time window.

[0099] It should be noted that different initial thresholds for signal fluctuations are set for different environments. For example, the environment can be divided into indoor and outdoor. The initial threshold for signal fluctuations indoors is set to 3dB, and the initial threshold for signal fluctuations outdoors is set to 5dB. The stability index of the previous sliding time window is set to... The preset signal fluctuation threshold for the current sliding time window Its formula is ,in The initial threshold for signal fluctuations in the current environment. The set smoothing coefficient, for example The initial threshold for signal fluctuations in the current environment is optimized by using the stability index of the previous sliding time window, thereby improving the adaptability to the current environment.

[0100] According to an embodiment of the present invention, the evolutionary steps specifically include:

[0101] Extract the network load and available bandwidth from the network status data of the current time point and the previous time point;

[0102] By comparing and analyzing the network load at the current time point with the network load at the previous time point, the absolute value of the change in network load can be obtained.

[0103] By comparing and analyzing the available bandwidth at the current time point with the available bandwidth at the previous time point, the absolute value of the change in available bandwidth is obtained.

[0104] The current environmental change index is determined based on the absolute values ​​of the network load change rate and the available bandwidth change rate.

[0105] Based on the range within which the environmental change index falls, the evolutionary range of the corresponding strategy chromosome is determined;

[0106] Based on the evolutionary range, the values ​​of one or more gene positions in the strategy chromosome are randomly changed according to the preset gene mutation probability to obtain a new strategy chromosome.

[0107] It should be noted that the dual mutation mechanism includes gene mutation and environmental adaptation mutation. The strategy chromosome evolves through this mechanism. Gene mutation randomly changes the values ​​of one or more gene loci in the strategy chromosome using a preset mutation probability, thus achieving the evolutionary process. For example, changing the power level from 2 to 3 or the channel number from 4 to 6. The preset mutation probability prevents premature convergence or over-adjustment of the algorithm, keeping the computational load within a controllable range. Furthermore, the absolute value of the change in network load is obtained by subtracting the network load at the previous time point from the current time point's network load, and by subtracting the available bandwidth at the previous time point from the available bandwidth at the current time point, and taking the absolute value. The environmental change index is set as R, and its formula is... ,in These represent the corresponding weight coefficients, and , This represents the absolute value of the change in network load. Indicates the maximum load capacity of the network. This represents the absolute value of the change in available bandwidth. This indicates the maximum available bandwidth. When the environmental change index approaches zero, it indicates that the current network environment is stable, and therefore the range of deployment strategy adjustments is small. When the environmental change index approaches 1, it indicates that the current environment is changing drastically, and the range of deployment strategy adjustments is large. The larger the value of the environmental change index, the larger the evolution range of the corresponding strategy chromosome. The entire evolution range can be normalized, and then the environmental change index can be set as the corresponding evolution range. For example, if the environmental change index is 0.5, then the evolution range of the corresponding strategy chromosome is 0.5. Its specific evolution range is multiplied by the environmental change index and the corresponding actual evolution range. The environmental adaptation variation is limited by adjusting the evolution range.

[0108] According to an embodiment of the present invention, it further includes:

[0109] The preset environmental sensitivity coefficient is optimized based on the environmental change index to obtain the gene mutation probability adjustment value;

[0110] Let the preset gene mutation probability be P, and its formula is: ,in denoted as the initial probability of gene mutation, and k represents the adjustment value of the gene mutation probability.

[0111] It should be noted that the preset environmental sensitivity coefficient is set to 1.2, and the gene mutation probability adjustment value is equal to the environmental change index multiplied by the preset environmental sensitivity coefficient. When the preset gene mutation probability is greater than 1, the corresponding preset gene mutation probability is set to 1, for example, the initial gene mutation probability is set to 5%.

[0112] According to an embodiment of the present invention, the optimization step specifically includes:

[0113] Obtain the service to be transmitted;

[0114] Set the corresponding optimization weight parameters according to the service to be transmitted;

[0115] Based on the corresponding optimization weight parameters, set the strategy chromosome optimization function;

[0116] The network state data is divided according to the policy chromosome to obtain the network state data of the corresponding policy chromosome.

[0117] Send the network state data of the corresponding policy chromosome to the policy chromosome optimization function to obtain the optimization index of the corresponding policy chromosome;

[0118] If the optimization index of the strategy chromosome is greater than the optimization index of the strategy chromosome before evolution, then the evolved strategy chromosome will replace the previous strategy chromosome.

[0119] If the optimization index of the strategy chromosome is less than or equal to the optimization index of the strategy chromosome before evolution, then the strategy chromosome before evolution is restored, and the corresponding evolution path is recorded.

[0120] After a set number of evolutions, the optimized strategy chromosome is output.

[0121] It should be noted that the optimization index is set as F, and its formula is:

[0122] Where A represents link latency, B represents available bandwidth, C represents network packet loss rate, and E represents node energy consumption. , , and These are the corresponding weight coefficients. Based on the service to be transmitted, determine the corresponding service type and set the corresponding optimization weight parameters accordingly. Dynamic configuration is performed based on the current service type; for example, if the service to be transmitted is real-time video, the corresponding weight coefficient can be set to... , , , Prioritizing low latency and high bandwidth; if the service to be transmitted is a lot data acquisition service, the corresponding weighting coefficient can be set to... , , , Prioritizing low packet loss rate and low energy consumption; for example, if the number of evolutions is set to 60, then the strategy chromosome that remains after 60 evolutions is the optimal deployment strategy; in addition, the recorded evolution path prevents the calculation of duplicate paths, further reducing the amount of computation.

[0123] Furthermore, when the evolution time exceeds a preset evolution time threshold, the evolution step is stopped, the currently retained policy chromosome is output, and the retained policy chromosome is set as the optimal deployment strategy. The preset evolution time threshold is used to reasonably control the computation latency, for example, setting the preset evolution time threshold to 0.5 seconds. The preset evolution time threshold prevents excessive redundant computation during the evolution process, which would lead to excessive latency, and further improves the efficiency of network deployment strategies.

[0124] According to an embodiment of the present invention, it further includes:

[0125] Based on the established blockchain smart contract, the edge nodes periodically call out the names of the sensor nodes;

[0126] Extract the time points at which edge nodes mark sensor nodes and start a countdown for a set time.

[0127] If the countdown timer reaches zero and the sensor node has not yet reported data, the sensor node will be marked, and the marked sensor node will be obtained.

[0128] Replace the corresponding tagged sensor node with a preset backup sensor node and write it to the blockchain to broadcast to other edge nodes and the central controller.

[0129] It should be noted that, through blockchain smart contracts, edge nodes periodically call out the sensor nodes on the blockchain. After receiving the call notification, the sensor node needs to respond, set the response data, and report the response data. If the edge node does not receive the response data from the corresponding sensor node within a set time, the sensor node is set to invalid, for example, the set time is 10 seconds. This invention greatly improves the reliability and operation and maintenance efficiency of the network through the network's "self-healing".

[0130] According to embodiments of the present invention, it further includes:

[0131] Obtain the number of currently detected failed sensor nodes;

[0132] Divide the number of failed sensor nodes by the total number of nodes in the current coverage area to obtain the percentage of failed sensor nodes.

[0133] If the percentage of failed sensor nodes exceeds the preset failure threshold, a warning message will be generated.

[0134] It should be noted that the preset failure threshold is 0.1. When the proportion of failed sensor nodes is greater than 0.1, there may be large-scale natural disasters or other phenomena in the corresponding coverage area. These phenomena damage the wireless network transmission facilities in a large area of ​​the coverage area. Therefore, a warning message is sent to the corresponding management terminal. In addition, the deployment strategy is replaced on a large scale based on the warning message.

[0135] Figure 2 A block diagram of a wireless network intelligent optimization deployment system according to the present invention is shown.

[0136] like Figure 2 As shown, a second aspect of the present invention provides a wireless network intelligent optimization deployment system 2, including a memory 21 and a processor 22. The memory stores a wireless network intelligent optimization deployment method program, which, when executed by the processor, performs the following steps:

[0137] Obtain the sensor node location and store the edge nodes of the sensor node location within the corresponding area;

[0138] Edge nodes report the stored sensor node locations to the central controller;

[0139] Genetic algorithms are used to generate an initial policy set containing multiple network deployment strategies, and each deployment strategy is encoded as a policy chromosome.

[0140] Based on the sampling information, the edge nodes collect network status data from the sensor nodes;

[0141] When the deployment strategy is only within the scope of the corresponding edge node, the corresponding edge node evolves and optimizes the strategy chromosome based on network state data to obtain the optimized deployment strategy;

[0142] When a deployment strategy exists in multiple edge node ranges, the network status data is uploaded to the central controller. The central controller evolves and optimizes the strategy chromosome based on the network status data to obtain the optimized deployment strategy.

[0143] The optimized deployment strategy is sent to the corresponding edge nodes for execution;

[0144] The network status data includes link latency, network packet loss rate, network load, available bandwidth, and node energy consumption.

[0145] In this scheme, the step of generating the sampling information includes:

[0146] Based on a fixed frequency, edge nodes acquire the raw received signal strength or signal-to-noise ratio;

[0147] Arrange the original received signal strengths or signal-to-noise ratios in chronological order of acquisition to obtain the dataset. ;

[0148] Based on the set sliding time window, extract adjacent data within the corresponding sliding time window;

[0149] Calculate the difference between adjacent data within the sliding time window, take the absolute value, and obtain the difference between adjacent indicators.

[0150] By traversing the entire sliding time window, a set of differences between adjacent indicators is obtained. The average value of the values ​​in the set of differences between adjacent indicators is then calculated to obtain the stability index corresponding to the current sliding time window. ;

[0151] Set the current signal fluctuation value to Its formula is If the current signal fluctuation value is greater than the preset signal fluctuation threshold, sampling information is generated.

[0152] In this solution, the step of obtaining the preset signal fluctuation threshold specifically includes:

[0153] Acquire the environment in which the original received signal strength or signal-to-noise ratio is collected;

[0154] Determine the initial threshold for signal fluctuations based on the corresponding environment;

[0155] Extract the stability metrics from the previous sliding time window;

[0156] The initial threshold for signal fluctuation is optimized based on the stability index of the previous sliding time window to obtain the preset signal fluctuation threshold for the current sliding time window.

[0157] This invention discloses a method and system for intelligent optimization deployment of wireless networks. By distributing network deployment strategies to edge nodes, the computational load on the central controller is reduced, improving the optimization efficiency of network deployment strategies. Furthermore, by using a "double mutation mechanism" to evolve the strategy chromosome, dynamically changing gene mutation probabilities and environmental evolution ranges are introduced, enabling the algorithm to quickly escape local optima and dynamically track and adapt to changes in the network environment, significantly improving the convergence speed of the evolutionary algorithm. Finally, the strategy chromosome is analyzed based on network state data to determine the optimized deployment strategy. This invention significantly reduces the overall overhead and latency of network deployment strategies and improves efficiency.

[0158] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0159] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0160] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0161] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0162] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for intelligent optimization deployment of a wireless network, characterized in that, include: Obtain the sensor node location and store the edge nodes of the sensor node location within the corresponding area; Edge nodes report the stored sensor node locations to the central controller; Genetic algorithms are used to generate an initial policy set containing multiple network deployment strategies, and each deployment strategy is encoded as a policy chromosome. Based on the sampling information, the edge nodes collect network status data from the sensor nodes; When the deployment strategy is only within the scope of the corresponding edge node, the corresponding edge node evolves and optimizes the strategy chromosome based on network state data to obtain the optimized deployment strategy; When a deployment strategy exists in multiple edge node ranges, the network status data is uploaded to the central controller. The central controller evolves and optimizes the strategy chromosome based on the network status data to obtain the optimized deployment strategy. The optimized deployment strategy is sent to the corresponding edge nodes for execution; The network status data includes link latency, network packet loss rate, network load, available bandwidth, and node power consumption. The steps for generating the sampling information include: Based on a fixed frequency, edge nodes acquire the raw received signal strength or signal-to-noise ratio; The original received signal strength or signal-to-noise ratio is arranged in chronological order of acquisition time to obtain the data set. ; Based on the set sliding time window, extract adjacent data within the corresponding sliding time window; Calculate the difference between adjacent data within the sliding time window, take the absolute value, and obtain the difference between adjacent indicators. By traversing the entire sliding time window, a set of differences between adjacent indicators is obtained. The average value of the values ​​in the set of differences between adjacent indicators is then calculated to obtain the stability index corresponding to the current sliding time window. ; Set the current signal fluctuation value to Its formula is If the current signal fluctuation value is greater than the preset signal fluctuation threshold, sampling information is generated; The evolutionary steps specifically include: Extract the network load and available bandwidth from the network status data of the current time point and the previous time point; By comparing and analyzing the network load at the current time point with the network load at the previous time point, the absolute value of the change in network load can be obtained. By comparing and analyzing the available bandwidth at the current time point with the available bandwidth at the previous time point, the absolute value of the change in available bandwidth is obtained. The current environmental change index is determined based on the absolute values ​​of the network load change rate and the available bandwidth change rate. Based on the range within which the environmental change index falls, the evolutionary range of the corresponding strategy chromosome is determined; Based on the evolutionary range, the values ​​of one or more gene sites in the strategy chromosome are randomly changed according to the preset gene mutation probability to obtain a new strategy chromosome. Also includes: The preset environmental sensitivity coefficient is optimized based on the environmental change index to obtain the gene mutation probability adjustment value; Let the preset gene mutation probability be P, and its formula is: ,in represents the initial probability of gene mutation, and k represents the adjustment value of the gene mutation probability; The optimization steps specifically include: Obtain the service to be transmitted; Set the corresponding optimization weight parameters according to the service to be transmitted; Based on the corresponding optimization weight parameters, set the strategy chromosome optimization function; The network state data is divided according to the policy chromosome to obtain the network state data of the corresponding policy chromosome. Send the network state data of the corresponding policy chromosome to the policy chromosome optimization function to obtain the optimization index of the corresponding policy chromosome; If the optimization index of the strategy chromosome is greater than the optimization index of the strategy chromosome before evolution, then the evolved strategy chromosome will replace the previous strategy chromosome. If the optimization index of the strategy chromosome is less than or equal to the optimization index of the strategy chromosome before evolution, then the strategy chromosome before evolution is restored, and the corresponding evolution path is recorded. After a set number of evolutions, the optimized strategy chromosome is output.

2. The method for intelligent optimization deployment of a wireless network according to claim 1, characterized in that, The steps for obtaining the preset signal fluctuation threshold specifically include: Acquire the environment in which the original received signal strength or signal-to-noise ratio is collected; Determine the initial threshold for signal fluctuations based on the corresponding environment; Extract the stability metrics from the previous sliding time window; The initial threshold for signal fluctuation is optimized based on the stability index of the previous sliding time window to obtain the preset signal fluctuation threshold for the current sliding time window.

3. The method for intelligent optimization deployment of a wireless network according to claim 1, characterized in that, Also includes: Based on the established blockchain smart contract, the edge nodes periodically call out the names of the sensor nodes; Extract the time points at which edge nodes mark sensor nodes and start a countdown for a set time. If the countdown timer reaches zero and the sensor node has not yet reported data, the sensor node will be marked, and the marked sensor node will be obtained. Replace the corresponding tagged sensor node with a preset backup sensor node and write it to the blockchain to broadcast to other edge nodes and the central controller.

4. A wireless network intelligent optimization deployment system, characterized in that, The system includes a memory and a processor. The memory stores a program for a wireless network intelligent optimization deployment method. When the processor executes the program, the wireless network intelligent optimization deployment method performs the following steps: Obtain the sensor node location and store the edge nodes of the sensor node location within the corresponding area; Edge nodes report the stored sensor node locations to the central controller; Genetic algorithms are used to generate an initial policy set containing multiple network deployment strategies, and each deployment strategy is encoded as a policy chromosome. Based on the sampling information, the edge nodes collect network status data from the sensor nodes; When the deployment strategy is only within the scope of the corresponding edge node, the corresponding edge node evolves and optimizes the strategy chromosome based on network state data to obtain the optimized deployment strategy; When a deployment strategy exists in multiple edge node ranges, the network status data is uploaded to the central controller. The central controller evolves and optimizes the strategy chromosome based on the network status data to obtain the optimized deployment strategy. The optimized deployment strategy is sent to the corresponding edge nodes for execution; The network status data includes link latency, network packet loss rate, network load, available bandwidth, and node power consumption. The steps for generating the sampling information include: Based on a fixed frequency, edge nodes acquire the raw received signal strength or signal-to-noise ratio; The original received signal strength or signal-to-noise ratio is arranged in chronological order of acquisition time to obtain the data set. ; Based on the set sliding time window, extract adjacent data within the corresponding sliding time window; Calculate the difference between adjacent data within the sliding time window, take the absolute value, and obtain the difference between adjacent indicators. By traversing the entire sliding time window, a set of differences between adjacent indicators is obtained. The average value of the values ​​in the set of differences between adjacent indicators is then calculated to obtain the stability index corresponding to the current sliding time window. ; Set the current signal fluctuation value to Its formula is If the current signal fluctuation value is greater than the preset signal fluctuation threshold, sampling information is generated; The evolutionary steps specifically include: Extract the network load and available bandwidth from the network status data of the current time point and the previous time point; By comparing and analyzing the network load at the current time point with the network load at the previous time point, the absolute value of the change in network load can be obtained. By comparing and analyzing the available bandwidth at the current time point with the available bandwidth at the previous time point, the absolute value of the change in available bandwidth is obtained. The current environmental change index is determined based on the absolute values ​​of the network load change rate and the available bandwidth change rate. Based on the range within which the environmental change index falls, the evolutionary range of the corresponding strategy chromosome is determined; Based on the evolutionary range, the values ​​of one or more gene sites in the strategy chromosome are randomly changed according to the preset gene mutation probability to obtain a new strategy chromosome. Also includes: The preset environmental sensitivity coefficient is optimized based on the environmental change index to obtain the gene mutation probability adjustment value; Let the preset gene mutation probability be P, and its formula is: ,in represents the initial probability of gene mutation, and k represents the adjustment value of the gene mutation probability; The optimization steps specifically include: Obtain the service to be transmitted; Set the corresponding optimization weight parameters according to the service to be transmitted; Based on the corresponding optimization weight parameters, set the strategy chromosome optimization function; The network state data is divided according to the policy chromosome to obtain the network state data of the corresponding policy chromosome. Send the network state data of the corresponding policy chromosome to the policy chromosome optimization function to obtain the optimization index of the corresponding policy chromosome; If the optimization index of the strategy chromosome is greater than the optimization index of the strategy chromosome before evolution, then the evolved strategy chromosome will replace the previous strategy chromosome. If the optimization index of the strategy chromosome is less than or equal to the optimization index of the strategy chromosome before evolution, then the strategy chromosome before evolution is restored, and the corresponding evolution path is recorded. After a set number of evolutions, the optimized strategy chromosome is output.

5. The wireless network intelligent optimization deployment system according to claim 4, characterized in that, The steps for obtaining the preset signal fluctuation threshold specifically include: Acquire the environment in which the original received signal strength or signal-to-noise ratio is collected; Determine the initial threshold for signal fluctuations based on the corresponding environment; Extract the stability metrics from the previous sliding time window; The initial threshold for signal fluctuation is optimized based on the stability index of the previous sliding time window to obtain the preset signal fluctuation threshold for the current sliding time window.

Images