Intelligent construction site networking and monitoring method based on WAPI technology and MESH network

Abstract

The invention discloses an intelligent construction site networking and monitoring method based on a WAPI technology and an MESH network, and the method comprises the steps: collecting the operation data of a super node in a construction site environment, and dividing a region according to the data; based on the operation data of the super nodes, obtaining power consumption of the super nodes by using an adaptive energy consumption optimization method, and adjusting task distribution of the super nodes according to the power consumption; after task distribution is adjusted, the weighted priority of the super node tasks is obtained in combination with a weighted priority adjustment method, and the transmission weights of the super node tasks are adjusted; and after the transmission weight of the task is adjusted, evaluating the comprehensive task cost of the super node by using a comprehensive task cost evaluation method, performing task scheduling and topological adjustment of the super node, and completing construction site networking and monitoring. The method can be adaptive to topology change in a complex dynamic environment, network stability is improved, the service life of network nodes is prolonged, and task flow and resource allocation can be effectively managed.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to an intelligent construction site networking and monitoring method based on WAPI technology and MESH network. Background Art

[0002] WAPI (Wireless Authentication and Privacy Infrastructure) has powerful security authentication and encryption functions, which can ensure the security and privacy protection of wireless network communications. In the MESH network of the construction site, WAPI technology can be used as the core technology of data encryption and identity authentication to ensure the confidentiality and integrity of the monitoring data of the construction site. Through the dynamic key negotiation and authentication mechanism of WAPI, external attacks can be effectively prevented to ensure the security and reliability of the system's data transmission process.

[0003] With the rapid development of information technology, communication networks are increasingly used in various fields, especially in large-scale wireless communications and the Internet of Things. MESH networks, as a self-organizing and adaptive wireless network architecture, have been widely used in many fields. It can effectively cover large areas through multi-hop routing, especially in complex indoor environments, remote areas or temporary places (such as construction sites, disaster relief, etc.), and has significant advantages.

[0004] However, in these complex and dynamically changing environments, traditional MESH networks often have many problems. First, in environments such as construction sites, the dynamic changes of nodes are very frequent. The joining, moving, and leaving of nodes cause the network topology to change constantly, which poses great challenges to the stability and reliability of the network. Secondly, due to the limited battery power and computing resources of network nodes, how to efficiently utilize these limited resources, extend the service life of the network, and improve the stability and efficiency of data transmission have become important issues in the design and optimization of MESH networks. In addition, in construction sites and other similar application scenarios, equipment and personnel are often replaced, and the real-time update and management of network topology becomes more complicated.

[0005] In the existing technology, some MESH networks use static topology management or routing algorithms based on preset rules. Although they can meet the needs in some simple scenarios, they cannot adapt to the frequent changes in dynamic environments. These traditional methods lack flexibility and real-time performance, resulting in low network efficiency and large data transmission delays. Especially when nodes move frequently and the environment changes drastically, the stability and coverage of the network cannot be effectively guaranteed. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide an intelligent construction site networking and monitoring method based on WAPI technology and MESH network, which can adapt to topology changes, improve network stability, extend the service life of network nodes in a complex and dynamic environment, and effectively manage task traffic and resource allocation.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0008] The intelligent construction site networking and monitoring method based on WAPI technology and MESH network includes the following steps:

[0009] S1. Collect the operation data of super nodes in the construction site environment and divide the area according to the data.

[0010] S2. Based on the operation data in step S1, the power consumption of the super node is obtained by using an adaptive energy consumption optimization method, and the task allocation of the super node is adjusted according to the power consumption.

[0011] S3. After the task allocation is adjusted, the weighted priority of the super node task is obtained by combining the weighted priority adjustment method, and the transmission weight of the super node task is adjusted.

[0012] S4. After the transmission weight of the task is adjusted, the comprehensive task cost of the super node is evaluated using the comprehensive task cost evaluation method, and the task scheduling and topology adjustment of the super node are carried out to complete the networking and monitoring of the construction site.

[0013] Furthermore, in step S1, the super nodes include first-level super nodes, second-level super nodes and third-level super nodes.

[0014] The operation data of super nodes include the distribution, load, communication quality, signal strength, battery power and movement trajectory of super nodes; the load includes computing tasks, data transmission tasks and energy consumption.

[0015] When the load of a super node exceeds 80% of the maximum carrying capacity of the node, the area is divided into a high-load area; when the load of a super node is less than 50% of the maximum carrying capacity of the node, the area is divided into a low-load area.

[0016] When the signal strength of the super node is greater than -60dBm, or the delay is less than 50ms and the packet loss rate is less than 1%, the area is divided into an area with good communication quality; when the signal strength of the super node is lower than -70dBm and the bandwidth is lower than 1Mbps, or the delay is more than 100ms and the packet loss rate is more than 5%, the area is divided into an area with poor communication quality.

[0017] When the signal strength of the super node is greater than -60dBm, the area is divided into a strong signal area; when the signal strength of the super node is less than -80dBm, the area is divided into a weak signal area.

[0018] When the battery level is ≥80%, it indicates that the battery level in this area is normal; when 50%≤battery level<80%, it indicates that the battery level in this area is low; when 0%≤battery level<50%, it indicates that the battery level in this area is low; when the battery level is<20%, ​​it indicates that the battery level in this area is extremely low.

[0019] When the super node's position moving speed is less than 1m / s, the area is divided into a stable area; when the super node's position moving speed is greater than or equal to 1m / s, the area is divided into a dynamic area.

[0020] Furthermore, the first-level super node is used to collect field data in a specific area of ​​the construction site, the data including environmental parameters and construction progress, wherein the environmental parameters include temperature, humidity and air pressure, and the construction progress includes material usage and personnel distribution, and the data is cleaned, filtered and formatted; the processed data is sent to the second-level super node.

[0021] The second-level super node integrates and analyzes the processed data, identifies potential construction bottlenecks, equipment failures or safety hazards, and adjusts the priority and execution order of tasks based on the analysis results; the second-level super node conducts two-way data communication with the first-level super node.

[0022] The third-level super node receives the summary information of the second-level super node and optimizes the overall network structure and task execution strategy of the construction site based on this information. The strategy includes global task scheduling, resource optimization, energy consumption control and topology adjustment.

[0023] Furthermore, areas with poor communication quality require relay nodes or additional communication support. Specifically, when -70dBm≤signal strength≤-60dBm, 1 relay node is required; when -80dBm≤signal strength<-70dBm, 2 relay nodes are required; when signal strength<-80dBm, 3 or more relay nodes are required.

[0024] Furthermore, in step S2, adjusting task allocation includes the following:

[0025] The calculation formula for super node power consumption is:

[0026] P i (t) = α·L i (t)+χ·R i (t)+γ·(E max -E i (t))

[0027] Among them, P i (t) represents the power consumption of the i-th super node at the t-th moment; α represents the influence of the task load on the node power consumption; χ represents the influence of the data transmission frequency on the node power consumption; γ represents the influence of the battery power on the node power consumption; L i (t) represents the task load of the i-th super node at time t; R i (t) represents the data transmission frequency of the i-th super node at time t; E max represents the maximum battery capacity of the node, E i (t) represents the battery power of the i-th supernode at the t-th moment.

[0028] Based on the historical movement trajectory and power consumption of the super node, the future location or power consumption requirement of the node is predicted through the machine learning model, the topology structure and routing path are adjusted, and data forwarding and task allocation are adjusted according to the preset task priority.

[0029] Offload computationally intensive tasks to nodes whose load is less than 50% of the maximum capacity of the supernode.

[0030] Data forwarding tasks are assigned to nodes with signal strength greater than -60dBm and bandwidth higher than 1Mbps, or with latency less than 50ms and packet loss rate less than 1%.

[0031] When the battery power is less than 20%, reduce the super node load by 50%; when 20% ≤ battery power greater than < 50%, reduce the super node load by 30%; when 50% ≤ battery power < 80%, reduce the super node load by 10%.

[0032] Furthermore, in step S3, adjusting the transmission weight includes the following:

[0033] The calculation formula for the weighted priority of super node tasks is:

[0034] W i =aQ i +bC i +cE i

[0035] Among them, W i represents the weighted priority of the i-th supernode, Q i represents the priority of the i-th super node task, C i represents the network load of the ith supernode, E i represents the battery power of the ith supernode, and a, b, and c represent weighted coefficients.

[0036] The priority range is 0 to 100, where 0 represents the lowest priority and 100 represents the highest priority. When 0≤priority≤30, it is a low priority task and is assigned a transmission weight of 1. When 30<priority≤60, it is a medium priority task and is assigned a transmission weight of 2. When 60<priority≤90, it is a high priority task and is assigned a transmission weight of 3. When 90<priority≤100, it is an extremely high priority task and is assigned a transmission weight of 4.

[0037] When the load of the super node is less than 50% of the maximum carrying capacity of the node, 2 transmission weights are added; when the load of the super node is greater than 50% of the maximum carrying capacity of the node and less than or equal to 75%, 1 transmission weight is added; when the load of the super node is greater than 75% of the maximum carrying capacity of the node, no transmission weight is added.

[0038] When the battery power is ≥80%, add 3 transmission weights; when 50%≤battery power<80%, add 2 transmission weights; when the battery power is<50%, add 1 transmission weight.

[0039] Furthermore, in step S4, the calculation formula for evaluating the comprehensive task cost of the super node is:

[0040] D i (t) = α·λ i (t)+β·L i (t)+γ·E i (t)+δ·σ i (t)

[0041] Among them, D i (t) represents the task cost of the i-th super node at the t-th time, α, β, γ, δ are all adjustable weight coefficients, λ i (t) represents the position offset of the i-th super node, L i (t) represents the task load of the i-th super node at time t, E i (t) represents the battery power of the i-th super node at the t-th moment, σ i (t) represents the signal quality of the i-th supernode at time t.

[0042] Furthermore, the present invention also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the intelligent construction site networking and monitoring method based on WAPI technology and MESH network are implemented.

[0043] Furthermore, the present invention also proposes a computer-readable storage medium, which stores a computer program. When the computer program is run by a processor, it executes the intelligent construction site networking and monitoring method based on WAPI technology and MESH network.

[0044] Compared with the prior art, the present invention adopts the above technical solution and has the following technical effects:

[0045] 1. The present invention can adapt to topology changes in a complex and dynamic environment, improve network stability, extend the service life of network nodes, and effectively manage task traffic and resource allocation.

[0046] Second, the present invention can evaluate the priority of each node in real time, automatically adjust task allocation and data routing paths, and thus optimize the overall performance of the network. Over time, the system will continue to learn and adjust the weight coefficients to adapt to network requirements under different construction stages and environmental conditions.

[0047] 3. The present invention can give priority to transmitting data of high-priority tasks by dynamically adjusting the transmission weight of tasks, while preventing low-priority tasks from occupying too many resources and avoiding network congestion. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is an overall implementation flow chart of the present invention. DETAILED DESCRIPTION

[0049] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0050] In order to further improve the stability, efficiency and sustainability of the MESH network at the construction site, this paper proposes an intelligent construction site networking and monitoring method based on WAPI technology and MESH network to ensure that the construction site can better adapt to changes in a dynamic and complex environment, such as Figure 1 As shown, the specific steps are as follows:

[0051] S1. The environment of the construction site is complex and changeable, with a large number of nodes and frequent dynamic changes. Traditional single-level topology management often cannot efficiently handle these changes. Through reasonable regional division, a super node is configured in each area, which not only manages the nodes in the area, but also undertakes the function of cross-regional communication coordination.

[0052] In addition to the basic regional division, the multi-level super node architecture introduces super nodes at different levels to solve the problems of distributed management and cross-regional coordination in large-scale construction site networks. Super nodes include first-level super nodes, second-level super nodes, and third-level super nodes.

[0053] The first-level super node collects data from sensor nodes or ordinary equipment in a specific area of ​​the construction site. The data includes environmental parameters and construction progress. Environmental parameters include temperature, humidity and air pressure, and construction progress includes material usage and personnel distribution. The data is preliminarily processed, including data cleaning, filtering and formatting, to ensure that the transmitted data is accurate, complete and meets the requirements of subsequent processing; the processed data is sent to the second-level super node for further analysis and task allocation.

[0054] The second-level super node integrates and analyzes the processed data to form more comprehensive construction site status information, identify potential construction bottlenecks, equipment failures or safety hazards, and adjust the priority and execution order of tasks based on the analysis results; the second-level super node also conducts two-way data communication with the first-level super node to ensure smooth information flow and task collaboration.

[0055] The third-level super node receives the summary information of the second-level super node, and optimizes the overall network structure and task execution strategy of the construction site based on this information. The strategy includes global task scheduling, resource optimization, energy consumption control and topology adjustment. Through global monitoring and scheduling, the third-level super node ensures that the intelligent management system of the construction site always maintains efficient, coordinated and sustainable operation.

[0056] The operation data of each super node in the construction site environment is collected, and the area is divided according to the data. This variable topology mechanism ensures that the network can maintain optimal performance under different construction stages and environmental changes. For example, in the early stage of construction, the area division may be large, while in the later stage of construction, according to the dynamic changes of personnel and equipment, the area can be appropriately reduced to cope with more intensive task requirements and more frequent node changes; the specific content is:

[0057] The operation data of super nodes include the distribution, load, communication quality, signal strength, battery power and movement trajectory of super nodes; the load includes computing tasks, data transmission tasks and energy consumption.

[0058] When the load of a super node exceeds 80% of the maximum carrying capacity of the node, the area is divided into a high-load area; when the load of a super node is less than 50% of the maximum carrying capacity of the node, the area is divided into a low-load area.

[0059] If the load of nodes in a certain area is too high, that is, the CPU load is close to or exceeds 2 times the number of cores, or the memory usage exceeds 85%-90%, or the IOWait of disk I / O exceeds 30%, or the network bandwidth usage exceeds 80%-90%, the load of tasks or nodes will be distributed to other areas with lower loads to avoid network overload or task delays in a certain area.

[0060] When the signal strength of the super node is greater than -60dBm, or the delay is less than 50ms and the packet loss rate is less than 1%, the area is divided into an area with good communication quality and no additional intervention is required; when the signal strength of the super node is lower than -70dBm and the bandwidth is lower than 1Mbps, or the delay is more than 100ms and the packet loss rate is more than 5%, the area is divided into an area with poor communication quality.

[0061] When the signal strength of the super node is greater than -60dBm, the area is divided into a strong signal area, which can be used as the main area for task allocation and data processing. When the signal strength of the super node is less than -80dBm, the area is divided into a weak signal area, which requires adding relay nodes or enhancing the signal strength through other means to avoid network interruption or instability.

[0062] When the battery level is ≥80%, the battery level is normal; when 50%≤battery level<80%, the battery level is low. At this time, the device can still be used, but it is recommended to pay attention; when 0%≤battery level<50%, the battery level is low. It is recommended to charge as soon as possible to prevent the device from suddenly losing power; when the battery level is <20%, the battery level is extremely low. At this time, the operating time of the device has been greatly shortened. It is recommended to charge immediately.

[0063] When the super node's position moving speed is less than 1m / s, the area is divided into a stable area; when the super node's position moving speed is greater than or equal to 1m / s, the area is divided into a dynamic area, and the node's moving path is considered when allocating tasks to reduce task backlogs.

[0064] Areas with poor communication quality require more relay nodes or additional communication support to ensure the reliability of data transmission. Specifically, when -70dBm≤signal strength≤-60dBm, 1 relay node is required; when -80dBm≤signal strength<-70dBm, 2 relay nodes are required; when signal strength<-80dBm, 3 or more relay nodes are required. The specific number depends on the complexity of the environment and network design requirements.

[0065] S2. Based on the operation data in step S1, the power consumption of each super node is obtained by using an adaptive energy consumption optimization method, and the task allocation of each super node is adjusted according to the power consumption; the specific contents are as follows:

[0066] The calculation formula for the power consumption of each super node is:

[0067] P i (t) = α·L i (t)+χ·R i (t)+γ·(E max -E i(t))

[0068] Among them, P i (t) represents the power consumption of the i-th super node at the t-th moment; α represents the influence of the task load on the node power consumption; χ represents the influence of the data transmission frequency on the node power consumption; γ represents the influence of the battery power on the node power consumption; L i (t) represents the task load of the i-th super node at time t, such as the amount of data collection or data forwarding tasks; R i (t) represents the data transmission frequency of the i-th supernode at the t-th time, in bits per second (bps); E max represents the maximum battery capacity of the node, E i (t) represents the battery power of the i-th supernode at the t-th moment.

[0069] The above formula combines the node's task load, data transmission frequency and battery power, and can calculate the node's energy consumption in real time and adjust the task allocation based on this. For example, the super node will dynamically adjust its task allocation according to the battery power and task load of each node, ensuring that nodes with sufficient batteries take on more data forwarding tasks, while nodes with low power will reduce their participation in data relay, thereby optimizing the energy efficiency of the overall network.

[0070] Through adaptive algorithms, the system can adjust the network topology and task allocation in real time according to environmental changes and node status at the construction site, ensuring network stability and efficiency.

[0071] Direct correlation between task load and energy consumption: According to the task load undertaken by the node, its energy consumption is evaluated and the working state of the node is adjusted. When the node load is heavy, the data forwarding task is reduced to extend the battery life of the node.

[0072] Combination of data transmission frequency and energy consumption management: nodes with high-frequency data transmission will be given priority in task allocation, while nodes with low battery power will be switched to low-power mode and only participate in minimal communication tasks.

[0073] Traditional topology adjustment mechanisms often rely on periodic detection and global decision-making. This invention proposes an event-driven dynamic topology adjustment mechanism, which predicts node state changes in advance through adaptive resource pre-allocation, and adjusts the topology structure in advance. The advantage of this mechanism is that it can predict possible node problems in advance and perform self-repair based on the behavior pattern, load trend, and energy consumption of each node, reducing the time and cost required for topology adjustment.

[0074] Based on the historical movement trajectory and power consumption of the super node, the machine learning model is used to predict the future location or power consumption requirements of the node. Based on the predicted information, the super node adjusts the topology and routing path in advance to avoid network interruption due to node movement or uneven load.

[0075] Adjust the topology and routing paths, and adjust data forwarding and task allocation according to preset task priorities to minimize network bottlenecks and avoid resource waste.

[0076] The machine learning model continuously optimizes the network coordination strategy by learning from historical data. The system can not only learn the behavior of each node in real time, but also predict and optimize based on factors such as changes in task requirements and environmental interference at the construction site:

[0077] Reinforcement learning algorithm: Through the reinforcement learning model, the system can adjust the task allocation and data routing strategies to find the best network coordination solution at different construction stages and under different environmental conditions. The system gradually learns the network coordination method that best suits the dynamic changes of the construction site by continuously evaluating and rewarding different scheduling solutions.

[0078] Co-evolution algorithm: Based on the multi-agent co-evolution algorithm, the collaborative optimization of task allocation is achieved among various nodes, ensuring the stability of the entire network topology and the efficiency of task completion.

[0079] When the load of a super node exceeds 80% of the node's maximum carrying capacity or the battery power is less than 20%, the node will be marked as an adjustment node; the system will monitor other super nodes in the network in real time, and give priority to nodes with a load less than 50% of the node's maximum carrying capacity and a battery power higher than 20% to receive additional tasks.

[0080] By using the prediction function of machine learning, the present invention can also predict the evolution of network topology according to environmental changes and make adjustments in advance. For example, the system can identify the hot spots of nodes, predict the problems such as excessive load and bandwidth bottlenecks that may occur in the area, and make data routing adjustments and task allocations in advance to avoid potential network bottlenecks.

[0081] The machine learning algorithm adjusts the task priority of the node in real time based on dynamic factors such as the node's communication quality, battery power, and task requirements. Through continuous learning and adjustment, the system can gradually improve the accuracy of task scheduling and ensure the continuous and stable operation of the network.

[0082] Reassign tasks:

[0083] Computational tasks: Offload computationally intensive tasks to nodes whose load is less than 50% of the maximum carrying capacity of the supernode.

[0084] Data transmission task: Data forwarding tasks are assigned to nodes with signal strength greater than -60dBm and bandwidth higher than 1Mbps, or latency less than 50ms and packet loss rate less than 1%.

[0085] Energy consumption tasks: When the battery power is less than 20%, reduce the super node load by 50% or reduce task allocation, which means that the node should reduce the number of tasks processed or reduce its communication frequency to prioritize the execution of important tasks. When 20% ≤ battery power is greater than <50%, reduce the super node load by 30% or reduce task allocation. In this power range, although the battery power is not completely low, measures still need to be taken to ensure that the node can maintain operation for a longer time. When 50% ≤ battery power is less than 80%, reduce the super node load by 10%. At this time, although the battery power is still acceptable, in scenarios of multi-tasking and long-term use, appropriately reducing the load will help balance power consumption and performance requirements.

[0086] S3. After the task allocation is adjusted, the weighted priority of each super node task is obtained by combining the weighted priority adjustment method, and the transmission weight of each super node task is adjusted; the specific content is:

[0087] The calculation formula for the weighted priority of each super node task is:

[0088] W i =aQ i +bC i +cE i

[0089] Among them, W i represents the weighted priority of the i-th supernode, Q i represents the priority of the i-th super node task, C i represents the network load of the ith supernode, E i represents the battery power of the i-th super node, a, b, and c are weighted coefficients used to adjust the influence weight of each factor.

[0090] High priority tasks: For high priority tasks, a higher transmission weight is assigned, that is, the data transmission frequency is increased or the transmission is given priority. Specifically: the priority range is set to 0-100, 0 represents the lowest priority, and 100 represents the highest priority; when 0≤priority≤30, it is a low priority task, and a transmission weight of 1 is assigned; when 30<priority≤60, it is a medium priority task, and a transmission weight of 2 is assigned; when 60<priority≤90, it is a high priority task, and a transmission weight of 3 is assigned; when 90<priority≤100, it is an extremely high priority task, and a transmission weight of 4 is assigned.

[0091] Low network load node: When the load of the super node is less than 50% of the maximum carrying capacity of the node, 2 transmission weights are added; when the load of the super node is greater than 50% of the maximum carrying capacity of the node and less than or equal to 75%, 1 transmission weight is added; when the load of the super node is greater than 75% of the maximum carrying capacity of the node, no transmission weight is added.

[0092] Nodes with sufficient battery power: When the battery power is ≥80%, add 3 transmission weights; when 50%≤battery power<80%, add 2 transmission weights; when the battery power is<50%, add 1 transmission weight; this ensures that nodes with sufficient battery power take on more transmission tasks.

[0093] The present invention introduces machine learning models (such as reinforcement learning, neural networks, etc.) and uses their powerful data processing and pattern recognition capabilities to make real-time predictions and dynamic adjustments to node status, signal quality, task priority, etc. The specific solution design is as follows:

[0094] 1. Network status prediction and adjustment

[0095] The signal strength, connection quality, and environmental changes of nodes at the construction site are predicted through machine learning algorithms (such as deep learning and neural networks). Based on these prediction results, the system dynamically adjusts the network topology and selects the optimal transmission path, thereby improving the stability of data transmission, reducing latency, and ensuring the optimal use of network resources. For example, the system can predict fluctuations in signal strength or possible movement trajectories of nodes, so as to adjust the transmission path in advance when signal quality degrades to avoid network interruptions.

[0096] 2. Intelligent routing selection

[0097] In a MESH network, optimization of routing selection is crucial to ensure network efficiency. The system uses reinforcement learning (RL) algorithms to automatically select the optimal transmission path by learning the current network status (such as node battery power, signal quality, node load, etc.) in real time. Reinforcement learning continuously optimizes routing strategies through interaction with the environment to improve the stability and reliability of data transmission. For example, when the battery power of a node is low, the system will give priority to nodes with lighter loads and higher battery power for data transmission to avoid communication interruptions caused by node failure or insufficient power.

[0098] 3. Anomaly detection and self-healing mechanism

[0099] The construction site environment is complex and dynamic, and anomalies in the network (such as node failure, communication interference, etc.) may affect the stability of data transmission. The anomaly detection system based on machine learning can monitor the network status in real time. When an anomaly is found, the system will automatically enable the self-healing mechanism, including rerouting, adjusting the topology structure, and other methods to quickly restore the network connection. For example, if a node fails, the system will automatically detect the absence of the node and restore normal data transmission by finding adjacent nodes or adjusting the network path.

[0100] 4. Task traffic scheduling

[0101] Different tasks have different priorities. In the MESH network of the construction site, it is necessary to ensure that high-priority tasks can be transmitted first when the network is busy. For example, security monitoring and environmental perception data have high timeliness requirements, while equipment status monitoring data is relatively less urgent. In order to optimize network performance and resource allocation, the present invention proposes to dynamically adjust the priority and path of task traffic through an intelligent algorithm. Through the weighted priority adjustment formula, the transmission weight of the task is dynamically adjusted according to the status of each node, the task type and the network load. In this way, the system can give priority to transmitting data of high-priority tasks, while avoiding low-priority tasks from occupying too many resources and avoiding network congestion.

[0102] S4. After the transmission weight of the task is adjusted, the comprehensive task cost of each super node is evaluated using the comprehensive task cost evaluation method, and the task scheduling and topology adjustment of each super node are carried out to complete the networking and monitoring of the construction site; the specific contents are as follows:

[0103] The calculation formula for evaluating the comprehensive task cost of each super node is:

[0104] D i (t) = α·λ i (t)+β·L i (t)+γ·E i (t)+δ·σ i (t)

[0105] Among them, D i (t) represents the task cost of the i-th supernode at the t-th moment, which comprehensively reflects the node's load, battery power, location change, and signal quality; α, β, γ, and δ all represent adjustable weight coefficients, and λ i (t) represents the position offset of the i-th super node, reflecting the movement change of the node; L i (t) represents the task load of the i-th super node at time t, which means the amount of data forwarding or computing tasks carried by the node; E i (t) represents the battery power of the i-th supernode at the t-th time, which affects the working stability and duration of the node; σ i(t) represents the signal quality of the i-th supernode at time t, which directly affects the stability and efficiency of data transmission.

[0106] Through the above formula, the machine learning algorithm can evaluate the priority of each node in real time in the complex and dynamic environment of the construction site, automatically adjust the task allocation and data routing path, and thus optimize the overall performance of the network. Over time, the system will continue to learn and adjust the weight coefficients to adapt to the network needs in different construction stages and environmental conditions.

[0107] When the battery of a super node is low, the data collection frequency of the super node is reduced or it is switched to low power mode, and the super node performs dynamic task scheduling based on the information of each node in the area.

[0108] The invention has the following unique advantages in terms of innovations in hierarchical dynamic topology management, adaptive topology adjustment, energy efficiency optimization and task scheduling, and machine learning network coordination:

[0109] Higher topological stability and adaptability: Through hierarchical management and multi-level super node architecture, the frequency of topological updates caused by changes in the construction site environment is effectively reduced, and the robustness and flexibility of the network are improved.

[0110] Efficient energy management and extended node life: Intelligent energy efficiency perception and task scheduling mechanism realizes efficient utilization of battery energy, reduces node energy consumption, and extends node life.

[0111] Accurate task scheduling and network optimization: The adaptive network coordination algorithm based on machine learning enables the system to learn and predict network changes in real time, optimize task allocation, data routing and topology adjustment, and significantly improve the communication efficiency of the system.

[0112] Sustainability and scalability: By introducing dynamic topology management and intelligent adjustment mechanisms, the system can flexibly respond to the complex and dynamically changing environmental requirements of the construction site and has good scalability.

[0113] The present invention realizes intelligent adjustment and optimization of the network through the following key links:

[0114] Network status perception and prediction: By deploying sensors and collecting historical data of the construction site environment, a dynamic model of the construction site network is constructed. The node's mobility pattern, signal quality, load condition, etc. are predicted by combining machine learning algorithms to achieve forward-looking perception of the network status. For example, through time series analysis, regression analysis and other technologies, the node's historical location data and signal quality data are used to predict future node status changes, and the network topology is adjusted in advance to avoid network interruptions.

[0115] Intelligent decision-making and task allocation: Through machine learning models, the status of each node (such as signal quality, battery power, task priority, etc.) and the overall load of the network are analyzed to intelligently and dynamically adjust task allocation and data transmission paths. This process not only avoids resource waste, but also effectively eliminates potential communication bottlenecks, ensuring that the workload of each node meets its capabilities, thereby improving the overall performance of the network.

[0116] Adaptive topology adjustment: Combined with machine learning algorithms such as reinforcement learning and K-means clustering, possible network topology changes are predicted based on the behavior patterns and historical change trends of nodes. Through real-time monitoring and analysis of the load and status of nodes and regions, network configuration is adjusted in advance, task allocation and communication paths are optimized, thereby ensuring network stability and efficiency. The system will continuously adjust the topology structure according to network status, environmental changes and task requirements to ensure the best communication quality and reliability.

[0117] Machine learning models play a vital role in adaptive network coordination mechanisms. Here are several key models and their applications:

[0118] 1. Node behavior prediction model

[0119] Use time series analysis (such as LSTM, long short-term memory network) or regression analysis models based on historical data to predict the future behavior of nodes. Specific applications are as follows:

[0120] LSTM (Long Short-Term Memory Network): It can capture long-term dependencies in time series data and is suitable for predicting node movement trajectories or signal quality changes. By learning the historical movement patterns of nodes, LSTM can predict the future location and signal quality of nodes in advance, and then adjust the network topology in advance to reduce network disconnection or signal quality degradation caused by node movement.

[0121] Regression analysis: By establishing the relationship between node behavior and environmental factors, the regression model can predict the state changes of nodes (such as battery power, communication quality, etc.) and optimize network management accordingly.

[0122] 2. Reinforcement learning to optimize task allocation

[0123] Reinforcement Learning (RL) is an adaptive decision-making model in which the system continuously learns the optimal strategy through interaction with the environment. In this invention, the reinforcement learning algorithm is used to optimize task allocation and data routing:

[0124] Task allocation: The intelligent agent selects the best node to undertake the task based on the current network status (such as load, battery level, task priority, etc.). For example, nodes with light load and sufficient battery power are given priority to undertake data relay tasks.

[0125] Data transmission path selection: The RL model can also optimize the data transmission path between nodes and intelligently adjust the communication path of the nodes to avoid data delay and packet loss caused by path congestion.

[0126] 3. Clustering and topology optimization

[0127] Using algorithms such as K-means clustering, the construction site is divided into multiple sub-areas according to the node status and task requirements, and the network in each area is optimized:

[0128] K-means clustering: Nodes can be divided into different sub-areas by clustering them according to factors such as their location, signal quality, and task load. The super nodes in each sub-area dynamically adjust the communication path and topology structure according to the node status and load in the area to ensure the efficient operation of the network in each area.

[0129] Topology optimization: The topology structure and communication path in each clustered area will be adaptively adjusted according to the battery power, signal quality and load of the nodes to avoid performance degradation caused by excessive load or insufficient node power.

[0130] It is known from common technical knowledge that the present invention can be implemented by other embodiments that do not deviate from its spirit or essential features. Therefore, the above disclosed embodiments are only illustrative in all respects and are not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are included in the present invention.

[0131] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0135] The embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. It should be noted that when the processor executes the computer program, the specific steps of the method provided in the embodiment of the present invention are corresponding to the specific steps of the method provided in the embodiment of the present invention, and the processor has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided in the embodiment of the present invention.

[0136] The embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. It should be noted that when the computer program is executed by the processor, it corresponds to the specific steps of the method provided in the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided in the embodiment of the present invention.

[0137] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent construction site networking and monitoring method based on WAPI technology and MESH network, characterized in that: include: S1. Collect the operation data of super nodes in the construction site environment and divide the area according to the data; S2. Based on the operation data in step S1, the power consumption of the super node is obtained by using an adaptive energy consumption optimization method, and the task allocation of the super node is adjusted according to the power consumption; S3. After the task allocation is adjusted, the weighted priority of the super node task is obtained by combining the weighted priority adjustment method, and the transmission weight of the super node task is adjusted; S4. After the transmission weight of the task is adjusted, the comprehensive task cost of the super node is evaluated using the comprehensive task cost evaluation method, and the task scheduling and topology adjustment of the super node are carried out to complete the networking and monitoring of the construction site.

2. The intelligent construction site networking and monitoring method based on WAPI technology and MESH network according to claim 1, characterized in that: In step S1, the super nodes include first-level super nodes, second-level super nodes and third-level super nodes; The operation data of super nodes include the distribution, load, communication quality, signal strength, battery power and movement trajectory of super nodes; the load includes computing tasks, data transmission tasks and energy consumption; When the load of a super node exceeds 80% of the maximum carrying capacity of the node, the area is divided into a high-load area; When the load of a super node is less than 50% of the maximum carrying capacity of the node, the area is divided into a low-load area; When the signal strength of the super node is greater than -60dBm, or the delay is less than 50ms and the packet loss rate is less than 1%, the area is classified as a good communication quality area; when the signal strength of the super node is less than -70dBm and the bandwidth is less than 1Mbps, or the delay is more than 100ms and the packet loss rate is more than 5%, the area is classified as a poor communication quality area; When the signal strength of the super node is greater than -60dBm, the area is classified as a strong signal area; When the signal strength of the super node is less than -80dBm, the area is classified as a weak signal area; When the battery level is ≥80%, it indicates that the battery level in the area is normal; when 50%≤battery level<80%, it indicates that the battery level in the area is low; when 0%≤battery level<50%, it indicates that the battery level in the area is low; when the battery level is<20%, ​​it indicates that the battery level in the area is extremely low; When the super node's position moving speed is less than 1m / s, the area is divided into a stable area; when the super node's position moving speed is greater than or equal to 1m / s, the area is divided into a dynamic area.

3. The intelligent construction site networking and monitoring method based on WAPI technology and MESH network according to claim 2, characterized in that: The first-level super node is used to collect on-site data in a specific area of ​​the construction site. The data includes environmental parameters and construction progress, where environmental parameters include temperature, humidity and air pressure, and construction progress includes material usage and personnel distribution. The data is cleaned, filtered and formatted, and the processed data is sent to the second-level super node. The secondary supernode integrates and analyzes the processed data, identifies potential construction bottlenecks, equipment failures or safety hazards, and adjusts the priority and execution order of tasks based on the analysis results; Two-way data communication is carried out between the second-level super node and the first-level super node; The third-level super node receives the summary information of the second-level super node and optimizes the overall network structure and task execution strategy of the construction site based on this information. The strategy includes global task scheduling, resource optimization, energy consumption control and topology adjustment.

4. The intelligent construction site networking and monitoring method based on WAPI technology and MESH network according to claim 2 is characterized in that: Areas with poor communication quality require relay nodes or additional communication support. Specifically, when -70dBm≤signal strength≤-60dBm, 1 relay node is required; when -80dBm≤signal strength<-70dBm, 2 relay nodes are required; when signal strength<-80dBm, 3 or more relay nodes are required.

5. The intelligent construction site networking and monitoring method based on WAPI technology and MESH network according to claim 1 is characterized in that: In step S2, adjusting task allocation includes the following: The calculation formula for super node power consumption is: P i (t)=α·L i (t)+χ·R i (t)+γ·(E max -E i (t)) Among them, P i (t) represents the power consumption of the i-th super node at the t-th moment; α represents the influence of the task load on the node power consumption; χ represents the influence of the data transmission frequency on the node power consumption; γ represents the influence of the battery power on the node power consumption; L i (t) represents the task load of the i-th super node at time t; R i (t) represents the data transmission frequency of the i-th super node at time t; E max represents the maximum battery capacity of the node, E i (t) represents the battery power of the i-th supernode at time t; According to the historical movement trajectory and power consumption of the super node, the machine learning model is used to predict the future location or power consumption demand of the node, adjust the topology structure and routing path, and adjust data forwarding and task allocation according to the preset task priority; Offload computationally intensive tasks to nodes with loads below 50% of the maximum capacity of the supernode; Assign data forwarding tasks to nodes with signal strength greater than -60dBm and bandwidth higher than 1Mbps, or latency less than 50ms and packet loss rate less than 1%; When the battery power is less than 20%, reduce the super node load by 50%; when 20% ≤ battery power greater than < 50%, reduce the super node load by 30%; when 50% ≤ battery power < 80%, reduce the super node load by 10%.

6. The intelligent construction site networking and monitoring method based on WAPI technology and MESH network according to claim 1 is characterized in that: In step S3, adjusting the transmission weight includes the following: The calculation formula for the weighted priority of super node tasks is: W i =aQ i +bC i +cE i Among them, W i represents the weighted priority of the i-th supernode, Q i represents the priority of the i-th super node task, C i represents the network load of the ith supernode, E i represents the battery power of the i-th supernode, a, b, c all represent weighting coefficients; The priority range is 0 to 100, where 0 represents the lowest priority and 100 represents the highest priority. When 0 ≤ priority ≤ 30, it is a low priority task and is assigned a transmission weight of 1. When 30 < priority ≤ 60, it is a medium priority task and is assigned a transmission weight of 2. When 60 < priority ≤ 90, it is a high priority task and is assigned a transmission weight of 3. When 90 < priority ≤ 100, it is an extremely high priority task and is assigned a transmission weight of 4. When the load of a super node is less than 50% of the maximum carrying capacity of the node, 2 transmission weights are added; when the load of a super node is greater than 50% of the maximum carrying capacity of the node and less than or equal to 75%, 1 transmission weight is added; when the load of a super node is greater than 75% of the maximum carrying capacity of the node, no transmission weight is added; When the battery power is ≥80%, add 3 transmission weights; when 50%≤battery power<80%, add 2 transmission weights; when the battery power is<50%, add 1 transmission weight.

7. The intelligent construction site networking and monitoring method based on WAPI technology and MESH network according to claim 1 is characterized in that: In step S4, the calculation formula for evaluating the comprehensive task cost of the super node is: D i (t)=a·λ i (t)+β·L i (t)+γ·E i (t)+δ·σ i (t) Among them, D i (t) represents the task cost of the i-th super node at the t-th time, α, β, γ, δ are all adjustable weight coefficients, λ i (t) represents the position offset of the i-th super node, L i (t) represents the task load of the i-th super node at time t, E i (t) represents the battery power of the i-th super node at the t-th moment, σ i (t) represents the signal quality of the i-th supernode at time t.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the intelligent construction site networking and monitoring method based on WAPI technology and MESH network as described in any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the intelligent construction site networking and monitoring method based on WAPI technology and MESH network described in any one of claims 1 to 7 is executed.

Images