Edge computing node deployment system and method in industrial internet of things environment

Abstract

The invention discloses an edge computing node deployment system and method in an industrial Internet of Things environment, and relates to the field of computers, and the system comprises a data collection module which is connected with terminal equipment in the industrial Internet of Things environment and is used for collecting equipment data of key equipment in the terminal equipment in real time, the equipment data comprises equipment state information and operation environment data; the data processing module is connected with the data acquisition module and is used for performing feature extraction on the equipment data to obtain feature data; the task scheduling and resource management module is connected with the data processing module and is used for determining the optimal deployment number and the optimal deployment position of the edge computing nodes according to the task requirements of the key equipment and the feature data; and deploying the edge computing nodes in the industrial Internet of Things environment according to the optimal deployment number and the optimal deployment position.

Description

Technical Field

[0001] This application relates to the field of computers, and more particularly to an edge computing node deployment system and method in an industrial Internet of Things (IoT) environment. Background Technology

[0002] Industrial environments are complex, and safety accidents occur frequently, leading to significant personal injury and property damage. Currently, numerous intelligent devices are deployed in industrial settings to assess the status of critical equipment and the industrial environment. Traditional methods transmit this collected data to a cloud center for processing, consuming considerable time. However, accidents often occur instantaneously, and prolonged transmission can compromise the safety of industrial manufacturing. Edge computing can reduce transmission time and is widely used for processing equipment data. However, the limited resources and heterogeneity of edge nodes make their efficient deployment a challenge. The hardware architecture and software configuration of sensing devices differ; interactions between different devices, between devices and edge nodes, and between devices and sensors are heterogeneous; and edge nodes from different manufacturers exhibit significant differences in computing resources, storage capacity, and communication resources. Therefore, efficient deployment of edge nodes at the network edge is a prerequisite for implementing edge computing in an industrial IoT environment, and it is also a crucial method for ensuring service quality through edge computing platforms.

[0003] Traditional random deployment methods result in concentrated edge node deployments, easily overlooking hotspot areas and failing to effectively handle terminal data transmissions, leading to resource waste. Uniform deployment methods do not consider differences in device density, resulting in insufficient coverage of high-production lines and wasted resources in vacant areas.

[0004] In the context of the Industrial Internet of Things (IIoT), there are currently no effective solutions to the challenges of deploying edge computing nodes and experiencing delays in task services due to the massive amount of data, limited communication bandwidth, and device mobility. Summary of the Invention

[0005] This application provides an edge computing node deployment system and method in an industrial Internet of Things (IIoT) environment, to at least solve the problems of difficult edge computing node deployment and task service latency caused by the large amount of data, limited communication bandwidth and device mobility in the industrial Internet of Things environment.

[0006] This application provides an edge computing node deployment system in an industrial Internet of Things (IIoT) environment, comprising: a data acquisition module connected to a terminal device in the IIoT environment, used to collect device data of key devices in the terminal device in real time, wherein the device data includes device status information and operating environment data; a data processing module connected to the data acquisition module, used to extract features from the device data to obtain feature data; and a task scheduling and resource management module connected to the data processing module, used to determine the optimal deployment quantity and optimal deployment location of edge computing nodes based on the task requirements of the key devices and the feature data, and deploy edge computing nodes in the IIoT environment according to the optimal deployment quantity and the optimal deployment location.

[0007] In an exemplary embodiment, the data acquisition module includes: an environmental data acquisition unit, used to perform environmental monitoring on the industrial IoT environment to obtain the operating environment data, wherein the operating environment data includes at least one of the following: air quality data, meteorological parameter data; and an equipment data acquisition unit, connected to the terminal device, used to collect at least the equipment status information of the key equipment.

[0008] In an exemplary embodiment, the data processing module includes: a data processing unit, configured to receive device data sent by the data acquisition module, preprocess the device data to obtain processed device data; and a data calculation unit, connected to the data processing unit, configured to perform calculations on the processed device data and extract the feature data from the obtained calculation results.

[0009] In an exemplary embodiment, the data processing module further includes a data analysis unit connected to the data computing unit, configured to: perform data analysis on historical device data stored in the edge computing node deployment system using data mining techniques, and establish a fault prediction model based on the data analysis results; perform fault analysis on the processed device data using the fault prediction model to obtain fault analysis results.

[0010] In an exemplary embodiment, the task scheduling and resource management module includes: a node deployment unit, configured to deploy an optimal number of edge computing nodes at the optimal deployment location according to the optimal deployment number and the optimal deployment location; and a task scheduling unit, connected to the node deployment unit, configured to perform task scheduling among the optimal number of edge computing nodes according to the task requirements and the node capabilities of the optimal number of edge computing nodes.

[0011] In an exemplary embodiment, the node deployment unit is further configured to: initialize a sand cat population using a chaotic mapping method, wherein the sand cat population comprises multiple sand cat individuals, each sand cat individual being used to indicate multiple edge computing nodes; calculate the fitness values ​​of the multiple sand cat individuals based on the task service latency of the edge computing nodes to obtain multiple first fitness values; update the positions of the multiple sand cat individuals and recalculate the fitness values ​​of the multiple sand cat individuals based on the updated positions to obtain multiple second fitness values; determine the optimal sand cat based on the multiple first fitness values ​​and the multiple second fitness values; and, if a preset iteration condition is satisfied, output the deployment quantity and deployment position corresponding to the optimal sand cat, determining the deployment quantity as the optimal deployment quantity and the deployment position as the optimal deployment position, wherein the preset iteration condition includes at least one of the following: a maximum number of iterations, and a fitness threshold.

[0012] In an exemplary embodiment, the node deployment unit is further configured to: determine a sensitivity value corresponding to the optimal sand cat when the preset iteration condition is not met; determine whether the sensitivity value is less than or equal to a preset threshold; if the sensitivity value is less than or equal to the preset threshold, determine that the sand cat population has entered the development phase and update the positions of the plurality of sand cat individuals using a Levy walking strategy; if the sensitivity value is greater than the preset threshold, determine that the sand cat population has entered the exploration phase and update the positions of the plurality of sand cat individuals using a spiral search strategy.

[0013] In one exemplary embodiment, the node deployment unit is further configured to: use a formula Calculate the task service latency T of the edge computing node max ,in, , For task transmission time, For task execution time, Let T be the task waiting time, T be the task set, and E be the edge computing node set.

[0014] In an exemplary embodiment, the node deployment unit is further configured to: calculate using the following formulas respectively , and : , , ,in, This is used to indicate whether the i-th task in the task set T is executed on the j-th node in the edge computing node set E. For the input quantities of the task, The output of the task. The data transmission rate in the channel. The workload of the task. Used to indicate the processing capacity of a node. Let be the time when the i-th task leaves. Let be the arrival time of the i-th task.

[0015] In an exemplary embodiment, the task scheduling and resource management module further includes a resource management unit, configured to: monitor the device data and task requirements of the key equipment; and, in the event of changes in the device data or task requirements, redetermine the deployment method of the edge computing nodes based on the changed device data or task requirements, wherein the deployment method includes: the number of nodes deployed and the location of nodes deployed; and redeploy the edge computing nodes based on the redetermined deployment method.

[0016] This application provides a method for deploying edge computing nodes in an industrial Internet of Things (IIoT) environment, comprising: real-time acquisition of device data of key devices in the terminal device, wherein the device data includes device status information and operating environment data; feature extraction of the device data to obtain feature data; determining the optimal deployment quantity and optimal deployment location of edge computing nodes based on the task requirements of the key devices and the feature data; and deploying edge computing nodes in the industrial Internet of Things environment based on the optimal deployment quantity and the optimal deployment location.

[0017] In one exemplary embodiment, real-time acquisition of device data of key devices in the terminal device includes: performing environmental monitoring on the industrial IoT environment through an environmental data acquisition unit to obtain the operating environment data, wherein the operating environment data includes at least one of the following: air quality data, meteorological parameter data; and acquiring the device status information of the key devices through the device data acquisition unit.

[0018] In one exemplary embodiment, feature extraction of the device data to obtain feature data includes: preprocessing the device data to obtain processed device data; performing calculations on the processed device data and extracting the feature data from the obtained calculation results.

[0019] In one exemplary embodiment, the method further includes: performing data analysis on historical device data stored in the edge computing node deployment system using data mining techniques, and establishing a fault prediction model based on the data analysis results; performing fault analysis on the processed device data using the fault prediction model to obtain fault analysis results.

[0020] In an exemplary embodiment, deploying edge computing nodes in the industrial Internet of Things environment according to the optimal deployment quantity and the optimal deployment location includes: deploying the optimal deployment quantity of edge computing nodes according to the optimal deployment location; and scheduling tasks among the optimal deployment quantity of edge computing nodes according to the task requirements and the node capabilities of the optimal deployment quantity of edge computing nodes.

[0021] In an exemplary embodiment, determining the optimal deployment quantity and optimal deployment location of edge computing nodes based on the task requirements of the key equipment and the feature data includes: initializing a sand cat population using a chaotic mapping method, wherein the sand cat population contains multiple sand cat individuals, each of which is used to indicate multiple edge computing nodes; calculating the fitness values ​​of the multiple sand cat individuals based on the task service latency of the edge computing nodes to obtain multiple first fitness values; updating the positions of the multiple sand cat individuals and recalculating the fitness values ​​of the multiple sand cat individuals based on the updated positions to obtain multiple second fitness values; determining the optimal sand cat based on the multiple first fitness values ​​and the multiple second fitness values; and, if a preset iteration condition is met, outputting the deployment quantity and deployment location corresponding to the optimal sand cat, determining the deployment quantity as the optimal deployment quantity, and determining the deployment location as the optimal deployment location, wherein the preset iteration condition includes at least one of the following: a maximum number of iterations, and a fitness threshold.

[0022] In an exemplary embodiment, after determining the optimal sand cat based on the plurality of first fitness values ​​and the plurality of second fitness values, the method further includes: if it is determined that the preset iteration condition is not met, determining a sensitivity value corresponding to the optimal sand cat; determining whether the sensitivity value is less than or equal to a preset threshold; if the sensitivity value is less than or equal to the preset threshold, determining that the sand cat population has entered the development phase, and updating the positions of the plurality of sand cat individuals using a Levy walking strategy; if the sensitivity value is greater than the preset threshold, determining that the sand cat population has entered the exploration phase, and updating the positions of the plurality of sand cat individuals using a spiral search strategy.

[0023] This application also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the edge computing node deployment method in any of the above-described industrial Internet of Things environments.

[0024] This application also provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the edge computing node deployment method in any of the above-described industrial Internet of Things environments.

[0025] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described industrial Internet of Things (IIoT) environment edge computing node deployment methods.

[0026] This application provides an edge computing node deployment system, comprising: a data acquisition module connected to a terminal device in an industrial IoT environment, used to collect real-time device data of key devices in the terminal device, wherein the device data includes device status information and operating environment data; a data processing module connected to the data acquisition module, used to extract features from the device data to obtain feature data; and a task scheduling and resource management module connected to the data processing module, used to determine the optimal deployment quantity and optimal deployment location of edge computing nodes based on the task requirements and feature data of the key devices, and then deploy edge computing nodes in the industrial IoT environment according to the optimal deployment quantity and optimal deployment location. By adopting the above scheme, the optimal deployment quantity and location of edge computing nodes are determined based on the device status and task requirements of key devices in the industrial IoT environment, achieving reasonable deployment of edge computing nodes, minimizing task service latency, and optimizing resource allocation, thereby improving the deployment efficiency and task processing performance of edge nodes in industrial settings. This solves the problems of difficult edge computing node deployment and task service latency caused by the large amount of data, limited communication bandwidth, and device mobility in the industrial IoT environment in related technologies. Attached Figure Description

[0027] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a hardware structure block diagram of an edge computing node deployment system in an industrial Internet of Things environment according to an embodiment of this application;

[0029] Figure 2 This is a structural block diagram of an edge computing node deployment system in an industrial Internet of Things environment according to an embodiment of this application;

[0030] Figure 3 This is a structural block diagram of an optional edge computing node deployment device according to an embodiment of this application;

[0031] Figure 4 This is a schematic diagram of an iterative calculation process for an optional optimal deployment method according to an embodiment of this application;

[0032] Figure 5 This is a flowchart of an edge computing node deployment method in an industrial Internet of Things environment according to an embodiment of this application. Detailed Implementation

[0033] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0034] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0035] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0036] The specific application environment architecture or specific hardware architecture on which the execution of the edge computing node deployment method in the industrial Internet of Things environment depends is described here.

[0037] The methods and embodiments provided in this application can be executed in an edge computing node deployment system or similar computing device in an industrial Internet of Things (IIoT) environment. Taking an edge computing node deployment system running in an IIoT environment as an example... Figure 1 This is a hardware structure block diagram of an edge computing node deployment system in an industrial Internet of Things environment according to an embodiment of this application. Figure 1 As shown, an edge computing node deployment system in an industrial IoT environment may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a central processing unit (CPU), microprocessor (MCU), or programmable logic device (FPGA), etc.) and a memory 104 for storing data are also shown. The edge computing node deployment system in the aforementioned industrial IoT environment may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1The structure shown is for illustrative purposes only and does not limit the structure of the edge computing node deployment system in the aforementioned industrial IoT environment. For example, the computer terminal may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0038] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the operating system startup method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, thus implementing the aforementioned method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0039] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider for an edge computing node deployment system in an Industrial Internet of Things (IIoT) environment. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module for wireless communication with the Internet.

[0040] This embodiment provides an edge computing node deployment system in an industrial Internet of Things (IoT) environment. Figure 2 This is a structural block diagram of an edge computing node deployment system in an industrial Internet of Things environment according to an embodiment of this application, such as... Figure 2 As shown, the system includes:

[0041] The data acquisition module 22 is connected to the terminal device in the industrial Internet of Things environment and is used to collect the device data of key devices in the terminal device in real time, wherein the device data includes device status information and operating environment data;

[0042] It should be noted that the aforementioned key equipment includes large key equipment located on industrial sites, such as loading equipment (loaders, etc.), transportation equipment (conveyor belts, etc.), sensors, robotic arms, cameras, etc.

[0043] Data processing module 24, connected to the data acquisition module, is used to extract features from the device data to obtain feature data;

[0044] The task scheduling and resource management module 26, connected to the data processing module, is used to determine the optimal number and optimal deployment location of edge computing nodes based on the task requirements of the key equipment and the feature data, and to deploy edge computing nodes in the industrial Internet of Things environment based on the optimal number and optimal deployment location.

[0045] The above solution provides an edge computing node deployment system, comprising: a data acquisition module connected to terminal devices in an industrial IoT environment, used to collect real-time device data of key devices in the terminal devices, including device status information and operating environment data; a data processing module connected to the data acquisition module, used to extract features from the device data to obtain feature data; and a task scheduling and resource management module connected to the data processing module, used to determine the optimal deployment quantity and optimal deployment location of edge computing nodes based on the task requirements and feature data of the key devices, and then deploy edge computing nodes in the industrial IoT environment according to the optimal deployment quantity and optimal deployment location. By adopting the above solution, the optimal deployment quantity and location of edge computing nodes are determined based on the device status and task requirements of key devices in the industrial IoT environment, achieving reasonable deployment of edge computing nodes, minimizing task service latency, and optimizing resource allocation, thereby improving the deployment efficiency and task processing performance of edge nodes in industrial settings. This solves the problems of difficult edge computing node deployment and task service latency caused by the large amount of data, limited communication bandwidth, and device mobility in the industrial IoT environment.

[0046] In an exemplary embodiment, the data acquisition module includes: an environmental data acquisition unit, used to perform environmental monitoring on the industrial IoT environment to obtain the operating environment data, wherein the operating environment data includes at least one of the following: air quality data, meteorological parameter data; and an equipment data acquisition unit, connected to the terminal device, used to collect at least the equipment status information of the key equipment.

[0047] The environmental data acquisition unit not only monitors key components in the air such as dust concentration, carbon dioxide, and methane, but also tracks meteorological changes such as ambient temperature, humidity, and precipitation, ensuring comprehensive operational safety and environmental monitoring. The equipment data acquisition unit captures the real-time status of critical equipment, covering details of vehicle operation such as speed and location, conveyor belt operating frequency, and core indicators of ventilation equipment such as fan speed, voltage, and current status, providing data support for accurate diagnosis and preventative maintenance.

[0048] The data acquisition module relies on advanced sensor and communication technologies to ensure the real-time performance and accuracy of the data. Sensors, as the front end of data acquisition, are keenly aware of subtle changes in the surrounding environment and equipment. Communication technology ensures unimpeded data transmission, whether wired or wireless, enabling massive amounts of data to be quickly delivered to the data processing module, laying a solid foundation for subsequent analysis and decision-making.

[0049] The extended functions of the data acquisition module also include comprehensive monitoring of equipment health status and precise understanding of resource status, as well as real-time perception of task requirements. This information collectively constitutes a complete picture of the industrial IoT environment, providing detailed input for subsequent data processing and task scheduling, thereby achieving efficient resource utilization and precise task execution. Through this module, every change in the industrial field can be captured in a timely manner.

[0050] In an optional embodiment, the data processing module includes: a data processing unit, configured to receive the device data sent by the data acquisition module, preprocess the device data to obtain processed device data; and a data calculation unit, connected to the data processing unit, configured to perform calculations on the processed device data and extract the feature data from the obtained calculation results.

[0051] The data processing unit in the data processing module receives and preprocesses the raw equipment data from the data acquisition module. Through data cleaning and format conversion, it produces structured and noise-reduced processed equipment data. Then, the data computing unit deeply mines the value of the processed equipment data and performs complex calculations, including but not limited to real-time data analysis, pattern recognition and fault prediction, to obtain feature data and provide decision-making basis for task scheduling and resource management.

[0052] During preprocessing, the data processing unit employs data science methods, such as standardization and normalization, to ensure data consistency and the effectiveness of analysis. Furthermore, it is responsible for data integration, fusing heterogeneous data from different sensors into a unified view, improving the overall quality and usability of the dataset. The data computation unit focuses on in-depth data mining, revealing the complex relationships and patterns hidden behind the data by executing algorithms and models. This encompasses not only basic data operations but also advanced data analysis techniques, such as machine learning, used to train models, predict equipment behavior, and even provide early fault warnings, significantly enhancing the system's intelligence and predictive capabilities.

[0053] This continuous data processing flow, from initial data organization to in-depth analysis, ensures the efficient use of data in the industrial IoT environment, laying a solid data foundation for optimizing industrial operations, improving equipment management efficiency, and realizing intelligent manufacturing.

[0054] Optionally, the data processing module further includes a data analysis unit connected to the data computing unit, used for: performing data analysis on historical device data stored in the edge computing node deployment system using data mining technology, and establishing a fault prediction model based on the data analysis results; performing fault analysis on the processed device data using the fault prediction model to obtain fault analysis results.

[0055] The data analysis unit employs data mining techniques to extract equipment operating modes, trends, and potential fault signals from the massive historical records stored in the edge computing node deployment system, thereby constructing a fault prediction model. This model can gain insight into the essence of processed equipment data, provide early warnings of potential equipment problems, and output fault analysis results, providing strong support for preventative maintenance and real-time decision-making in the industrial IoT environment.

[0056] Data analysis, in essence, is the sorting and interpretation of historical data. It goes beyond simple statistical calculations, delving into the intrinsic relationships between data and identifying subtle differences between normal operations and abnormal situations. Data mining techniques, such as cluster analysis, regression analysis, and neural networks, are flexibly applied to extract signals from noise, predict the future from the past, and ensure the accuracy and reliability of models.

[0057] It should be noted that the fault prediction model is an intelligent tool built based on data analysis results. It combines multiple factors such as equipment characteristics, operating environment, and workload. By learning from historical fault cases, it can predict potential fault risks hidden in processed equipment data, promptly notify the maintenance team to take intervention measures, avoid equipment downtime or accidents, and maintain production continuity and safety.

[0058] In summary, the data analysis unit plays a dual role in this embodiment: it is both a miner of historical data and a predictor of future failures. Its core value lies in using data mining technology to build a failure prediction model, realizing the leap from data to knowledge, and bringing forward-looking equipment health management capabilities to the Industrial Internet of Things.

[0059] Optionally, the task scheduling and resource management module includes: a node deployment unit, configured to deploy the optimal number of edge computing nodes according to the optimal deployment location based on the optimal deployment number and the optimal deployment location; and a task scheduling unit, connected to the node deployment unit, configured to perform task scheduling among the optimal number of edge computing nodes based on the task requirements and the node capabilities of the optimal number of edge computing nodes.

[0060] The node deployment unit precisely deploys edge computing nodes based on the calculated optimal number and location, ensuring that the distribution of computing resources meets both the hotspots of task requirements and overall global balance, laying the foundation for efficient task processing. The task scheduling unit flexibly schedules tasks to the optimally deployed edge computing node cluster, achieving a perfect match between tasks and resources. This process is not merely simple task assignment, but intelligent scheduling based on dynamic load balancing and priority considerations, ensuring that every task is processed promptly and effectively while maximizing the conservation of computing resources and improving the overall system response speed and task processing efficiency.

[0061] Edge computing nodes, located close to the data source in an industrial IoT environment, can respond to and process data generated by devices in real time, reducing the pressure on cloud servers and shortening task execution latency. The optimal deployment quantity and location are determined by comprehensively considering factors such as device layout, task requirements, network conditions, and edge node performance, using an improved sandcat swarm optimization algorithm. This ensures the rational allocation of edge resources and avoids resource waste and deployment blind spots.

[0062] Task scheduling not only considers the urgency and resource consumption of current tasks but also anticipates future task trends and resource requirements. By dynamically adjusting the task load of edge nodes, it avoids bottlenecks and overload, maintaining high availability and high performance of the system. The intelligent decision-making of the task scheduling unit relies on real-time data and historical analysis, enabling it to respond quickly to changes in system status, ensuring smooth task execution, and optimizing the resource utilization of edge computing nodes, thus safeguarding the efficient operation of the Industrial Internet of Things (IIoT).

[0063] Optionally, the node deployment unit is further configured to: initialize a sand cat population using a chaotic mapping method, wherein the sand cat population contains multiple sand cat individuals, each of which is used to indicate multiple edge computing nodes; calculate the fitness values ​​of the multiple sand cat individuals based on the task service latency of the edge computing nodes to obtain multiple first fitness values; update the positions of the multiple sand cat individuals and recalculate the fitness values ​​of the multiple sand cat individuals based on the updated positions to obtain multiple second fitness values; determine the optimal sand cat based on the multiple first fitness values ​​and the multiple second fitness values; and, if a preset iteration condition is met, output the deployment quantity and deployment position corresponding to the optimal sand cat, determining the deployment quantity as the optimal deployment quantity and the deployment position as the optimal deployment position, wherein the preset iteration condition includes at least one of the following: maximum number of iterations, fitness threshold.

[0064] The node deployment unit uses chaotic mapping techniques to generate a sand cat population, where each sand cat represents a deployment scheme for an edge computing node, and the population covers multiple potential node layout options. Next, the unit calculates a fitness value for each sand cat based on the quantitative metric of task service latency, evaluating the merits of each scheme. This series of fitness values ​​is considered the first round of evaluation.

[0065] Subsequently, the unit drives the dynamic migration of the sand cat population, simulating positional adjustments in natural evolution. The fitness of the updated individual sand cats is then quantified again to obtain a second round of evaluation values. By comparing the fitness values ​​from the two rounds, the unit identifies the best-performing sand cat, representing the optimal deployment strategy. At the evolutionary endpoint of reaching the maximum number of iterations or exceeding a preset fitness threshold, the optimal sand cat emerges, and its deployment quantity and location coordinates are locked as the optimal deployment quantity and optimal deployment location for edge computing nodes.

[0066] It should be noted that the chaotic mapping method is a mathematical tool that mimics chaotic phenomena in nature, used to generate sequences that appear random but actually follow certain patterns. In this application scenario, it provides a non-linear randomization method for setting the initial position of the sand cat population, ensuring the breadth and depth of the search and creating a good starting point for finding the optimal solution.

[0067] The construction of a sand cat population draws on the evolutionary strategy of biological groups. Each sand cat represents a possible solution, and the population as a whole gradually approaches the optimal solution through iterative evolution. The location update of an individual sand cat is actually a search for a better deployment plan in the search space, a process that simulates the principles of natural selection and survival of the fittest.

[0068] Task service latency refers to the time required from task creation to completion, encompassing the total time for task transmission, processing, and waiting. Reducing task service latency is crucial for improving real-time performance and response speed in industrial IoT environments, directly impacting overall system performance and user experience.

[0069] The iteration conditions are set to prevent the search process from getting stuck in an infinite loop. The maximum number of iterations limits the search period, while the fitness threshold sets a quality standard for the search. Once either condition is met, the search process terminates, the optimal sand cat is identified, and its deployment plan then becomes the blueprint guiding the actual deployment.

[0070] Optionally, the node deployment unit is further configured to: determine the sensitivity value corresponding to the optimal sand cat when it is determined that the preset iteration condition is not met; determine whether the sensitivity value is less than or equal to a preset threshold; if the sensitivity value is less than or equal to the preset threshold, determine that the sand cat population has entered the development stage and update the positions of the multiple sand cat individuals using a Levy walking strategy; if the sensitivity value is greater than the preset threshold, determine that the sand cat population has entered the exploration stage and update the positions of the multiple sand cat individuals using a spiral search strategy.

[0071] When a node deployment unit fails to meet the preset iteration conditions, it calculates the sensitivity value of the current optimal solution, i.e., the optimal sand cat, as an indicator to measure the stability of the solution and the optimization space. Subsequently, the unit determines whether the sensitivity value is less than or equal to a preset optimization threshold, using this as the basis for decision-making to guide the sand cat population into the next stage of optimization strategy.

[0072] When the sensitivity value meets the condition, that is, it is less than or equal to the preset threshold, the population enters the development stage and adopts the Levy walking strategy to adjust the position of individual sand cats. This strategy simulates the behavior pattern of animals searching for food in the environment. It has the characteristics of efficient exploration in known areas and helps to further refine the position adjustment when approaching the optimal solution, thereby improving the accuracy of the solution.

[0073] Conversely, when the sensitivity value exceeds a preset threshold, the population enters the exploration phase, activating a spiral search strategy to update the sand cat's position. The spiral search strategy, like expanding a search in an unknown domain, helps broaden the search scope in the early stages of the search or when the solution space is large, avoiding getting trapped in local optima and ensuring the comprehensiveness of the search and the diversity of solutions.

[0074] It should be noted that the sensitivity value is an indicator for evaluating the overall impact of small changes in the objective function on the solution. A low sensitivity value means that the solution is more tolerant of parameter changes and has the potential for further optimization; while a high sensitivity value suggests that the solution may be close to the optimum or has fallen into the trap of local optima.

[0075] The Levy roaming strategy, based on the Levy flight theory, is characterized by a combination of long-distance jumps and short-distance exploration. It can efficiently search near the known solution domain while maintaining the ability to explore more distant solution domains, making it suitable for fine-tuning the details of the solution in the later stages of optimization.

[0076] The spiral search strategy, inspired by the orderly exploration behavior of animals in complex environments, expands outward along a spiral path. This strategy helps to quickly cover a large area in the early stages of solution space exploration and discover potential better solutions. It is an effective means of optimizing the initial expansion of the search boundary.

[0077] When the iteration conditions are not met, the node deployment unit can flexibly adapt to different stages of the optimization process by evaluating sensitivity values ​​and dynamically switching different search strategies, and use the most suitable method to advance the search, ultimately producing an edge node deployment scheme that is both globally optimal and locally adaptive.

[0078] Optionally, the node deployment unit is further configured to: use a formula Calculate the task service latency T of the edge computing node max ,in, , For task transmission time, For task execution time, Let T be the task waiting time, T be the task set, and E be the edge computing node set.

[0079] Node deployment unit uses formula To quantify the maximum latency that edge computing nodes may encounter when processing various tasks, among which, , in the formula, It represents the transmission time required for task i to be transmitted to edge node j in the channel, and it is directly affected by communication bandwidth, task size, and network latency. This reveals the execution time of task i on edge node j, which is related to the node's processing power, task complexity, and algorithm efficiency; while The waiting time of task i before edge node j reflects the length of the task queue and the efficiency of the scheduling strategy; T is the set of tasks, and E is the set of edge computing nodes.

[0080] T max The computation is not only a consideration of a single task and node, but also a comprehensive examination of all possible task-node combinations to ensure that the system design can cope with the most demanding situations, guarantee smooth data processing in the Industrial Internet of Things, and improve the overall service quality and response speed.

[0081] It should be noted that task service latency, as a comprehensive indicator, encompasses the time consumption of three key stages: task transmission, execution, and waiting. It directly reflects the efficiency of edge computing node deployment and resource scheduling, and is crucial for evaluating and optimizing deployment schemes. Accurate calculation of T... max The node deployment unit can clearly perceive the system's extreme pressure points during task processing, providing a clear direction for optimizing the deployment plan and ensuring that the system can maintain a highly efficient and stable operating state even during peak task periods.

[0082] Optionally, the node deployment unit is further configured to: calculate using the following formulas respectively , and : , , ,in, This is used to indicate whether the i-th task in the task set T is executed on the j-th node in the edge computing node set E. For the input quantities of the task, The output of the task. The data transmission rate in the channel. The workload of the task. Used to indicate the processing capacity of a node. Let be the time when the i-th task leaves. Let be the arrival time of the i-th task.

[0083] In this embodiment, the node deployment unit uses a series of calculation formulas to subdivide and quantify the service latency of each task on each edge computing node, and capture the task transmission time, task execution time and task waiting time.

[0084] Specifically, the task transmission time is expressed by the formula calculate, As a switch for associating tasks with nodes, it determines whether task i is executed on node j. and These refer to the input and output data volumes of the task, respectively, intuitively reflecting the data burden of the task. (R) i This symbolizes the speed at which data travels through the channel, directly affecting transmission efficiency and latency.

[0085] Task execution time is expressed by formula The calculation shows the task load. This reflects the computational intensity of the task and the processing capacity of the nodes. This reflects the computing power of the edge computing nodes, and the relationship between the two determines the execution time of the task.

[0086] As for the task waiting time, it is determined by a formula. Calculations show that and The departure and arrival times of task i are marked, and the time difference between the two is the waiting time, which reveals the length of time the task waits in the queue for processing resources and reflects the efficiency of the task scheduling mechanism.

[0087] Through these precise calculations, the node deployment unit can gain a deep understanding of the behavior patterns of tasks in the edge computing environment, providing accurate data support for optimizing resource allocation and task scheduling, thereby reducing overall service latency and improving task processing efficiency and user satisfaction in industrial IoT scenarios.

[0088] In an optional embodiment, the task scheduling and resource management module further includes a resource management unit, configured to: monitor the device data and task requirements of the key equipment; and, in the event of changes in the device data or task requirements, redetermine the deployment method of the edge computing nodes based on the changed device data or task requirements, wherein the deployment method includes: the number of nodes deployed and the location of nodes deployed; and redeploy the edge computing nodes based on the redetermined deployment method.

[0089] The resource management unit monitors the dynamic data and task demand fluctuations of key equipment in the Industrial Internet of Things (IIoT). Upon detecting any changes in equipment data or task requirements, the unit responds immediately, re-planning the deployment strategy for edge computing nodes based on the updated information. This includes adjusting the number of nodes deployed and reselecting their locations. This dynamic adjustment mechanism ensures a close alignment between computing resources and real-time task demands, enabling the system to quickly adapt to environmental changes and maintain a high level of efficient and stable service.

[0090] It should be noted that equipment data for critical equipment, including but not limited to equipment operating status, health status, and resource utilization, serves as a window for resource management units to understand the health status and working efficiency of equipment in the industrial field, and is crucial for predicting potential failures and optimizing task allocation.

[0091] Task requirements refer to the characteristics and priorities of various tasks in the Industrial Internet of Things (IIoT) scenario. They include the task's computational requirements, data transmission volume, and time limits. By evaluating task requirements, the resource management unit can rationally allocate edge computing nodes to ensure the priority execution of important tasks while avoiding resource constraints and excessive consumption.

[0092] In an optional embodiment, this application provides a deployment device for edge computing nodes in an optional industrial Internet of Things (IIoT) scenario, the structural block diagram of which is shown below. Figure 3 As shown, it includes a data acquisition module, a data processing module, and a task scheduling and resource management module. The data acquisition module collects real-time health status data, operational status data, resource status data, and task data of key equipment; the data processing module analyzes and processes the collected raw data; and the task scheduling and resource management module enables rapid deployment of edge computing nodes, task allocation, and resource scheduling.

[0093] based on Figure 3 The application also provides an optional edge computing node deployment method, comprising the following steps: (The image shows an edge computing node deployment apparatus.)

[0094] 1. The data acquisition module collects equipment status information and environmental information of key equipment in real time through sensing devices, and transmits them to the data processing module through wired or wireless networks;

[0095] 2. The data processing module receives real-time information from the acquisition module and performs preliminary preprocessing and analysis;

[0096] 3. The task scheduling and resource management module uses the processed data, storage capacity, real-time requirements, and network bandwidth to determine the range of the number and location of nodes to be deployed.

[0097] 4. Minimize service latency as the solution objective for the deployment node; wherein, the task service latency is calculated as follows:

[0098] ;

[0099] ;

[0100] ;

[0101] ;

[0102] ;

[0103] in, This indicates whether task i is executed in edge node j. and Indicates the input and output quantities of the task. This indicates the data transmission rate in the channel. This indicates the workload of the task. This indicates the processing capacity of the node itself. Let be the time when the i-th task leaves. Let i be the arrival time of the i-th task. Indicates the task transmission time. Indicates the task execution time. Indicates the task waiting time. The service time for task i includes the transmission time from the terminal device to the edge node, the processing time of the task at the node, and the waiting time of the task. E represents the set of edge nodes, and T represents the set of tasks. This indicates the maximum task latency.

[0104] 5. Utilize the improved deployment device for iterative calculations to obtain the number and location of edge computing nodes, thereby optimizing resource allocation and task scheduling.

[0105] Specifically, the iterative calculation process is as follows: Figure 4 As shown, it includes the following steps:

[0106] Step 1: Determine the encoding method for the problem. Determine how to encode the edge node deployment problem in a form that the Sand Cat Swarm Optimization algorithm can handle. Encode the positions of the edge nodes as binary strings, where each gene represents the position of a node.

[0107] Step 2: Initialize the population. Initialize an initial population using the Logistic chaotic mapping method, where each individual represents one possible node deployment location.

[0108] Step 3: Calculate the fitness value. Calculate the fitness function value for each individual to assess its fitness level. The fitness function can be defined according to the specific problem's objectives and constraints; in this scenario, the task service delay formula described above is used as the fitness function.

[0109] Step 4: Update the optimal location. Based on the fitness function value, find the best sand cat (i.e., the optimal sand cat mentioned above).

[0110] Step 5: Iteration condition check. Determine if the maximum number of iterations or fitness (i.e., the preset iteration conditions mentioned above) are met. If the conditions are met, output the optimal solution; otherwise, proceed to Step 6 to continue iteration.

[0111] Step 6: Determine if the sensitivity value is less than 1 (equivalent to the preset threshold mentioned above). If it is less than 1, proceed to the development phase and use the Levy walking strategy to update the sand cat's position. Otherwise, proceed to the exploration phase and use the spiral search strategy to update the sand cat's position.

[0112] Step 7: Repeat steps 3 to 5 until the stopping condition is met.

[0113] Based on the individuals in the final population, select the individual with the best fitness as the optimal solution, which is the best deployment scheme for edge nodes.

[0114] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0115] Embodiments of this application also provide a method for deploying edge computing nodes in an industrial Internet of Things (IoT) environment. Figure 5 This is a flowchart of an edge computing node deployment method in an industrial Internet of Things environment according to an embodiment of this application, such as... Figure 5 As shown, the method includes the following steps:

[0116] Step S502: Collect device data of key devices in the terminal device in real time, wherein the device data includes device status information and operating environment data;

[0117] Step S504: Extract features from the device data to obtain feature data;

[0118] Step S506: Determine the optimal number and optimal deployment location of edge computing nodes based on the task requirements of the key equipment and the feature data, and deploy the edge computing nodes in the industrial IoT environment according to the optimal number and optimal deployment location.

[0119] The above scheme collects real-time equipment data from key devices in the terminal device, including equipment status information and operating environment data. Feature extraction is performed on the equipment data to obtain feature data. Based on the task requirements of the key devices and the feature data, the optimal deployment quantity and location of edge computing nodes are determined. Then, edge computing nodes are deployed in the industrial IoT environment according to this optimal deployment quantity and location. By adopting this scheme, the optimal deployment quantity and location of edge computing nodes are determined based on the equipment status and task requirements of key devices in the industrial IoT environment, achieving reasonable deployment of edge computing nodes, minimizing task service latency, and optimizing resource allocation. This improves the deployment efficiency and task processing performance of edge nodes in the industrial field. Thus, it solves the problems of difficult edge computing node deployment and task service latency caused by the large amount of data, limited communication bandwidth, and device mobility in the industrial IoT environment.

[0120] Optionally, real-time acquisition of equipment data from key devices in the terminal device includes: performing environmental monitoring on the industrial IoT environment through an environmental data acquisition unit to obtain the operating environment data, wherein the operating environment data includes at least one of the following: air quality data, meteorological parameter data; and acquiring the equipment status information of the key devices through the equipment data acquisition unit.

[0121] Optionally, feature extraction is performed on the device data to obtain feature data, including: preprocessing the device data to obtain processed device data; performing calculations on the processed device data, and extracting the feature data from the obtained calculation results.

[0122] Optionally, the method further includes: performing data analysis on historical device data stored in the edge computing node deployment system using data mining technology, and establishing a fault prediction model based on the data analysis results; performing fault analysis on the processed device data using the fault prediction model to obtain fault analysis results.

[0123] Optionally, deploying edge computing nodes in the industrial IoT environment according to the optimal deployment quantity and the optimal deployment location includes: deploying the optimal deployment quantity of edge computing nodes according to the optimal deployment location; and scheduling tasks among the optimal deployment quantity of edge computing nodes according to the task requirements and the node capabilities of the optimal deployment quantity of edge computing nodes.

[0124] Optionally, determining the optimal deployment quantity and optimal deployment location of edge computing nodes based on the task requirements of the key equipment and the feature data includes: initializing a sand cat population using a chaotic mapping method, wherein the sand cat population contains multiple sand cat individuals, each of which is used to indicate multiple edge computing nodes; calculating the fitness values ​​of the multiple sand cat individuals based on the task service latency of the edge computing nodes to obtain multiple first fitness values; updating the positions of the multiple sand cat individuals and recalculating the fitness values ​​of the multiple sand cat individuals based on the updated positions to obtain multiple second fitness values; determining the optimal sand cat based on the multiple first fitness values ​​and the multiple second fitness values; and, if a preset iteration condition is met, outputting the deployment quantity and deployment location corresponding to the optimal sand cat, determining the deployment quantity as the optimal deployment quantity, and determining the deployment location as the optimal deployment location, wherein the preset iteration condition includes at least one of the following: maximum number of iterations, fitness threshold.

[0125] Optionally, after determining the optimal sand cat based on the plurality of first fitness values ​​and the plurality of second fitness values, the method further includes: if it is determined that the preset iteration condition is not met, determining the sensitivity value corresponding to the optimal sand cat; determining whether the sensitivity value is less than or equal to a preset threshold; if the sensitivity value is less than or equal to the preset threshold, determining that the sand cat population has entered the development stage, and updating the positions of the plurality of sand cat individuals using a Levy walk strategy; if the sensitivity value is greater than the preset threshold, determining that the sand cat population has entered the exploration stage, and updating the positions of the plurality of sand cat individuals using a spiral search strategy.

[0126] Embodiments of this application also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any of the above embodiments of the firmware management method for a multi-board interconnect device.

[0127] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above embodiments of the firmware management method for multi-board interconnection devices at runtime.

[0128] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0129] The embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the firmware management method embodiments of the multi-board interconnection device described above.

[0130] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the firmware management method embodiments of the multi-board interconnect device described above.

[0131] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0132] The foregoing provides a detailed description of an edge computing node deployment system and method in an industrial Internet of Things (IoT) environment. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of these embodiments are only intended to aid in understanding the method and core ideas of this application. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. An edge computing node deployment system in an industrial Internet of Things (IoT) environment, characterized in that, include: The data acquisition module is connected to the terminal device in the industrial Internet of Things environment and is used to collect the device data of key devices in the terminal device in real time. The device data includes device status information and operating environment data. A data processing module, connected to the data acquisition module, is used to extract features from the device data to obtain feature data; The task scheduling and resource management module, connected to the data processing module, is used to determine the optimal number and optimal deployment location of edge computing nodes based on the task requirements of the key equipment and the feature data, and to deploy edge computing nodes in the industrial Internet of Things environment based on the optimal number and optimal deployment location.

2. The system according to claim 1, characterized in that, The data acquisition module includes: An environmental data acquisition unit is used to perform environmental monitoring on the industrial IoT environment and obtain the operating environment data, wherein the operating environment data includes at least one of the following: air quality data and meteorological parameter data; The equipment data acquisition unit is connected to the terminal device and is used at least to collect the equipment status information of the key equipment.

3. The system according to claim 1, characterized in that, The data processing module includes: A data processing unit is used to receive the device data sent by the data acquisition module, preprocess the device data, and obtain processed device data. A data calculation unit, connected to the data processing unit, is used to calculate the processed device data and extract the feature data from the obtained calculation results.

4. The system according to claim 3, characterized in that, The data processing module further includes a data analysis unit connected to the data calculation unit, used for: Data mining techniques are used to analyze historical device data stored in the edge computing node deployment system, and a fault prediction model is established based on the data analysis results. The fault prediction model is used to perform fault analysis on the processed equipment data to obtain fault analysis results.

5. The system according to claim 1, characterized in that, The task scheduling and resource management module includes: A node deployment unit is used to deploy the optimal number of edge computing nodes according to the optimal deployment location based on the optimal deployment number and the optimal deployment location; The task scheduling unit, connected to the node deployment unit, is used to schedule tasks among the optimal number of edge computing nodes according to the task requirements and the node capabilities of the optimal number of edge computing nodes.

6. The system according to claim 5, characterized in that, The node deployment unit is also used for: The sand cat population is initialized using a chaotic mapping method, wherein the sand cat population contains multiple sand cat individuals, and the multiple sand cat individuals are used to indicate multiple edge computing nodes respectively; The fitness values ​​of the multiple sand cat individuals are calculated based on the task service latency of the edge computing node to obtain multiple first fitness values; Update the positions of the multiple sand cat individuals, and recalculate the fitness values ​​of the multiple sand cat individuals based on the updated positions to obtain multiple second fitness values; The optimal sand cat is determined based on the plurality of first fitness values ​​and the plurality of second fitness values; If the preset iteration conditions are met, the number of deployments and the deployment location corresponding to the optimal sand cat are output. The number of deployments is determined as the optimal number of deployments, and the deployment location is determined as the optimal deployment location. The preset iteration conditions include at least one of the following: maximum number of iterations, fitness threshold.

7. The system according to claim 6, characterized in that, The node deployment unit is also used for: If the preset iteration conditions are not met, determine the sensitivity value corresponding to the optimal sand cat; Determine whether the sensitive value is less than or equal to a preset threshold; If the sensitivity value is less than or equal to the preset threshold, the sand cat population is determined to have entered the development stage, and the positions of the multiple sand cat individuals are updated using the Levy walking strategy. If the sensitivity value is greater than the preset threshold, the sand cat population is determined to enter the exploration phase, and the positions of the multiple sand cat individuals are updated through a spiral search strategy.

8. The system according to claim 6, characterized in that, The node deployment unit is also used for: Through formula Calculate the task service latency T of the edge computing node max ,in, , For task transmission time, For task execution time, Let T be the task waiting time, T be the task set, and E be the edge computing node set.

9. The system according to claim 8, characterized in that, The node deployment unit is also used for: Calculate using the following formulas respectively. , and : ， ， ,in, This is used to indicate whether the i-th task in the task set T is executed on the j-th node in the edge computing node set E. For the input quantities of the task, The output of the task. The data transmission rate in the channel. The workload of the task. Used to indicate the processing capacity of a node. Let be the time when the i-th task leaves. Let be the arrival time of the i-th task.

10. The system according to claim 5, characterized in that, The task scheduling and resource management module further includes a resource management unit, used for: Monitor the equipment data and task requirements of the key equipment; If the device data or the task requirements change, the deployment method of the edge computing nodes shall be re-determined based on the changed device data or task requirements, wherein the deployment method includes: the number of nodes deployed and the deployment location. The edge computing nodes will be redeployed according to the redefined deployment method.

11. A method for deploying edge computing nodes in an industrial Internet of Things (IoT) environment, characterized in that, include: Real-time acquisition of equipment data from key devices in the terminal device, wherein the equipment data includes equipment status information and operating environment data; Feature data is obtained by extracting features from the device data; The optimal number and location of edge computing nodes are determined based on the task requirements of the key equipment and the characteristic data, and the edge computing nodes are deployed in the industrial IoT environment according to the optimal number and location.

12. The method according to claim 11, characterized in that, Real-time acquisition of device data from key devices in the terminal device, including: The industrial IoT environment is monitored by an environmental data acquisition unit to obtain the operating environment data, wherein the operating environment data includes at least one of the following: air quality data and meteorological parameter data; The equipment status information of the key equipment is collected through the equipment data acquisition unit.

13. The method according to claim 11, characterized in that, Feature extraction is performed on the device data to obtain feature data, including: The device data is preprocessed to obtain processed device data; The processed device data is calculated, and the feature data is extracted from the calculation results.

14. The method according to claim 13, characterized in that, The method further includes: Data mining techniques are used to analyze historical device data stored in the edge computing node deployment system, and a fault prediction model is established based on the data analysis results. The fault prediction model is used to perform fault analysis on the processed equipment data to obtain fault analysis results.

15. The method according to claim 11, characterized in that, Deploying edge computing nodes in the industrial IoT environment according to the optimal deployment quantity and the optimal deployment location includes: The optimal number of edge computing nodes are deployed according to the optimal deployment location based on the optimal deployment number and the optimal deployment location; Task scheduling is performed on the optimal number of edge computing nodes based on the task requirements and the node capabilities of the optimal number of edge computing nodes.

16. The method according to claim 15, characterized in that, Determining the optimal deployment number and optimal deployment location of edge computing nodes based on the task requirements of the key equipment and the characteristic data includes: The sand cat population is initialized using a chaotic mapping method, wherein the sand cat population contains multiple sand cat individuals, and the multiple sand cat individuals are used to indicate multiple edge computing nodes respectively; The fitness values ​​of the multiple sand cat individuals are calculated based on the task service latency of the edge computing node to obtain multiple first fitness values; Update the positions of the multiple sand cat individuals, and recalculate the fitness values ​​of the multiple sand cat individuals based on the updated positions to obtain multiple second fitness values; The optimal sand cat is determined based on the plurality of first fitness values ​​and the plurality of second fitness values; If the preset iteration conditions are met, the number of deployments and the deployment location corresponding to the optimal sand cat are output. The number of deployments is determined as the optimal number of deployments, and the deployment location is determined as the optimal deployment location. The preset iteration conditions include at least one of the following: maximum number of iterations, fitness threshold.

17. The method according to claim 16, characterized in that, After determining the optimal sand based on the plurality of first fitness values ​​and the plurality of second fitness values, the method further includes: If the preset iteration conditions are not met, determine the sensitivity value corresponding to the optimal sand cat; Determine whether the sensitive value is less than or equal to a preset threshold; If the sensitivity value is less than or equal to the preset threshold, the sand cat population is determined to have entered the development stage, and the positions of the multiple sand cat individuals are updated using the Levy walking strategy. If the sensitivity value is greater than the preset threshold, the sand cat population is determined to enter the exploration phase, and the positions of the multiple sand cat individuals are updated through a spiral search strategy.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of claims 11 to 17.

19. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the method as claimed in any one of claims 11 to 17.

20. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 11 to 17.

Images