Method and system for realizing improvement of mine communication signal based on edge calculation

Abstract

The invention discloses a method and a system for realizing mine communication signal improvement based on edge computing, and relates to the technical field of mine communication signal improvement, and the method comprises the following steps: integrating a real-time monitoring system on each edge node, so as to continuously detect the fluctuation of communication flow and data request quantity, the real-time monitoring system identifies a potential communication peak period by collecting real-time data and generates an early warning signal to notify a network administrator or automatically trigger a load management program. According to the invention, through the real-time monitoring and early warning system on the edge node, active monitoring and peak prediction of mine communication are realized, the overload risk caused by traffic surge is reduced, and the stability of data transmission is ensured. And intelligent scheduling and dynamic resource allocation are combined, so that efficient execution of tasks under high load is ensured, and node overload is prevented. A self-adaptive load balancing and feedback mechanism enables the system to dynamically adjust distribution, quickly respond to a bottleneck and improve self-adaptability and stability.

Description

Technical Field

[0001] The present invention relates to the technical field of mine communication signal enhancement, and in particular to a method and system for enhancing mine communication signals based on edge computing. Background Art

[0002] Improving mine communication signals based on edge computing means performing computations at local nodes close to mining equipment and user terminals to reduce data transmission latency and bandwidth requirements, thereby enhancing the efficiency and stability of the communication system. This method distributes computing power from the central data center to edge nodes, making it possible to process and analyze data at the edge of the network. This approach not only improves the real-time response capability of signals, but also optimizes resource allocation and fault detection, effectively improving the reliability and coverage quality of communication systems in mining environments.

[0003] The prior art has the following deficiencies:

[0004] In the existing technology, when improving mine communication signals based on edge computing, due to the volatility of communication needs and the complexity of data volume in the mining environment, edge nodes may be over-requested during peak hours, which will lead to insufficient computing power and task processing delays. If this overload phenomenon is not monitored and managed in time, it may lead to the overall failure of the communication network, affecting the continuity of data transmission and the safety of mine operations, and ultimately increasing operational risks and causing production stagnation or safety accidents.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method and system for improving mine communication signals based on edge computing. By deploying a real-time traffic monitoring and early warning system at the edge node, active monitoring and peak prediction of mine communication traffic are achieved, reducing the risk of system overload and failure due to traffic surge, and improving the continuity and reliability of data transmission. Combined with intelligent task scheduling and dynamic resource allocation, it ensures that high-priority tasks are executed smoothly under high load, prevents single node overload, and optimizes system efficiency and operational capabilities in a multi-task environment. The adaptive load balancing algorithm and feedback mechanism enable the system to dynamically adjust task allocation, quickly respond to node bottlenecks, and improve the system's adaptability, stability, and the level of automation of operations to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for improving mine communication signals based on edge computing, comprising the following steps:

[0008] Integrate a real-time monitoring system on each edge node to continuously detect fluctuations in communication traffic and data request volume. The real-time monitoring system collects real-time data to identify potential communication peaks and generates early warning signals to notify network administrators or automatically trigger load management procedures.

[0009] When a potential communication peak is identified, the dynamic resource management system is triggered by early warning signals to automatically reallocate computing and bandwidth resources. The resource allocation strategy includes priority allocation and task diversion mechanisms to distribute computing tasks among multiple edge nodes to avoid overloading a single node.

[0010] Apply data compression algorithms in the signal processing phase of edge nodes and dynamically adjust the compression rate based on the content of the data;

[0011] Combined with multi-factor analysis models to achieve intelligent task scheduling, the scheduling algorithm is used to intelligently allocate computing tasks to appropriate edge nodes, ensuring that the system operates efficiently in a multi-tasking environment and avoiding node overload;

[0012] Deploy an adaptive load balancing algorithm in the edge network, dynamically adjust the task allocation strategy based on real-time data, and continuously update the load model to cope with changing communication needs.

[0013] Preferably, the real-time monitoring system identifies potential communication peak periods by collecting real-time data and generates early warning signals. The specific steps are as follows:

[0014] First, a real-time monitoring system is deployed on each edge node to collect key performance indicators;

[0015] Analyze traffic patterns using data analysis algorithms and identify changing patterns and potential anomalies in traffic by building a normal traffic model;

[0016] After completing the data analysis, the peak period prediction is carried out based on the extracted features. Specifically, the machine learning algorithm is used to predict the traffic changes in the future period based on historical data and current traffic trends. If the prediction result shows that it is about to be greater than or equal to the set threshold, an early warning signal is generated;

[0017] Once the warning signal is generated, the load management program is automatically triggered, and the current network status is evaluated based on the warning information, and a response strategy is formulated.

[0018] Preferably, when a potential communication peak period is identified, the dynamic resource management system is triggered by an early warning signal to automatically reallocate computing and bandwidth resources. The specific steps are as follows:

[0019] When the real-time monitoring system generates an early warning signal, the dynamic resource management system first analyzes the early warning signal, evaluates the current network load and computing resource requirements, and defines the triggering condition of the early warning signal as S alert , whose value is obtained by comparing the real-time traffic with the preset overload threshold, namely: Among them, L(t) represents the flow data at the current time t, L threshold is the defined overload threshold, if S alert =1, the system enters resource analysis mode to analyze the computing power and bandwidth that need to be reallocated.

[0020] Preferably, based on resource analysis, the system calculates the priority of the task P i , each task i is assigned a weight based on its urgency and computing requirements. The weight formula is: P i =α·U i +β·C i , where U i is the urgency of the task, C i is the computational complexity of the task, α and β are weight coefficients used to balance the two factors.

[0021] Preferably, according to the priority P of the task i , divide the computing tasks, calculate the load distribution scheme on different edge nodes, and assume that the remaining computing capacity of edge node j is Task allocation follows the conditions: Use heuristic algorithms or advanced allocation models to calculate the task combination accepted by each node j to ensure global load balancing;

[0022] The resource management system adjusts bandwidth allocation according to the actual allocation plan of the task. The bandwidth adjustment formula is: Among them B j represents the bandwidth allocated to node j, B max is the maximum bandwidth that the node can provide, D i is the data demand of task i, and γ is the bandwidth adjustment coefficient.

[0023] Preferably, the specific steps of dynamic data compression in the edge node signal processing link are as follows:

[0024] After the edge node receives the data, it first analyzes and classifies the data content;

[0025] After completing data classification, the edge node dynamically sets the compression rate through the compression manager, which selects the best compression strategy based on the real-time and importance of the data;

[0026] The data is actually processed according to the set compression strategy, using the pre-selected compression algorithm, and the data is transmitted immediately after compression. The edge node adjusts the compression rate in combination with the real-time network status during the compression process;

[0027] Finally, the edge node introduces a monitoring and feedback mechanism for the compression effect to evaluate the performance of the compressed data during transmission, check the data transmission delay, packet loss rate and integrity of the decompressed data in real time, and feed back the inspection information to the compression manager. If data loss or increased delay is detected, the compression rate is automatically adjusted or the compression algorithm is switched to maintain communication quality and data availability.

[0028] Preferably, a scheduling algorithm is used in combination with a multi-factor analysis model to intelligently allocate computing tasks to appropriate edge nodes. The specific steps are as follows:

[0029] Before the intelligent task scheduling starts, the parameters of all tasks to be assigned and the status information of the current edge nodes are first collected;

[0030] After collecting data, prioritize and sort the tasks based on their different factors;

[0031] The scheduling system uses advanced scheduling algorithms to match tasks and edge nodes, considers the results of multi-factor analysis, combines real-time network status with historical data prediction, and intelligently allocates tasks to the most appropriate nodes;

[0032] After the task allocation is completed, the allocation plan is verified to monitor the execution effect of the task on each edge node and the overall load balance of the system.

[0033] Preferably, an adaptive load balancing algorithm is deployed in the edge network to dynamically adjust the task allocation strategy. The specific steps are as follows:

[0034] The adaptive load balancing algorithm obtains real-time data through the interface with the edge node, uses the acquired real-time data to establish the current network load model, provides data support for subsequent load balancing decisions, and captures the trend of network load changes and predicts future demand through continuous analysis of real-time information;

[0035] Based on the analysis results, the adaptive load balancing algorithm dynamically updates the load model to reflect the current network status and node performance;

[0036] After the load model is updated, the adaptive load balancing algorithm dynamically adjusts the task allocation strategy according to the new model, analyzes the available computing resources, current load and network status of each node through the algorithm, and optimizes the task allocation path and priority;

[0037] After completing the task allocation, the adaptive load balancing algorithm enters the execution monitoring stage to track the real-time effect of task processing at each node. The monitoring data is used in the feedback loop to help the adaptive load balancing algorithm perform the next round of model adjustment and strategy optimization. If some nodes are detected to be overloaded or delayed abnormally, the immediate response mechanism is triggered to reallocate tasks to other nodes or temporarily adjust task priorities.

[0038] A system for improving mine communication signals based on edge computing, including real-time monitoring module, dynamic resource management module, adaptive data compression module, intelligent task scheduling module and adaptive load balancing module;

[0039] Real-time monitoring module: A real-time monitoring system is integrated on each edge node to continuously detect fluctuations in communication traffic and data request volume. The real-time monitoring system collects real-time data to identify potential communication peaks and generates early warning signals to notify network administrators or automatically trigger load management procedures;

[0040] The dynamic resource management module triggers the dynamic resource management system through early warning signals when a potential communication peak is identified, automatically reallocating computing and bandwidth resources. The resource allocation strategy includes priority allocation and task diversion mechanisms to distribute computing tasks among multiple edge nodes to avoid overloading a single node.

[0041] Adaptive data compression module, which applies data compression algorithm in the signal processing link of edge nodes and dynamically adjusts the compression rate according to the content of the data;

[0042] The intelligent task scheduling module combines a multi-factor analysis model to implement intelligent task scheduling. It uses a scheduling algorithm to intelligently allocate computing tasks to appropriate edge nodes, ensuring that the system operates efficiently in a multi-tasking environment and avoiding node overload.

[0043] The adaptive load balancing module deploys an adaptive load balancing algorithm in the edge network, dynamically adjusts the task allocation strategy based on real-time data, and continuously updates the load model to cope with changing communication needs.

[0044] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0045] By deploying real-time traffic monitoring modules and early warning systems at edge nodes, the present invention enables the mine communication network to actively monitor traffic changes and predict and respond before the peak arrives, effectively reducing the risk of system overload and failure caused by a surge in communication traffic, ensuring the continuity and stability of data transmission, and reducing the impact of sudden network interruptions on production operations and personnel communications in mines, an environment with extremely high safety requirements, thereby significantly improving the reliability and emergency response capabilities of the system.

[0046] By applying intelligent task scheduling and dynamic resource allocation strategies, the present invention can optimally configure the computing and bandwidth resources of each edge node. The system allocates resources according to the priority and urgency of the task, ensuring that key tasks can still proceed smoothly under high load, while avoiding the performance bottleneck caused by single node overload. This resource allocation method not only improves the overall processing efficiency of the mine communication system, but also provides a guarantee for efficient operation in a multi-tasking environment, making the system perform more smoothly and efficiently when dealing with complex and changing communication needs.

[0047] Through the adaptive load balancing algorithm and feedback optimization mechanism, the system can dynamically adjust the task allocation strategy according to real-time data and respond quickly when bottlenecks occur in node performance. The continuous updating of the load model and the automated scheduling adjustment enable the system to continuously optimize the task path and distribution in the changing communication needs. Such adaptability enables the mine communication network to cope with sudden task changes and traffic fluctuations, maintain efficient operation, reduce human intervention and the complexity of system management, and further improve the reliability and stability of operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0049] Figure 1 The present invention is a method flow chart of a method for improving mine communication signals based on edge computing.

[0050] Figure 2 This is a module schematic diagram of the system for improving mine communication signals based on edge computing in the present invention. DETAILED DESCRIPTION

[0051] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0052] The present invention provides Figure 1 The method for improving mine communication signals based on edge computing shown includes the following steps:

[0053] Integrate a real-time monitoring system on each edge node to continuously detect fluctuations in communication traffic and data request volume. The real-time monitoring system collects real-time data to identify potential communication peaks and generates early warning signals to notify network administrators or automatically trigger load management procedures.

[0054] The real-time monitoring system collects real-time data to identify potential communication peaks and generate early warning signals. The specific steps are as follows:

[0055] First, a real-time monitoring system is deployed at each edge node to collect key performance indicators such as network traffic, data request volume, and latency. The real-time monitoring system is connected to network devices through interfaces, obtains data packet information in real time, and uses traffic analysis algorithms to regularly collect and summarize this information. The collected data includes not only traffic during normal operation, but also historical data for trend analysis. This process ensures a comprehensive understanding of the network status and lays the foundation for subsequent peak forecasts;

[0056] The real-time monitoring system is an intelligent system embedded in edge computing nodes to continuously monitor the operating status and data traffic of the network. The real-time monitoring system obtains real-time data such as packet traffic, request frequency and latency from network devices through interfaces, and uses algorithms to analyze these data to identify potential anomalies and peak periods. It can predict traffic fluctuations that may cause overloads and generate early warning signals to notify administrators or automatically trigger load management programs, thereby ensuring the smooth operation of the network and optimizing resource allocation.

[0057] Once enough real-time data is collected, the real-time monitoring system will use data analysis algorithms (such as time series analysis, anomaly detection, etc.) to analyze traffic patterns. By building a normal traffic model, the module can identify changing patterns and potential anomalies in traffic, such as bursts or a continuous increase in the number of requests. The key to this stage is to extract features from the data, such as the average value, standard deviation, peak value, etc. of the traffic, which can help determine the usage trend of the network and predict possible peak periods in the future.

[0058] After completing the data analysis, the monitoring module makes a peak forecast based on the extracted features. Using machine learning algorithms (such as regression analysis, neural networks, etc.), the system can predict traffic changes in the future based on historical data and current traffic trends. If the forecast results show that the set threshold is about to be reached or exceeded, the module will generate an early warning signal. These signals can be graphical dashboard notifications, email or SMS alerts, ensuring that network administrators are informed of potential communication peaks in a timely manner.

[0059] Once the warning signal is generated, the real-time monitoring system can automatically trigger the load management program. This program will evaluate the current network status based on the warning information and formulate corresponding response strategies. For example, the resource allocation of edge nodes can be dynamically adjusted and computing tasks can be reconfigured to balance the load. This process ensures that before the peak period arrives, the system can take proactive measures to avoid communication congestion and improve overall network performance and reliability. This automated response mechanism significantly reduces the need for manual intervention and improves the network's adaptability and stress resistance.

[0060] This step ensures that overloads are predicted and responded to before they occur, thereby improving the stability of the mine communication network.

[0061] When a potential communication peak is identified, the dynamic resource management system is triggered by early warning signals to automatically reallocate computing and bandwidth resources. The resource allocation strategy includes priority allocation and task diversion mechanisms to distribute computing tasks among multiple edge nodes to avoid overloading a single node.

[0062] When a potential communication peak is identified, the dynamic resource management system is triggered by early warning signals to automatically reallocate computing and bandwidth resources. The specific steps are as follows:

[0063] When the real-time monitoring system generates an early warning signal, the dynamic resource management system first analyzes the signal, evaluates the current network load and computing resource requirements, and defines the triggering condition of the early warning signal as S alert , whose value is obtained by comparing the real-time traffic with the preset overload threshold, namely: Among them, L(t) represents the flow data at the current time t, L threshold is the defined overload threshold, if S alert =1, the system enters the resource analysis mode to analyze the computing capacity and bandwidth that need to be reallocated;

[0064] Based on resource analysis, the system calculates the priority of the task P i , each task i is assigned a weight based on its urgency and computing requirements. The weight formula is: P i =α·U i +β·C i , where U i is the urgency of the task (such as real-time requirements, the higher the value, the more urgent it is), C i is the computational complexity of the task (such as the required CPU or bandwidth), and α and β are weight coefficients used to balance the two factors. The highest priority tasks will be allocated resources first to ensure that critical tasks are not affected by peak traffic.

[0065] According to the priority of the task P i, the system distributes the computing tasks and calculates the distribution scheme of the computing load on different edge nodes. Suppose the remaining computing capacity of edge node j is Task allocation follows the conditions: Use heuristic algorithms or advanced allocation models (such as linear programming or genetic algorithms) to calculate the combination of tasks accepted by each node j to ensure global load balancing;

[0066] In this step, the system dynamically adjusts the load distribution of node j to maximize the overall performance.

[0067] The resource management system adjusts the bandwidth allocation according to the actual allocation plan of the task. The bandwidth adjustment formula is: j =min(B max ,γ·∑ i∈Tj D i ), where B j represents the bandwidth allocated to node j, B max is the maximum bandwidth that the node can provide, D i is the data demand of task i, γ is the bandwidth adjustment coefficient;

[0068] The verification step includes monitoring the network operation status under the new configuration to ensure system stability and continued load balancing.

[0069] This approach optimizes the allocation of computing resources under real-time conditions and reduces the risk of task delays.

[0070] Apply data compression algorithms in the signal processing phase of edge nodes and dynamically adjust the compression rate based on the content of the data;

[0071] The specific steps of dynamic data compression in the edge node signal processing link are as follows:

[0072] After the edge node receives the data, the data content is first analyzed and classified. This step uses the content analysis module to perform a preliminary scan of the data stream to determine its nature (such as text, image, video, or sensor data). Depending on the data type and its real-time requirements, the module can identify different compression requirements. For example, for video and image data, the analysis module will detect the resolution and frame rate, while for text data, the character set and content length will be considered. The classification process makes the subsequent compression steps more efficient and targeted, which helps to optimize the use of resources.

[0073] After completing data classification, the edge node dynamically sets the appropriate compression rate through the compression manager. The compression manager selects the appropriate compression strategy based on the real-time and importance of the data. For example, for data with low delay tolerance, a lossless compression algorithm is selected to ensure data integrity; for content that can tolerate a certain amount of data loss, such as video streaming, moderate lossy compression is selected to reduce the amount of transmission. This dynamic adjustment mechanism can intelligently find the best balance between data transmission efficiency and quality.

[0074] The data compression module actually processes the data according to the set compression strategy. This module uses a pre-selected compression algorithm (such as deep learning-driven adaptive compression algorithm or traditional Huffman coding) to compress the data and transmit it immediately. During the compression process, the edge node combines the real-time network status, such as bandwidth availability and transmission queue length, to adjust the compression rate. This process ensures that the amount of data transmitted is effectively reduced when the network is congested, thereby maintaining the stability and responsiveness of the system.

[0075] Finally, the edge node introduces a monitoring and feedback mechanism for compression effects to evaluate the performance of compressed data during transmission. The monitoring module checks the data transmission delay, packet loss rate, and integrity of decompressed data in real time, and feeds this information back to the compression manager. If data loss or increased latency is detected, the system automatically adjusts the compression rate or switches the compression algorithm to maintain communication quality and data availability. This closed-loop feedback mechanism enables data compression strategies to be adaptively adjusted to cope with dynamically changing network and application environments.

[0076] Combined with multi-factor analysis models to achieve intelligent task scheduling, the scheduling algorithm is used to intelligently allocate computing tasks to appropriate edge nodes, ensuring that the system operates efficiently in a multi-tasking environment and avoiding node overload;

[0077] Combined with the multi-factor analysis model, a scheduling algorithm is used to intelligently allocate computing tasks to appropriate edge nodes. The specific steps are as follows:

[0078] Before intelligent task scheduling begins, the system first needs to collect the parameters of all tasks to be assigned and the status information of the current edge nodes. Task parameters include the computing requirements, priority, execution time window, etc. of the task, while the edge node status covers the remaining computing power, current load, and available bandwidth of the node. The multi-factor analysis model analyzes these parameters in this step to ensure that the scheduling algorithm can make decisions based on the most real-time and accurate data. Through this process, the system can have a comprehensive understanding of task characteristics and node performance, ensuring the adaptability of the scheduling strategy.

[0079] After collecting the data, the scheduling system will evaluate and sort the tasks according to different factors of the task, such as urgency and computational complexity. High-priority tasks are usually those with high real-time requirements and large impact ranges. The scheduling system will prioritize these tasks to maintain the stability and responsiveness of the system. This step will also evaluate the suitability of the task based on the current load level of the node to prevent high computing demand tasks from being assigned to nodes that are close to the load limit, avoiding potential performance bottlenecks and overload problems.

[0080] The scheduling system uses advanced scheduling algorithms (such as genetic algorithms or reinforcement learning methods) to match tasks and edge nodes. The algorithm considers the results of multi-factor analysis, combines real-time network status with historical data prediction, and intelligently assigns tasks to the most suitable nodes. This process dynamically adjusts the task allocation scheme to ensure that high-priority tasks are processed quickly, optimizes the distribution of overall tasks, and improves the system's processing capabilities in a multi-tasking environment. The system also needs to adapt to the insertion of sudden tasks to ensure the flexibility and robustness of the scheduling scheme.

[0081] After the task allocation is completed, the scheduling system verifies the allocation plan, monitors the execution effect of the task on each edge node and the overall load balance of the system. In this stage, the load changes of the nodes and the task execution status are monitored through the real-time feedback mechanism, and dynamic adjustments are made when necessary. If a node is detected to have performance degradation or is close to overload, the scheduling system will immediately re-evaluate and transfer some tasks to other nodes to maintain the stability and efficient operation of the system. The addition of the feedback mechanism makes the scheduling system adaptive and can be optimized as network conditions change.

[0082] Deploy adaptive load balancing algorithms in edge networks, dynamically adjust task allocation strategies based on real-time data, and continuously update load models to cope with changing communication needs;

[0083] Deploy an adaptive load balancing algorithm in the edge network to dynamically adjust the task allocation strategy. The specific steps are as follows:

[0084] The basis of adaptive load balancing is to continuously collect and analyze real-time data to understand the status of the network and nodes. The load balancing algorithm obtains data such as traffic information, the number of current computing tasks, processor utilization, and latency through the interface with the edge node. This stage includes data preprocessing steps to ensure the accuracy and timeliness of the data, such as data cleaning and denoising. The analysis step uses this real-time data to build a model of the current network load and provide data support for subsequent load balancing decisions. By continuously analyzing real-time information, the algorithm can capture the trend of network load changes and predict future demand.

[0085] Based on the analysis results, the algorithm dynamically updates the load model to reflect the current network status and node performance. This process includes multivariate analysis, such as a comprehensive evaluation of computing power, storage capacity, network latency, and task processing speed. The model is updated not only based on the currently collected data, but also based on historical data and trend analysis for prediction. In this way, the adaptive algorithm can foresee possible load peaks or node performance bottlenecks, and adjust the strategy in advance to disperse the tasks, ensuring that the nodes will not affect the stability and efficiency of communication due to excessive load.

[0086] After the load model is updated, the load balancing algorithm will dynamically adjust the task allocation strategy according to the new model. This process uses the algorithm to analyze the available computing resources, current load and network conditions of each node to optimize the task allocation path and priority. For example, the algorithm will set the node with lower load as the priority task recipient, or distribute the computing task to the node closest to the task source to reduce latency when the communication demand is high. This real-time adjustment strategy allows the system to adapt to rapid changes in network conditions and ensure that the task distribution remains balanced throughout the network.

[0087] After completing the task allocation, the adaptive algorithm enters the execution monitoring phase to track the real-time effect of task processing at each node, such as task completion time, response speed, and whether anomalies occur. Monitoring data is used in the feedback loop to help the algorithm adjust the model and optimize the strategy for the next round. If some nodes are detected to be overloaded or delayed abnormally, the algorithm will trigger an immediate response mechanism to reallocate tasks to other nodes or temporarily adjust task priorities. Through continuous feedback and adjustment, the load balancing algorithm gradually optimizes its strategy, allowing the edge network to maintain efficient and stable operation under changing communication needs.

[0088] The algorithm optimizes the allocation path through continuous learning and feedback mechanisms, enabling the entire edge computing system to respond quickly to burst traffic, ensuring the stability and continuity of communication signals.

[0089] Implementation method 1: Deployment and operation of real-time traffic monitoring and early warning system;

[0090] In a mining environment, the stability of the communication network is crucial, especially when different devices, sensors, and personnel use the network at the same time, the traffic and data demand will show greater volatility. For this reason, it is particularly necessary to deploy a real-time traffic monitoring module on each edge node. By connecting to the network device interface, the module can capture key performance indicators such as real-time data traffic, packet transmission rate, latency, and packet loss rate. In the initial stage, the module will collect and preprocess data, including removing noise and outliers to ensure the accuracy and reliability of the data.

[0091] When the module collects enough data, it uses advanced analytical algorithms for real-time evaluation. Through time series analysis and machine learning techniques, the module can identify fluctuation trends and abnormal peaks in traffic. For example, a baseline model built based on historical data can establish standards for normal network behavior. When the current traffic data deviates from the baseline by more than a set threshold, the module will generate an early warning signal. This early warning signal can be an alarm notification on the dashboard, a text message reminder from the administrator, or even an automatically triggered load management program so that the network system can take quick action.

[0092] Deploying a real-time traffic monitoring module can not only detect immediate communication peaks, but also predict peaks. The prediction model combined with machine learning regression analysis or neural network algorithms can identify traffic trends in the next few seconds or minutes. This function is particularly important in mining operations, because communication interruptions not only lead to reduced production efficiency, but also affect mine safety. The generation of early warning signals provides administrators with enough time to adjust resources and scheduling strategies, or trigger automation systems to distribute or transfer network loads when necessary.

[0093] Finally, the real-time monitoring system and the early warning system ensure the sustainable operation of the network during peak hours, avoiding system crashes caused by delays or overloads. This technology has significant advantages in mining operations, not only improving the stability of data transmission, but also reducing communication conflicts and interruptions between devices, ensuring information flow and operational safety in the mining environment.

[0094] Implementation method 2: Dynamic resource allocation based on priority and task diversion;

[0095] In the mine communication environment, due to the different communication requirements of different devices and tasks, the traditional static resource allocation method cannot meet the dynamically changing network requirements. To solve this problem, the system needs to start a dynamic resource allocation strategy after detecting a potential peak period. The core of this strategy is to conduct a comprehensive analysis based on factors such as task priority, computing requirements, and network load, and reallocate resources to each edge node. The first step to implement this solution is to evaluate the urgency and computational complexity of the task. The system will perform parameter analysis on each task, including real-time requirements, data processing requirements, and the importance of the task.

[0096] After the system determines the priority of the task, it will use an intelligent diversion algorithm to reasonably distribute the task to different nodes. For example, during peak hours, when a certain edge node is close to full load, the system will automatically transfer some tasks to other nodes with lower loads through a scheduling algorithm. Such a diversion mechanism effectively avoids the computing bottleneck of a single node, ensuring efficient execution of tasks and stable operation of the network. This process involves not only the reallocation of tasks, but also the dynamic adjustment of bandwidth to adapt to the different needs of tasks.

[0097] In addition, intelligent algorithms are applied in the dynamic resource allocation system to optimize the use of computing resources. Through these algorithms, the system can adjust the priority and allocation strategy of tasks in real time to meet the needs of different communication conditions. For example, in an emergency, the system can automatically prioritize high-priority tasks and postpone or lower the priority of non-critical tasks. This strategy ensures that in mining operations, communication and computing resources always serve critical tasks and equipment, reducing the risk of network delays and data transmission congestion.

[0098] This resource allocation scheme based on priority and task diversion ultimately achieves optimal resource utilization. Through real-time monitoring and dynamic adjustment, the mine network can maintain smooth communication under high load conditions, ensuring production operations and personnel safety. Intelligent diversion and scheduling strategies reduce manual intervention, improve the system's automation level, and reduce the complexity of system maintenance and management.

[0099] Implementation method 3: Adaptive load balancing and feedback optimization mechanism;

[0100] In order to ensure the stable transmission of signals and data in the mine communication system, an adaptive load balancing algorithm is required. The main feature of this type of algorithm is the ability to dynamically adjust the allocation strategy of network tasks based on real-time data. The first step in implementing this solution is to deploy a powerful monitoring system that continuously collects traffic, task load, and computing performance data from each node. By analyzing this data, the adaptive algorithm can have a comprehensive understanding of the current state of the network and establish a real-time load model through multi-factor analysis.

[0101] The updating of the load model is the core part of the adaptive algorithm, which not only relies on current data, but also combines historical data and trend analysis to predict future loads. This ensures that the algorithm can respond quickly when network conditions change. For example, when it detects that the load of a node continues to rise and may exceed its computing capacity, the algorithm will start the task reallocation procedure in advance and move some tasks to nodes with lower loads, thereby preventing performance degradation and communication interruption.

[0102] In the dynamic adjustment of the task allocation strategy, the adaptive algorithm will perform global optimization based on factors such as the remaining computing resources of each node, the current task type, and network latency. The system will use load balancing strategies, such as scheduling based on response time or scheduling based on task priority, to ensure that the load of each node operates within a controllable range. If a node is detected to have a performance bottleneck, the algorithm will automatically adjust the task path or modify the task execution strategy to avoid overloading a single node.

[0103] Finally, the load balancing system has a powerful feedback optimization mechanism. By monitoring the actual task execution of the nodes, the system collects feedback data and adjusts and optimizes future task allocation strategies. This feedback loop enables the algorithm to improve its decisions with each adjustment, allowing the entire network to adapt to dynamically changing communication needs at any time. In the long run, this mechanism significantly improves the flexibility and reliability of the edge network, ensuring that the mine can maintain an efficient and secure communication network under various operating conditions.

[0104] By deploying real-time traffic monitoring modules and early warning systems at edge nodes, the present invention enables mine communication networks to actively monitor traffic changes and predict and respond before peak traffic arrives, effectively reducing the risk of system overload and failure caused by a surge in communication traffic, and ensuring the continuity and stability of data transmission. Especially in mines, which have extremely high safety requirements, the impact of sudden network interruptions on production operations and personnel communications is reduced, significantly improving the reliability and emergency response capabilities of the system.

[0105] By applying intelligent task scheduling and dynamic resource allocation strategies, the computing and bandwidth resources of each edge node can be optimally configured. The system allocates resources according to the priority and urgency of the task, ensuring that key tasks can still proceed smoothly under high load, while avoiding the performance bottleneck caused by single node overload. This resource allocation method not only improves the overall processing efficiency of the mine communication system, but also provides a guarantee for efficient operation in a multi-tasking environment, making the system more stable and efficient when dealing with complex and changing communication needs.

[0106] Through the adaptive load balancing algorithm and feedback optimization mechanism, the system can dynamically adjust the task allocation strategy according to real-time data and respond quickly when node performance bottlenecks occur. The continuous update of the load model and the automated scheduling adjustment enable the system to continuously optimize the task path and distribution in the changing communication needs. Such adaptability enables the mine communication network to cope with sudden task changes and traffic fluctuations, maintain efficient operation, reduce the complexity of human intervention and system management, and further improve the reliability and stability of operations.

[0107] The present invention provides Figure 2 The illustrated system for realizing mine communication signal improvement based on edge computing includes a real-time monitoring module, a dynamic resource management module, an adaptive data compression module, an intelligent task scheduling module, and an adaptive load balancing module;

[0108] Real-time monitoring module: A real-time monitoring system is integrated on each edge node to continuously detect fluctuations in communication traffic and data request volume. The real-time monitoring system collects real-time data to identify potential communication peaks and generates early warning signals to notify network administrators or automatically trigger load management procedures;

[0109] The dynamic resource management module triggers the dynamic resource management system through early warning signals when a potential communication peak is identified, automatically reallocating computing and bandwidth resources. The resource allocation strategy includes priority allocation and task diversion mechanisms to distribute computing tasks among multiple edge nodes to avoid overloading a single node.

[0110] Adaptive data compression module, which applies data compression algorithm in the signal processing link of edge nodes and dynamically adjusts the compression rate according to the content of the data;

[0111] The intelligent task scheduling module combines a multi-factor analysis model to implement intelligent task scheduling. It uses a scheduling algorithm to intelligently allocate computing tasks to appropriate edge nodes, ensuring that the system operates efficiently in a multi-tasking environment and avoiding node overload.

[0112] Adaptive load balancing module, which deploys adaptive load balancing algorithms in edge networks, dynamically adjusts task allocation strategies based on real-time data, and continuously updates load models to cope with changing communication needs;

[0113] The method for improving mine communication signals based on edge computing provided in an embodiment of the present invention is realized by the above-mentioned system for improving mine communication signals based on edge computing. The specific method and process of the system for improving mine communication signals based on edge computing are detailed in the embodiment of the method for improving mine communication signals based on edge computing, which will not be repeated here.

[0114] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for improving mine communication signals based on edge computing, characterized in that: The following steps are involved: Integrate a real-time monitoring system on each edge node to continuously detect fluctuations in communication traffic and data request volume. The real-time monitoring system collects real-time data to identify potential communication peaks and generates early warning signals to notify network administrators or automatically trigger load management procedures. When a potential communication peak is identified, the dynamic resource management system is triggered by early warning signals to automatically reallocate computing and bandwidth resources. The resource allocation strategy includes priority allocation and task diversion mechanisms to distribute computing tasks among multiple edge nodes to avoid overloading a single node. Apply data compression algorithms in the signal processing phase of edge nodes and dynamically adjust the compression rate based on the content of the data; Combined with multi-factor analysis models to achieve intelligent task scheduling, the scheduling algorithm is used to intelligently allocate computing tasks to appropriate edge nodes, ensuring that the system operates efficiently in a multi-tasking environment and avoiding node overload; Deploy an adaptive load balancing algorithm in the edge network, dynamically adjust the task allocation strategy based on real-time data, and continuously update the load model to cope with changing communication needs.

2. The method for improving mine communication signals based on edge computing according to claim 1 is characterized in that: The real-time monitoring system collects real-time data to identify potential communication peaks and generate early warning signals. The specific steps are as follows: First, a real-time monitoring system is deployed on each edge node to collect key performance indicators; Analyze traffic patterns using data analysis algorithms and identify changing patterns and potential anomalies in traffic by building a normal traffic model; After completing the data analysis, the peak period prediction is carried out based on the extracted features. Specifically, the machine learning algorithm is used to predict the traffic changes in the future period based on historical data and current traffic trends. If the prediction result shows that it is about to be greater than or equal to the set threshold, an early warning signal is generated; Once the warning signal is generated, the load management program is automatically triggered, and the current network status is evaluated based on the warning information, and a response strategy is formulated.

3. The method for improving mine communication signals based on edge computing according to claim 1 is characterized in that: When a potential communication peak is identified, the dynamic resource management system is triggered by early warning signals to automatically reallocate computing and bandwidth resources. The specific steps are as follows: When the real-time monitoring system generates an early warning signal, the dynamic resource management system first analyzes the early warning signal, evaluates the current network load and computing resource requirements, and defines the triggering condition of the early warning signal as S alert , whose value is obtained by comparing the real-time traffic with the preset overload threshold, namely: Among them, L(t) represents the flow data at the current time t, L threshold is the defined overload threshold, if S alert =1, the system enters resource analysis mode to analyze the computing power and bandwidth that need to be reallocated.

4. The method for improving mine communication signals based on edge computing according to claim 3 is characterized in that: Based on resource analysis, the system calculates the priority of the task P i , each task i is assigned a weight based on its urgency and computing requirements. The weight formula is: P i =α·U i +β·C i , where U i is the urgency of the task, C i is the computational complexity of the task, α and β are weight coefficients used to balance the two factors.

5. The method for improving mine communication signals based on edge computing according to claim 4 is characterized in that: According to the priority of the task P i , divide the computing tasks, calculate the load distribution scheme on different edge nodes, and set the remaining computing capacity of edge node j as C j available , the task allocation follows the conditions: Use heuristic algorithms or advanced allocation models to calculate the task combination accepted by each node j to ensure global load balancing; The resource management system adjusts bandwidth allocation according to the actual allocation plan of the task. The bandwidth adjustment formula is: Among them B j represents the bandwidth allocated to node j, B max is the maximum bandwidth that the node can provide, D i is the data demand of task i, and γ is the bandwidth adjustment coefficient.

6. The method for improving mine communication signals based on edge computing according to claim 1, characterized in that: The specific steps of dynamic data compression in the edge node signal processing link are as follows: After the edge node receives the data, it first analyzes and classifies the data content; After completing data classification, the edge node dynamically sets the compression rate through the compression manager, which selects the best compression strategy based on the real-time and importance of the data; The data is actually processed according to the set compression strategy, using the pre-selected compression algorithm, and the data is transmitted immediately after compression. The edge node adjusts the compression rate in combination with the real-time network status during the compression process; Finally, the edge node introduces a monitoring and feedback mechanism for the compression effect to evaluate the performance of the compressed data during transmission, check the data transmission delay, packet loss rate and integrity of the decompressed data in real time, and feed back the inspection information to the compression manager. If data loss or increased delay is detected, the compression rate is automatically adjusted or the compression algorithm is switched to maintain communication quality and data availability.

7. The method for improving mine communication signals based on edge computing according to claim 1, characterized in that: Combined with the multi-factor analysis model, a scheduling algorithm is used to intelligently allocate computing tasks to appropriate edge nodes. The specific steps are as follows: Before the intelligent task scheduling starts, the parameters of all tasks to be assigned and the status information of the current edge nodes are first collected; After collecting the data, the tasks are prioritized and sorted according to their different factors; The scheduling system uses advanced scheduling algorithms to match tasks and edge nodes, considers the results of multi-factor analysis, combines real-time network status with historical data prediction, and intelligently allocates tasks to the most appropriate nodes; After the task allocation is completed, the allocation plan is verified to monitor the execution effect of the task on each edge node and the overall load balance of the system.

8. The method for improving mine communication signals based on edge computing according to claim 1, characterized in that: Deploy an adaptive load balancing algorithm in the edge network to dynamically adjust the task allocation strategy. The specific steps are as follows: The adaptive load balancing algorithm obtains real-time data through the interface with the edge node, uses the acquired real-time data to establish the current network load model, provides data support for subsequent load balancing decisions, and captures the trend of network load changes and predicts future demand through continuous analysis of real-time information; Based on the analysis results, the adaptive load balancing algorithm dynamically updates the load model to reflect the current network status and node performance; After the load model is updated, the adaptive load balancing algorithm dynamically adjusts the task allocation strategy according to the new model, analyzes the available computing resources, current load and network status of each node through the algorithm, and optimizes the task allocation path and priority; After completing the task allocation, the adaptive load balancing algorithm enters the execution monitoring stage to track the real-time effect of task processing at each node. The monitoring data is used in the feedback loop to help the adaptive load balancing algorithm perform the next round of model adjustment and strategy optimization. If some nodes are detected to be overloaded or delayed abnormally, the immediate response mechanism is triggered to reallocate tasks to other nodes or temporarily adjust task priorities.

9. A system for improving mine communication signals based on edge computing, used to implement the method for improving mine communication signals based on edge computing as described in any one of claims 1 to 8, characterized in that: It includes real-time monitoring module, dynamic resource management module, adaptive data compression module, intelligent task scheduling module and adaptive load balancing module; Real-time monitoring module: A real-time monitoring system is integrated on each edge node to continuously detect fluctuations in communication traffic and data request volume. The real-time monitoring system collects real-time data to identify potential communication peaks and generates early warning signals to notify network administrators or automatically trigger load management procedures; The dynamic resource management module triggers the dynamic resource management system through early warning signals when a potential communication peak is identified, automatically reallocating computing and bandwidth resources. The resource allocation strategy includes priority allocation and task diversion mechanisms to distribute computing tasks among multiple edge nodes to avoid overloading a single node. Adaptive data compression module, which applies data compression algorithm in the signal processing link of edge nodes and dynamically adjusts the compression rate according to the content of the data; The intelligent task scheduling module combines a multi-factor analysis model to implement intelligent task scheduling. It uses a scheduling algorithm to intelligently allocate computing tasks to appropriate edge nodes, ensuring that the system operates efficiently in a multi-tasking environment and avoiding node overload. The adaptive load balancing module deploys an adaptive load balancing algorithm in the edge network, dynamically adjusts the task allocation strategy based on real-time data, and continuously updates the load model to cope with changing communication needs.

Images