Internet of Things equipment resource management method and device, equipment and storage medium

Abstract

The invention discloses an Internet of Things equipment resource management method and device, equipment and a storage medium, and relates to the technical field of Internet of Things, and the method comprises the steps: collecting the characteristic data of each piece of Internet of Things equipment in a preset object model, the characteristic data comprising hardware description data, software function data, network state data, environment parameter data and real-time state data; grouping all Internet of Things devices in a preset object model based on a preset grouping index and the characteristic data to obtain at least one device group; inputting the characteristic data of each equipment group into a preset resource configuration optimization model to obtain an output resource allocation scheme of each equipment group; and performing resource management on the Internet of Things equipment in each equipment group according to the resource allocation scheme of each equipment group. According to the invention, efficient operation of the Internet of Things equipment in a complex environment can be ensured.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to a method, apparatus, device and storage medium for managing Internet of Things device resources. Background Art

[0002] With the rapid development of Internet of Things (IoT) technology, the types and number of IoT devices have increased dramatically. From smart bulbs and smart sockets in smart homes to sensors and controllers in the industrial Internet, and to various monitoring devices in smart cities, the application scope of IoT devices is becoming more and more extensive.

[0003] ‌Thing models are data models used in IoT platforms to describe product functions. They digitize entities in physical space and build data models in the cloud. Things models are widely used in various IoT devices, such as sensors, vehicle-mounted devices, buildings, and factories. By defining thing models, the functions and behaviors of these devices can be clearly described, and intelligent management and control of devices can be achieved. However, traditional thing models can usually only describe and manage a limited number of devices, and lack sufficient flexibility and scalability. When the number and types of devices increase, a single-level model is difficult to effectively manage the configuration of IoT device resources, resulting in system performance degradation, low resource utilization, and even problems such as device overload and system failure.

[0004] Therefore, how to improve the operating performance of IoT devices in complex environments has become an urgent problem to be solved.

[0005] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0006] The main purpose of this application is to provide an IoT device resource management method, apparatus, device and storage medium, aiming to solve the technical problem of how to improve the operating effect of IoT devices in complex environments.

[0007] To achieve the above purpose, the present application proposes an IoT device resource management method, which includes: Collect characteristic data of each IoT device in the preset object model, wherein the characteristic data includes hardware description data, software function data, network status data, environmental parameter data and real-time status data; Grouping all IoT devices in the preset object model based on a preset grouping index and the characteristic data to obtain at least one device group; Input the characteristic data of each equipment group into a preset resource configuration optimization model to obtain the output resource allocation plan for each equipment group; Resource management is performed on the IoT devices in each of the device groups according to the resource allocation scheme of each of the device groups.

[0008] In one embodiment, before the step of collecting characteristic data of each IoT device in the preset object model, the step includes: According to the functional characteristics of each IoT device in the preset object model, each IoT device is subjected to hierarchical processing, wherein the functional characteristics are the responsibilities or functions undertaken by each IoT device in the preset object model; Allocating sensor devices used for data collection in each of the IoT devices to a preset perception layer; Allocating edge computing node devices for performing data preprocessing and preliminary analysis in each of the IoT devices to a preset edge layer; Allocating devices for managing network communications between the devices in the IoT devices to a preset network layer; Allocating high-performance devices or cloud resource devices for advanced data processing and complex computing in each of the IoT devices to a preset core layer; The devices for providing user service interfaces in the Internet of Things devices are allocated to a preset application layer.

[0009] In one embodiment, the step of grouping all IoT devices in the preset object model based on the preset grouping index and the characteristic data to obtain at least one device group includes: Extracting first characteristic data corresponding to the preset grouping indicator from the characteristic data of each of the IoT devices according to the preset grouping indicator, wherein the preset grouping indicator includes at least one type of indicator among device performance, function type and working status; Performing clustering processing on the first characteristic data of all IoT devices belonging to the perception layer to obtain a perception layer clustering result, and grouping IoT devices with the same cluster label among all IoT devices belonging to the perception layer into a device group according to the perception layer clustering result; Clustering the first characteristic data of all IoT devices belonging to the edge layer to obtain an edge layer clustering result, and grouping IoT devices with the same cluster label among all IoT devices belonging to the edge layer into a device group according to the edge layer clustering result; Clustering the first characteristic data of all IoT devices belonging to the network layer to obtain a network layer clustering result, and grouping the IoT devices with the same cluster label among all IoT devices belonging to the network layer into a device group according to the network layer clustering result; Clustering the first characteristic data of all IoT devices belonging to the core layer to obtain a core layer clustering result, and grouping the IoT devices with the same cluster label among all IoT devices belonging to the core layer into a device group according to the core layer clustering result; Clustering is performed on the first characteristic data of all IoT devices belonging to the application layer to obtain an application layer clustering result, and based on the application layer clustering result, IoT devices with the same cluster label among all IoT devices belonging to the application layer are divided into a device group.

[0010] In one embodiment, the step of inputting the characteristic data of each device group into a preset resource configuration optimization model to obtain an output resource allocation plan for each device group includes: Obtaining a target resource function of a preset resource configuration optimization model, and determining constraints of the target resource function, wherein the target resource function is a function for calculating total resource consumption; Inputting the characteristic data of each of the equipment groups into the target resource function for optimization, and limiting the optimization result of the target resource function according to the constraint condition to determine the optimization result with the minimum total resource consumption; A resource allocation scheme for each IoT device in each device group is generated according to the optimization result with the minimum total resource consumption, wherein the resource allocation scheme includes a resource configuration scheme, a task allocation scheme and a load adjustment scheme for various resource types of the IoT devices.

[0011] In one embodiment, the constraints include: For each resource type, the total resource usage of all IoT devices for each resource type does not exceed the preset maximum available resource of the resource type; The device load of each of the IoT devices does not exceed the preset maximum allowable load of the IoT device; The task completion time of each of the IoT devices is before the preset deadline.

[0012] In one embodiment, the step of generating a resource allocation scheme for each IoT device in each device group according to the optimization result with the minimum total resource consumption includes: Analyze the optimization result with the minimum total resource consumption to obtain a target matrix, wherein the target matrix includes resource configuration, task allocation and load adjustment information of each IoT device; Extracting the resource allocation amount of each IoT device on each resource type from the target matrix; Extracting a task list and task priority assigned to each IoT device from the target matrix; extracting a load adjustment amount for each IoT device from the target matrix; A resource allocation scheme for each IoT device is generated according to the resource allocation amounts on each resource type, the task list and task priority, and the load adjustment amount.

[0013] In one embodiment, the IoT device resource management method further includes: Continuously monitor the real-time status data of IoT devices at all levels in the preset object model; storing the plurality of real-time status data as a status data sequence based on a time series; Inputting the state data sequence of each of the IoT devices into a preset prediction model for prediction to obtain future state data of each of the IoT devices; An abnormal device is determined according to the future state data, and a task list, a task priority, and a load adjustment amount of the abnormal device are adjusted according to the future state data.

[0014] In addition, to achieve the above purpose, the present application also proposes an IoT device resource management device, the IoT device resource management device comprising: A collection module, used to collect characteristic data of each IoT device in a preset object model, wherein the characteristic data of the IoT device in the preset object model includes hardware description data, software function data, network status data, environmental parameter data and real-time status data; A grouping module, configured to group all IoT devices in the preset object model based on a preset grouping index and the characteristic data to obtain at least one device group; An optimization module is used to input characteristic data of each equipment group into a preset resource configuration optimization model for each equipment group, and obtain an output resource allocation plan for each equipment group; The management module is used to manage the resources of the Internet of Things devices in each of the device groups according to the resource allocation plan of each of the device groups.

[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes an IoT device resource management device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the IoT device resource management method as described above.

[0016] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the IoT device resource management method as described above are implemented.

[0017] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the IoT device resource management method as described above are implemented.

[0018] This application collects characteristic data of each IoT device in a preset object model, wherein the characteristic data includes hardware description data, software function data, network status data, environmental parameter data and real-time status data; groups all IoT devices in the preset object model based on preset grouping indicators and characteristic data to obtain at least one device group; inputs the characteristic data of each device group into a preset resource configuration optimization model to obtain an output resource allocation plan for each device group; and manages resources for IoT devices in each device group according to the resource allocation plan for each device group. This application performs comprehensive data collection, reasonable device grouping, optimized resource allocation and effective resource management based on the object model, thereby realizing efficient, adaptive and stable resource management of IoT devices in complex environments, which not only improves resource utilization, reduces energy consumption and operating costs, but also enhances the reliability and flexibility of the IoT system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0020] 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 or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A flowchart of the first embodiment of the method for managing IoT device resources provided in this application; Figure 2 This is a schematic diagram of the hierarchical structure of the preset object model in the first embodiment of the present application; Figure 3 A flowchart of the second embodiment of the method for managing IoT device resources provided in this application; Figure 4 This is a schematic diagram of the module structure of the IoT device resource management device according to an embodiment of the present application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the IoT device resource management method in the embodiment of the present application.

[0022] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0023] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0024] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0025] Based on this, the present application embodiment provides a method for managing IoT device resources, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the IoT device resource management method of the present application.

[0026] In this embodiment, the IoT device resource management method includes steps S10 to S40: Step S10, collecting characteristic data of each IoT device in the preset object model, wherein the characteristic data includes hardware description data, software function data, network status data, environmental parameter data and real-time status data.

[0027] It should be noted that the preset thing model is the super thing model used in this embodiment. The thing model is an abstract representation of an IoT device, which is used to describe the properties, functions and services of the device. The thing model provides a standardized way to manage and control devices, making the interaction between different devices easier and more consistent. The present application provides an enhanced thing model, namely the super thing model, which is used to describe and manage large-scale, heterogeneous IoT devices. The super thing model generally includes the following key components: Hardware description: covers the computing resources of the device (such as CPU, memory, storage) and their utilization.

[0028] Software capabilities: Describes the operating system the device runs, and the protocols and applications it supports.

[0029] Network status: Contains information such as the device's network connection status, bandwidth utilization, and communication delay.

[0030] Environmental parameters: reflect the physical characteristics of the environment where the device is located, such as temperature, humidity, and location.

[0031] Real-time status: Track the current operating status of the equipment, including load conditions, health status, and fault records.

[0032] Each IoT device has characteristic data, which corresponds to the data in the above key components. Generally, only the network delay of the device in the network status data, the CPU usage, memory usage, storage usage, task status, current energy consumption of the device and the current load of the device in the real-time status data are applied in subsequent steps.

[0033] In a feasible implementation manner, before step S10, steps S01 to S06 are also included: Step S01, hierarchical processing is performed on each IoT device according to the functional characteristics of each IoT device in the preset object model, wherein the functional characteristics are the responsibilities or functions undertaken by each IoT device in the preset object model.

[0034] Step S02: Allocate sensor devices used for data collection in each IoT device to a preset perception layer.

[0035] Step S03, allocating the edge computing node devices in each IoT device for performing data preprocessing and preliminary analysis to a preset edge layer.

[0036] Step S04, allocating the devices in each IoT device for managing network communications between the devices to a preset network layer.

[0037] Step S05, allocating high-performance devices or cloud resource devices in each IoT device for advanced data processing and complex computing to a preset core layer.

[0038] Step S06: Allocate the devices for providing user service interfaces in each IoT device to a preset application layer.

[0039] It should be noted that, in this embodiment, the preset object model divides each IoT device into five levels according to the functions and characteristics of the IoT devices, see Figure 2 ,include: Perception layer 1, including sensor devices for data collection; Edge layer 2, which includes edge computing node devices that perform data preprocessing and preliminary analysis; Network layer 3, which includes devices that manage network communications between devices; Core layer 4, including high-performance devices or cloud resource devices for advanced data processing and complex computing; Application layer 5, contains devices that provide user service interfaces.

[0040] The preset object model provided in this application is a super object model, which simplifies the management complexity by dividing the equipment into multiple levels according to functions and characteristics. Among them, the main function of the perception layer is to collect various data in the environment, such as temperature, humidity, light, sound, etc., such as temperature and humidity sensors, light sensors, sound sensors, acceleration sensors, etc. The functions of the edge layer include temperature and humidity sensors, light sensors, sound sensors, acceleration sensors, etc., to perform simple data analysis, such as threshold judgment, anomaly detection, and make local decisions based on preprocessing and analysis results, such as triggering alarms and controlling equipment. The devices in the edge layer are such as edge gateways, edge servers, and embedded computing devices. The functions of the network layer include managing network communications between devices, routing and forwarding data packets according to the network topology, and ensuring the security of network communications to prevent data leakage and attacks. The types of equipment include routers, switches, and gateways. The functions of the core layer include complex data processing and analysis, such as big data analysis, machine learning, performing high-performance computing tasks, such as image processing, video analysis, and providing large-scale data storage and management. The types of equipment may include high-performance equipment, such as high-performance servers, supercomputers, and cloud resource equipment, such as cloud computing platforms and big data platforms. The functions of the application layer include providing an interactive interface between users and the IoT system, such as Web interfaces and mobile applications, processing business logic, such as order management and user management, and presenting processed data to users in the form of charts and reports. Device types include front-end devices, such as Web servers and mobile application servers, and user terminals: such as smartphones, tablets, and PCs.

[0041] The hierarchical structure provides a logical organization for the hyper-object model, and each key component (hardware description, software function, etc.) is concretized in different layers. For example, the perception layer emphasizes the sensor hardware description, while the edge layer and core layer may involve more software functions and real-time status.

[0042] It is understandable that the Super IoT Model divides IoT devices into the perception layer, edge layer, network layer, core layer and application layer. Each layer of devices assumes specific responsibilities and together builds an efficient and reliable IoT system. This hierarchical division not only helps to clarify the functions and characteristics of each device, but also facilitates system management and optimization, improving the overall performance of the system and user experience.

[0043] Step S20: grouping all IoT devices in the preset object model based on preset grouping indicators and characteristic data to obtain at least one device group.

[0044] It should be noted that preliminary data analysis and clustering are required before optimization. Clustering algorithms such as K-means or DBSCAN can be used to group devices at each layer according to their characteristics and performance indicators. The clustering results can help identify performance bottlenecks and overloaded devices, providing a basis for the optimization process.

[0045] The preset grouping indicators are the standards and basis for grouping devices. These indicators can be selected and adjusted according to actual needs, and can include device performance (CPU, memory, network capabilities), function type (sensor, edge computing node, core server) and working status (load, health status). Since there is a corresponding relationship between the preset grouping indicators and the characteristic data collected in S10, the characteristic data can be used as the basis for evaluating the preset grouping indicators. The grouping method can adopt a variety of technologies and algorithms to ensure the rationality and effectiveness of the grouping.

[0046] Common grouping methods include: rule-based grouping: grouping according to preset rules and conditions; clustering algorithm: grouping using clustering algorithms in machine learning (such as K-means, DBSCAN); graph theory method: grouping using graph theory methods (such as community detection algorithm).

[0047] In a feasible implementation, step S20 may include steps S21 to S26: Step S21, extracting first characteristic data corresponding to the preset grouping index from the characteristic data of each IoT device according to the preset grouping index, wherein the preset grouping index includes at least one type of index among device performance, function type and working status.

[0048] It should be noted that appropriate grouping indicators are selected according to actual needs, and at least one type of indicator is selected from device performance, function type and working status. Among them, device performance includes CPU utilization, memory utilization, network bandwidth usage, function type includes sensor, edge computing node, core server, and working status includes load.

[0049] Data of a type related to the preset grouping index is extracted from the characteristic data as first characteristic data, and the first characteristic data is used for subsequent grouping. The first characteristic data corresponding to each level of the IoT device in the preset object model can be input into a preset clustering algorithm to obtain a clustering result of each level of the IoT device, and the IoT devices at each level are divided into at least one device group according to the clustering result.

[0050] It should be noted that clustering algorithm is the process of dividing a group of objects into multiple clusters, so that the similarity of objects in the same cluster is high, while the similarity of objects in different clusters is low. Common clustering algorithms include: K-means, which is suitable for large-scale data sets and can converge quickly; DBSCAN, which is suitable for data sets with uneven density distribution and can find clusters of any shape; hierarchical clustering, which is suitable for smaller data sets and can generate tree-structured clustering results; spectral clustering, which is suitable for nonlinear data and can find complex clustering structures.

[0051] Taking the K-means algorithm as an example, the standardized CPU utilization, memory usage, network bandwidth usage, function type and working status data of each layer are input into the K-means algorithm to obtain the clustering results of each layer of equipment. The output of the clustering algorithm is usually the cluster label to which each device belongs. Through these labels, devices can be grouped.

[0052] Step S22, clustering the first characteristic data of all IoT devices belonging to the perception layer to obtain a perception layer clustering result, and dividing all IoT devices belonging to the perception layer with the same cluster label into a device group according to the perception layer clustering result.

[0053] Step S23, clustering the first characteristic data of all IoT devices belonging to the edge layer to obtain edge layer clustering results, and grouping IoT devices with the same cluster label among all IoT devices belonging to the edge layer into a device group according to the edge layer clustering results.

[0054] Step S24, clustering the first characteristic data of all IoT devices belonging to the network layer to obtain a network layer clustering result, and dividing all IoT devices belonging to the network layer with the same cluster label into a device group according to the network layer clustering result.

[0055] Step S25, clustering the first characteristic data of all IoT devices belonging to the core layer to obtain a core layer clustering result, and according to the core layer clustering result, grouping all IoT devices belonging to the core layer with the same cluster label into a device group.

[0056] Step S26, clustering the first characteristic data of all IoT devices belonging to the application layer to obtain an application layer clustering result, and grouping all IoT devices belonging to the application layer with the same cluster label into a device group according to the application layer clustering result.

[0057] It should be noted that the clustering result is usually a label list, each label represents the cluster (i.e., device group) to which the device belongs. Get the cluster label of each device from the label list output by the clustering algorithm, create an empty device group for each cluster, and assign the device to the corresponding device group based on the mapping relationship between the device ID and the cluster label.

[0058] For example, suppose we choose K-means algorithm for clustering and divide the devices of perception layer into 3 groups. First, we need to obtain the first characteristic data of each device of perception layer, including CPU utilization, memory utilization, network bandwidth usage, function type, and working status. Input the standardized CPU utilization, memory utilization, network bandwidth usage, function type, and working status data into K-means algorithm, and set the number of clusters to 3. The clustering results can be: Group 1: contains devices with low CPU utilization, moderate memory utilization, low network bandwidth usage, function type of data acquisition, and working status of online; Group 2: contains devices with high CPU utilization, high memory utilization, high network bandwidth usage, function type of data processing, and working status of online; Group 3: contains devices with moderate CPU utilization, low memory utilization, moderate network bandwidth usage, function type of network management, and working status of offline.

[0059] This implementation method groups all IoT devices in a preset object model based on preset grouping indicators and characteristic data to obtain device groups at each level, which can subdivide each device and improve the efficiency of resource management.

[0060] Step S30, inputting the characteristic data of each device group into a preset resource configuration optimization model to obtain an output resource allocation plan for each device group.

[0061] It should be noted that the resource allocation optimization model is a mathematical model or algorithm used to optimize resource allocation, which aims to generate the optimal resource allocation plan based on the characteristic data of the device and the requirements of the system. Common resource allocation optimization models include linear programming, which is applicable to resource allocation problems, and the objective function and constraints are linear. The output of the optimization model is usually a resource allocation plan for each device group, including the resource allocation amount and allocation strategy for each device, where the resource allocation amount includes the amount of resources allocated to each device, such as CPU usage, memory usage, network bandwidth, etc., and the allocation strategy includes specific strategies for resource allocation, such as load balancing, priority allocation, etc.

[0062] It is understandable that after the devices are grouped according to their characteristics, the optimization model does not need to deal with the individual optimization problems of all devices. Each group can be included in the optimization calculation as a whole, thereby reducing the scale of the original problem from the device level to the group level. For example, the original problem requires the optimization of 1,000 devices, but after grouping, only 10 device groups need to be optimized, significantly reducing the computational complexity. By optimizing resource allocation, resource utilization can be improved, and load optimization can achieve load balancing and avoid overloading of certain devices. At the same time, certain performance can be improved to improve the overall system performance and reduce response time.

[0063] In a feasible implementation, step S30 may include steps S31 to S33: Step S31, obtaining a target resource function of a preset resource configuration optimization model, and determining constraints of the target resource function, wherein the target resource function is a function for calculating total resource consumption.

[0064] It should be noted that the objective resource function is a mathematical expression used to calculate the total resource consumption. Its purpose is to minimize the resource consumption in the entire system, thereby improving resource utilization efficiency and system performance. Common objective resource function forms include linear objective functions and nonlinear objective functions. The linear objective function is the most commonly used form and is suitable for situations where the resource consumption and resource allocation are linearly related. Constraints are conditions that ensure that the optimization results are feasible. Common constraints include resource upper limits, resource lower limits, load balancing, task dependencies, etc.

[0065] In a feasible implementation, the target resource function of the preset resource configuration optimization model is: , Among them, C is the total resource consumption, Minimize means to minimize the total resource consumption, is the energy consumption of all resource types of IoT devices at layer i, is the data transmission delay of the IoT device at layer i, is the device load of the IoT device at layer i, , and is the weight coefficient.

[0066] It should be noted that the goal of the optimization function is to minimize the total resource consumption C, which is composed of three main factors: energy consumption , Data transmission delay and equipment load Each factor has a corresponding weight coefficient , and ,These weight coefficients reflect the relative importance of different factors in the total resource consumption.

[0067] Among them, IoT devices have various types of resources, such as network bandwidth, computing resources (CPU, memory), storage resources, etc. These resources will directly affect the energy consumption of IoT devices, so energy consumption is the sum of the energy consumption of the required resource types.

[0068] The constraints include: For each resource type, the total resource usage of all IoT devices for each resource type shall not exceed the preset maximum available resource amount of the resource type; The device load of each IoT device does not exceed the preset maximum permissible load of the IoT device; The task completion time of each IoT device is before the preset deadline.

[0069] It should be noted that in this embodiment, there are three constraints: resource limitation, load limitation, and task completion time limitation. The resource limitation can be expressed in the form of a formula as follows: , The meaning of this constraint is that for each resource type , the total resource usage of all devices i on this resource The maximum available resource must not exceed the preset resource limit. For example, if a resource is network bandwidth, the total resource usage of all devices on the network bandwidth cannot exceed the maximum bandwidth capacity of the network.

[0070] The load limit can be expressed in the form of a formula: , The meaning of this constraint is that the load of each device i Do not exceed the maximum permissible load For example, if the maximum permissible load of a device is 80%, then its actual load cannot exceed 80%. The task completion time limit can be expressed in the form of a formula: , The meaning of this constraint is that the completion time of each task k Must be within its deadline Before, for example, if a task had a deadline of 10 minutes, then the task had to be completed within 10 minutes.

[0071] Step S32, inputting the characteristic data of each device group into the target resource function for optimization, and restricting the optimization result of the target resource function according to the constraint conditions to determine the optimization result with the minimum total resource consumption.

[0072] It should be noted that the present application uses a linear programming model to optimize resource allocation. Specifically, according to the target resource function defined in step S31, the characteristic data is input into the target resource function for optimization, and the optimization calculation can be performed according to a linear programming solver (such as Python's scipy.optimize.linprog). According to the result of the optimization calculation, the resource allocation amount of each device is determined. At the same time, it is necessary to check whether the optimization result meets all the constraints to ensure the feasibility of the result.

[0073] Specifically, genetic algorithms (GA) or particle swarm optimization algorithms (PSO) can be used to search for the optimal solution for resource allocation in high-dimensional space. GA generates new resource allocation solutions through operations such as selection, crossover, and mutation, while PSO optimizes resource allocation by simulating the movement trajectory of a particle swarm.

[0074] Step S33, generating a resource allocation plan for each IoT device in each device group according to the optimization result with the minimum total resource consumption, wherein the resource allocation plan includes resource configuration plans, task allocation plans and load adjustment plans for various resource types of IoT devices.

[0075] It should be noted that, according to the optimization result of the minimum total resource consumption obtained in step S32, a resource allocation plan for each IoT device in each device group is generated. This plan should include the following three aspects: resource allocation plan, including the resource allocation amount of each device, such as CPU usage, memory usage, network bandwidth usage, etc.; task allocation plan, including which device each task is executed on; load adjustment plan, including how to adjust the load of the device to ensure load balancing.

[0076] This implementation method can dynamically adjust the resource allocation plan according to the real-time device status and system requirements through the optimization model, improve the flexibility and scalability of the system, and achieve optimal resource configuration for IoT devices.

[0077] In a feasible implementation, step S33 may include steps S331 to S335: Step S331, analyzing the optimization result with the minimum total resource consumption to obtain a target matrix, wherein the target matrix includes resource configuration, task allocation and load adjustment information of each IoT device.

[0078] It should be noted that the optimization result is usually a vector or matrix containing the resource allocation, task allocation, and load adjustment information for each device. The target matrix should contain the resource configuration, task allocation, and load adjustment information for each IoT device. The resource configuration, task allocation, and load adjustment information for each device are extracted from the optimization results and filled into the target matrix. The target matrix can be defined by creating a two-dimensional array or table, where each row represents a device and each column represents an attribute (such as CPU usage, memory usage, network bandwidth usage, task list, task priority, and load adjustment).

[0079] Step S332: extract the resource allocation amount of each IoT device on each resource type from the target matrix.

[0080] Step S333: extracting the task list and task priority assigned to each IoT device from the target matrix.

[0081] Step S334: extract the load adjustment amount of each IoT device from the target matrix.

[0082] Exemplarily, the target matrix is ​​shown in Table 1 below: Table 1

[0083] In the above Table 1, the three columns of CPU usage, memory usage, and network bandwidth usage represent resource allocation on the three resource types, the two columns of task list and task priority represent the task list and task priority, and the column of load adjustment represents the load adjustment.

[0084] Step S335: Generate a resource allocation plan for each IoT device based on the resource allocation amount, task list, task priority, and load adjustment amount on each resource type.

[0085] It should be noted that various data have been read in the previous steps, and the resource allocation, task list, task priority and load adjustment of the same device ID are integrated together to form a resource allocation plan for each device. For example, D: CPU usage: 10, memory usage: 20, network bandwidth usage: 50, task list: [T1], task priority: [1], load adjustment: 0.

[0086] In the actual adjustment process, if the energy consumption of a certain layer is too high, its task allocation can be reduced or low-energy consumption equipment can be added; if the delay is too high, faster network paths or adjacent nodes can be given priority; if the load is too high, some tasks can be dynamically migrated to other layers.

[0087] This implementation can generate a resource allocation plan for each IoT device, thereby achieving optimal resource allocation, improving resource utilization efficiency, and ensuring efficient operation and optimized management of the system.

[0088] Step S40: performing resource management on the IoT devices in each device group according to the resource allocation plan of each device group.

[0089] It should be noted that in step S335, a resource allocation plan for each IoT device has been generated. First, according to the resource allocation plan, the CPU usage, memory usage, and network bandwidth usage of each device are set, and the configuration is applied to the corresponding device to ensure that the device runs according to the specified resource usage. According to the task list, tasks are assigned to the corresponding devices, and according to the task priority, high-priority tasks are executed first. According to the load adjustment amount, the load of the device is dynamically adjusted to ensure load balancing, and the load of the device is monitored in real time to ensure that the adjusted load meets expectations.

[0090] It can be understood that the resource usage of each device is in line with the optimization results, which can reduce resource waste and improve resource utilization efficiency. At the same time, by dynamically adjusting the load, it can ensure load balancing of each device, avoid overloading of certain devices, improve the response speed and stability of the system, and adapt to changing system requirements.

[0091] In addition, in actual operation, the system needs to continuously monitor the optimization effect and adjust the optimization model parameters in real time through the feedback mechanism, including the three weights, to ensure that resource allocation is always in the optimal state in a dynamic environment.

[0092] This embodiment collects characteristic data of each IoT device in a preset object model, wherein the characteristic data includes hardware description data, software function data, network status data, environmental parameter data, and real-time status data; groups all IoT devices in the preset object model based on preset grouping indicators and characteristic data to obtain at least one device group; inputs the characteristic data of each device group into a preset resource configuration optimization model to obtain an output resource allocation plan for each device group; and manages resources for the IoT devices in each device group according to the resource allocation plan for each device group. This embodiment performs comprehensive data collection, reasonable device grouping, optimized resource allocation, and effective resource management based on the object model, thereby achieving efficient, adaptive, and stable resource management of IoT devices, which not only improves resource utilization, reduces energy consumption and operating costs, but also enhances the reliability and flexibility of the IoT system.

[0093] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3, the IoT device resource management method further includes steps A10 to A40: Step A10, continuously monitor the real-time status data of IoT devices at all levels in the preset object model.

[0094] It should be noted that the real-time status data may include resource usage, such as CPU usage, memory usage, network bandwidth usage, etc., environmental parameters, such as temperature, humidity, etc., and other parameters, such as battery power, signal strength, etc.

[0095] Step A20: storing a plurality of real-time status data as a status data sequence based on a time series.

[0096] It should be noted that each state data point contains various attribute values ​​of the device, such as CPU usage, memory usage, network bandwidth usage, temperature, humidity, etc. Each state data point should be accompanied by a timestamp, indicating the collection time of the data point. An empty state data sequence can be created for each device, and each collected data point can be added to the state data sequence of the corresponding device in chronological order, maintaining the continuity of the data and facilitating subsequent trend analysis and anomaly detection.

[0097] Step A30, inputting the state data sequence of each IoT device into a preset prediction model for prediction to obtain the future state data of each IoT device.

[0098] It should be noted that the preset forecasting model can be ARIMA or LSTM. ARIMA (Autoregressive Integrated Moving Average Model) is suitable for linear time series data and can capture the trend and seasonality of the time series, while LSTM (Long Short-Term Memory Network) is suitable for nonlinear time series data and can capture long-term dependencies.

[0099] In the training of the preset prediction model, you first need to select a suitable prediction model based on the data characteristics and use historical data to train the prediction model.

[0100] The latest state data is used as input into the trained model, and the model can directly output the predicted future state data.

[0101] Step A40, determining abnormal equipment according to the future state data, and adjusting the task list, task priority and load adjustment amount of the abnormal equipment according to the future state data.

[0102] It should be noted that the determination of abnormal devices requires the setting of abnormal detection rules, such as defining thresholds and setting normal ranges for various status data, such as CPU usage, memory usage, network bandwidth usage, etc., and then judging whether the device exceeds the normal range based on future status data. If so, it is marked as an abnormal device.

[0103] There are many ways to adjust abnormal devices, such as removing some low-priority tasks to reduce the burden on abnormal devices; migrating some tasks to other normal devices to disperse the load; lowering the priority of high-priority tasks on abnormal devices to ensure that other devices can handle these tasks first; or reallocating the priority of tasks based on the new task list; reducing the load of abnormal devices based on future status data to ensure that they are not overloaded; and dynamically adjusting the load based on real-time data to ensure load balancing.

[0104] This embodiment automatically adjusts the configuration and resource allocation of each layer of equipment according to real-time monitoring data, ensures the best performance of the system under various conditions, and realizes intelligent management and optimization of IoT devices.

[0105] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the IoT device resource management method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0106] This application also provides an IoT device resource management device, please refer to Figure 4 , the Internet of Things device resource management device includes: The acquisition module 10 is used to collect characteristic data of each IoT device in the preset object model, wherein the characteristic data includes hardware description data, software function data, network status data, environmental parameter data and real-time status data; A grouping module 20, configured to group all IoT devices in the preset object model based on a preset grouping index and the characteristic data to obtain at least one device group; The optimization module 30 is used to input the characteristic data of each device group into a preset resource configuration optimization model to obtain the output resource allocation plan of each device group; The management module 40 is used to manage the resources of the IoT devices in each of the device groups according to the resource allocation scheme of each of the device groups.

[0107] The IoT device resource management device provided by the present application adopts the IoT device resource management method in the above embodiment, which can solve the technical problem of how to improve the operation effect of IoT devices in complex environments. Compared with the prior art, the beneficial effects of the IoT device resource management device provided by the present application are the same as the beneficial effects of the IoT device resource management method provided by the above embodiment, and the other technical features in the IoT device resource management device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0108] The present application provides an Internet of Things device resource management device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the Internet of Things device resource management method in the above-mentioned embodiment one.

[0109] Reference below Figure 5 , which shows a schematic diagram of the structure of an IoT device resource management device suitable for implementing the embodiment of the present application. The IoT device resource management device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The IoT device resource management device shown is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present application.

[0110] like Figure 5As shown, the IoT device resource management device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the IoT device resource management device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the IoT device resource management device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an IoT device resource management device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0111] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0112] The IoT device resource management device provided by this application adopts the IoT device resource management method in the above embodiment, which can solve the technical problem of how to improve the operation effect of IoT devices in complex environments. Compared with the prior art, the beneficial effects of the IoT device resource management device provided by this application are the same as the beneficial effects of the IoT device resource management method provided by the above embodiment, and the other technical features in the IoT device resource management device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0113] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0114] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0115] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the IoT device resource management method in the above-mentioned embodiment.

[0116] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0117] The above-mentioned computer-readable storage medium may be included in the IoT device resource management device; or it may exist independently without being assembled into the IoT device resource management device.

[0118] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the IoT device resource management device, the IoT device resource management device: collects characteristic data of each IoT device in the preset object model, wherein the characteristic data includes hardware description data, software function data, network status data, environmental parameter data and real-time status data; groups all IoT devices in the preset object model based on preset grouping indicators and characteristic data to obtain at least one device group; inputs the characteristic data of each device group into a preset resource configuration optimization model to obtain a resource allocation plan for each device group as output; and performs resource management on the IoT devices in each device group according to the resource allocation plan of each device group.

[0119] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0120] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0121] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0122] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned IoT device resource management method, and can solve the technical problem of how to improve the operating effect of IoT devices in complex environments. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the IoT device resource management method provided by the above-mentioned embodiment, and will not be elaborated here.

[0123] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned IoT device resource management method when executed by a processor.

[0124] The computer program product provided by this application can solve the technical problem of how to improve the operation effect of IoT devices in complex environments. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the IoT device resource management method provided by the above embodiment, which will not be repeated here.

[0125] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for managing IoT device resources, characterized in that: The IoT device resource management method comprises: Collect characteristic data of each IoT device in the preset object model, wherein the characteristic data includes hardware description data, software function data, network status data, environmental parameter data and real-time status data; Grouping all IoT devices in the preset object model based on a preset grouping index and the characteristic data to obtain at least one device group; Input the characteristic data of each equipment group into a preset resource configuration optimization model to obtain the output resource allocation plan for each equipment group; Resource management is performed on the IoT devices in each of the device groups according to the resource allocation scheme of each of the device groups.

2. The method for managing IoT device resources according to claim 1, wherein: Before the step of collecting characteristic data of each IoT device in the preset object model, the method includes: According to the functional characteristics of each IoT device in the preset object model, each IoT device is subjected to layered processing, wherein the functional characteristics are the responsibilities or functions undertaken by each IoT device in the preset object model; Allocating sensor devices used for data collection in each of the IoT devices to a preset perception layer; Allocating edge computing node devices for performing data preprocessing and preliminary analysis in each of the IoT devices to a preset edge layer; Allocating devices for managing network communications between the devices in the IoT devices to a preset network layer; Allocating high-performance devices or cloud resource devices for advanced data processing and complex computing in each of the IoT devices to a preset core layer; The devices for providing user service interfaces in the Internet of Things devices are allocated to a preset application layer.

3. The method for managing IoT device resources as claimed in claim 2, characterized in that: The step of grouping all IoT devices in the preset object model based on the preset grouping index and the characteristic data to obtain at least one device group includes: Extracting first characteristic data corresponding to the preset grouping indicator from the characteristic data of each of the IoT devices according to the preset grouping indicator, wherein the preset grouping indicator includes at least one type of indicator among device performance, function type and working status; Clustering the first characteristic data of all IoT devices belonging to the perception layer to obtain a perception layer clustering result, and grouping IoT devices with the same cluster label among all IoT devices belonging to the perception layer into a device group according to the perception layer clustering result; Clustering the first characteristic data of all IoT devices belonging to the edge layer to obtain an edge layer clustering result, and grouping IoT devices with the same cluster label among all IoT devices belonging to the edge layer into a device group according to the edge layer clustering result; Clustering the first characteristic data of all IoT devices belonging to the network layer to obtain a network layer clustering result, and grouping IoT devices with the same cluster label among all IoT devices belonging to the network layer into a device group according to the network layer clustering result; Clustering the first characteristic data of all IoT devices belonging to the core layer to obtain a core layer clustering result, and grouping IoT devices with the same cluster label among all IoT devices belonging to the core layer into a device group according to the core layer clustering result; Clustering is performed on the first characteristic data of all IoT devices belonging to the application layer to obtain an application layer clustering result, and based on the application layer clustering result, IoT devices with the same cluster label among all IoT devices belonging to the application layer are divided into a device group.

4. The method for managing IoT device resources according to claim 1, wherein: The step of inputting the characteristic data of each device group into a preset resource configuration optimization model to obtain an output resource allocation plan for each device group includes: Obtaining a target resource function of a preset resource configuration optimization model, and determining constraints of the target resource function, wherein the target resource function is a function for calculating total resource consumption; Inputting the characteristic data of each of the equipment groups into the target resource function for optimization, and limiting the optimization result of the target resource function according to the constraint condition to determine the optimization result with the minimum total resource consumption; A resource allocation scheme for each IoT device in each device group is generated according to the optimization result with the minimum total resource consumption, wherein the resource allocation scheme includes a resource configuration scheme, a task allocation scheme and a load adjustment scheme for various resource types of the IoT devices.

5. The method for managing IoT device resources as claimed in claim 4, characterized in that: The constraints include: For each resource type, the total resource usage of all IoT devices for each resource type does not exceed the preset maximum available resource of the resource type; The device load of each of the IoT devices does not exceed the preset maximum allowable load of the IoT device; The task completion time of each of the IoT devices is before the preset deadline.

6. The method for managing IoT device resources as claimed in claim 5, characterized in that: The step of generating a resource allocation scheme for each IoT device in each device group according to the optimization result with the minimum total resource consumption includes: Analyze the optimization result with the minimum total resource consumption to obtain a target matrix, wherein the target matrix includes resource configuration, task allocation and load adjustment information of each IoT device; Extracting the resource allocation amount of each IoT device on each resource type from the target matrix; Extracting a task list and task priority assigned to each IoT device from the target matrix; extracting a load adjustment amount for each IoT device from the target matrix; A resource allocation scheme for each IoT device is generated according to the resource allocation amounts on each resource type, the task list and task priority, and the load adjustment amount.

7. The method for managing IoT device resources according to any one of claims 1 to 6, characterized in that: The IoT device resource management method further includes: Continuously monitor the real-time status data of IoT devices at all levels in the preset object model; storing the plurality of real-time status data as a status data sequence based on a time series; Inputting the state data sequence of each of the IoT devices into a preset prediction model for prediction to obtain future state data of each of the IoT devices; An abnormal device is determined according to the future state data, and a task list, a task priority, and a load adjustment amount of the abnormal device are adjusted according to the future state data.

8. An IoT device resource management device, characterized in that: The Internet of Things device resource management device comprises: A collection module, used to collect characteristic data of each IoT device in a preset object model, wherein the characteristic data includes hardware description data, software function data, network status data, environmental parameter data and real-time status data; A grouping module, configured to group all IoT devices in the preset object model based on a preset grouping index and the characteristic data to obtain at least one device group; An optimization module, used to input characteristic data of each equipment group into a preset resource configuration optimization model to obtain an output resource allocation plan for each equipment group; The management module is used to manage the resources of the Internet of Things devices in each of the device groups according to the resource allocation plan of each of the device groups.

9. An IoT device resource management device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for managing IoT device resources as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for managing resources of an Internet of Things device as described in any one of claims 1 to 7 are implemented.

Images