Communication ad hoc network method and system applied to capital construction non-signal site

Abstract

The invention discloses a communication ad hoc network method and system applied to a capital construction non-signal site, and belongs to the technical field of communication, and the method comprises the steps: determining the spatial distribution of node equipment, and obtaining each initial planning path; creating a four-dimensional spectrum map, and dynamically adjusting a modulation mode; determining the quality of each initial planning path; establishing a service priority; judging whether energy supply is needed or not; establishing a communication-energy consumption optimization algorithm to obtain a network optimization scheme; constructing a node equipment credibility model, and determining an optimal transmission path; and constructing a node fault prediction model, predicting a node equipment fault, and triggering a maintenance instruction. According to the invention, a stable communication network can be quickly established, the cost is reduced, the communication reliability and safety are improved, the energy consumption management is optimized, the service life of a node equipment battery is prolonged, the continuity of key services is ensured, a dynamic construction environment is adapted, and intelligent and automatic communication management is realized.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and specifically to a communication self-organizing network method and system applied to infrastructure signal-free sites. Background Art

[0002] Infrastructure signal-free sites are usually located in areas far from cities, such as mountains, tunnels, underground projects, offshore platforms, etc. Traditional communication networks (such as 4G / 5G, optical fibers) in these places cannot cover or have extremely weak signals. Such scenarios have the following typical characteristics: there is no public network coverage, and operator base station signals cannot reach, resulting in the failure of conventional communication devices such as mobile phones and walkie-talkies; the environment is complex, and factors such as terrain obstacles (such as tunnels, forests), electromagnetic interference (such as high-voltage equipment), or extreme climates (such as heavy rain, high cold) further hinder communication; the dynamics are high, and the positions of construction workers, vehicles, and equipment change frequently, requiring a flexible and adaptable communication solution.

[0003] Communication self-organizing network is a wireless network technology that does not require fixed infrastructure and allows nodes to self-organize into a network. Its core features include decentralization, self-organization and self-repair, and multi-hop transmission. Typical technologies include Wi-Fi Mesh, ZigBee, LoRa self-organizing network, and anti-interference protocols designed specifically for industry. However, existing communication self-organizing network technologies have many deficiencies: on the one hand, some solutions rely on satellite communication, resulting in high costs and large communication delays; on the other hand, the network security is insufficient, making it difficult to effectively resist external attacks and the risk of data leakage. These drawbacks make it difficult for existing technologies to meet the requirements of infrastructure signal-free sites for real-time, low-cost, and highly reliable communication. Summary of the Invention

[0004] The present invention provides a communication self-organizing network method and system applied to infrastructure signal-free sites, which can quickly build a stable communication network, reduce costs, improve communication reliability and security, optimize energy consumption management, extend the battery life of node devices, ensure the continuity of critical services, adapt to the dynamic construction environment, and achieve intelligent and automated communication management.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: A communication self-organizing network method applied to infrastructure signal-free sites, comprising the following steps: Based on multiple node devices deployed in the construction area, construct a three-dimensional topological structure of the construction area, combine the digital elevation model of the construction area generated by lidar scanning carried by an unmanned aerial vehicle, determine the spatial distribution of the node devices, and obtain each initial planned path; Based on the spatial distribution of the node devices, create a four-dimensional spectrum map and dynamically adjust the modulation method; Based on the spatial distribution of the node devices and the four-dimensional spectrum map, establish a path quality prediction algorithm to determine the quality of each initial planned path; Establish service priorities based on the quality of each initial planned path; Obtain the remaining power of each node device, determine whether energy replenishment is required, and if so, perform energy replenishment according to the corresponding service priorities; Based on the quality of each initial planned path, service priorities, and energy replenishment results, combined with the remaining power of each node device obtained, establish a communication - energy consumption optimization algorithm, obtain a network optimization plan, and perform network optimization; Based on each node device after network optimization, construct a node device trust model to determine the optimal transmission path; Obtain the historical fault operation data of each node device, construct a node fault prediction model, predict node device faults, and trigger maintenance instructions.

[0006] Preferably, determine the spatial distribution of node devices as follows: Node devices include master node devices, backbone node devices, relay node devices, sensing node devices, mobile node devices, and energy node devices; Obtain the motion state data of node devices, including acceleration, angular velocity, and magnetic field intensity; Obtain the relative distances between each node device, combined with the motion state data of the node devices, to obtain the three - dimensional coordinates of each node device, and construct a three - dimensional topological structure of the construction area; Obtain the size and shape of the construction area in the data repository, plan the flight path of the unmanned aerial vehicle, and based on the lidar device carried by the unmanned aerial vehicle, emit laser pulses and measure the time difference of the reflected laser to obtain the distance of the target object; The data collected by the lidar device is stored in the form of point clouds. Each point contains three - dimensional coordinate and reflection intensity information. Import the collected point cloud data into geographic information system software for pre - processing, and convert the point cloud data into regular grid data through an interpolation algorithm to generate a digital elevation model; The digital elevation model represents the elevation information of the terrain in the form of a two - dimensional grid, and each grid cell corresponds to an elevation value; The generated digital elevation model is pre - loaded into the storage units of each node device in the three - dimensional topological structure of the construction area. The node devices access the digital elevation model to obtain the terrain information of the construction area, perform terrain analysis, and obtain each initial planned path.

[0007] Preferably, create a four - dimensional spectrum map and dynamically adjust the modulation method as follows: Divide the wide frequency band into multiple sub - bands. The RF front - end of the node device sequentially scans each sub - band within 5 seconds to obtain the signal strength, interference strength, and center frequency within the sub - band; Store the center frequency, the timestamp of the scan, the signal strength, the interference strength, and the three-dimensional coordinates of the node device in the local storage unit of the node device to obtain a four-dimensional spectrum map; Based on the signal strength and interference strength in the four-dimensional spectrum map, evaluate the channel quality of the sub-band to obtain the channel quality evaluation result of the sub-band; Compare the channel quality evaluation result of the sub-band with the channel quality evaluation results of each reference sub-band stored in the data repository. The modulation method corresponding to the channel quality evaluation result of the same reference sub-band is the modulation method corresponding to the channel quality evaluation result of this sub-band; Among them, the process of obtaining the channel quality evaluation result of the sub-band is as follows: Compare the signal strength with the signal evaluation threshold stored in the data repository. If the signal strength is less than the corresponding evaluation threshold, the channel quality level of the corresponding sub-band is level one, and the channel quality of the corresponding sub-band is poor; If the signal strength is not less than the signal evaluation threshold, compare the interference strength with the interference evaluation threshold stored in the data repository. If the interference strength is less than the interference evaluation threshold, the channel quality level of the corresponding sub-band is level one, and the channel quality of the corresponding sub-band is good; If the interference strength is not less than the interference evaluation threshold, the channel quality level of the corresponding sub-band is level two, and the channel quality of the corresponding sub-band is medium.

[0008] Preferably, establish a path quality prediction algorithm to determine the path quality of each path. The process is as follows: Divide the initial planned path, including the main path, the backup path, and the emergency path; The master node device obtains the path quality evaluation data of each initial planned path, including signal strength, bit error rate, signal-to-noise ratio, delay time, and packet loss rate, and performs weighted summation on the path quality evaluation data of each initial planned path to obtain the comprehensive quality score of each initial planned path; Compare the comprehensive quality score of each initial planned path with the comprehensive quality score threshold of the corresponding reference path stored in the data repository. If the comprehensive quality score of the initial planned path is greater than the comprehensive quality score threshold of the corresponding reference path, the path quality of this initial planned path is high, otherwise, the path quality of this path is low; If the quality of the main path is low, switch to the backup path with high path quality, otherwise, do not switch; If the main path and each backup path are both of low path quality, switch to the emergency path with high path quality; If the main path, each backup path, and each emergency path are all of low path quality, issue an alarm.

[0009] Preferably, establish service priorities. The process is as follows: Divide the business priorities, including the lowest priority 4, low priority 3, medium priority 2, high priority 1, and highest priority 0; Among them, the lowest priority 4 corresponds to non-real-time data transmission, the low priority 3 corresponds to device status monitoring, the medium priority 2 corresponds to video monitoring, the high priority 1 corresponds to dangerous gas alarm, and the highest priority 0 corresponds to emergency braking instructions; Allocate a dedicated frequency band, dedicated broadband, and dedicated path for the emergency braking instruction. Sort the comprehensive quality scores corresponding to the paths with high quality in each path from largest to smallest, and select the path with high quality and the largest comprehensive quality score as the dedicated path for the emergency braking instruction. When the emergency braking instruction needs to be transmitted, transmit it immediately.

[0010] Preferably, judge whether energy replenishment is required. The process is as follows: Measure the energy consumption values of each node device under different environmental conditions in the laboratory control environment. Divide the energy consumption values and historical environmental data into a training set and a validation set. Input the training set into the neural network model to establish an energy consumption model, and then use the validation set to verify the energy consumption model; Obtain the current energy consumption values and current environmental data of each node device, and input them into the trained energy consumption model to obtain the predicted energy consumption values of each node device; Subtract the obtained current remaining power of each node device from the corresponding predicted energy consumption value to obtain the comprehensive power of each node device. Compare the comprehensive power of each node device with the power threshold stored in the data repository in turn to judge whether the comprehensive power of each node device is less than the power threshold. If it is less, the energy replenishment process of this node device is triggered for energy replenishment. If it is not less, it is not triggered.

[0011] Preferably, establish a communication-energy consumption optimization algorithm to obtain a network optimization plan. The process is as follows: Obtain the energy transmission efficiency of the node device. Divide the energy consumption value of the node device by the energy transmission efficiency to obtain the total energy consumption. Obtain communication data, including delay time, reliability, and data transmission rate, and sum the communication data weighted to obtain a communication performance score; Define an objective function based on the total energy consumption and the communication performance score; Determine the constraint conditions, including delay constraint, data rate constraint, reliability constraint, transmission power constraint, battery capacity constraint, and energy transmission efficiency constraint: Delay constraint: The delay time of data transmission does not exceed the maximum allowable delay time; Data rate constraint: The data rate of data transmission is not less than the minimum data transmission rate; Reliability constraint: The reliability of data transmission is not less than the minimum reliability; Transmission power constraint, where the transmission power does not exceed the maximum transmission power; Battery capacity constraint, where the remaining power before energy replenishment is not less than the minimum remaining energy; Energy transmission efficiency constraint, where the energy transmission efficiency is not less than the minimum efficiency; Determine the minimized objective function based on the genetic algorithm. The optimal solution includes the optimal delay time, optimal data rate, optimal reliability, optimal transmission power, optimal remaining power, and optimal energy transmission efficiency, denoted as the network adjustment scheme.

[0012] Preferably, construct a node device trustworthiness model to determine the best transmission path, and the process is as follows: Obtain the historical performance data of the node device, including the data transmission success rate, historical failure rate, and energy consumption efficiency. Compare the obtained data transmission success rate, historical failure rate, and energy consumption efficiency with the data transmission success rate threshold, historical failure rate threshold, and energy consumption efficiency threshold stored in the data repository, and perform weighted summation to obtain the initial trustworthiness; Compare the initial trustworthiness with each reference trustworthiness stored in the data repository. The trust level corresponding to the closest reference trustworthiness is the trust level of the initial trustworthiness; Based on the trust level of the node device, select the initial planned path corresponding to the node device with the highest trust level as the best transmission path.

[0013] Preferably, construct a node fault prediction model to predict node device faults and trigger maintenance instructions, and the process is as follows: Extract features from the historical fault operation data to obtain historical fault operation feature data; Design an LSTM network architecture, including an input layer, an LSTM layer, a fully connected layer, and an output layer; set network hyperparameters, including the number of LSTM units, the number of layers, the learning rate, the batch size, the activation function, and the optimizer; Divide the historical node device fault feature data into a training set, a validation set, and a test set. Use the training set to train the LSTM neural network prediction model to obtain the node fault prediction model; Use the validation set to validate the node fault prediction model and use the test set to test the node fault prediction model; Obtain the operation data of the node device and input it into the trained node fault prediction model to obtain the fault prediction result of the node device. If the fault prediction result is that a node device fault occurs, trigger a maintenance instruction.

[0014] Applied to the communication ad hoc network system at the infrastructure signal-free site to implement the above method, including: An initial planning path establishment module, which is used to construct a three-dimensional topological structure of the construction area based on multiple node devices deployed in the construction area, combine the lidar scanning carried by the unmanned aerial vehicle to generate a digital elevation model of the construction area, determine the spatial distribution of the node devices, and obtain each initial planning path; A spectrum management module, which is used to create a four-dimensional spectrum map based on the spatial distribution of the node devices and dynamically adjust the modulation mode; A path quality evaluation module, which is used to establish a path quality prediction algorithm based on the spatial distribution of the node devices and the four-dimensional spectrum map, and determine the quality of each initial planning path; A service priority management module, which is used to establish a service priority based on the quality of each initial planning path; An energy management module, which is used to obtain the remaining power of each node device, judge whether energy replenishment is required, and if so, perform energy replenishment according to the corresponding service priority; A communication - energy consumption optimization module, which is used to establish a communication - energy consumption optimization algorithm based on the quality of each initial planning path, service priority, and energy replenishment result, combine the remaining power of each node device obtained, obtain a network optimization plan, and perform network optimization; A path selection module, which is used to construct a node device trust model based on each node device after network optimization and determine the best transmission path; A fault prediction and maintenance module, which is used to obtain the historical fault operation data of each node device, construct a node fault prediction model, predict the faults of the node devices, and trigger maintenance instructions.

[0015] The present invention has the following beneficial effects: Through the dynamic self - organizing network technology, the present invention quickly establishes a stable and reliable communication network in the construction area, reduces costs, significantly improves the reliability and security of communication, optimizes energy consumption management at the same time, prolongs the battery life of node devices, and improves the user experience. In addition, it can adapt to the dynamically changing construction environment, ensure the continuity of critical services and the overall performance of the network, thereby providing an intelligent and automated communication solution for the signal - free site of infrastructure construction, and significantly improving the economic benefits of the network and user satisfaction. Description of the Drawings

[0016] Figure 1 It is the method flow chart of the present invention; Figure 2 It is the module schematic diagram of the system of the present invention. Detailed Embodiments

[0017] Next, in combination with the drawings, the technical solutions in the embodiments of the present invention will be described clearly and completely.

[0018] Embodiment 1: As Figure 1As shown, a communication ad-hoc network method applied to infrastructure signal-free sites includes the following steps: Based on multiple node devices deployed in the construction area, construct a three-dimensional topological structure of the construction area, combine with the lidar scanning carried by the unmanned aerial vehicle to generate a digital elevation model of the construction area, determine the spatial distribution of the node devices, and obtain each initial planned path; Based on the spatial distribution of the node devices, create a four-dimensional spectrum map and dynamically adjust the modulation method; Based on the spatial distribution of the node devices and the four-dimensional spectrum map, establish a path quality prediction algorithm to determine the quality of each initial planned path; Based on the quality of each initial planned path, establish a service priority; Obtain the remaining power of each node device, determine whether energy replenishment is required, and if so, perform energy replenishment according to the corresponding service priority; Based on the quality of each initial planned path, service priority, and energy replenishment result, combine with the remaining power of each node device obtained, establish a communication-energy consumption optimization algorithm, obtain a network optimization plan, and perform network optimization; Based on each node device after network optimization, construct a node device trust model and determine the best transmission path; Obtain the historical fault operation data of each node device, construct a node fault prediction model, predict node device faults, and trigger maintenance instructions.

[0019] Determine the spatial distribution of the node devices, and the process is as follows: The node devices include master node devices, backbone node devices, relay node devices, sensing node devices, mobile node devices, and energy node devices; Obtain the motion state data of the node devices, including acceleration, angular velocity, and magnetic field strength; Obtain the relative distance between each node device, combine with the motion state data of the node devices, obtain the three-dimensional coordinates of each node device, and construct a three-dimensional topological structure of the construction area; Obtain the size and shape of the construction area in the data repository, plan the flight path of the unmanned aerial vehicle, based on the lidar device carried by the unmanned aerial vehicle, emit laser pulses, measure the time difference of the reflected laser, and obtain the distance of the target object; The data collected by the lidar device is stored in the form of point clouds. Each point contains three-dimensional coordinate and reflection intensity information. Import the collected point cloud data into geographic information system software for preprocessing, and convert the point cloud data into regular grid data through interpolation algorithm to generate a digital elevation model; The digital elevation model represents the elevation information of the terrain in the form of a two-dimensional grid, and each grid cell corresponds to an elevation value; The generated digital elevation model is pre-loaded into the storage units of each node device in the three-dimensional topology of the construction area. The node device accesses the digital elevation model to obtain the terrain information of the construction area, conducts terrain analysis, and obtains each initial planned path.

[0020] Obtain the acceleration, angular velocity, and magnetic field intensity of the node device, and provide the dynamic position information of the node device in three-dimensional space, including whether the node device moves and the direction and speed of movement. Measure the distance between node devices, provide accurate spatial relationship data, and construct a three-dimensional model reflecting the actual positions of node devices. The unmanned aerial vehicle is equipped with a lidar for flight scanning. The lidar emits laser pulses and receives the reflected pulses, and determines the distance to the target object by calculating the time difference. It can quickly cover a large area and generate high-precision three-dimensional point cloud data. The point cloud data is processed by GIS software and converted into regular grid data to form a digital elevation model. The digital elevation model represents the elevation information of the terrain in the form of a two-dimensional grid. Each grid cell corresponds to an elevation value, providing terrain information for the node device for terrain analysis and communication path planning.

[0021] The three-dimensional topology provides the accurate position of each node device, which helps to optimize the selection of communication links and reduce signal attenuation. The digital elevation model enables the node device to adjust the communication path according to the terrain features, such as bypassing obstacles or selecting the best propagation path. The unmanned aerial vehicle scanning can quickly generate high-precision topographic maps, which is suitable for areas with complex or frequently changing terrains, providing real-time data support for communication path planning.

[0022] Create a four-dimensional spectrum map and dynamically adjust the modulation mode. The process is as follows: Divide the wide frequency band into multiple sub-bands. The RF front-end of the node device sequentially scans each sub-band within 5 seconds to obtain the signal strength, interference strength, and center frequency within the sub-band; Store the center frequency, scanned timestamp, signal strength, interference strength, and the three-dimensional coordinates of the node device in the local storage unit of the node device to obtain a four-dimensional spectrum map; Based on the signal strength and interference strength in the four-dimensional spectrum map, evaluate the channel quality of the sub-band to obtain the channel quality evaluation result of the sub-band; Compare the channel quality evaluation result of the sub-band with the channel quality evaluation results of each reference sub-band stored in the data repository. The modulation mode corresponding to the channel quality evaluation result of the same reference sub-band is the modulation mode corresponding to the channel quality evaluation result of the sub-band; Among them, the process of obtaining the channel quality evaluation result of the sub-band is as follows: Compare the signal strength with the signal evaluation threshold stored in the data repository. If the signal strength is less than the corresponding evaluation threshold, the channel quality level of the corresponding sub-band is level one, and the channel quality of the corresponding sub-band is poor. If the signal strength is not less than the signal evaluation threshold, compare the interference strength with the interference evaluation threshold stored in the data repository. If the interference strength is less than the interference evaluation threshold, the channel quality level of the corresponding sub-band is level one, and the channel quality of the corresponding sub-band is good. If the interference strength is not less than the interference evaluation threshold, the channel quality level of the corresponding sub-band is level two, and the channel quality of the corresponding sub-band is medium.

[0023] The radio frequency front end of the node device sequentially scans multiple predefined sub-bands within 5 seconds, and each sub-band covers a specific frequency range. Within each sub-band, the node device measures the signal strength, interference strength, and center frequency, which are crucial for evaluating the communication quality of the evaluation band. Store the measured center frequency, timestamp, signal strength, interference strength, and the three-dimensional coordinates of the node device in the local storage unit to form a four-dimensional data set, where each point represents the signal and interference conditions of a sub-band at a specific time and space position. Evaluate the channel quality of the sub-band based on the signal strength and interference strength to obtain the channel quality evaluation result. Compare the evaluation result with the reference channel quality evaluation result in the data repository to determine the optimal modulation method. Select the most suitable modulation method for each sub-band according to the channel quality evaluation result, such as QPSK, 16QAM, or OFDM, etc.

[0024] Accurate frequency band division and quality evaluation can effectively utilize the available spectrum, avoid wasting resources on inefficient frequency bands, ensure the best communication quality under different channel conditions, reduce the bit error rate, and improve the data transmission rate.

[0025] Establish a path quality prediction algorithm to determine the quality of each path. The process is as follows: Divide the initial planned path, including the main path, backup path, and emergency path; The master control node device obtains the path quality evaluation data of each initial planned path, including signal strength, bit error rate, signal-to-noise ratio, delay time, and packet loss rate, and performs a weighted sum of the path quality evaluation data of each initial planned path to obtain the comprehensive quality score of each initial planned path; Compare the comprehensive quality score of each initial planned path with the comprehensive quality score threshold of the corresponding reference path stored in the data repository. If the comprehensive quality score of the initial planned path is greater than the comprehensive quality score threshold of the corresponding reference path, the path quality of the initial planned path is high; otherwise, the path quality of this path is low; If the quality of the primary path is low, switch to the backup path with high path quality; otherwise, do not switch. If the primary path and all backup paths have low path quality, switch to the emergency path with high path quality. If the primary path, all backup paths, and all emergency paths have low path quality, issue an alarm.

[0026] The primary path is the path with the best and most stable signal quality, used for transmitting critical services. The backup path is an alternative path when the primary path has problems, and its quality is slightly lower than that of the primary path. The emergency path is the last resort when both the primary path and the backup path are unavailable. It may have lower quality but can provide basic communication guarantee.

[0027] Dynamically select the best path to reduce communication failures caused by path quality problems. According to the path quality score, select the optimal path to reduce unnecessary energy consumption and extend the battery life of node devices. Through prediction and preventive maintenance, reduce the maintenance requirements and costs caused by path failures. By ensuring the stable transmission of critical services, improve the user's service quality experience. In a dynamically changing construction environment, the network can still maintain stable communication.

[0028] Establish service priorities as follows: Divide service priorities into lowest priority 4, low priority 3, medium priority 2, high priority 1, and highest priority 0. Among them, the lowest priority 4 corresponds to non-real-time data transmission, the low priority 3 corresponds to device status monitoring, the medium priority 2 corresponds to video monitoring, the high priority 1 corresponds to hazardous gas alarm, and the highest priority 0 corresponds to emergency braking instructions. Allocate a dedicated frequency band, dedicated broadband, and dedicated path for emergency braking instructions. Sort the comprehensive quality scores corresponding to the paths with high quality in each path from largest to smallest, and select the path with high quality and the largest comprehensive quality score as the dedicated path for emergency braking instructions. When emergency braking instructions need to be transmitted, transmit them immediately.

[0029] Businesses are divided into five priorities according to their requirements for real-time performance, importance, and quality of service. Each priority corresponds to a different type of business. Allocate a dedicated channel for the emergency braking command: Determine that the emergency braking command is the highest priority level 0 because it requires the highest reliability and the lowest latency. Allocate a dedicated frequency band, dedicated broadband, and dedicated path for services at the highest priority level 0 to ensure that their transmissions are not interfered with by other services. Evaluate the quality of each path, including key indicators such as signal strength, bit error rate, signal-to-noise ratio, latency time, and packet loss rate. Convert the evaluation results into a comprehensive quality score and assign a score to each path. Sort the paths in descending order of the comprehensive quality score and select the path with the highest score as the dedicated path for the emergency braking command. When the emergency braking command needs to be transmitted, immediately use this dedicated path for transmission.

[0030] Allocate a dedicated channel for the emergency braking command to ensure rapid and reliable transmission under any circumstances and avoid possible catastrophic consequences. Dynamically allocate network resources according to business priorities, giving priority to high-priority services while effectively using the remaining resources to handle low-priority services. The dedicated path reduces the waiting time and potential interference of data transmission, thereby reducing network latency.

[0031] Select the path with the highest quality as the dedicated path, which improves the reliability of data transmission and reduces the possibility of packet loss and errors. Allocate appropriate network resources for services with different priorities, avoiding waste of resources, and thus optimizing the energy consumption of the entire network. For users, the rapid response and high reliability of critical services (such as emergency braking commands) are directly related to the satisfaction of the user experience. In a dynamically changing infrastructure environment, it is possible to quickly adjust the transmission path of services according to the real-time path quality evaluation results to adapt to environmental changes. Efficient resource allocation and reliable transmission reduce the maintenance requirements caused by communication failures and lower the long-term maintenance costs.

[0032] Judge whether energy replenishment is required. The process is as follows: Measure the energy consumption values of each node device under different environmental conditions in a laboratory control environment. Divide the energy consumption values and historical environmental data into a training set and a validation set. Input the training set into a neural network model to establish an energy consumption model, and then use the validation set to verify the energy consumption model; Obtain the current energy consumption values and current environmental data of each node device, and input them into the trained energy consumption model to obtain the predicted energy consumption values of each node device; The remaining power of each node device obtained is subtracted from the corresponding predicted energy consumption value to obtain the comprehensive power of each node device. The comprehensive power of each node device is compared with the power threshold stored in the data repository in sequence to determine whether the comprehensive power of each node device is less than the power threshold. If it is less, the node device triggers the energy replenishment process for energy replenishment; if it is not less, it does not trigger.

[0033] Energy transfer efficiency refers to the energy consumed when transmitting a certain amount of data. By accurately predicting energy consumption and timely energy replenishment, over-discharging of the battery is avoided, thereby extending the battery life. Ensure that node devices do not fail due to power exhaustion during critical tasks, improving the overall reliability of the network. Dynamically adjust the transmission power and modulation method, optimize energy usage according to energy efficiency, and reduce waste. Reduce the costs incurred by battery replacement and maintenance, and reduce long-term operating costs by predicting and optimizing the energy replenishment process.

[0034] The network can be dynamically adjusted according to real-time energy consumption data and environmental changes, improving its adaptability to dynamic environments. Monitoring and predicting the energy consumption of different node devices can more evenly distribute the network load and avoid overloading of certain node devices. For users relying on network communication, such as remote monitoring or automation systems, a more reliable network means fewer service interruptions and a better experience. The automated energy monitoring and replenishment process reduces the need for manual intervention, making maintenance work more intelligent and efficient.

[0035] Establish a communication - energy consumption optimization algorithm to obtain a network optimization plan. The process is as follows: Obtain the energy transfer efficiency of the node device, divide the energy consumption value of the node device by the energy transfer efficiency to obtain the total energy consumption, obtain communication data, including delay time, reliability, and data transmission rate, and perform a weighted sum of the communication data to obtain a communication performance score; Define an objective function based on the total energy consumption and the communication performance score; Determine the constraint conditions, including delay constraint, data rate constraint, reliability constraint, transmission power constraint, battery capacity constraint, and energy transfer efficiency constraint: Delay constraint: The delay time of data transmission does not exceed the maximum allowable delay time; Data rate constraint: The data rate of data transmission is not less than the minimum data transmission rate; Reliability constraint: The reliability of data transmission is not less than the minimum reliability; Transmission power constraint: The transmission power does not exceed the maximum transmission power; Battery capacity constraint: The remaining power before energy replenishment is not less than the minimum remaining energy; Energy transfer efficiency constraint: The energy transfer efficiency is not less than the minimum efficiency; Determine the minimization of the objective function based on the genetic algorithm. The optimal solution includes the optimal delay time, optimal data rate, optimal reliability, optimal transmission power, optimal remaining battery power, and optimal energy transfer efficiency, denoted as the network adjustment scheme.

[0036] The genetic algorithm process is as follows: S1. Encode the decision variables. For example, map the delay time, data rate, reliability, transmission power, remaining battery power, and energy transfer efficiency to genes in the genetic algorithm; S2. Randomly generate an initial population, where each individual represents a set of parameter settings; S3. Construct a fitness function to evaluate the performance of each individual, that is, the objective function value; S4. Select excellent individuals from the current population into the next generation population based on the roulette wheel selection method; S5. Perform a crossover operation on the selected next generation population to obtain the crossed population; S6. Perform a mutation operation on the crossed population to obtain the mutated population; S7. Repeat steps S4 - S6 until the maximum number of iterations, stop the calculation and output the current optimal solution, which is the network adjustment scheme.

[0037] By implementing the communication - energy consumption optimization algorithm, a more intelligent and efficient network management strategy can be achieved. It can not only significantly improve the energy efficiency of the network, extend the battery life of node devices by reducing unnecessary energy consumption, but also reduce the operating cost while ensuring the quality of service. The optimized network can operate more stably, reduce service interruptions caused by insufficient energy, thereby enhancing the user experience. In addition, it supports the network to adapt to dynamic environmental conditions, ensuring that the network can maintain optimal performance under different conditions. Through the intelligent network adjustment scheme, the network parameters can be automatically adjusted, reducing manual intervention and making network management more efficient and convenient.

[0038] Construct a node device trustworthiness model to determine the best transmission path. The process is as follows: Obtain the historical performance data of the node device, including the data transmission success rate, historical failure rate, and energy consumption efficiency. Compare the obtained data transmission success rate, historical failure rate, and energy consumption efficiency with the data transmission success rate threshold, historical failure rate threshold, and energy consumption efficiency threshold stored in the data repository, and perform a weighted sum to obtain the initial trustworthiness; Compare the initial trustworthiness with each reference trustworthiness stored in the data repository. The trust level corresponding to the closest reference trustworthiness is the trust level of the initial trustworthiness; Based on the trust level of the node device, select the initial planned path corresponding to the node device with the highest trust level as the best transmission path.

[0039] By analyzing the historical performance data of the node device and calculating the trustworthiness of each node device, it provides an empirical basis for the behavior of the node device in the model, making the calculation of trustworthiness more objective and accurate.

[0040] The node device trustworthiness model collects the data transmission success rate, historical failure rate, and energy consumption efficiency of each node device in past operations, and compares these metrics with preset thresholds, which represent the ideal performance of node devices in the network. By weighted summing the deviations between these metrics and the thresholds, the model generates a comprehensive initial trustworthiness score, reflecting the overall reliability of the node device.

[0041] By implementing the node device trustworthiness model, the overall performance and reliability of the communication ad-hoc network are significantly improved. It accurately evaluates the historical performance and real-time behavior of node devices, providing an intelligent path selection mechanism for the network to ensure that critical data is transmitted through the most reliable and secure paths. It not only optimizes resource allocation, prioritizing the most reliable node devices and paths, thus improving the network operation efficiency, but also reduces the maintenance requirements caused by node device failures, effectively reducing the operation and maintenance costs.

[0042] In addition, the node device trustworthiness model enhances network security by identifying and avoiding the use of untrusted node devices, improving the defense against potential security threats. For end-users, a more reliable network connection means fewer service interruptions and higher data transmission quality, thus significantly enhancing user satisfaction. The dynamic adjustment ability of the node device trustworthiness model enables the network to adapt to changing environments and conditions, ensuring the long-term stability and adaptability of the network.

[0043] Construct a node failure prediction model to predict node device failures and trigger maintenance instructions, as follows: Extract features from the historical failure operation data to obtain historical failure operation feature data; Design an LSTM network architecture, including an input layer, an LSTM layer, a fully connected layer, and an output layer; set network hyperparameters, including the number of LSTM units, the number of layers, the learning rate, the batch size, the activation function, and the optimizer; Divide the historical node device failure feature data into a training set, a validation set, and a test set, and use the training set to train the LSTM neural network prediction model to obtain the node failure prediction model; Use the validation set to validate the node failure prediction model and use the test set to test the node failure prediction model; Obtain the operation data of the node device and input it into the trained node failure prediction model to obtain the failure prediction result of the node device. If the failure prediction result indicates a node device failure, trigger a maintenance instruction.

[0044] Analyzing historical fault operation data can identify the patterns and precursors of faults, which can be used to predict future faults. Real-time monitoring of the status of node devices and fault prediction can enable proactive measures to avoid potential serious problems. Once a fault is predicted, the maintenance process is immediately triggered, which can reduce the impact of the fault on the business. Reducing unexpected downtime, ensuring the continuity of critical services, and effectively reducing maintenance costs and resource consumption.

[0045] In addition, predictive maintenance strategies make the allocation of network resources more reasonable, giving priority to processing node devices most likely to fail, thereby enhancing the reliability and stability of the entire network. Intelligent fault management and maintenance process optimization improve the user experience, reduce service interruptions, improve service quality, and significantly enhance the overall performance and economic benefits of the network.

[0046] Example 2: As Figure 2 shown, a communication ad-hoc network system applied to the infrastructure signal-free site is used to implement the method in Example 1, including: An initial planning path establishment module, which is used to construct a three-dimensional topological structure of the construction area based on multiple node devices deployed in the construction area, combine the lidar scanning carried by the unmanned aerial vehicle to generate a digital elevation model of the construction area, determine the spatial distribution of the node devices, and obtain each initial planning path; A spectrum management module, which is used to create a four-dimensional spectrum map based on the spatial distribution of the node devices and dynamically adjust the modulation method; A path quality evaluation module, which is used to establish a path quality prediction algorithm based on the spatial distribution of the node devices and the four-dimensional spectrum map, and determine the quality of each initial planning path; A service priority management module, which is used to establish a service priority based on the quality of each initial planning path; An energy management module, which is used to obtain the remaining power of each node device, determine whether energy replenishment is required, and if so, perform energy replenishment according to the corresponding service priority; A communication-energy consumption optimization module, which is used to establish a communication-energy consumption optimization algorithm based on the quality of each initial planning path, service priority, and energy replenishment result, combined with the remaining power of each node device obtained, obtain a network optimization plan, and perform network optimization; A path selection module, which is used to construct a node device trust model based on the node devices after network optimization and determine the best transmission path; A fault prediction and maintenance module, which is used to obtain the historical fault operation data of each node device, construct a node fault prediction model, predict the faults of the node devices, and trigger maintenance instructions.

[0047] Example 3: On the basis of Example 1, the initial planning path establishment module is improved to optimize the process of determining the spatial distribution of node devices: When constructing the three-dimensional topological structure of the construction area, an environmental perception algorithm is introduced to enable the node devices to perceive environmental changes in real time, including minor changes in terrain, the emergence of temporary obstacles, and changes in the intensity of electromagnetic interference, and dynamically feedback this environmental perception data into the three-dimensional topological structure; at the same time, a reinforcement learning algorithm is used to intelligently optimize the flight path planning of the drone, making the flight path of the drone more efficient and safer in complex environments, thereby improving the generation efficiency and accuracy of the digital elevation model, further optimizing the spatial distribution of node devices, and enhancing the adaptability and stability of the communication network.

[0048] Embodiment 4: A communication ad-hoc network device applied to the signal-free site of infrastructure construction, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor. The method in Embodiment 1 or Embodiment 3 is implemented by the processor executing the computer program.

Claims

1. A communication self-organizing network method applied to infrastructure sites without signals, characterized in that, Including the following steps: Based on multiple node devices deployed in the construction area, construct a three-dimensional topological structure of the construction area, combine the digital elevation model of the construction area generated by lidar scanning carried by the unmanned aerial vehicle (UAV), determine the spatial distribution of the node devices, and obtain each initial planned path; Based on the spatial distribution of the node devices, create a four-dimensional spectrum map and dynamically adjust the modulation method; Based on the spatial distribution of the node devices and the four-dimensional spectrum map, establish a path quality prediction algorithm to determine the quality of each initial planned path; Based on the quality of each initial planned path, establish a service priority; Obtain the remaining power of each node device, determine whether energy replenishment is required, and if so, perform energy replenishment according to the corresponding service priority; Based on the quality of each initial planned path, service priority, and energy replenishment result, combined with the remaining power of each obtained node device, establish a communication-energy consumption optimization algorithm, obtain a network optimization plan, and perform network optimization; Based on each node device after network optimization, construct a node device trust model to determine the optimal transmission path; Obtain the historical fault operation data of each node device, construct a node fault prediction model, predict the faults of the node devices, and trigger maintenance instructions.

2. The communication ad-hoc network method applied to the infrastructure signal-free site according to claim 1, wherein Determine the spatial distribution of the node devices, and the process is as follows: The node devices include a main control node device, a backbone node device, a relay node device, a sensing node device, a mobile node device, and an energy node device; Obtain the motion state data of the node devices, including acceleration, angular velocity, and magnetic field strength; Obtain the relative distance between each node device, combine the motion state data of the node devices, obtain the three-dimensional coordinates of each node device, and construct a three-dimensional topological structure of the construction area; Obtain the size and shape of the construction area in the data repository, plan the flight path of the UAV, and based on the lidar device carried by the UAV, emit laser pulses and measure the time difference of the reflected laser to obtain the distance of the target object; The data collected by the lidar device is stored in the form of point clouds. Each point contains three-dimensional coordinates and reflection intensity information. Import the collected point cloud data into geographic information system software for preprocessing, and convert the point cloud data into regular grid data through an interpolation algorithm to generate a digital elevation model; The digital elevation model represents the elevation information of the terrain in the form of a two-dimensional grid, and each grid unit corresponds to an elevation value; The generated digital elevation model is pre-loaded into the storage unit of each node device in the three-dimensional topological structure of the construction area. The node device accesses the digital elevation model to obtain the terrain information of the construction area, performs terrain analysis, and obtains each initial planned path.

3. The communication ad-hoc network method applied to the infrastructure signal-free site according to claim 1, wherein, Create a four-dimensional spectrum map and dynamically adjust the modulation method, and the process is as follows: Divide the wide frequency band into multiple sub-bands. The radio frequency front end of the node device sequentially scans each sub-band within 5 seconds to obtain the signal strength, interference strength, and center frequency within the sub-band; Store the center frequency, scanned timestamp, signal strength, interference strength, and the three-dimensional coordinates of the node device in the local storage unit of the node device to obtain a four-dimensional spectrum map; Based on the signal strength and interference strength in the four-dimensional spectrum map, evaluate the channel quality of the sub-band to obtain the channel quality evaluation result of the sub-band; Compare the channel quality assessment result of the sub - band with the channel quality assessment results of each reference sub - band stored in the data repository. The modulation method corresponding to the channel quality assessment result of the same reference sub - band is the modulation method corresponding to the channel quality assessment result of this sub - band; Among them, the process of obtaining the channel quality assessment result of the sub - band is as follows: Compare the signal strength with the signal assessment threshold stored in the data repository. If the signal strength is less than the corresponding assessment threshold, the channel quality level of the corresponding sub - band is level one, and the channel quality of the corresponding sub - band is poor; If the signal strength is not less than the signal assessment threshold, compare the interference strength with the interference assessment threshold stored in the data repository. If the interference strength is less than the interference assessment threshold, the channel quality level of the corresponding sub - band is level one, and the channel quality of the corresponding sub - band is good; If the interference strength is not less than the interference assessment threshold, the channel quality level of the corresponding sub - band is level two, and the channel quality of the corresponding sub - band is medium.

4. The communication ad-hoc network method applied to the infrastructure signal-free site according to claim 1, characterized in that Establish a path quality prediction algorithm to determine the path quality of each path. The process is as follows: Divide the initial planned path, including the main path, backup path, and emergency path; The master node device obtains the path quality assessment data of each initial planned path, including signal strength, bit error rate, signal - to - noise ratio, delay time, and packet loss rate, and performs a weighted sum of the path quality assessment data of each initial planned path to obtain the comprehensive quality score of each initial planned path; Compare the comprehensive quality score of each initial planned path with the comprehensive quality score threshold of the corresponding reference path stored in the data repository. If the comprehensive quality score of the initial planned path is greater than the comprehensive quality score threshold of the corresponding reference path, the path quality of this initial planned path is high; otherwise, the path quality of this path is low; If the quality of the main path is low, switch to the backup path with high path quality; otherwise, do not switch; If the quality of the main path and all backup paths are low, switch to the emergency path with high path quality; If the quality of the main path, all backup paths, and all emergency paths are low, issue an alarm.

5. The communication ad-hoc network method applied to the infrastructure signal-free site according to claim 1, characterized in that Establish service priorities. The process is as follows: Divide the service priorities, including the lowest priority 4, low priority 3, medium priority 2, high priority 1, and highest priority 0; Among them, the lowest priority 4 corresponds to non - real - time data transmission, the low priority 3 corresponds to device status monitoring, the medium priority 2 corresponds to video monitoring, the high priority 1 corresponds to dangerous gas alarm, and the highest priority 0 corresponds to an emergency braking instruction; Allocate a dedicated frequency band, dedicated bandwidth, and dedicated path for the emergency braking instruction. Sort the comprehensive quality scores corresponding to the paths with high path quality from large to small, and select the path with high path quality and the largest comprehensive quality score as the dedicated path for the emergency braking instruction. When the emergency braking instruction needs to be transmitted, transmit it immediately.

6. The communication self-organizing network method applied to the infrastructure signal-free site according to claim 1, characterized in that Judge whether energy replenishment is required. The process is as follows: Measure the energy consumption values of each node device under different environmental conditions in a laboratory-controlled environment. Divide the energy consumption values and historical environmental data into a training set and a validation set. Input the training set into a neural network model to establish an energy consumption model, and then use the validation set to verify the energy consumption model; Obtain the current energy consumption value and current environmental data of each node device, and input them into the trained energy consumption model to obtain the predicted energy consumption value of each node device; Subtract the obtained current remaining power of each node device from the corresponding predicted energy consumption value to obtain the comprehensive power of each node device. Compare the comprehensive power of each node device with the power threshold stored in the data repository in sequence to determine whether the comprehensive power of each node device is less than the power threshold. If it is less, the node device triggers an energy replenishment process for energy replenishment. If it is not less, it does not trigger.

7. The communication self-organizing network method applied to the infrastructure signal-free site according to claim 1, characterized in that, Establish a communication-energy consumption optimization algorithm to obtain a network optimization plan. The process is as follows: Obtain the energy transmission efficiency of the node device, divide the energy consumption value of the node device by the energy transmission efficiency to obtain the total energy consumption. Obtain communication data, including delay time, reliability, and data transmission rate, and perform a weighted sum of the communication data to obtain a communication performance score; Define an objective function based on the total energy consumption and the communication performance score; Determine the constraint conditions, including delay constraint, data rate constraint, reliability constraint, transmission power constraint, battery capacity constraint, energy transmission efficiency constraint: Delay constraint, the delay time of data transmission does not exceed the maximum allowable delay time; Data rate constraint, the data transmission rate of data transmission is not less than the minimum data transmission rate; Reliability constraint, the reliability of data transmission is not less than the minimum reliability; Transmission power constraint, the transmission power does not exceed the maximum transmission power; Battery capacity constraint, the remaining power before energy replenishment is not less than the minimum remaining energy; Energy transmission efficiency constraint, the energy transmission efficiency is not less than the minimum efficiency; Based on the genetic algorithm, determine the minimum of the objective function. The optimal solution includes the optimal delay time, optimal data rate, optimal reliability, optimal transmission power, optimal remaining power, and optimal energy transmission efficiency, denoted as the network adjustment plan.

8. The communication self-organizing network method applied to the infrastructure signal-free site according to claim 1, characterized in that Construct a node device trustworthiness model to determine the best transmission path. The process is as follows: Obtain the historical performance data of the node device, including data transmission success rate, historical failure rate, and energy consumption efficiency. Compare the obtained data transmission success rate, historical failure rate, and energy consumption efficiency with the data transmission success rate threshold, historical failure rate threshold, and energy consumption efficiency threshold stored in the data repository, and perform a weighted sum to obtain the initial trustworthiness; Compare the initial trustworthiness with each reference trustworthiness stored in the data repository. The trust level corresponding to the closest reference trustworthiness is the trust level of the initial trustworthiness; Based on the trust level of the node device, select the initial planned path corresponding to the node device with the highest trust level as the best transmission path.

9. The communication ad-hoc network method applied to the infrastructure signal-free site according to claim 1, characterized in that, Construct a node fault prediction model to predict node device faults and trigger maintenance instructions. The process is as follows: Extract features from the historical fault operation data to obtain historical fault operation feature data; Design an LSTM network architecture, including an input layer, an LSTM layer, a fully connected layer, and an output layer; set network hyperparameters, including the number of LSTM units, the number of layers, the learning rate, the batch size, the activation function, and the optimizer; Divide the historical node device fault feature data into a training set, a validation set, and a test set, and use the training set to train the LSTM neural network prediction model to obtain the node fault prediction model; Use the validation set to validate the node fault prediction model and use the test set to test the node fault prediction model; Obtain the operation data of the node device and input it into the trained node fault prediction model to obtain the fault prediction result of the node device. If the fault prediction result is that the node device fails, trigger a maintenance instruction.

10. A communication self-organizing network system applied to the infrastructure signal-free site for implementing the method according to any one of claims 1-9, characterized in that, Include: An initial planning path establishment module for constructing a three-dimensional topological structure of the construction area based on multiple node devices deployed in the construction area, combining the lidar scan carried by the drone to generate a digital elevation model of the construction area, determining the spatial distribution of the node devices, and obtaining each initial planning path; A spectrum management module for creating a four-dimensional spectrum map based on the spatial distribution of the node devices and dynamically adjusting the modulation method; A path quality evaluation module for establishing a path quality prediction algorithm based on the spatial distribution of the node devices and the four-dimensional spectrum map to determine the quality of each initial planning path; A service priority management module for establishing service priorities based on the quality of each initial planning path; An energy management module for obtaining the remaining power of each node device, determining whether energy replenishment is required, and if so, performing energy replenishment according to the corresponding service priority; A communication-energy consumption optimization module for establishing a communication-energy consumption optimization algorithm based on the quality of each initial planning path, service priority, and energy replenishment result, combined with the remaining power of each node device obtained, to obtain a network optimization plan and perform network optimization; A path selection module for constructing a node device trust model based on each node device after network optimization to determine the best transmission path; A fault prediction and maintenance module for obtaining the historical fault operation data of each node device, constructing a node fault prediction model, predicting node device faults, and triggering maintenance instructions.

Images