Edge device task management method, device, equipment, medium and product

Abstract

The embodiment of the invention discloses an edge device task management method and device, equipment, a medium and a product, and the method comprises the steps: determining a target edge device group for executing a to-be-allocated task; performing task allocation according to the computing power condition of each target edge device in the target edge device group; calculating a computing resource demand feature of each target edge device and determining an average computing resource demand feature of the target edge device group; generating a target file package required by the target edge device group to execute the to-be-allocated task according to the average computing resource demand feature; and sending the target file package to the target edge device group. According to the technical scheme provided by the embodiment of the invention, the problem that the generation of the target file package required for executing the task by the edge equipment is not reasonable enough is solved, and the target file package can be sent according to the task allocation condition and the calculation performance of the equipment group, so that the suitability of the target file package and the equipment task execution process is ensured; and resource waste is reduced.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer technology, and in particular, to an edge device task management method, apparatus, equipment, medium and product. Background Art

[0002] As the number of edge devices increases dramatically, the power system faces increasingly complex challenges in managing and dispatching edge devices. There are differences in computing performance between devices. How to reasonably manage edge devices and reasonably generate the file packages required for edge devices to perform tasks has become a major problem in the modernization of the power system. Summary of the invention

[0003] The embodiments of the present invention provide an edge device task management method, apparatus, equipment, medium and product, which can generate and send target file packages according to the task allocation status and computing performance of the device group, ensure the adaptability of the target file package to the device task execution process, and reduce resource waste.

[0004] In a first aspect, an embodiment of the present invention provides an edge device task management method, the method comprising:

[0005] Acquire the task to be assigned, and determine a target edge device group for executing the task to be assigned in at least one edge device group according to the task information of the task to be assigned;

[0006] According to the computing power status of each target edge device in the target edge device group, determine the subtask to be assigned to each target edge device in the task to be assigned, and assign the subtask to be assigned to the corresponding target edge device;

[0007] Calculate the computing resource requirement characteristics of each target edge device to execute the corresponding subtask to be assigned, and determine the average computing resource requirement characteristics of the target edge device group according to the computing resource requirement characteristics;

[0008] Optimizing the basic file package according to the average computing resource demand characteristics to generate a target file package required for the target edge device group to execute the task to be assigned, wherein the basic file package includes the application file content required to execute the task to be assigned;

[0009] The target file package is sent to the target edge device group, so that the target edge device group executes the to-be-assigned task based on the target file package.

[0010] In a second aspect, an embodiment of the present invention provides an edge device task management device, the device comprising:

[0011] A target edge device group determination module is used to obtain the task to be assigned, and determine a target edge device group for executing the task to be assigned in at least one edge device group according to the task information of the task to be assigned;

[0012] A task allocation module is used to determine the subtasks to be allocated to each target edge device in the task to be allocated according to the computing power status of each target edge device in the target edge device group, and allocate the subtasks to be allocated to the corresponding target edge devices;

[0013] An average computing resource requirement characteristic determination module is used to calculate the computing resource requirement characteristics of each target edge device to execute the corresponding subtask to be assigned, and determine the average computing resource requirement characteristics of the target edge device group according to the computing resource requirement characteristics;

[0014] A target file package generation module is used to optimize the basic file package according to the average computing resource demand characteristics, and generate a target file package required for the target edge device group to perform the task to be assigned, wherein the basic file package includes the application file content required to perform the task to be assigned;

[0015] The target file package sending module is used to send the target file package to the target edge device group so that the target edge device group executes the task to be assigned based on the target file package.

[0016] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising:

[0017] one or more processors;

[0018] A memory for storing one or more programs;

[0019] When the above one or more programs are executed by one or more processors, the above one or more processors implement the edge device task management method provided by any embodiment of the present invention.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements an edge device task management method as provided in any embodiment of the present invention.

[0021] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements an edge device task management method as provided in any embodiment of the present invention.

[0022] The embodiments of the above invention have the following advantages or beneficial effects:

[0023] In an embodiment of the present invention, by obtaining a task to be assigned, and according to the task information of the task to be assigned, a target edge device group that executes the task to be assigned is determined in at least one edge device group; according to the computing power status of each target edge device in the target edge device group, the subtask to be assigned to each target edge device in the task to be assigned is determined, and the subtask to be assigned is assigned to the corresponding target edge device; the computing resource requirement characteristics of each target edge device executing the corresponding subtask to be assigned are calculated, and the average computing resource requirement characteristics of the target edge device group are determined according to the computing resource requirement characteristics; according to the average computing resource requirement characteristics, the basic file package is optimized to generate the target file package required for the target edge device group to execute the task to be assigned, wherein the basic file package includes the application file content required to execute the task to be assigned; the target file package is sent to the target edge device group so that the target edge device group executes the task to be assigned based on the target file package. The technical solution of the embodiment of the present invention solves the problem that the generation of the target file package required for the edge device to execute the task is not reasonable at present, and the target file package can be generated and sent according to the task allocation status and computing performance of the device group, so as to ensure the adaptability of the target file package and the device task execution process and reduce resource waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of an edge device task management method provided by an embodiment of the present invention;

[0025] Figure 2 is a flow chart of an edge device task management method provided by an embodiment of the present invention;

[0026] Figure 3 is a flow chart of an edge device task management method provided by an embodiment of the present invention;

[0027] Figure 4 is a flow chart of an edge device task management method provided by an embodiment of the present invention;

[0028] Figure 5 It is a structural diagram of an edge device task management device provided by an embodiment of the present invention;

[0029] Figure 6 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0031] Figure 1 A flowchart of an edge device task management method provided by an embodiment of the present invention, which can be applied to edge device task management scenarios. The method can be executed by an edge device task management device, which can be implemented by software and / or hardware and integrated into a computer device with application development functions.

[0032] like Figure 1 As shown, the edge device task management method of this embodiment includes the following steps:

[0033] S110: Acquire a task to be assigned, and determine a target edge device group for executing the task to be assigned in at least one edge device group according to task information of the task to be assigned.

[0034] Edge devices may include, for example, power distribution terminals, smart meters, and sensors. The tasks to be assigned may be tasks such as data collection, equipment status monitoring, data processing and analysis, local control and protection, communication and networking, etc. The task information of the tasks to be assigned may be the total amount of computing resources required to perform the tasks to be assigned. The edge device groups that can perform the tasks to be assigned are matched according to the task information, and the target edge device group that performs the tasks to be assigned is determined in at least one edge device group.

[0035] Before obtaining the tasks to be assigned, the clustering data of all edge devices, including device performance data and geographic location information, can be collected in advance, and the collected data can be preprocessed to form a device status database. Based on the clustering data of edge devices, a clustering algorithm is used to divide the devices into different edge device groups, and the edge devices in each edge device group have similar computing performance characteristics. Therefore, when the tasks to be assigned are obtained, the target edge device group that executes the tasks to be assigned can be determined from the edge device groups obtained by pre-clustering.

[0036] S120. Determine the subtasks to be assigned to each target edge device in the task to be assigned according to the computing capability status of each target edge device in the target edge device group, and assign the subtasks to be assigned to the corresponding target edge devices.

[0037] According to the computing power status of each target edge device in the target edge device group, the load status of each target edge device is determined. According to the load status of each target edge device, the subtask to be assigned is determined and assigned to the corresponding target edge device to balance the load among the target edge devices.

[0038] S130. Calculate the computing resource requirement characteristics of each target edge device to execute the corresponding subtask to be assigned, and determine the average computing resource requirement characteristics of the target edge device group based on the computing resource requirement characteristics.

[0039] Calculate the computing resource requirements of the target edge device for the subtask to be assigned, obtain the computing resource requirement characteristics of the target edge device executing the corresponding subtask to be assigned, add the computing resource requirement characteristics to obtain the total computing resource requirement characteristics, and determine the average computing resource requirement characteristics of the target edge device group based on the total computing resource requirement characteristics and the number of target edge devices included in the target edge device group.

[0040] S140. Optimize the basic file package according to the average computing resource demand characteristics, and generate the target file package required for the target edge device group to execute the task to be assigned.

[0041] The file package can be a mirror image, which contains all the data and information required to create or restore the environment or system for executing the task. The basic file package includes the application file content required to execute the task to be assigned. Specifically, the historical task information of each edge device in the edge device group can be analyzed in advance to determine the files required for the edge device group to execute the task, such as operating system files, application files, and data files, and the files can be packaged to generate a basic file package.

[0042] It is understandable that for different tasks to be assigned, not all files in the basic file package are necessarily required when they are executed. Therefore, it is necessary to optimize the basic file package according to the average computing resource requirement characteristics, delete redundant files or file contents, and generate the target file package required for the target edge device group to execute the tasks to be assigned.

[0043] S150: Send the target file package to the target edge device group, so that the target edge device group executes the task to be assigned based on the target file package.

[0044] The target file package is sent to each target edge device in the target edge device group, so that the target edge devices in the target edge device group execute the subtask to be assigned based on the target file package, thereby completing the task to be assigned.

[0045] The technical solution of this embodiment obtains the task to be assigned, and determines the target edge device group that executes the task to be assigned in at least one edge device group according to the task information of the task to be assigned; determines the subtask to be assigned to each target edge device in the task to be assigned according to the computing power status of each target edge device in the target edge device group, and assigns the subtask to be assigned to the corresponding target edge device; calculates the computing resource requirement characteristics of each target edge device to execute the corresponding subtask to be assigned, and determines the average computing resource requirement characteristics of the target edge device group according to the computing resource requirement characteristics; optimizes the basic file package according to the average computing resource requirement characteristics, and generates the target file package required for the target edge device group to execute the task to be assigned, wherein the basic file package includes the application file content required to execute the task to be assigned; sends the target file package to the target edge device group, so that the target edge device group executes the task to be assigned based on the target file package. The technical solution of the embodiment of the present invention solves the problem that the generation of the target file package required for the edge device to execute the task is not reasonable at present, and can ensure the adaptability of the target file package to the device task execution process and reduce resource waste by generating and sending the target file package according to the task allocation status and computing performance of the device group.

[0046] Figure 2 A flowchart of an edge device task management method provided in an embodiment of the present invention. This embodiment and the edge device task management method in the above embodiment belong to the same inventive concept, and further describes the process of task allocation and target file package generation. The method can be executed by an edge device task management device, which can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0047] like Figure 2 As shown, the edge device task management method of this embodiment includes the following steps:

[0048] S210: Acquire a task to be assigned, and determine a target edge device group for executing the task to be assigned in at least one edge device group according to task information of the task to be assigned.

[0049] S220. Determine the task allocation weight of each target edge device according to the computing capacity load parameter of each target edge device in the target edge device group and the device workload measurement parameter of each target edge device executing the task to be assigned.

[0050] For example, the task allocation weight of each target edge device can be calculated according to the following formula:

[0051]

[0052] Among them, w ikrepresents the task allocation weight of the target edge device i in the task to be assigned k; C ik represents the computing capacity load parameter of the target edge device i; T ik It represents the requirement complexity or workload of the task k to be assigned, i.e., the equipment workload measurement parameter.

[0053] S230: Determine the to-be-assigned subtasks assigned to each target edge device in the to-be-assigned task and assigned to the target edge device group according to the task assignment weight and the total workload measurement parameter of the to-be-assigned task.

[0054] For example, task allocation can be expressed by the following formula:

[0055]

[0056] Among them, T assigned Indicates the allocation to the target edge device group G k The total task volume; T k The total workload measurement parameter representing the task k to be assigned can be the total workload or requirement complexity of the task k to be assigned, that is, the task assignment weight is multiplied by the total workload measurement parameter of the task to be assigned to obtain the subtask workload measurement parameter, and the subtask to be assigned to each target edge device of the target edge device group is obtained according to the task to be assigned and the subtask workload measurement parameter.

[0057] S240: Allocate the subtask to be assigned to the corresponding target edge device.

[0058] S250. Calculate the computing resource requirement characteristics of each target edge device to execute the corresponding subtask to be assigned, and determine the average computing resource requirement characteristics of the target edge device group based on the computing resource requirement characteristics.

[0059] The computing resource demand characteristics include at least one computing resource demand characteristic, and the computing resources may include CPU, memory resources, storage resources, and bandwidth resources. For example, the average computing resource demand characteristics are calculated according to the following formula:

[0060]

[0061] Where, |G| represents the number of devices in the target edge device group G; represents the CPU performance requirement of the target edge device i for the assigned subtask k; represents the memory requirement of the target edge device i for the assigned subtask k; represents the storage requirement of the target edge device i for the assigned subtask k; represents the bandwidth requirement of the target edge device i for the assigned subtask k; T g Represents the average computing resource demand characteristics.

[0062] S260. Determine the key file package content in the basic file package according to the average computing resource requirement characteristics, so that when the target edge device group runs the key file package content, the computing resource demand generated is not greater than the average computing resource demand indicated by the average computing resource requirement characteristics.

[0063] Based on the average computing resource requirement characteristics, the key file package content in the basic file package can be determined. The key file package content may, for example, include configuration files and applications required to execute the tasks to be assigned, and ensure that when the target edge device group runs the key file package content, the computing resource demand generated is not greater than the average computing resource demand indicated by the average computing resource requirement characteristics, thereby ensuring that the edge device executes tasks smoothly without lag, and extending the service life of the edge device hardware.

[0064] S270: Delete redundant file package contents in the basic file package according to the key file package contents, and generate a target file package required for the target edge device group to execute the task to be assigned.

[0065] The redundant file package content may include redundant parts of system configuration files and application files in the basic file package, as well as unused dependencies for the required dependent applications. The target file package is compressed using a compression algorithm to facilitate subsequent sending of the target file package.

[0066] S280: Send the target file package to the target edge device group, so that the target edge device group executes the task to be assigned based on the target file package.

[0067] The technical solution of this embodiment obtains the task to be assigned, and determines the target edge device group that executes the task to be assigned in at least one edge device group according to the task information of the task to be assigned; determines the task assignment weight of each target edge device according to the computing power load parameter of each target edge device in the target edge device group and the device workload measurement parameter of each target edge device executing the task to be assigned; determines the subtask to be assigned to each target edge device in the task to be assigned that is assigned to the target edge device group according to the task assignment weight and the total workload measurement parameter of the task to be assigned; assigns the subtask to be assigned to the corresponding target edge device; calculates the number of times each target edge device executes the task The computing resource requirement characteristics of the corresponding subtask to be assigned are used to determine the average computing resource requirement characteristics of the target edge device group according to the computing resource requirement characteristics; the key file package content in the basic file package is determined according to the average computing resource requirement characteristics, so that when the target edge device group runs the key file package content, the computing resource requirement generated is not greater than the average computing resource requirement indicated by the average computing resource requirement characteristics; according to the key file package content, the redundant file package content in the basic file package is deleted to generate the target file package required for the target edge device group to perform the task to be assigned; the target file package is sent to the target edge device group so that the target edge device group performs the task to be assigned based on the target file package. The technical solution of the embodiment of the present invention solves the problem that the target file package required for the edge device to perform the task is not generated reasonably at present. Tasks can be assigned according to the computing performance of the device and the resource requirements of the task, and the target file package is generated according to the task allocation status, computing performance and average computing resource requirement characteristics of the device group, so as to ensure the adaptability of the target file package to the device task execution process and reduce resource waste.

[0068] Figure 3 This is a flowchart of an edge device task management method provided by an embodiment of the present invention. This embodiment and the edge device task management method in the above embodiment belong to the same inventive concept, and further describes the process of sending the target file package. The method can be executed by an edge device task management device, which can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0069] like Figure 3 As shown, the edge device task management method of this embodiment includes the following steps:

[0070] S310: Acquire a task to be assigned, and determine a target edge device group for executing the task to be assigned in at least one edge device group according to task information of the task to be assigned.

[0071] S320. Determine the subtasks to be assigned to each target edge device in the task to be assigned according to the computing capability status of each target edge device in the target edge device group, and assign the subtasks to be assigned to the corresponding target edge devices.

[0072] S330. Calculate the computing resource requirement characteristics of each target edge device to execute the corresponding subtask to be assigned, and determine the average computing resource requirement characteristics of the target edge device group based on the computing resource requirement characteristics.

[0073] S340. Optimize the basic file package according to the average computing resource demand characteristics, and generate the target file package required for the target edge device group to execute the task to be assigned.

[0074] S350. Obtain the current task processing status of each target edge device in the target edge device group.

[0075] In this embodiment, the target file package is intelligently sent to the edge device based on the task allocation result. Therefore, it is necessary to obtain the current task processing status of each target edge device in the target edge device group to determine whether the target edge device is currently suitable for receiving the target file package according to the current task processing status.

[0076] S360. Determine the load status of the target edge device according to the current task processing status.

[0077] For example, a comprehensive analysis is performed based on the computing resource load status and task queue in the current task processing status to obtain the load status of the target edge device.

[0078] S370: Sort the load conditions to obtain a load condition sorting result.

[0079] The load conditions are sorted to determine the relative task processing busyness between the target edge devices, and the load condition sorting result is obtained.

[0080] S380. Determine the order in which the target file package is sent to each target edge device according to the load status sorting result, and send the target file package to each target edge device of the target edge device group according to the sending order, so that the target edge device group executes the task to be assigned based on the target file package.

[0081] According to the load status sorting result, the order of sending the target file package to each target edge device is determined, and the target file package can be sent to the target edge device with a lighter load status, that is, a relatively idle one, first.

[0082] The technical solution of this embodiment obtains the task to be assigned, and determines the target edge device group that executes the task to be assigned in at least one edge device group according to the task information of the task to be assigned; determines the subtask to be assigned to each target edge device in the task to be assigned according to the computing power status of each target edge device in the target edge device group, and assigns the subtask to be assigned to the corresponding target edge device; calculates the computing resource requirement characteristics of each target edge device to execute the corresponding subtask to be assigned, and determines the average computing resource requirement characteristics of the target edge device group according to the computing resource requirement characteristics; optimizes the basic file package according to the average computing resource requirement characteristics to generate the target file package required for the target edge device group to execute the task to be assigned; obtains the current task processing status of each target edge device in the target edge device group; determines the load status of the target edge device according to the current task processing status; sorts the load status to obtain the load status sorting result; determines the sending order of sending the target file package to each target edge device according to the load status sorting result, and sends the target file package to each target edge device of the target edge device group according to the sending order, so that the target edge device group executes the task to be assigned based on the target file package. The technical solution of the embodiment of the present invention solves the problem that the target file package generation and sending required for the edge device to perform tasks are not reasonable. The target file package can be generated according to the task allocation status and computing performance of the device group, and the sending order can be determined according to the load status of the edge device. On the basis of ensuring the adaptability of the target file package to the device task execution process, the intelligence of the sending strategy is improved.

[0083] In a specific edge device task management example of the present invention, the target file package sending process can comprehensively consider factors such as the geographical location of the target edge device, network bandwidth, and device status such as idle state and load condition to achieve the optimization of mirror sending. Through intelligent scheduling and bandwidth optimization strategies, the data transmission efficiency during the target file package sending process can be ensured to avoid network bottlenecks and resource waste.

[0084] For each target edge device in the target edge device group, the same target file package is sent to avoid repeated transmission and reduce network bandwidth consumption. According to the load situation in the device group, the target file package is allocated to the device with the lowest load as needed.

[0085] If the target edge devices are geographically close, the target edge devices in the region are given priority when sending the target file package to reduce the delay and bandwidth consumption of cross-region transmission. When sending the target file package, the order in which the target edge devices receive it is adjusted according to the geographical distance. For example, the device that is closer to the server is given priority to reduce transmission delay.

[0086] In this embodiment, in order to avoid network bandwidth overload, a bandwidth dynamic adjustment strategy can be used to ensure that the target file packet does not exceed the upper limit of the network bandwidth. The specific method is as follows:

[0087]

[0088] Among them, S push Indicates the sending rate; B current Indicates the current network available bandwidth; B max Indicates the maximum bandwidth of the network; T load Indicates the current network load ratio; T max Indicates the maximum load bearing capacity of the network.

[0089] For devices that have saved the historical version file package, only the incremental part is sent to reduce unnecessary bandwidth usage. Incremental sending compares the hash value of the historical version file package and the target file package to identify the difference:

[0090]

[0091] Among them, Incremental data i Indicates the incremental data that needs to be sent; Current hash i Indicates the hash value of the historical version file package on the target edge device i; Target hash i Indicates the hash value of the target target file package; Indicates a skew operation, indicating the difference between two hash values. This ensures that only the changed data is sent, reducing the amount of data transmitted.

[0092] During the target file package sending process, the network bandwidth usage, the device receiving progress, and the task completion status are monitored in real time. If it is found that the target file package sending progress of some devices is slow or the bandwidth utilization is insufficient, the sending strategy can be dynamically adjusted based on the monitoring data. According to the real-time network bandwidth feedback, the sending rate is dynamically adjusted to avoid excessive bandwidth occupation. According to the load of the device, the idle or lightly loaded device is dynamically selected to send the target file package. According to the priority of the device, the sending order and the content of the target file package are adjusted in time. For example, if a device has a higher priority, the target file package sending can be assigned to this device first.

[0093] This embodiment can efficiently complete the sending of target file packages through strategies such as device grouping, geographical location optimization, bandwidth adaptation and incremental sending, ensure the maximum utilization of network resources, and avoid bandwidth bottlenecks.

[0094] Figure 4A flowchart of an edge device task management method provided in an embodiment of the present invention. This embodiment and the edge device task management method in the above embodiment belong to the same inventive concept, and further describes the generation process of the edge device group. The method can be executed by an edge device task management device, which can be implemented by software and / or hardware and integrated in a computer device with application development function.

[0095] like Figure 4 As shown, the process of generating an edge device group in the edge device task management method of this embodiment includes the following steps:

[0096] S410: Collect device feature data of edge devices, and determine a device feature vector of each edge device according to the device feature data.

[0097] The device characteristic data at least includes device computing performance characteristic data. The computing performance characteristic data may include CPU performance characteristic data, memory characteristic data, storage capacity characteristic data, and network bandwidth characteristic data. The device characteristic data may also include task requirement indicators and geographic location parameters.

[0098] For example, the feature vector v of each edge device i =[CPU i ,MEM i ,STO i ,BW i ,Task i ,Loc i ], where CPU i is the CPU performance value of the i-th edge device; MEM i Indicates the memory size of the i-th edge device; STO i represents the storage capacity of the i-th edge device; BW i represents the network bandwidth of the i-th edge device; Task i represents the task requirement index of the i-th edge device; Loc i Represents the geographic location parameter of the i-th edge device.

[0099] S420 , calculating the weighted Euclidean distance between device feature vectors to obtain a distance calculation result, clustering the edge devices according to the distance calculation result, and obtaining an edge device combination.

[0100] Using weighted Euclidean distance d ij To measure the difference between device i and device j, it can be expressed by the following formula:

[0101]

[0102] Among them, w krepresents the weight of the kth eigenvalue; x ik Indicates the value of the kth feature of the ith device.

[0103] The initial cluster center is selected probabilistically. Based on distance calculation, the device farthest from the existing center is selected as the new cluster center. The K-means algorithm is used to iteratively update the cluster center of the device and redistribute the grouping of each device until the convergence condition is reached to obtain the edge device combination.

[0104] The device grouping can be updated by setting the current grouping of the device to G i , device i and each cluster center C k The distance is d ik , device i will be assigned to the cluster with the smallest distance:

[0105]

[0106] Among them, |G k | represents the number of devices in the kth group.

[0107] In this embodiment, the K-means algorithm comprehensively considers the device performance and task requirements, so that efficient grouping of devices can be achieved. The devices in each group have similar properties, which helps to optimize task allocation so that each device can undertake appropriate computing or storage tasks, avoiding resource waste or processing delays caused by performance mismatch. Through reasonable grouping, it can be ensured that the devices in the same group are highly consistent in performance and task requirements, thereby avoiding conflicts between tasks between different devices, especially under heavy loads. K-means can ensure that the devices in each cluster cooperate with each other by allocating devices to the optimal cluster, thereby improving the efficiency of task execution.

[0108] In an optional embodiment, after obtaining the edge device combination, a preset number of key clustering feature items are determined from at least one clustering feature item of the device feature data; the similarity of the feature values ​​of the key clustering feature items between the edge devices is calculated to obtain the key feature similarity calculation results; the comprehensive feature similarity results are calculated based on the key feature similarity calculation results, and based on the comprehensive feature similarity results, the grouping of the edge devices is adjusted by a preset clustering algorithm.

[0109] For example, the density-based spatial clustering algorithm DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is used to optimize the edge device grouping after the K-means algorithm iteration to deal with the sparse or dense distribution of edge devices. The specific steps are as follows:

[0110] Initialization parameters ∈ and MinPts, where ∈ represents the radius of the neighborhood, indicating the maximum distance around a device, and is used to define the range of neighboring devices; MinPts represents the minimum number of neighbors within the range of ∈ for a device to become a core point.

[0111] The geographical distance between devices is calculated using the following formula:

[0112]

[0113] Among them, d geo,ij Indicates device e i and equipment j The geographical distance between i ,y i Indicates device e i The longitude and latitude of x j ,y j Indicates device e j The longitude and latitude of

[0114] The computing performance similarity between devices is calculated using the following formula:

[0115]

[0116] Among them, d perf,ij Indicates device e i and equipment j The performance difference between ik , p jk Respectively represent the device e i and equipment j The value of the kth performance dimension; n represents the number of dimensions of the performance characteristic;

[0117] The comprehensive distance metric is calculated by the following formula:

[0118] d′ ij =w geo ·d geo,ij +w perf ·d perf,ij ;

[0119] Among them, w geo and w perf Represent the weights of geographical distance and computing performance differences respectively;

[0120] Based on the comprehensive distance metric, the distance matrix D between devices is constructed, where D in the matrix ij Indicates device e i and equipment j The combined distance between .

[0121] For each K-means group C iFor the devices in the cluster, DBSCAN clusters the devices based on the set parameters ∈ and MinPts to identify the high-density areas and detect the noisy devices. i If there are at least MinPts other devices in its neighborhood, then device e i As the core point. i has fewer than MinPts neighbors, but at least one core neighbor, then e i is the boundary point. i Areas that do not belong to any core point are considered noise points. If the average distance of devices in the neighborhood is less than the set average distance threshold, the two domains are merged into a new group. For the devices in each K-means group, the distribution is calculated based on the density. If it is found that the density of some devices in a K-means group is lower than MinPts, and the distance between devices is greater than the distance threshold, it is considered that the group should be split. For the split devices, DBSCAN is reapplied for new grouping based on their density information. Among the devices after K-means grouping, the DBSCAN algorithm is used to identify noise devices. If the number of neighbors of a device in the group is less than MinPts and the density value is lower than the density threshold, the device is considered to be a noise device and the noise device is removed or grouped separately.

[0122] This embodiment further optimizes the K-means grouping results by using the DBSCAN algorithm, which can identify and eliminate noise data, and does not need to preset the number of clusters K, thereby improving the robustness and accuracy of K-means grouping. By analyzing the density of device data, DBSCAN can draw more appropriate boundaries between different device groups, rather than relying solely on the K value of the K-means algorithm. This density-based grouping method can better handle device data with complexity or irregular distribution, thereby further improving the accuracy of device grouping. DBSCAN further refines the grouping results of K-means to make the boundaries between device groups clearer. The optimized grouping can make task allocation more accurate, avoid resource conflicts between devices, and improve the collaborative efficiency of edge devices. In addition, DBSCAN's nonlinear grouping method can better adapt to uneven load conditions and improve the flexibility and responsiveness of task scheduling.

[0123] The technical solution of this embodiment collects device feature data of edge devices and determines the device feature vector of each edge device based on the device feature data. The device feature data includes at least device computing performance feature data. The weighted Euclidean distance between the device feature vectors is calculated to obtain a distance calculation result, and the edge devices are clustered according to the distance calculation result to obtain an edge device combination. The technical solution of the embodiment of the present invention solves the current problem of difficult edge device management. The edge device combination can be obtained by clustering the feature data of the edge devices, thereby facilitating subsequent task allocation and target file package generation.

[0124] Figure 5 This is a schematic diagram of the structure of an edge device task management device provided by an embodiment of the present invention. This embodiment is applicable to edge device task management scenarios. The edge device task management device can be implemented by software and / or hardware and integrated into a computer terminal device with application development function.

[0125] like Figure 5 As shown, the edge device task management apparatus includes: a target edge device group determination module 510, a task allocation module 520, an average computing resource requirement characteristic determination module 530, a target file package generation module 540 and a target file package sending module 550.

[0126] Among them, the target edge device group determination module 510 is used to obtain the task to be assigned, and determine the target edge device group that executes the task to be assigned in at least one edge device group according to the task information of the task to be assigned; the task allocation module 520 is used to determine the subtask to be assigned to each target edge device in the task to be assigned according to the computing power status of each target edge device in the target edge device group, and assign the subtask to be assigned to the corresponding target edge device; the average computing resource requirement characteristic determination module 530 is used to calculate the computing resource requirement characteristics of each target edge device to execute the corresponding subtask to be assigned, and determine the average computing resource requirement characteristics of the target edge device group according to the computing resource requirement characteristics; the target file package generation module 540 is used to optimize the basic file package according to the average computing resource requirement characteristics, and generate the target file package required for the target edge device group to execute the task to be assigned, wherein the basic file package includes the application file content required to execute the task to be assigned; the target file package sending module 550 is used to send the target file package to the target edge device group so that the target edge device group executes the task to be assigned based on the target file package.

[0127] The technical solution of this embodiment obtains the task to be assigned, and determines the target edge device group that executes the task to be assigned in at least one edge device group according to the task information of the task to be assigned; determines the subtask to be assigned to each target edge device in the task to be assigned according to the computing power status of each target edge device in the target edge device group, and assigns the subtask to be assigned to the corresponding target edge device; calculates the computing resource requirement characteristics of each target edge device to execute the corresponding subtask to be assigned, and determines the average computing resource requirement characteristics of the target edge device group according to the computing resource requirement characteristics; optimizes the basic file package according to the average computing resource requirement characteristics, and generates the target file package required for the target edge device group to execute the task to be assigned, wherein the basic file package includes the application file content required to execute the task to be assigned; sends the target file package to the target edge device group, so that the target edge device group executes the task to be assigned based on the target file package. The technical solution of the embodiment of the present invention solves the problem that the generation of the target file package required for the edge device to execute the task is not reasonable at present, and can ensure the adaptability of the target file package to the device task execution process and reduce resource waste by generating and sending the target file package according to the task allocation status and computing performance of the device group.

[0128] In an optional implementation, the task allocation module 520 is specifically used to:

[0129] Determine the task allocation weight of each target edge device based on the computing power load parameters of each target edge device in the target edge device group and the device workload measurement parameters of each target edge device executing the task to be assigned; determine the subtask to be assigned to each target edge device in the task to be assigned that is assigned to the target edge device group based on the task allocation weight and the total workload measurement parameters of the task to be assigned.

[0130] In an optional implementation, the target file package generation module 540 is specifically used to:

[0131] According to the average computing resource requirement characteristics, the key file package content in the basic file package is determined so that when the target edge device group runs the key file package content, the computing resource demand generated is no greater than the average computing resource demand indicated by the average computing resource requirement characteristics; according to the key file package content, the redundant file package content in the basic file package is deleted to generate the target file package required for the target edge device group to execute the task to be assigned.

[0132] In an optional implementation manner, the target file package sending module 550 is specifically configured to:

[0133] Obtain the current task processing status of each target edge device in the target edge device group; determine the load status of the target edge device based on the current task processing status; sort the load status to obtain the load status sorting result; determine the sending order of sending the target file package to each target edge device based on the load status sorting result, and send the target file package to each target edge device in the target edge device group according to the sending order.

[0134] In an optional embodiment, the device further comprises:

[0135] The edge device grouping module is used to collect device feature data of edge devices, determine the device feature vector of each edge device based on the device feature data, wherein the device feature data at least includes device computing performance feature data; calculate the weighted Euclidean distance between the device feature vectors to obtain the distance calculation result, cluster the edge devices according to the distance calculation result, and obtain the edge device combination.

[0136] In an optional implementation, the edge device grouping module is further used to:

[0137] Determine a preset number of key clustering feature items from at least one clustering feature item of device feature data; calculate the similarity of feature values ​​of key clustering feature items between edge devices to obtain key feature similarity calculation results; calculate comprehensive feature similarity results based on the key feature similarity calculation results, and adjust the grouping of edge devices based on the comprehensive feature similarity results through a preset clustering algorithm.

[0138] The edge device task management apparatus provided in the embodiment of the present invention can execute the edge device task management method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0139] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Figure 6 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 6 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities, such as an intelligent controller and server, a mobile phone and other terminal devices.

[0140] like Figure 6 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0141] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0142] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0143] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 6 not shown, usually called a "hard drive"). Although Figure 6 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0144] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0145] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RFID systems, tape drives, and data backup storage systems.

[0146] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing the edge device task management method provided in the embodiment of the present invention, the method comprising:

[0147] Acquire the task to be assigned, and determine a target edge device group for executing the task to be assigned in at least one edge device group according to the task information of the task to be assigned;

[0148] According to the computing power status of each target edge device in the target edge device group, determine the subtask to be assigned to each target edge device in the task to be assigned, and assign the subtask to be assigned to the corresponding target edge device;

[0149] Calculate the computing resource requirement characteristics of each target edge device to execute the corresponding subtask to be assigned, and determine the average computing resource requirement characteristics of the target edge device group according to the computing resource requirement characteristics;

[0150] Optimizing the basic file package according to the average computing resource demand characteristics to generate a target file package required for the target edge device group to execute the task to be assigned, wherein the basic file package includes the application file content required to execute the task to be assigned;

[0151] The target file package is sent to the target edge device group, so that the target edge device group executes the to-be-assigned task based on the target file package.

[0152] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the edge device task management method provided in any embodiment of the present invention is implemented. The method includes:

[0153] Acquire the task to be assigned, and determine a target edge device group for executing the task to be assigned in at least one edge device group according to the task information of the task to be assigned;

[0154] According to the computing power status of each target edge device in the target edge device group, determine the subtask to be assigned to each target edge device in the task to be assigned, and assign the subtask to be assigned to the corresponding target edge device;

[0155] Calculate the computing resource requirement characteristics of each target edge device to execute the corresponding subtask to be assigned, and determine the average computing resource requirement characteristics of the target edge device group according to the computing resource requirement characteristics;

[0156] Optimizing the basic file package according to the average computing resource demand characteristics to generate a target file package required for the target edge device group to execute the task to be assigned, wherein the basic file package includes the application file content required to execute the task to be assigned;

[0157] The target file package is sent to the target edge device group, so that the target edge device group executes the to-be-assigned task based on the target file package.

[0158] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0159] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0160] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0161] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, Python, 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).

[0162] An embodiment of the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the edge device task management method provided in any embodiment of the present application.

[0163] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, Python, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can 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 can 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 can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0164] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0165] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for managing edge device tasks, characterized in that: include: Acquire a task to be assigned, and determine a target edge device group for executing the task to be assigned in at least one edge device group according to task information of the task to be assigned; According to the computing power status of each target edge device in the target edge device group, determine the subtask to be assigned to each target edge device in the task to be assigned, and assign the subtask to be assigned to the corresponding target edge device; Calculate the computing resource requirement characteristics of each target edge device executing the corresponding subtask to be assigned, and determine the average computing resource requirement characteristics of the target edge device group according to the computing resource requirement characteristics; Optimizing the basic file package according to the average computing resource requirement characteristics to generate a target file package required for the target edge device group to execute the task to be assigned, wherein the basic file package includes application file content required to execute the task to be assigned; The target file package is sent to the target edge device group, so that the target edge device group executes the to-be-assigned task based on the target file package.

2. The method according to claim 1, characterized in that The determining, according to the computing capability status of each target edge device in the target edge device group, a subtask to be assigned to each target edge device in the task to be assigned, comprises: Determine the task allocation weight of each target edge device according to the computing capacity load parameter of each target edge device in the target edge device group and the device workload measurement parameter of each target edge device executing the task to be assigned; According to the task allocation weight and the total workload measurement parameter of the task to be allocated, the subtask to be allocated in the task to be allocated and allocated to each target edge device of the target edge device group is determined.

3. The method according to claim 1, characterized in that The step of optimizing the basic file package according to the average computing resource requirement characteristics to generate the target file package required for the target edge device group to execute the task to be assigned includes: Determine the key file package content in the basic file package according to the average computing resource requirement characteristic, so that when the target edge device group runs the key file package content, the computing resource demand generated is not greater than the average computing resource demand indicated by the average computing resource requirement characteristic; According to the key file package content, redundant file package content in the basic file package is deleted to generate a target file package required for the target edge device group to execute the task to be assigned.

4. The method according to claim 1, characterized in that: The sending the target file package to the target edge device group includes: Obtaining the current task processing status of each target edge device in the target edge device group; Determine the load status of the target edge device according to the current task processing status; Sorting the load conditions to obtain a load condition sorting result; According to the load status sorting result, a sending order of sending the target file package to each of the target edge devices is determined, and the target file package is sent to each of the target edge devices in the target edge device group according to the sending order.

5. The method according to claim 1, characterized in that: The generation process of the edge device group includes: Collect device feature data of edge devices, and determine a device feature vector of each edge device according to the device feature data, wherein the device feature data at least includes device computing performance feature data; A weighted Euclidean distance between the device feature vectors is calculated to obtain a distance calculation result, and the edge devices are clustered according to the distance calculation result to obtain an edge device combination.

6. The method according to claim 5, characterized in that Also includes: Determining a preset number of key clustering feature items from at least one clustering feature item of the device feature data; Calculating the similarity of the feature values ​​of the key clustering feature items between the edge devices to obtain a key feature similarity calculation result; A comprehensive feature similarity result is calculated according to the key feature similarity calculation result, and based on the comprehensive feature similarity result, the grouping of the edge devices is adjusted by a preset clustering algorithm.

7. An edge device task management device, characterized in that: include: A target edge device group determination module is used to obtain a task to be assigned, and determine a target edge device group for executing the task to be assigned in at least one edge device group according to task information of the task to be assigned; A task allocation module, used to determine the subtask to be allocated to each target edge device in the task to be allocated according to the computing power status of each target edge device in the target edge device group, and allocate the subtask to be allocated to the corresponding target edge device; An average computing resource requirement characteristic determination module is used to calculate the computing resource requirement characteristics of each target edge device executing the corresponding subtask to be assigned, and determine the average computing resource requirement characteristics of the target edge device group according to the computing resource requirement characteristics; A target file package generation module, used to optimize the basic file package according to the average computing resource requirement characteristics, and generate a target file package required for the target edge device group to execute the task to be assigned, wherein the basic file package includes the application file content required to execute the task to be assigned; The target file package sending module is used to send the target file package to the target edge device group, so that the target edge device group executes the task to be assigned based on the target file package.

8. A computer device, characterized in that: The computer device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the edge device task management method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the edge device task management method as described in any one of claims 1-6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the edge device task management method as described in any one of claims 1 to 6.

Images