CN115941258A - Edge calculation task distribution method, device, equipment and medium - Google Patents
Edge calculation task distribution method, device, equipment and medium Download PDFInfo
- Publication number
- CN115941258A CN115941258A CN202211321553.8A CN202211321553A CN115941258A CN 115941258 A CN115941258 A CN 115941258A CN 202211321553 A CN202211321553 A CN 202211321553A CN 115941258 A CN115941258 A CN 115941258A
- Authority
- CN
- China
- Prior art keywords
- semantic
- edge
- data
- slicing
- tasks
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004364 calculation method Methods 0.000 title abstract description 24
- 238000007405 data analysis Methods 0.000 claims abstract description 46
- 230000011218 segmentation Effects 0.000 claims abstract description 29
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 abstract description 17
- 230000005540 biological transmission Effects 0.000 abstract description 10
- 230000007547 defect Effects 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 6
- 230000003993 interaction Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Information Transfer Between Computers (AREA)
Abstract
The invention provides a method, a device, equipment and a medium for distributing edge computing tasks, wherein the method comprises the following steps: performing semantic segmentation on data to be transmitted to obtain different types of semantic slicing tasks; distributing the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks, and determining the slicing tasks to be distributed corresponding to each edge node; and distributing the slice tasks to be distributed to corresponding edge nodes. The invention is used for solving the defect of low data transmission efficiency among edge nodes in the prior art, ensuring lower time delay of edge calculation under the condition of performing data analysis and processing among cross nodes, meeting the requirements of reducing network occupation and network cost by reducing the size of transmitted data, or not influencing the normal operation of services under the condition of poor network quality, meeting the usability requirement and improving the overall efficiency of an edge calculation system.
Description
Technical Field
The present invention relates to the field of computer communication network technologies, and in particular, to a method, an apparatus, a device, and a medium for distributing an edge computing task.
Background
In contrast to the traditional model based entirely on the cloud, the edge system architecture deploys the cloud functions of storage, computation, processing, and networking on the side close to the end user. In recent years, due to low delay and high bandwidth capability brought by the edge computing industry, the technology development is rapid, the market scale is expanded continuously, and the edge computing industry plays an important role in ICT infrastructure gradually in various industries.
However, the standards and technologies of the edge computing system are mainly aimed at functions and interactions of modules in a unified system, and with the deep development of industrial applications such as the industrial internet and the like, the interaction requirements of the edge computing system are gradually enhanced, a large amount of data needs to be transmitted in a network during the interaction of the edge computing system, and especially video data occupies a large amount of network resources.
Therefore, a processing method for improving the data transmission efficiency between edge nodes in an edge computing system is needed.
Disclosure of Invention
The invention provides a method, a device, equipment and a medium for distributing edge computing tasks, which are used for solving the defect of low data transmission efficiency among edge nodes in the prior art and realizing the improvement of the data transmission efficiency among the edge nodes.
The invention provides an edge computing task distribution method, which comprises the following steps:
performing semantic segmentation on data to be transmitted to obtain different types of semantic slicing tasks;
distributing the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks, and determining the slicing tasks to be distributed corresponding to each edge node;
and distributing the slice tasks to be distributed to corresponding edge nodes.
According to the edge calculation task distribution method provided by the invention, the data to be transmitted is subjected to semantic segmentation to obtain different types of semantic slicing tasks, and the method comprises the following steps:
acquiring preset semantic environment types, wherein the semantic environment types comprise data segmentation rules corresponding to various different application places;
and based on the semantic environment types, cutting the data to be transmitted into a plurality of semantic slices to obtain different types of semantic slice tasks.
According to the edge computing task distribution method provided by the invention, the semantic slicing tasks are distributed based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks, and the slicing tasks to be distributed corresponding to each edge node are determined, wherein the method comprises the following steps:
determining that the slicing task to be distributed comprises sensitive data;
determining a data security level corresponding to the slicing task to be distributed based on the sensitive data;
if the data security level exceeds a preset security threshold, distributing the to-be-distributed slicing task to a local edge node;
and if the data security level does not exceed the preset security threshold, distributing the semantic slice tasks based on the data analysis capability of each edge node, and determining the slice tasks to be distributed to other edge nodes except the local edge node in each edge node.
According to the method for distributing the edge computing task, the semantic slicing task is distributed based on the data analysis capability of each edge node, the slicing task to be distributed which is distributed to other edge nodes except the local edge node in each edge node is determined, and the method comprises the following steps:
determining a semantic slice label corresponding to the semantic slice task;
matching the node capacity deployment identifier in the node capacity deployment list with the semantic slice mark, and determining slice tasks to be distributed to other edge nodes except the local edge node in each edge node;
wherein the node capability deployment identifier is used for characterizing data analysis capability.
According to the edge computing task distribution method provided by the invention, each edge node internally maintains the node capability deployment list;
each edge node is used for broadcasting the node capacity deployment identification to be updated of the edge node to the adjacent nodes of the edge node, and the node capacity deployment identification to be updated is used for updating to the node capacity deployment list.
According to the edge computing task distribution method provided by the invention, after the to-be-distributed slicing task is distributed to the corresponding edge node, the method comprises the following steps:
if the slice task to be distributed belongs to a local edge node, acquiring the local computing capacity of the local edge node;
and if the occupied computing power of the local computing power exceeds a preset threshold value, distributing the to-be-distributed slicing task to other edge nodes except the local edge node.
The invention also provides an edge computing task distributing device, which comprises:
the segmentation module is used for carrying out semantic segmentation on data to be transmitted to obtain different types of semantic slicing tasks;
the distribution module is used for distributing the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks and determining the slicing tasks to be distributed corresponding to each edge node;
and the distribution module is used for distributing the to-be-distributed slicing tasks to the corresponding edge nodes.
The invention further provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the edge computing task distribution method.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements an edge computing task distribution method as described in any one of the above.
The present invention also provides a computer program product comprising a computer program which, when executed by a processor, implements the edge computing task distribution method as described in any one of the above.
The invention provides a method, a device, equipment and a medium for distributing edge calculation tasks, which are used for obtaining different types of semantic slicing tasks by performing semantic segmentation on data, distributing the semantic slicing tasks to edge nodes with corresponding data analysis capability, enabling the edge nodes capable of providing processing results for the semantic slicing tasks to be matched with the semantic slicing tasks, distributing the data to the corresponding edge nodes in a way of pre-segmentation and pre-redistribution, and being used as a way for transmitting data between the edge calculation nodes, ensuring lower time delay under the condition that data analysis and processing are performed between nodes in edge calculation, and meeting the requirements of reducing network occupation and network cost by reducing the size of transmitted data, or under the condition that the network quality is poor, not influencing the normal operation of service, meeting the availability requirement, improving the data transmission efficiency between the edge nodes and improving the overall efficiency of an edge calculation system.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of an edge computing task distribution method provided by the present invention;
FIG. 2 is a second schematic flowchart of the method for distributing edge calculation tasks according to the present invention;
FIG. 3 is a third schematic flowchart of a method for distributing edge calculation tasks according to the present invention;
FIG. 4 is a fourth flowchart of the method for distributing edge calculation tasks according to the present invention;
FIG. 5 is a fifth flowchart illustrating a method for distributing edge calculation tasks according to the present invention;
fig. 6 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The edge calculation task distribution method of the present invention is described below in conjunction with fig. 1-5.
Referring to fig. 1, the method for distributing edge calculation tasks according to the present invention includes:
in the application scene of the edge computing system, along with the deep development of the industrial internet industry, the interaction requirement of the edge computing system is gradually enhanced, a large amount of data needs to be transmitted in a network during the interaction of the edge computing system, particularly video data, so that a large amount of network resources are occupied.
The data to be transmitted may include voice data, video data, image data, text data, file data, and the like. The embodiment of the application is applied to an edge computing system, and the edge computing system comprises a large number of data analysis and computing nodes, which are collectively called edge nodes, namely the edge computing system comprises a large number of edge nodes, and the edge nodes are used for providing data analysis and computing resources.
after the data to be transmitted is obtained, performing semantic segmentation on the data to be transmitted to obtain semantic slicing tasks of different semantic types, wherein the purpose of the step is to segment the data to be transmitted into the semantic slicing tasks of different semantic types according to the different semantic types. And then, receiving the data analysis capability of other edge nodes, determining the slicing tasks which can be processed by the edge nodes according to the data analysis capability of the edge nodes, and obtaining the slicing tasks to be distributed which are distributed to the edge nodes.
It can be understood that, in the task slicing step, the purpose is to perform semantic slicing tasks which are divided into different semantic types according to different semantic types and data security levels; in this step of slicing task assignment, the objective is to determine to which edge node the slicing task belongs. In a possible embodiment, firstly, data to be transmitted is divided into face data, pedestrian behavior data, voice data and license plate data, then edge nodes with data analysis capability possessed by the face data are determined to be face recognition capability nodes, then the face data are distributed to the face recognition capability nodes, and distribution of the pedestrian behavior data, the voice data and the license plate data are performed in the same way.
It should be noted that, a semantic slice task distribution module is deployed in the edge computing system, and the semantic slice task distribution module is used for analyzing and processing data to be transmitted, dividing the data to be transmitted into different types of semantic slices, receiving data analysis capabilities of other edge nodes, and performing task distribution on semantic slice tasks according to the data analysis capabilities of each edge node to obtain slice tasks to be distributed corresponding to the edge nodes. By deploying the semantic slice task distribution module, lower time delay of edge computing under the condition of cross-node data analysis and processing is realized, the requirements of reducing network occupation and network cost are met by reducing the size of transmitted data, the real-time performance and reliability of data processing and analysis are ensured, and the overall efficiency of an edge computing system and the safety of irrelevant data not transmitted are improved.
The data analysis capability is the data analysis capability of each edge node for certain semantic data, and the data analysis capability can comprise face recognition capability, behavior recognition capability, fire recognition capability, helmet wearing recognition capability, voice recognition capability and the like.
And step 30, distributing the slice tasks to be distributed to corresponding edge nodes.
And after the semantic slice task is well distributed, distributing the obtained slice task to be distributed to the corresponding edge node. For example, in one possible example, face data in video data is assigned to a face recognition capability node, pedestrian behavior data is assigned to a pedestrian behavior recognition capability node, voice data is assigned to a voice recognition node, and license plate data is assigned to a license plate recognition capability node, etc.
The invention provides a method for distributing an edge calculation task, which is characterized in that different types of semantic slicing tasks are obtained by carrying out semantic segmentation on data, then the semantic slicing tasks are distributed to edge nodes with corresponding data analysis capability, so that the edge nodes capable of providing processing results for the semantic slicing tasks can be matched with the semantic slicing tasks, and the data are distributed to the corresponding edge nodes in a segmentation and redistribution mode, so that the semantic slicing tasks can be used as a mode for data transmission between the edge calculation nodes, lower time delay of the edge calculation under the condition of carrying out data analysis and processing between nodes is ensured, the requirements of reducing network occupation and network cost are met by reducing the size of transmission data, or the normal operation of services is not influenced under the condition of poor network quality, the availability requirement is met, the data transmission efficiency between the edge nodes is improved, and the overall efficiency of an edge calculation system is improved.
In an embodiment, referring to fig. 2, in step 10, performing semantic segmentation on data to be transmitted to obtain different types of semantic slicing tasks, including:
and step 12, based on the semantic environment types, dividing the data to be transmitted into a plurality of semantic slices to obtain different types of semantic slice tasks.
In the embodiment of the application, data are divided into different semantic slicing tasks according to different semantic environments and data segmentation rules corresponding to different application places. The same source data can be subjected to semantic segmentation by a semantic slicing task distribution module according to the semantic environment type preset by the system, so that the source data is divided into a plurality of semantic slicing tasks, the semantic contents contained in each slice are different, and the data volume in each semantic slice is far smaller than the data to be transmitted of the source data.
The semantic environment types are set by an operator according to actual needs, and can include road traffic scenes, indoor safety scenes and the like. For example, for video data collected by monitoring inside a factory, semantic slices such as behavior anomaly recognition, helmet wearing recognition, fire recognition and the like need to be performed on the video data, that is, semantic environment types include a behavior type, a helmet recognition type and a fire recognition type. For video data collected by monitoring traffic roads, semantic environment types can include pedestrian behavior recognition, vehicle behavior recognition, license plate recognition, violation of traffic type recognition and the like.
Furthermore, the method can also comprise the step of cutting the semantic slicing task and correspondingly marking according to the semantic environment type to obtain the semantic slicing marks corresponding to the semantic slicing task.
According to the embodiment, the data are divided into different semantic slices according to different semantic environments, the data to be transmitted can be divided into a plurality of semantic slices, the semantic slice tasks are divided into different semantic environment types, the data are reasonably divided according to different semantic environment types, the reasonability of data division is improved, and therefore the transmission efficiency between edge nodes is further improved.
In an embodiment, referring to fig. 3, in step 20, allocating the semantic slicing task based on the data analysis capability of each edge node and the data security level of the semantic slicing task, and determining the slicing task to be allocated corresponding to each edge node includes:
and step 24, if the data security level does not exceed the preset security threshold, distributing the semantic slicing tasks based on the data analysis capability of each edge node, and determining the slicing tasks to be distributed to other edge nodes except the local edge node in each edge node.
In the embodiment of the application, sensitive identification is carried out on the slice task to be distributed, whether the slice task to be distributed contains sensitive data or not is determined, if the slice task to be distributed contains the sensitive data, the data security level of the sensitive data is determined according to the data type contained in the sensitive data, and the data security level corresponding to the slice task to be distributed containing the sensitive data is obtained.
The sensitive data can be data such as human face, identity card, fingerprint and the like. The data security level can be divided into high, medium and low levels. The high-level to-be-distributed slicing tasks are distributed to the local computing nodes, and the middle-level to-be-distributed slicing tasks and the low-level to-be-distributed slicing tasks are distributed to other edge nodes except the local computing nodes.
For example, analysis requirements involving local or high security level databases such as face recognition can only be handled locally.
In the embodiment of the application, the data security level corresponding to the slice task to be distributed is distributed to the corresponding edge node for processing, so that the problem of data leakage of sensitive data is avoided, and the security of data processing is improved.
In an embodiment, referring to fig. 4, step 24, allocating the semantic slicing task based on the data analysis capability of each edge node, and determining the slicing tasks to be allocated to the edge nodes other than the local edge node in each edge node, includes:
241, determining a semantic slice mark corresponding to the semantic slice task;
wherein the node capability deployment identifier is used for characterizing data analysis capability.
And according to the semantic environment type, cutting the semantic slicing task and carrying out corresponding marking to obtain the semantic slicing mark corresponding to the semantic slicing task. That is, according to the semantic environment type, data is divided into different types of semantic slices according to different semantic environments, and semantic slice tasks are labeled, so that semantic slice labels corresponding to the semantic slice tasks are obtained. Wherein the semantic environment type corresponds to the data analysis capability of the edge node.
For example, when data (particularly video data) is generated, the data is transmitted to a node where a semantic slice task distribution module is deployed from the inside of an edge computing system by an end node, the semantic slice task distribution module is mainly responsible for analyzing and processing the data to be processed, the data is divided into different types of semantic slices according to different semantic environments and marked, and the marks correspond to node capability deployment identifiers.
The node capacity deployment identification and the semantic slice mark are matched, so that matching is realized according to the deployment capacity of the edge nodes and the processing capacity required by the semantic slices, the nodes capable of providing processing results for the semantic slices can be matched with the semantic slices, the distribution efficiency and the distribution accuracy of semantic slice tasks are improved, and the data transmission efficiency among the edge nodes is further improved.
In one embodiment, each edge node internally maintains the node capability deployment list, and a node capability deployment identifier in the node capability deployment list corresponds to the data analysis capability;
each edge node is used for broadcasting the deployment identifier of the node capacity to be updated of the edge node to the adjacent nodes of the edge node, and the deployment identifier of the node capacity to be updated is used for updating the deployment list of the node capacity.
In the edge computing nodes deployed through the computational power network, each node sends data analysis capabilities, such as face recognition capability, behavior recognition capability, fire recognition capability and the like, of the node to adjacent nodes in a broadcasting mode, and each node maintains a capability deployment table of adjacent nodes and carries out unified identification on corresponding capabilities. After the data analysis capability deployed by each node is updated (added, deleted and modified), the updated data analysis capability of the node is sent to the adjacent nodes in a broadcasting mode, and the capability deployment tables of the adjacent nodes are updated immediately.
In an embodiment, referring to fig. 5, step 30, after distributing the slice task to be allocated to the corresponding edge node, includes:
and step 50, if the occupied computing power of the local computing power exceeds a preset threshold, distributing the to-be-distributed slicing task to other edge nodes except the local edge node.
In the embodiment of the application, after the semantic slice task distribution module completes semantic slice and distribution, the semantic slice task distribution module compares the adjacent node capacity deployment table maintained inside with the adjacent node capacity deployment table, and for the data processing capacity of the node, whether the node is locally processed or distributed to other edge computing nodes for processing can be selected according to actual needs. The method can also comprise the steps that under the condition of being distributed to the local computing nodes, if the slice tasks to be distributed belong to the local computing nodes, the local computing power corresponding to the local computing nodes is obtained, and whether the occupied capacity of the local computing power exceeds a preset threshold value or not is determined; and if the occupied local computing capacity exceeds a preset threshold value, such as 80%, distributing to other edge computing nodes for processing.
After the edge computing node completes the semantic slice data analysis, an analysis result (for example, a fire occurrence is identified) and a node capability deployment identifier are returned to the source edge computing node. And after the source edge computing node obtains the analysis result, summarizing the result in the system, and performing services such as result reporting, alarming, uploading and the like.
Furthermore, based on the semantic slice, the maintenance and the update of the adjacent node capacity deployment table and the hierarchical task distribution of the semantic slice according to the data security level, the MEC system can provide normal service under the conditions of poor network conditions or limited computing capacity on the premise of not excessively repeatedly developing and excessively transforming the conventional MEC system. The intercommunication of edge ubiquitous computing power is further realized, the service continuity is improved, and the use experience and the service quality of the user are improved.
The following describes the edge calculation task distribution device provided by the present invention, and the edge calculation task distribution device described below and the edge calculation task distribution method described above may be referred to in correspondence with each other.
The invention provides an edge calculation task distribution device, which comprises:
the segmentation module is used for carrying out semantic segmentation on data to be transmitted to obtain different types of semantic slicing tasks;
the distribution module is used for distributing the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks and determining the to-be-distributed slicing tasks distributed to each edge node;
and the distribution module is used for distributing the to-be-distributed slicing tasks to the corresponding edge nodes.
Further, the segmentation module is further configured to:
acquiring preset semantic environment types, wherein the semantic environment types comprise data segmentation rules corresponding to various different application places;
and based on the semantic environment types, cutting the data to be transmitted into a plurality of semantic slices to obtain different types of semantic slice tasks.
Further, the segmentation module is further configured to:
determining that the slicing task to be allocated comprises sensitive data;
determining a data security level corresponding to the slicing task to be distributed based on the sensitive data;
if the data security level exceeds a preset security threshold, distributing the to-be-distributed slicing task to a local edge node;
and if the data security level does not exceed the preset security threshold, distributing the semantic slice tasks based on the data analysis capability of each edge node, and determining the slice tasks to be distributed to other edge nodes except the local edge node in each edge node.
Further, the slicing module is further configured to:
determining a semantic slice label corresponding to the semantic slice task;
matching the node capacity deployment identifier in the node capacity deployment list with the semantic slice mark, and determining slice tasks to be distributed to other edge nodes except the local edge node in each edge node;
wherein the node capability deployment identifier is used for characterizing data analysis capability.
Further, each edge node internally maintains the node capability deployment list;
each edge node is used for broadcasting the node capacity deployment identification to be updated of the edge node to the adjacent nodes of the edge node, and the node capacity deployment identification to be updated is used for updating to the node capacity deployment list.
Further, the edge computing task distribution device further includes a reallocation module configured to:
if the slice task to be distributed belongs to a local edge node, acquiring the local computing capacity of the local edge node;
and if the occupied computing power of the local computing power exceeds a preset threshold value, distributing the to-be-distributed slicing task to other edge nodes except the local edge node.
Fig. 6 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 6: a processor (processor) 610, a communication Interface 620, a memory (memory) 630 and a communication bus 640, wherein the processor 610, the communication Interface 620 and the memory 630 complete communication with each other through the communication bus 640. The processor 610 may invoke logic instructions in the memory 630 to perform an edge computing task distribution method comprising: performing semantic segmentation on data to be transmitted to obtain different types of semantic slicing tasks; distributing the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks, and determining the slicing tasks to be distributed corresponding to each edge node; and distributing the slice tasks to be distributed to corresponding edge nodes.
In addition, the logic instructions in the memory 630 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, a computer is capable of executing the edge calculation task distribution method provided by the above methods, the method including: performing semantic segmentation on data to be transmitted to obtain different types of semantic slicing tasks; distributing the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks, and determining the slicing tasks to be distributed corresponding to each edge node; and distributing the slice tasks to be distributed to corresponding edge nodes.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the edge computing task distribution method provided by the above methods, the method including: performing semantic segmentation on data to be transmitted to obtain different types of semantic slicing tasks; distributing the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks, and determining the slicing tasks to be distributed corresponding to each edge node; and distributing the slice tasks to be distributed to corresponding edge nodes.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An edge computing task distribution method, comprising:
performing semantic segmentation on data to be transmitted to obtain different types of semantic slicing tasks;
distributing the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks, and determining the slicing tasks to be distributed corresponding to each edge node;
and distributing the slice tasks to be distributed to corresponding edge nodes.
2. The edge computing task distribution method of claim 1, wherein performing semantic segmentation on data to be transmitted to obtain different types of semantic slicing tasks, comprises:
acquiring preset semantic environment types, wherein the semantic environment types comprise data segmentation rules corresponding to various different application places;
and based on the semantic environment types, segmenting the data to be transmitted into a plurality of semantic slices to obtain different types of semantic slice tasks.
3. The method for distributing the edge computing task according to claim 1, wherein the step of distributing the semantic slicing tasks based on data analysis capability of each edge node and data security level of the semantic slicing tasks, and determining the slicing tasks to be distributed that are distributed to each edge node comprises:
determining that the slicing task to be allocated comprises sensitive data;
determining a data security level corresponding to the slicing task to be distributed based on the sensitive data;
if the data security level exceeds a preset security threshold, distributing the to-be-distributed slicing task to a local edge node;
and if the data security level does not exceed the preset security threshold, distributing the semantic slice tasks based on the data analysis capability of each edge node, and determining the slice tasks to be distributed to other edge nodes except the local edge node in each edge node.
4. The method for distributing the edge computing task according to claim 3, wherein the semantic slicing task is distributed based on the data analysis capability of each edge node, and the slicing task to be distributed, which is distributed to the edge nodes other than the local edge node, is determined, and the method includes:
determining a semantic slice label corresponding to the semantic slice task;
matching the node capacity deployment identifier in the node capacity deployment list with the semantic slice mark, and determining slice tasks to be distributed to other edge nodes except the local edge node in each edge node;
wherein the node capability deployment identifier is used for characterizing data analysis capability.
5. The method for distributing the task of the edge computing according to claim 4, wherein each edge node internally maintains the node capability deployment list;
each edge node is used for broadcasting the deployment identifier of the node capacity to be updated of the edge node to the adjacent nodes of the edge node, and the deployment identifier of the node capacity to be updated is used for updating the deployment list of the node capacity.
6. The method for distributing the edge computing task according to claim 1, wherein after distributing the to-be-distributed slicing task to the corresponding edge node, the method includes:
if the to-be-distributed slice task belongs to a local edge node, acquiring the local computing capacity of the local edge node;
and if the occupied computing power of the local computing power exceeds a preset threshold value, distributing the to-be-distributed slicing task to other edge nodes except the local edge node.
7. An edge computing task distribution apparatus, comprising:
the segmentation module is used for carrying out semantic segmentation on data to be transmitted to obtain different types of semantic slicing tasks;
the distribution module is used for distributing the semantic slicing tasks based on the data analysis capability of each edge node and the data security level of the semantic slicing tasks and determining the slicing tasks to be distributed corresponding to each edge node;
and the distribution module is used for distributing the to-be-distributed slicing tasks to the corresponding edge nodes.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the edge computing task distribution method according to any one of claims 1 to 6 when executing the program.
9. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the edge computing task distribution method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the edge computing task distribution method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211321553.8A CN115941258A (en) | 2022-10-26 | 2022-10-26 | Edge calculation task distribution method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211321553.8A CN115941258A (en) | 2022-10-26 | 2022-10-26 | Edge calculation task distribution method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115941258A true CN115941258A (en) | 2023-04-07 |
Family
ID=86556635
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211321553.8A Pending CN115941258A (en) | 2022-10-26 | 2022-10-26 | Edge calculation task distribution method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115941258A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597043A (en) * | 2020-05-14 | 2020-08-28 | 行星算力(深圳)科技有限公司 | Method, device and system for calculating edge of whole scene |
| CN111600914A (en) * | 2020-07-27 | 2020-08-28 | 北京信安世纪科技股份有限公司 | Data transmission method, server and client |
| US20200351336A1 (en) * | 2019-04-30 | 2020-11-05 | Verizon Patent And Licensing Inc. | Methods and Systems for Intelligent Distribution of Workloads to Multi-Access Edge Compute Nodes on a Communication Network |
| CN112383427A (en) * | 2020-11-12 | 2021-02-19 | 广东电网有限责任公司 | 5G network slice deployment method and system based on IOTIPS fault early warning |
| CN113420338A (en) * | 2021-05-21 | 2021-09-21 | 华控清交信息科技(北京)有限公司 | Data processing method and device and data processing device |
| CN113849302A (en) * | 2021-08-27 | 2021-12-28 | 青岛海尔科技有限公司 | Task execution method and device, storage medium and electronic device |
| CN114610499A (en) * | 2022-03-22 | 2022-06-10 | 深圳须弥云图空间科技有限公司 | Task scheduling method and device, computer readable storage medium and electronic equipment |
| CN114970834A (en) * | 2022-06-23 | 2022-08-30 | 中国电信股份有限公司 | Task allocation method and device and electronic equipment |
| CN115169634A (en) * | 2022-05-11 | 2022-10-11 | 华北电力科学研究院有限责任公司 | Task allocation optimization processing method and device |
| CN115237568A (en) * | 2022-07-27 | 2022-10-25 | 杭州电子科技大学 | Mixed weight task scheduling method and system for edge heterogeneous equipment |
-
2022
- 2022-10-26 CN CN202211321553.8A patent/CN115941258A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200351336A1 (en) * | 2019-04-30 | 2020-11-05 | Verizon Patent And Licensing Inc. | Methods and Systems for Intelligent Distribution of Workloads to Multi-Access Edge Compute Nodes on a Communication Network |
| CN111597043A (en) * | 2020-05-14 | 2020-08-28 | 行星算力(深圳)科技有限公司 | Method, device and system for calculating edge of whole scene |
| CN111600914A (en) * | 2020-07-27 | 2020-08-28 | 北京信安世纪科技股份有限公司 | Data transmission method, server and client |
| CN112383427A (en) * | 2020-11-12 | 2021-02-19 | 广东电网有限责任公司 | 5G network slice deployment method and system based on IOTIPS fault early warning |
| CN113420338A (en) * | 2021-05-21 | 2021-09-21 | 华控清交信息科技(北京)有限公司 | Data processing method and device and data processing device |
| CN113849302A (en) * | 2021-08-27 | 2021-12-28 | 青岛海尔科技有限公司 | Task execution method and device, storage medium and electronic device |
| CN114610499A (en) * | 2022-03-22 | 2022-06-10 | 深圳须弥云图空间科技有限公司 | Task scheduling method and device, computer readable storage medium and electronic equipment |
| CN115169634A (en) * | 2022-05-11 | 2022-10-11 | 华北电力科学研究院有限责任公司 | Task allocation optimization processing method and device |
| CN114970834A (en) * | 2022-06-23 | 2022-08-30 | 中国电信股份有限公司 | Task allocation method and device and electronic equipment |
| CN115237568A (en) * | 2022-07-27 | 2022-10-25 | 杭州电子科技大学 | Mixed weight task scheduling method and system for edge heterogeneous equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111090807B (en) | Knowledge graph-based user identification method and device | |
| CN110430068B (en) | Characteristic engineering arrangement method and device | |
| CN108512672B (en) | Service arranging method, service management method and device | |
| CN112269718B (en) | Service system fault analysis method and device | |
| CN112764920B (en) | Edge application deployment method, device, equipment and storage medium | |
| CN108446270B (en) | Electronic device, early warning method of system sensitive content and storage medium | |
| CN114244683A (en) | Event classification method and device | |
| CN111931809A (en) | Data processing method and device, storage medium and electronic equipment | |
| CN108769207B (en) | Cloud platform resource monitoring method and system | |
| CN114842307A (en) | Mask image model training method, mask image content prediction method and device | |
| CN105335313A (en) | Basic data transmission method and apparatus | |
| CN115941258A (en) | Edge calculation task distribution method, device, equipment and medium | |
| CN116340009B (en) | Data processing method and system based on Internet of things technology | |
| CN106533882B (en) | Message processing method and device | |
| CN114520775A (en) | Application control method and device, electronic equipment and storage medium | |
| CN105335362A (en) | Real-time data processing method and system, and instant processing system | |
| CN112788768A (en) | Communication resource allocation method and device | |
| CN110647942B (en) | Intrusion detection method, device and equipment for satellite network | |
| CN110740172B (en) | Routing management method, device and system based on micro-service architecture | |
| CN113627526A (en) | Vehicle identification recognition method and device, electronic equipment and medium | |
| CN116932228B (en) | Edge AI task scheduling and resource management system based on volunteer calculation | |
| CN115080818A (en) | Number information processing method and device | |
| CN117135151B (en) | Fault detection method of GPU cluster, electronic equipment and storage medium | |
| CN114116142A (en) | Identification generation method and device, electronic equipment and storage medium | |
| US20230261951A1 (en) | System and method to provide priority based quality of service for telemetry data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |