CN110381159A - Task processing method and system - Google Patents
Task processing method and system Download PDFInfo
- Publication number
- CN110381159A CN110381159A CN201910684012.3A CN201910684012A CN110381159A CN 110381159 A CN110381159 A CN 110381159A CN 201910684012 A CN201910684012 A CN 201910684012A CN 110381159 A CN110381159 A CN 110381159A
- Authority
- CN
- China
- Prior art keywords
- equipment
- stand
- available
- list
- resources
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/63—Routing a service request depending on the request content or context
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Hardware Redundancy (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Present disclose provides a kind of task processing methods, the task processing method includes: for each fringe node, when the load for the specific resources for judging the fringe node reaches preset threshold, and when receiving the new task with specific resources demand for being sent to the fringe node, the specific resources demand stand-by equipment list corresponding with the fringe node of the new task is obtained, stand-by equipment list includes at least the device numbering of each stand-by equipment and the available resources data of each stand-by equipment in the corresponding multiple stand-by equipments of the fringe node;According to the available resources data of each stand-by equipment in the specific resources demand and stand-by equipment list of the new task, the stand-by equipment for being used to handle the new task is determined from stand-by equipment list;The new task is sent to the stand-by equipment determined;The task processing result of the stand-by equipment determined return is received, and sends task processing result to the fringe node.The disclosure additionally provides a kind of task processing system.
Description
Technical field
The embodiment of the present disclosure is related to field of communication technology, in particular to a kind of task processing method and system.
Background technique
Edge calculations refer in the side close to object or data source header, using network, calculating, storage, application core ability
The open platform being integrated provides most proximal end service nearby.
In edge calculations, aiming at the problem that inadequate resource of fringe node, the prior art is usually merely hard with dilatation
The mode of part resource solves, but is often limited by the various conditions of edge calculations, cannot achieve and increases on a large scale
Hardware resource.
Summary of the invention
The embodiment of the present disclosure aims to solve at least one of the technical problems existing in the prior art, provides a kind of task processing
Method and system.
In a first aspect, the embodiment of the present disclosure provides a kind of task processing method, which includes:
For each fringe node, when the load for the specific resources for judging the fringe node reaches preset threshold, and connect
When receiving the new task with specific resources demand for being sent to the fringe node, the specific resources demand of the new task is obtained
Stand-by equipment list corresponding with the fringe node, it is corresponding multiple standby that the stand-by equipment list includes at least the fringe node
With the device numbering of stand-by equipment each in equipment and the available resources data of each stand-by equipment;
According to the available resources of each stand-by equipment in the specific resources demand of the new task and the stand-by equipment list
Data determine the stand-by equipment for being used to handle the new task from the stand-by equipment list;
The new task is sent to the stand-by equipment determined;
The task processing result of the stand-by equipment determined return is received, and is sent at the task to the fringe node
Manage result.
In some embodiments, each in the specific resources demand and the stand-by equipment list according to the new task
The available resources data of stand-by equipment determine that one is used to handle the spare of the new task from the stand-by equipment list
Equipment, comprising:
According to the available resources data of the specific resources demand of the new task and each stand-by equipment, from the stand-by equipment
Determine that available resources data can satisfy the stand-by equipment of specific resources demand of the new task in list, generation can be used standby
Use list of devices;
The stand-by equipment for being used to handle the new task is determined from the available backup list of devices.
In some embodiments, the available resources data include available computational resources data, can use storage resource data
With available network resource data;
If the specific resources are computing resource, when the specific resources demand of the new task includes computational resource requirements,
It is described according to the specific resources demand of the new task and the available resources data of each stand-by equipment, from the stand-by equipment list
In determine that available resources data can satisfy the stand-by equipment of the specific resources demand of the new task, generate available backup and set
Standby list, comprising:
According to the available resources data of the computational resource requirements of the new task and each stand-by equipment, from the stand-by equipment
The available computational resources data and available network resource data of each stand-by equipment are extracted in list, generate the first available resources column
Table, first list of available resources include device numbering, corresponding available computational resources data and the correspondence of each stand-by equipment
Available network resource data;
Reject the computing resource that available computational resources data in first list of available resources are unsatisfactory for the new task
The stand-by equipment of demand obtains the first new list of available resources;
According to the first new list of available resources, the available backup list of devices, the available backup equipment column are generated
Table is the first new list of available resources.
In some embodiments, described to determine that one is used to handle the new post from the available backup list of devices
The stand-by equipment of business, comprising:
For each stand-by equipment in available backup list of devices, according to each spare in the available backup list of devices
The available computational resources data of equipment are normalized the available computational resources data of the stand-by equipment, it is standby to obtain this
With the corresponding computing resource normalized value of the available computational resources data of equipment;
For each stand-by equipment in available backup list of devices, according to each spare in the available backup list of devices
The available network resource data of equipment are normalized the available network resource data of the stand-by equipment, it is standby to obtain this
With the corresponding Internet resources normalized value of the available network resource data of equipment;
For each stand-by equipment in the available backup list of devices, according to preset first Rating Model, this is standby
With the corresponding computing resource normalized value of available computational resources data of equipment and the available network resource number of the stand-by equipment
According to corresponding Internet resources normalized value, corresponding first score value of the stand-by equipment is generated;
According to corresponding first score value of each stand-by equipment in the available backup list of devices, most by the first score value
High stand-by equipment is determined as the stand-by equipment for handling the new task.
In some embodiments, preset first Rating Model includes: the first score value formula: Pi=k1*Ai+k2*
Bi;
Wherein, PiIndicate corresponding first score value of i-th of stand-by equipment, A in the available backup list of devicesiIt indicates
The corresponding computing resource normalized value of the available computational resources data of i-th of stand-by equipment in the available backup list of devices,
BiIndicate the corresponding Internet resources normalizing of the available network resource data of i-th of stand-by equipment in the available backup list of devices
Change value, k1Indicate the corresponding weighted value of computing resource normalized value, k2Indicate the corresponding weighted value of Internet resources normalized value, k1+
k2=1, and k1Greater than k2。
In some embodiments, the available resources data include available computational resources data, can use storage resource data
With available network resource data;
If the specific resources are storage resource, when the specific resources demand of the new task includes storage resource demands,
It is described according to the specific resources demand of the new task and the available resources data of each stand-by equipment, from the stand-by equipment list
In determine that available resources data can satisfy the stand-by equipment of the specific resources demand of the new task, generate available backup and set
Standby list, comprising:
According to the available resources data of the storage resource demands of the new task and each stand-by equipment, from the stand-by equipment
The available storage resource data and available network resource data of each stand-by equipment are extracted in list, generate the second available resources column
Table, second list of available resources include device numbering, corresponding available storage resource data and the correspondence of each stand-by equipment
Available network resource data;
Reject the storage resource that can be unsatisfactory for the new task in second list of available resources with storage resource data
The stand-by equipment of demand obtains the second new list of available resources;
According to the second new list of available resources, the available backup list of devices, the available backup equipment column are generated
Table is the second new list of available resources.
In some embodiments, described to determine that one is used to handle the new post from the available backup list of devices
The stand-by equipment of business, comprising:
For each stand-by equipment in available backup list of devices, according to each spare in the available backup list of devices
The available storage resource data of equipment are normalized the available storage resource data of the stand-by equipment, it is standby to obtain this
With the corresponding storage resource normalized value of available storage resource data of equipment;
For each stand-by equipment in available backup list of devices, according to each spare in the available backup list of devices
The available network resource data of equipment are normalized the available network resource data of the stand-by equipment, it is standby to obtain this
With the corresponding Internet resources normalized value of the available network resource data of equipment;
For each stand-by equipment in the available backup list of devices, according to preset second Rating Model, this is standby
With the available corresponding storage resource normalized value of storage resource data of equipment and the available network resource number of the stand-by equipment
According to corresponding Internet resources normalized value, corresponding second score value of the stand-by equipment is generated;
According to corresponding second score value of each stand-by equipment in the available backup list of devices, most by the second score value
High stand-by equipment is determined as the stand-by equipment for handling the new task.
In some embodiments, preset second Rating Model includes: the second score value formula: Qi=k3*Ci+k2*
Bi;
Wherein, QiIndicate corresponding second score value of i-th of stand-by equipment, C in the available backup list of devicesiIt indicates
The corresponding storage resource normalized value of available storage resource data of i-th of stand-by equipment in the available backup list of devices,
BiIndicate the corresponding Internet resources normalizing of the available network resource data of i-th of stand-by equipment in the available backup list of devices
Change value, k3Indicate the corresponding weighted value of storage resource normalized value, k2Indicate the corresponding weighted value of Internet resources normalized value, k3+
k2=1, and k3Greater than k2。
Second aspect, the embodiment of the present disclosure provide a kind of task processing system, which includes:
Edge cloud management platform judges that the load of the specific resources of the fringe node is for being directed to each fringe node
It is no to reach preset threshold, and judge whether to receive the new task with specific resources demand for being sent to the fringe node;
Equipment screening module, for being directed to each fringe node, at edge, cloud management platform judges the fringe node
The load of specific resources reaches preset threshold, and when judging to receive the new task with specific resources demand, obtains the side
The corresponding stand-by equipment list of edge node, the stand-by equipment list include each in the corresponding multiple stand-by equipments of the fringe node
The available resources data of the device numbering of stand-by equipment and each stand-by equipment;According to the specific resources demand of the new task and
The available resources data of each stand-by equipment in the stand-by equipment list determine that one is used for from the stand-by equipment list
Handle the stand-by equipment of the new task;
Network control module, for sending the new task to the stand-by equipment determined;Receive this determine it is spare
The task processing result that equipment returns, and the task processing result is sent to the fringe node.
In some embodiments, the equipment screening module be specifically used for according to the specific resources demand of the new task and
It is described new to determine that available resources data can satisfy from the stand-by equipment list for the available resources data of each stand-by equipment
The stand-by equipment of the specific resources demand of task generates available backup list of devices;From the available backup list of devices really
One is made for handling the stand-by equipment of the new task.
In some embodiments, the available resources data include available computational resources data, can use storage resource data
With available network resource data;
If the specific resources are computing resource, when the specific resources demand of the new task includes computational resource requirements,
The equipment screening module is specifically used for according to the computational resource requirements of the new task and the available resources number of each stand-by equipment
According to, the available computational resources data and available network resource data of each stand-by equipment are extracted from the stand-by equipment list,
Generate the first list of available resources, first list of available resources includes the device numbering, corresponding available of each stand-by equipment
Computing resource data and corresponding available network resource data;Reject available computational resources number in first list of available resources
According to the stand-by equipment for the computational resource requirements for being unsatisfactory for the new task, the first new list of available resources is obtained;According to new
First list of available resources, generates the available backup list of devices, and the available backup list of devices is first newly
List of available resources.
In some embodiments, the equipment screening module is specifically used for standby for each of available backup list of devices
With equipment, according to the available computational resources data of each stand-by equipment in the available backup list of devices, to the stand-by equipment
Available computational resources data are normalized, and obtain the corresponding computing resource of available computational resources data of the stand-by equipment
Normalized value;For each stand-by equipment in available backup list of devices, according to each standby in the available backup list of devices
With the available network resource data of equipment, the available network resource data of the stand-by equipment are normalized, are somebody's turn to do
The corresponding Internet resources normalized value of the available network resource data of stand-by equipment;For in the available backup list of devices
Each stand-by equipment is provided according to the corresponding calculating of the available computational resources data of preset first Rating Model, the stand-by equipment
The corresponding Internet resources normalized value of the available network resource data of source normalized value and the stand-by equipment generates this and spare sets
Standby corresponding first score value;It, will according to corresponding first score value of each stand-by equipment in the available backup list of devices
The highest stand-by equipment of first score value is determined as the stand-by equipment for handling the new task.
In some embodiments, the available resources data include available computational resources data, can use storage resource data
With available network resource data;
If the specific resources are storage resource, when the specific resources demand of the new task includes storage resource demands,
The equipment screening module is specifically used for according to the storage resource demands of the new task and the available resources number of each stand-by equipment
According to, the available storage resource data and available network resource data of each stand-by equipment are extracted from the stand-by equipment list,
Generate the second list of available resources, second list of available resources includes the device numbering, corresponding available of each stand-by equipment
Storage resource data and corresponding available network resource data;Storage resource number can be used by rejecting in second list of available resources
According to the stand-by equipment for the storage resource demands for being unsatisfactory for the new task, the second new list of available resources is obtained;According to new
Second list of available resources, generates the available backup list of devices, and the available backup list of devices is second newly
List of available resources.
In some embodiments, the equipment screening module is specifically used for standby for each of available backup list of devices
With equipment, according to the available storage resource data of each stand-by equipment in the available backup list of devices, to the stand-by equipment
It can be normalized with storage resource data, obtain the corresponding storage resource of available storage resource data of the stand-by equipment
Normalized value;For each stand-by equipment in available backup list of devices, according to each standby in the available backup list of devices
With the available network resource data of equipment, the available network resource data of the stand-by equipment are normalized, are somebody's turn to do
The corresponding Internet resources normalized value of the available network resource data of stand-by equipment;For in the available backup list of devices
Each stand-by equipment is provided according to the corresponding storage of the available storage resource data of preset second Rating Model, the stand-by equipment
The corresponding Internet resources normalized value of the available network resource data of source normalized value and the stand-by equipment generates this and spare sets
Standby corresponding second score value;It, will according to corresponding second score value of each stand-by equipment in the available backup list of devices
The highest stand-by equipment of second score value is determined as the stand-by equipment for handling the new task.
Task processing method and system provided by the embodiment of the present disclosure, for each fringe node, when judging the side
The load of the specific resources of edge node reaches preset threshold, and receive be sent to the fringe node have specific resources demand
New task when, which is transmitted to the corresponding stand-by equipment that can be used for handling the new task of the fringe node,
On the one hand, the resource utilization that can effectively improve stand-by equipment avoids the wasting of resources of stand-by equipment, on the other hand, can be with
Effectively reduce the load of fringe node busy.
Detailed description of the invention
Fig. 1 is a kind of flow chart for task processing method that the embodiment of the present disclosure provides;
Fig. 2 is a kind of flow chart of specific embodiment of step 12 in the embodiment of the present disclosure;
Fig. 3 is a kind of flow chart of specific embodiment of step 121 in the embodiment of the present disclosure;
Fig. 4 is the flow chart of another specific embodiment of step 121 in the embodiment of the present disclosure;
Fig. 5 is a kind of flow chart of specific embodiment of step 122 in the embodiment of the present disclosure;
Fig. 6 is the flow chart of another specific embodiment of step 122 in the embodiment of the present disclosure;
Fig. 7 is the flow chart for another task processing method that the embodiment of the present disclosure provides;
Fig. 8 is a kind of structural schematic diagram for task processing system that the embodiment of the present disclosure provides.
Specific embodiment
To make those skilled in the art more fully understand the technical solution of the disclosure, the disclosure is mentioned with reference to the accompanying drawing
The task processing method and system of confession are described in detail.
Fig. 1 is a kind of flow chart for task processing method that the embodiment of the present disclosure provides, as shown in Figure 1, the task is handled
Method includes:
Step 11 is directed to each fringe node, when the load for the specific resources for judging the fringe node reaches default threshold
When being worth, and receiving the new task with specific resources demand for being sent to the fringe node, the specific money of the new task is obtained
The stand-by equipment list corresponding with the fringe node of source demand.
Wherein, stand-by equipment list includes at least each stand-by equipment in the fringe node corresponding multiple stand-by equipments and sets
The available resources data of standby number and each stand-by equipment.
In the embodiments of the present disclosure, resource can include but is not limited to: computing resource (such as CPU, memory), storage resource
(such as disk) and Internet resources (such as network bandwidth).In the embodiments of the present disclosure, the available resources data of each stand-by equipment
Including available computational resources data, storage resource data and available network resource data can be used.
In the embodiments of the present disclosure, task processing method provided by the embodiment of the present disclosure can by task processing system Lai
It executes, which can realize that the system can integrate in the server by way of software and/or hardware.The disclosure is real
Example is applied to be not specifically limited the specific implementation form of task processing system.
In the embodiments of the present disclosure, task processing system includes edge cloud management platform, equipment screening module and network control
Molding block.
In the embodiments of the present disclosure, stand-by equipment can be intelligent hardware devices, for example, intelligent hardware devices are intelligent network
Pass, intelligent sound, intelligence Wifi etc..Enterprise or operator etc. can release certain resource-sharing reward mechanism, encourage personal
User shares out the part resource (such as computing resource, storage resource, Internet resources) for meeting the intelligent hardware devices of its requirement
Come, enterprise, operator can be using these intelligent hardware devices as the stand-by equipment of its fringe node disposed, and according to a
The factors such as resource capability size, shared time span that people user shares give personal user in the order of edge service
Certain is preferential.
After determining the intelligent hardware devices (stand-by equipment) that personal user shares, edge cloud management platform can be by institute
All fringe nodes of deployment and all intelligent hardware devices (stand-by equipment) of user sharing are numbered respectively, obtain each
The device numbering of the node serial number of fringe node and each stand-by equipment, meanwhile, by each fringe node and its intelligence that can be dispatched
Energy hardware device (stand-by equipment) is matched, and one-to-many resource database is established, and includes each edge in resource database
The corresponding relationship of the device numbering of the node serial number of node and multiple intelligent hardware devices, wherein each intelligent hardware devices are (standby
With equipment) device numbering be correspondingly arranged multiple attribute fields, for record the intelligent hardware devices (stand-by equipment) can with money
The facility informations such as source data, IP address, port.
Table 1 shows the corresponding relationship of the node serial number of a fringe node and the device numbering of multiple stand-by equipments, with
For node serial number is the fringe node of ID11, as shown in table 1, in resource database, the fringe node is corresponding spare to be set
It is standby be it is multiple, the device numbering of multiple stand-by equipment be respectively ID21, ID22 ..., ID2n, attribute field 1 is standby for recording
With the available computational resources data of equipment, attribute field 2 is used to record the available storage resource data of stand-by equipment, attribute field
3 for recording the available network resource data of stand-by equipment, and attribute field 4 is used to record the IP address of stand-by equipment, attribute word
Section 5 is for recording the port of stand-by equipment.
Table 1
In the embodiments of the present disclosure, cloud management platform in edge can monitor the load of the specific resources of each fringe node, and
Monitoring transmission gives the new task of each fringe node.In a step 11, for each fringe node, when edge cloud management platform judges
The load of the specific resources of the fringe node reaches preset threshold out, and receive be sent to the fringe node have specific money
When the new task of source demand, edge cloud management platform calculates the specific resources demand of the new task, and from preset resource data
The corresponding device numbering list of the fringe node is transferred in library, wherein device numbering list includes that the fringe node is corresponding more
The device numbering of a stand-by equipment, and the corresponding device numbering list of the fringe node and the new post are sent to equipment screening module
The specific resources demand of business.
Equipment screening module receives the corresponding device numbering list of the fringe node and the specific resources of the new task and needs
After asking, according to the device numbering of each stand-by equipment in the device numbering list, the edge is obtained from preset resource database
The corresponding stand-by equipment list of node.
In the embodiments of the present disclosure, specific resources can be computing resource or storage resource, the specific money of the new task
Source demand includes computational resource requirements or storage resource demands.
In the embodiments of the present disclosure, if specific resources are computing resource, the load of specific resources can be computing resource
Utilization rate (such as cpu busy percentage, memory usage), the available computational resources data of stand-by equipment can be the stand-by equipment institute
The surplus of shared computing resource, wherein the surplus of computing resource can be according to the total amount and utilization rate meter of computing resource
It obtains;If the load of specific resources is storage resource, the load of specific resources can be utilization rate (such as magnetic of storage resource
Disk utilization rate), the surplus for the storage resource that the available storage resource data of stand-by equipment can be shared for the stand-by equipment,
Wherein, the surplus of storage resource can be calculated according to the total amount and utilization rate of storage resource.In the embodiments of the present disclosure,
The rate for the network bandwidth that the available network resource data of stand-by equipment can be shared for the stand-by equipment.
In the embodiments of the present disclosure, preset threshold can be set to 80%, can specifically be configured according to actual needs, this
Open embodiment to this with no restriction.
Table 2 shows the corresponding stand-by equipment list of the fringe node, and as shown in table 2, the fringe node is corresponding each standby
With the device numbering of equipment be respectively ID21, ID22 ..., ID2n, the available calculating of the corresponding each stand-by equipment of the fringe node
Resource data is respectively a1、a2、…、an, the available storage resource data of the corresponding each stand-by equipment of the fringe node are respectively
c1、c2、…、cn, the available network resource data of the corresponding each stand-by equipment of the fringe node are respectively b1、b2、…、bn, according to this
Analogize.
Table 2
Step 12, according in the specific resources demand and above-mentioned stand-by equipment list of the new task each stand-by equipment it is available
Resource data determines the stand-by equipment for being used to handle the new task from stand-by equipment list.
In step 12, equipment screening module is getting the corresponding stand-by equipment list of the fringe node and the new task
Specific resources demand after, according in the specific resources demand of the new task and above-mentioned stand-by equipment list each stand-by equipment can
With resource data, the stand-by equipment for being used to handle the new task is determined from stand-by equipment list.
Fig. 2 is a kind of flow chart of specific embodiment of step 12 in the embodiment of the present disclosure, as shown in Fig. 2, some
In embodiment, step 12 includes:
Step 121, according to the specific resources demand of the new task and the available resources data of each stand-by equipment, set from spare
Determine that available resources data can satisfy the stand-by equipment of the specific resources demand of the new task in standby list, generation can be used standby
Use list of devices.
In step 121, equipment screening module is according to the specific resources demand of the new task and can be used for each stand-by equipment
Resource data determines that available resources data can satisfy the stand-by equipment of specific resources demand of the new task, generates available
Stand-by equipment list.Wherein, available backup list of devices includes the specific resources that available resources data can satisfy the new task
The device numbering of the stand-by equipment of demand and corresponding available resources data.
Fig. 3 is a kind of flow chart of specific embodiment of step 121 in the embodiment of the present disclosure, as shown in figure 3, some
In embodiment, specific resources are computing resource, and the specific resources demand of the new task includes computational resource requirements, step 121 packet
It includes:
Step 1211a, according to the available resources data of the computational resource requirements of the new task and each stand-by equipment, from spare
The available computational resources data and available network resource data of each stand-by equipment are extracted in list of devices, generate the first available money
Source list.
In step 1211a, equipment screening module can according to the computational resource requirements of the new task and each stand-by equipment
With resource data, the available computational resources data and available network resource number of each stand-by equipment are extracted from stand-by equipment list
According to the first list of available resources of generation.
Wherein, the first list of available resources includes the device numbering of each stand-by equipment, corresponding available computational resources data
With corresponding available network resource data.
Table 3 shows a kind of first list of available resources, and as shown in table 3, the first list of available resources includes each spare sets
Available computational resources data (a of standby device numbering (ID21, ID22 ..., ID2n), each stand-by equipment1、a2、…、an) and it is each
Available network resource data (the b of stand-by equipment1、b2、…、bn)。
Table 3
Step 1211b, the calculating money that available computational resources data in the first list of available resources are unsatisfactory for new task is rejected
The stand-by equipment of source demand obtains the first new list of available resources.
In step 1211b, for each stand-by equipment in the first list of available resources, if equipment screening module is sentenced
When the available computational resources data of the disconnected stand-by equipment out are not able to satisfy the computational resource requirements of the new task, by the stand-by equipment
It is rejected from the first list of available resources, that is, rejects the device numbering of the stand-by equipment in the first list of available resources, corresponding
The first new list of available resources can be obtained according to this in available computational resources data and corresponding available network resource data.
It is understood that if in the first list of available resources each stand-by equipment the equal energy of available computational resources data
Enough meet the computational resource requirements of the new task, then the data in the first list of available resources are constant, new first in this step
List of available resources is still the first list of available resources generated in step 1211a.
For example, as shown in table 3, in step 1211b, it is assumed that the available computational resources data of the corresponding stand-by equipment of ID21
a1Be not able to satisfy the computational resource requirements of the new task, then by the device numbering ID21 of the corresponding stand-by equipment of ID21, can use tricks
Calculate resource data a1, available network resource data b1It is rejected from the first list of available resources, to form the available money of new first
Source list.
In the embodiments of the present disclosure, computational resource requirements can be demand of the new task to computing resource, stand-by equipment
The surplus of computing resource that can be shared by stand-by equipment of available computational resources data, can when judge stand-by equipment
When with calculating computational resource requirements of the resource data less than the new task, then it is assumed that the available computational resources data of the stand-by equipment
It is not able to satisfy the computational resource requirements of the new task, otherwise it is assumed that the available computational resources data of the stand-by equipment can satisfy this
The computational resource requirements of new task.
Step 1211c, according to the first new list of available resources, available backup list of devices is generated, which sets
Standby list is the first new list of available resources.
In step 1211c, equipment screening module generates available backup equipment column according to the first new list of available resources
Table.Wherein, which is the first new list of available resources, i.e. the available backup list of devices is to reject
Available computational resources data are not able to satisfy the first list of available resources after the stand-by equipment of the computational resource requirements of new task.That
It can be appreciated that the available backup list of devices includes the standby of the computational resource requirements that available computational resources data meet new task
With the device numbering of equipment, corresponding available computational resources data and corresponding available network resource data.
Fig. 4 is the flow chart of another specific embodiment of step 121 in the embodiment of the present disclosure, as shown in figure 4, one
In a little embodiments, specific resources are storage resource, and the specific resources demand of the new task includes storage resource demands, step 121
Include:
Step 1212a, according to the available resources data of the storage resource demands of the new task and each stand-by equipment, from spare
The available storage resource data and available network resource data of each stand-by equipment are extracted in list of devices, generate the second available money
Source list.
In step 1212a, equipment screening module can according to the storage resource demands of the new task and each stand-by equipment
With resource data, the available storage resource data and available network resource number of each stand-by equipment are extracted from stand-by equipment list
According to the second list of available resources of generation.
Wherein, the second list of available resources includes the device numbering of each stand-by equipment, corresponding available storage resource data
With corresponding available network resource data.
Table 4 shows a kind of second list of available resources, and as shown in table 3, the second list of available resources includes each spare sets
The available storage resource data (c of standby device numbering (ID21, ID22 ..., ID2n), each stand-by equipment1、c2、…、cn) and it is each
Available network resource data (the b of stand-by equipment1、b2、…、bn)。
Table 4
Step 1212b, the storage money that can be unsatisfactory for new task in the second list of available resources with storage resource data is rejected
The stand-by equipment of source demand obtains the second new list of available resources.
In step 1212b, for each stand-by equipment in the second list of available resources, if equipment screening module is sentenced
When the available storage resource data of the disconnected stand-by equipment out are not able to satisfy the storage resource demands of the new task, by the stand-by equipment
It is rejected from the second list of available resources, that is, rejects the device numbering of the stand-by equipment in the second list of available resources, corresponding
The second new list of available resources can be obtained according to this with storage resource data and corresponding available network resource data.
It is understood that if in the second list of available resources each stand-by equipment the available equal energy of storage resource data
Enough meet the storage resource demands of the new task, then the data in the second list of available resources are constant, new second in this step
List of available resources is still the second list of available resources generated in step 1212a.
For example, as shown in table 4, in step 1212b, it is assumed that the available storage resource data of the corresponding stand-by equipment of ID21
c1Be not able to satisfy the storage resource demands of the new task, then by the device numbering ID21 of the corresponding stand-by equipment of ID21, available deposit
Store up resource data c1, available network resource data b1It is rejected from the second list of available resources, to form the available money of new second
Source list.
In the embodiments of the present disclosure, storage resource demands can be demand of the new task to storage resource, stand-by equipment
The surplus of storage resource that can be shared by stand-by equipment of available storage resource data, can when judge stand-by equipment
When being less than the storage resource demands of the new task with storage resource data, then it is assumed that the available storage resource data of the stand-by equipment
It is not able to satisfy the storage resource demands of the new task, otherwise it is assumed that the available storage resource data of the stand-by equipment can satisfy this
The storage resource demands of new task.
Step 1212c, according to the second new list of available resources, available backup list of devices is generated, which sets
Standby list is the second new list of available resources.
In step 1212c, equipment screening module generates available backup equipment column according to the second new list of available resources
Table.Wherein, which is the second new list of available resources, i.e. the available backup list of devices is to reject
The second list of available resources after the stand-by equipment for the storage resource demands that new task can not be able to satisfy with storage resource data.That
It can be appreciated that the available backup list of devices includes the standby of the storage resource demands that available storage resource data meet new task
With the device numbering of equipment, corresponding available storage resource data and corresponding available network resource data.
Step 122 determines the stand-by equipment for being used to handle new task from available backup list of devices.
In step 122, equipment screening module determines that one is used to handle new task from available backup list of devices
Stand-by equipment, when in available backup list of devices only include a stand-by equipment when, then the stand-by equipment is determined as being used for
The stand-by equipment for handling the new task, when in available backup list of devices including multiple stand-by equipments, from available backup equipment
The stand-by equipment for being used to handle new task is determined in list.
According to the description of abovementioned steps 121, if specific resources are computing resource, the specific resources demand of new task includes meter
When calculating resource requirement, then the available backup list of devices in step 121 includes that available computational resources data can satisfy the new post
The device numbering of the stand-by equipment of the computational resource requirements of business, corresponding available computational resources data and corresponding available network money
Source data;If specific resources are storage resource, when the specific resources demand of new task includes storage resource demands, then step 121
In available backup list of devices include the spare of storage resource demands that available storage resource data can satisfy the new task
The device numbering of equipment, corresponding available storage resource data and corresponding available network resource data.
Fig. 5 is a kind of flow chart of specific embodiment of step 122 in the embodiment of the present disclosure, as shown in figure 5, some
In embodiment, specific resources are computing resource, and the specific resources demand of new task includes computational resource requirements, available backup equipment
List includes the device numbering, right of the stand-by equipment for the computational resource requirements that available computational resources data can satisfy the new task
The available computational resources data and corresponding available network resource data, step 122 answered include:
Step 1221a, for each stand-by equipment in available backup list of devices, according in available backup list of devices
The available computational resources data of each stand-by equipment are normalized the available computational resources data of the stand-by equipment, obtain
To the corresponding computing resource normalized value of available computational resources data of the stand-by equipment.
In step 1221a, equipment screening module is for each stand-by equipment in available backup list of devices, according to can
With the available computational resources data of stand-by equipment each in stand-by equipment list, to the available computational resources data of the stand-by equipment into
Row normalized obtains the corresponding computing resource normalized value of available computational resources data of the stand-by equipment.It obtains as a result,
The corresponding computing resource normalized value of the available computational resources data of each stand-by equipment in available backup list of devices.
Specifically, it is assumed that available backup list of devices is the first list of available resources shown in table 3, then in step 1221a
In, equipment screening module for i-th of stand-by equipment in available backup list of devices, according to i-th of stand-by equipment can
With the available computational resources data and computing resource normalizing of each stand-by equipment in calculating resource data, available backup list of devices
Change value formula:The corresponding computing resource normalization of available computational resources data of the stand-by equipment is calculated
Value.Wherein, aiIndicate the available computational resources data of i-th of stand-by equipment,It indicates in available backup list of devices
The sum of available computational resources data of each stand-by equipment, AiIndicate that the available computational resources data of i-th of stand-by equipment are corresponding
Computing resource normalized value.Thus, it is possible to which the available calculating of each stand-by equipment in available backup list of devices is calculated
The corresponding computing resource normalized value of resource data, the available computational resources number of each stand-by equipment in available backup list of devices
It is respectively A according to corresponding computing resource normalized value1、A2、…、Ai、…、An。
Step 1221b, for each stand-by equipment in available backup list of devices, according in available backup list of devices
The available network resource data of each stand-by equipment are normalized the available network resource data of the stand-by equipment, obtain
To the corresponding Internet resources normalized value of available network resource data of the stand-by equipment.
In step 1221b, equipment screening module is for each stand-by equipment in available backup list of devices, according to can
With the available network resource data of stand-by equipment each in stand-by equipment list, to the available network resource data of the stand-by equipment into
Row normalized obtains the corresponding Internet resources normalized value of available network resource data of the stand-by equipment.It obtains as a result,
The corresponding Internet resources normalized value of the available network resource data of each stand-by equipment in available backup list of devices.
Specifically, it is assumed that available backup list of devices is the first list of available resources shown in table 3, then in step 1221b
In, equipment screening module for i-th of stand-by equipment in available backup list of devices, according to i-th of stand-by equipment can
With the available network resource data and Internet resources normalizing of each stand-by equipment in network resource data, available backup list of devices
Change value formula:The corresponding computing resource normalization of available network resource data of the stand-by equipment is calculated
Value.Wherein, biIndicate the available network resource data of i-th of stand-by equipment,It indicates in available backup list of devices
The sum of available network resource data of each stand-by equipment, BiIndicate that the available network resource data of i-th of stand-by equipment are corresponding
Internet resources normalized value.Thus, it is possible to which the available network of each stand-by equipment in available backup list of devices is calculated
The corresponding Internet resources normalized value of resource data, the available network resource number of each stand-by equipment in available backup list of devices
It is respectively B according to corresponding Internet resources normalized value1、B2、…、Bi、…、Bn。
Step 1221c, for each stand-by equipment in available backup list of devices, according to preset first scoring mould
Type, the corresponding computing resource normalized value of available computational resources data of the stand-by equipment and the available network of the stand-by equipment
The corresponding Internet resources normalized value of resource data generates corresponding first score value of the stand-by equipment.
In step 1221c, equipment screening module is for each stand-by equipment in available backup list of devices, according to pre-
If the first Rating Model, the stand-by equipment the corresponding computing resource normalized value of available computational resources data and this is spare
The corresponding Internet resources normalized value of the available network resource data of equipment generates corresponding first score value of the stand-by equipment.
Corresponding first score value of each stand-by equipment in available backup list of devices is obtained as a result,.
In the embodiments of the present disclosure, preset first Rating Model includes: the first score value formula: Pi=k1*Ai+k2*Bi。
Wherein, PiIndicate corresponding first score value of i-th of stand-by equipment in available backup list of devices, AiIndicate available backup equipment
The corresponding computing resource normalized value of the available computational resources data of i-th of stand-by equipment, B in listiIndicate that available backup is set
The corresponding Internet resources normalized value of available network resource data of i-th of stand-by equipment, k in standby list1Indicate computing resource
The corresponding weighted value of normalized value, k2Indicate the corresponding weighted value of Internet resources normalized value, k1+k2=1, and k1Greater than k2, example
Such as, k1=0.8, k2=0.2.It is commented thus, it is possible to which each stand-by equipment in available backup list of devices corresponding first is calculated
Score value, corresponding first score value of each stand-by equipment is respectively P in available backup list of devices1、P2、…、Pi、…、Pn。
Step 1221d, according to corresponding first score value of each stand-by equipment in available backup list of devices, first is commented
The highest stand-by equipment of score value is determined as the stand-by equipment for handling new task.
In step 1221d, equipment screening module is according to each stand-by equipment in available backup list of devices corresponding
The highest stand-by equipment of first score value is determined as being used to handle the stand-by equipment of the new task by one score value.
In some embodiments, the quantity of the highest stand-by equipment of the first score value is multiple, that is, has two or two
Corresponding first score value of above stand-by equipment is identical and highest, then will be any in the highest multiple stand-by equipments of the first score value
One is determined as the stand-by equipment for handling the new task.
Fig. 6 is the flow chart of another specific embodiment of step 122 in the embodiment of the present disclosure, as shown in fig. 6, one
In a little embodiments, specific resources are storage resource, and the specific resources demand of new task includes storage resource demands, and available backup is set
Standby list include the stand-by equipment for the storage resource demands that available storage resource data can satisfy the new task device numbering,
Corresponding available storage resource data and corresponding available network resource data, step 122 include:
Step 1222a, for each stand-by equipment in available backup list of devices, according in available backup list of devices
The available storage resource data of each stand-by equipment are normalized the available storage resource data of the stand-by equipment, obtain
To the corresponding storage resource normalized value of available storage resource data of the stand-by equipment.
In step 1222a, equipment screening module is for each stand-by equipment in available backup list of devices, according to can
With the available storage resource data of stand-by equipment each in stand-by equipment list, to the available storage resource data of the stand-by equipment into
Row normalized obtains the corresponding storage resource normalized value of available storage resource data of the stand-by equipment.It obtains as a result,
The corresponding storage resource normalized value of available storage resource data of each stand-by equipment in available backup list of devices.
Specifically, it is assumed that available backup list of devices is the second list of available resources shown in table 4, then in step 1222a
In, equipment screening module for i-th of stand-by equipment in available backup list of devices, according to i-th of stand-by equipment can
With the available storage resource data and storage resource normalizing of each stand-by equipment in storage resource data, available backup list of devices
Change value formula:The corresponding storage resource normalization of available storage resource data of the stand-by equipment is calculated
Value.Wherein, ciIndicate the available storage resource data of i-th of stand-by equipment,It indicates in available backup list of devices
The sum of available storage resource data of each stand-by equipment, CiIndicate that the available storage resource data of i-th of stand-by equipment are corresponding
Storage resource normalized value.Thus, it is possible to which the available storage of each stand-by equipment in available backup list of devices is calculated
The corresponding storage resource normalized value of resource data, the available storage resource number of each stand-by equipment in available backup list of devices
It is respectively C according to corresponding storage resource normalized value1、C2、…、Ci、…、Cn。
Step 1222b, for each stand-by equipment in available backup list of devices, according in available backup list of devices
The available network resource data of each stand-by equipment are normalized the available network resource data of the stand-by equipment, obtain
To the corresponding Internet resources normalized value of available network resource data of the stand-by equipment.
In the embodiments of the present disclosure, it can be found in the above-mentioned description to step 1221b about the specific descriptions of step 1222b,
Details are not described herein again.
Step 1222c, for each stand-by equipment in available backup list of devices, according to preset second scoring mould
Type, the available corresponding storage resource normalized value of storage resource data of the stand-by equipment and the available network of the stand-by equipment
The corresponding Internet resources normalized value of resource data generates corresponding second score value of the stand-by equipment.
In step 1222c, equipment screening module is for each stand-by equipment in available backup list of devices, according to pre-
If the second Rating Model, the stand-by equipment the corresponding storage resource normalized value of available storage resource data and this is spare
The corresponding Internet resources normalized value of the available network resource data of equipment generates corresponding second score value of the stand-by equipment.
Corresponding second score value of each stand-by equipment in available backup list of devices is obtained as a result,.
In the embodiments of the present disclosure, preset second Rating Model includes: the second score value formula: Qi=k3*Ci+k2*Bi;
Wherein, QiIndicate corresponding second score value of i-th of stand-by equipment in available backup list of devices, CiIndicate available backup equipment
The corresponding storage resource normalized value of available storage resource data of i-th of stand-by equipment, B in listiIndicate that available backup is set
The corresponding Internet resources normalized value of available network resource data of i-th of stand-by equipment, k in standby list3Indicate storage resource
The corresponding weighted value of normalized value, k2Indicate the corresponding weighted value of Internet resources normalized value, k3+k2=1, and k3Greater than k2, example
Such as, k3=0.8, k2=0.2.It is commented thus, it is possible to which each stand-by equipment in available backup list of devices corresponding second is calculated
Score value, corresponding second score value of each stand-by equipment is respectively Q in available backup list of devices1、Q2、…、Qi、…、Qn。
Step 1222d, according to corresponding second score value of each stand-by equipment in available backup list of devices, second is commented
The highest stand-by equipment of score value is determined as the stand-by equipment for handling new task.
In step 1222d, equipment screening module is according to each stand-by equipment in available backup list of devices corresponding
Two score values are determined as the highest stand-by equipment of the second score value to be used to handle the stand-by equipment of new task.
In some embodiments, the quantity of the highest stand-by equipment of the second score value is multiple, that is, has two or two
Corresponding second score value of above stand-by equipment is identical and highest, then will be any in the highest multiple stand-by equipments of the second score value
One is determined as the stand-by equipment for handling the new task.
The stand-by equipment that step 13, Xiang Shangshu are determined sends the new task.
In the embodiments of the present disclosure, network control module sends this newly to the above-mentioned stand-by equipment determined by interchanger
Task.
Specifically, before network control module sends the new task to the above-mentioned stand-by equipment determined by interchanger,
For equipment screening module after determining that one is used to handle the stand-by equipment of new task, equipment screening module is flat to edge cloud management
The device numbering for the stand-by equipment that platform feedback is determined.
Then, cloud management platform in edge inquires the device numbering pair according to the device numbering of the stand-by equipment determined
The IP address for the stand-by equipment answered and port, and the task of the device numbering of the stand-by equipment determined, the new task is compiled
Number, the port of the IP address of the node serial number of the fringe node, the stand-by equipment determined, the stand-by equipment determined hair
Give network control module.
In the embodiments of the present disclosure, above-mentioned network control module is software defined network (Software Defined
Network, referred to as: SDN) control module, SDN control module includes SDN controller, and above-mentioned interchanger is SDN switch.
Network control module receive edge cloud management platform transmission the stand-by equipment determined device numbering,
The mission number of the new task, the node serial number of the fringe node, the stand-by equipment determined IP address, this determines
Behind the port of stand-by equipment, the SDN controller in network control module issues corresponding flow table to SDN switch, for SDN friendship
Change planes according to the flow table, the IP address of the stand-by equipment determined, the stand-by equipment determined port, by mission number
Corresponding new task is transmitted to the corresponding stand-by equipment of device numbering.
Step 14, the task processing result for receiving the stand-by equipment determined return, and sending to the fringe node should
Task processing result.
In the embodiments of the present disclosure, it after the completion of the stand-by equipment determined is to new task processing, is exchanged by SDN
Task processing result to the new task is returned to network control module by machine.
After network control module receives the task processing result of the stand-by equipment determined return, network control module
The task processing result is sent to the corresponding fringe node of node serial number that above-mentioned edge connects node by middle SDN controller.
In the embodiments of the present disclosure, by realizing opposite side using various intelligent hardware devices (stand-by equipment) shared resource
Edge node carries out the purpose of dilatation, for each fringe node, when the load for the specific resources for judging the fringe node reaches
Preset threshold, and when receiving the new task with specific resources demand for being sent to the fringe node, which is forwarded
It can be used for handling the stand-by equipment of the new task to the fringe node corresponding one, to expand without large-scale resource
In the case where appearance, the load of fringe node busy is reduced as far as possible.
Task processing method provided by the embodiment of the present disclosure, for each fringe node, when judging the fringe node
The loads of specific resources reach preset threshold, and receive the new post with specific resources demand for being sent to the fringe node
When business, which is transmitted to the corresponding stand-by equipment that can be used for handling the new task of the fringe node, on the one hand,
The resource utilization that can effectively improve intelligent hardware devices (stand-by equipment) avoids the money of intelligent hardware devices (stand-by equipment)
On the other hand source waste can effectively reduce the load of fringe node busy.
Fig. 7 is the flow chart for another task processing method that the embodiment of the present disclosure provides, as shown in fig. 7, at the task
Reason method includes:
Step 21 is directed to each fringe node, and when edge, cloud management platform judges the specific resources of the fringe node
When loading and reach preset threshold, and receiving the new task with specific resources demand for being sent to the fringe node, edge cloud
Management platform obtains the specific resources demand of the fringe node corresponding device numbering list and the new task.
Wherein, device numbering list includes the device numbering of the corresponding multiple stand-by equipments of the fringe node.
Step 22, edge cloud management platform to equipment screening module send the corresponding device numbering list of the fringe node and
The specific resources demand of the new task.
Step 23, equipment screening module obtain the side according to the device numbering of each stand-by equipment in the device numbering list
The corresponding stand-by equipment list of edge node.
Wherein, stand-by equipment list includes at least each stand-by equipment in the fringe node corresponding multiple stand-by equipments and sets
The available resources data of standby number and each stand-by equipment.
Step 24, equipment screening module are according to each standby in the specific resources demand and above-mentioned stand-by equipment list of the new task
With the available resources data of equipment, the stand-by equipment for being used to handle the new task is determined from stand-by equipment list.
The device numbering for the stand-by equipment that step 25, equipment screening module are determined to edge cloud management platform feedback.
Step 26, edge cloud management platform according to by the device numbering of the stand-by equipment determined, the new task appoint
The end of business number, the node serial number of the fringe node, the IP address of the stand-by equipment determined, the stand-by equipment determined
Mouth is sent to network control module.
Step 27, network control module issue corresponding according to the above- mentioned information received from edge cloud management platform
Flow table is to interchanger.
The new task is transmitted to the stand-by equipment determined according to the flow table by step 28, interchanger.
Step 29, the stand-by equipment determined are after having handled the new task, by interchanger by task processing result
Return to network control module.
The task processing result is returned to the corresponding fringe node of above-mentioned node serial number by step 30, network control module.
In addition, other specific descriptions about the embodiment of the present disclosure, reference can be made to task processing method in above-described embodiment
Specific descriptions, details are not described herein again.
Fig. 8 is a kind of structural schematic diagram for task processing system that the embodiment of the present disclosure provides, as shown in figure 8, the task
Processing system includes: edge cloud management platform 301, equipment screening module 302, network control module 303.
Wherein, edge cloud management platform 301 is used to be directed to each fringe node, judges the specific resources of the fringe node
Whether load reaches preset threshold, and judges whether to receive the new post with specific resources demand for being sent to the fringe node
Business.
Equipment screening module 302 is used to be directed to each fringe node, and at edge, cloud management platform 301 judges the edge section
The load of specific resources of point reaches preset threshold, and when judging to receive the new task with specific resources demand, obtains
The corresponding stand-by equipment list of the fringe node, the stand-by equipment list include the corresponding multiple stand-by equipments of the fringe node
In the device numbering of each stand-by equipment and the available resources data of each stand-by equipment;According to the specific resources need of the new task
It sums the available resources data of each stand-by equipment in the stand-by equipment list, determines one from the stand-by equipment list
For handling the stand-by equipment of the new task.
Network control module 303 is used to send the new task to the stand-by equipment determined;Receive this determine it is standby
The task processing result returned with equipment, and the task processing result is sent to the fringe node.
In some embodiments, equipment screening module 302 be specifically used for according to the specific resources demand of the new task and
It is described new to determine that available resources data can satisfy from the stand-by equipment list for the available resources data of each stand-by equipment
The stand-by equipment of the specific resources demand of task generates available backup list of devices;From the available backup list of devices really
One is made for handling the stand-by equipment of the new task.
In the embodiments of the present disclosure, the available resources data include available computational resources data, can use storage resource number
According to available network resource data.
In some embodiments, if the specific resources are computing resource, the specific resources demand of the new task includes
When computational resource requirements, equipment screening module 302 is specifically used for according to the computational resource requirements of the new task and each spare sets
Standby available resources data extract the available computational resources data of each stand-by equipment and be can be used from the stand-by equipment list
Network resource data, generates the first list of available resources, and first list of available resources includes that the equipment of each stand-by equipment is compiled
Number, corresponding available computational resources data and corresponding available network resource data;It rejects in first list of available resources
Available computational resources data are unsatisfactory for the stand-by equipment of the computational resource requirements of the new task, obtain the first new available resources
List;According to the first new list of available resources, the available backup list of devices is generated, the available backup list of devices is
The first new list of available resources.
In some embodiments, equipment screening module 302 is specifically used for standby for each of available backup list of devices
With equipment, according to the available computational resources data of each stand-by equipment in the available backup list of devices, to the stand-by equipment
Available computational resources data are normalized, and obtain the corresponding computing resource of available computational resources data of the stand-by equipment
Normalized value;For each stand-by equipment in available backup list of devices, according to each standby in the available backup list of devices
With the available network resource data of equipment, the available network resource data of the stand-by equipment are normalized, are somebody's turn to do
The corresponding Internet resources normalized value of the available network resource data of stand-by equipment;For in the available backup list of devices
Each stand-by equipment is provided according to the corresponding calculating of the available computational resources data of preset first Rating Model, the stand-by equipment
The corresponding Internet resources normalized value of the available network resource data of source normalized value and the stand-by equipment generates this and spare sets
Standby corresponding first score value;It, will according to corresponding first score value of each stand-by equipment in the available backup list of devices
The highest stand-by equipment of first score value is determined as the stand-by equipment for handling the new task.
In some embodiments, preset first Rating Model includes: the first score value formula: Pi=k1*Ai+k2*Bi;Its
In, PiIndicate corresponding first score value of i-th of stand-by equipment, A in the available backup list of devicesiIt can be with standby described in expression
With the corresponding computing resource normalized value of the available computational resources data of i-th of stand-by equipment in list of devices, BiDescribed in expression
The corresponding Internet resources normalized value of the available network resource data of i-th of stand-by equipment, k in available backup list of devices1Table
Show the corresponding weighted value of computing resource normalized value, k2Indicate the corresponding weighted value of Internet resources normalized value, k1+k2=1, and
k1Greater than k2。
In some embodiments, if the specific resources are storage resource, the specific resources demand of the new task includes
When storage resource demands, equipment screening module 302 is specifically used for according to the storage resource demands of the new task and each spare sets
Standby available resources data extract the available storage resource data of each stand-by equipment and be can be used from the stand-by equipment list
Network resource data, generates the second list of available resources, and second list of available resources includes that the equipment of each stand-by equipment is compiled
Number, corresponding available storage resource data and corresponding available network resource data;It rejects in second list of available resources
It can be unsatisfactory for the stand-by equipment of the storage resource demands of the new task with storage resource data, obtain the second new available resources
List;According to the second new list of available resources, the available backup list of devices is generated, the available backup list of devices is
The second new list of available resources.
In some embodiments, equipment screening module 302 is specifically used for standby for each of available backup list of devices
With equipment, according to the available storage resource data of each stand-by equipment in the available backup list of devices, to the stand-by equipment
It can be normalized with storage resource data, obtain the corresponding storage resource of available storage resource data of the stand-by equipment
Normalized value;For each stand-by equipment in available backup list of devices, according to each standby in the available backup list of devices
With the available network resource data of equipment, the available network resource data of the stand-by equipment are normalized, are somebody's turn to do
The corresponding Internet resources normalized value of the available network resource data of stand-by equipment;For in the available backup list of devices
Each stand-by equipment is provided according to the corresponding storage of the available storage resource data of preset second Rating Model, the stand-by equipment
The corresponding Internet resources normalized value of the available network resource data of source normalized value and the stand-by equipment generates this and spare sets
Standby corresponding second score value;It, will according to corresponding second score value of each stand-by equipment in the available backup list of devices
The highest stand-by equipment of second score value is determined as the stand-by equipment for handling the new task.
In some embodiments, preset second Rating Model includes: the second score value formula: Qi=k3*Ci+k2*Bi;Its
In, QiIndicate corresponding second score value of i-th of stand-by equipment, C in the available backup list of devicesiIt can be with standby described in expression
With the corresponding storage resource normalized value of available storage resource data of i-th of stand-by equipment in list of devices, BiDescribed in expression
The corresponding Internet resources normalized value of the available network resource data of i-th of stand-by equipment, k in available backup list of devices3Table
Show the corresponding weighted value of storage resource normalized value, k2Indicate the corresponding weighted value of Internet resources normalized value, k3+k2=1, and
k3Greater than k2。
In addition, task processing system provided by the embodiment of the present disclosure, for realizing provided by aforementioned any embodiment
Task processing method specifically describes the description that can be found in aforementioned any embodiment, and details are not described herein again.
It is understood that the principle that embodiment of above is intended to be merely illustrative of the present and the exemplary implementation that uses
Mode, however the present invention is not limited thereto.For those skilled in the art, essence of the invention is not being departed from
In the case where mind and essence, various changes and modifications can be made therein, these variations and modifications are also considered as protection scope of the present invention.
Claims (14)
1. a kind of task processing method characterized by comprising
For each fringe node, when the load for the specific resources for judging the fringe node reaches preset threshold, and receive
When being sent to the new task with specific resources demand of the fringe node, obtains the specific resources demand of the new task and be somebody's turn to do
The corresponding stand-by equipment list of fringe node, the stand-by equipment list include at least that the fringe node is corresponding multiple spare to be set
The device numbering of each stand-by equipment and the available resources data of each stand-by equipment in standby;
According to the available resources data of each stand-by equipment in the specific resources demand of the new task and the stand-by equipment list,
The stand-by equipment for being used to handle the new task is determined from the stand-by equipment list;
The new task is sent to the stand-by equipment determined;
The task processing result of the stand-by equipment determined return is received, and sends the task processing knot to the fringe node
Fruit.
2. task processing method according to claim 1, which is characterized in that the specific resources according to the new task
The available resources data of each stand-by equipment, determine one from the stand-by equipment list in demand and the stand-by equipment list
A stand-by equipment for being used to handle the new task, comprising:
According to the available resources data of the specific resources demand of the new task and each stand-by equipment, from the stand-by equipment list
In determine that available resources data can satisfy the stand-by equipment of the specific resources demand of the new task, generate available backup and set
Standby list;
The stand-by equipment for being used to handle the new task is determined from the available backup list of devices.
3. task processing method according to claim 2, which is characterized in that the available resources data include available calculate
Resource data can use storage resource data and available network resource data;
If the specific resources are computing resource, described when the specific resources demand of the new task includes computational resource requirements
According to the available resources data of the specific resources demand of the new task and each stand-by equipment, from the stand-by equipment list really
Making available resources data can satisfy the stand-by equipment of specific resources demand of the new task, generate available backup equipment column
Table, comprising:
According to the available resources data of the computational resource requirements of the new task and each stand-by equipment, from the stand-by equipment list
In extract the available computational resources data and available network resource data of each stand-by equipment, generate the first list of available resources,
First list of available resources include the device numbering of each stand-by equipment, corresponding available computational resources data and it is corresponding can
Use network resource data;
Reject the computational resource requirements that available computational resources data in first list of available resources are unsatisfactory for the new task
Stand-by equipment, obtain the first new list of available resources;
According to the first new list of available resources, the available backup list of devices is generated, the available backup list of devices is
The first new list of available resources.
4. task processing method according to claim 3, which is characterized in that described from the available backup list of devices
Determine the stand-by equipment for being used to handle the new task, comprising:
For each stand-by equipment in available backup list of devices, according to each stand-by equipment in the available backup list of devices
Available computational resources data, the available computational resources data of the stand-by equipment are normalized, this is obtained and spare sets
The corresponding computing resource normalized value of standby available computational resources data;
For each stand-by equipment in available backup list of devices, according to each stand-by equipment in the available backup list of devices
Available network resource data, the available network resource data of the stand-by equipment are normalized, this is obtained and spare sets
The corresponding Internet resources normalized value of standby available network resource data;
For each stand-by equipment in the available backup list of devices, according to preset first Rating Model, this spare is set
The available network resource data pair of the standby corresponding computing resource normalized value of available computational resources data and the stand-by equipment
The Internet resources normalized value answered generates corresponding first score value of the stand-by equipment;
It is according to corresponding first score value of each stand-by equipment in the available backup list of devices, the first score value is highest
Stand-by equipment is determined as the stand-by equipment for handling the new task.
5. task processing method according to claim 4, which is characterized in that preset first Rating Model includes:
First score value formula: Pi=k1*Ai+k2*Bi;
Wherein, PiIndicate corresponding first score value of i-th of stand-by equipment, A in the available backup list of devicesiDescribed in expression
The corresponding computing resource normalized value of the available computational resources data of i-th of stand-by equipment, B in available backup list of devicesiTable
Show the corresponding Internet resources normalization of the available network resource data of i-th of stand-by equipment in the available backup list of devices
Value, k1Indicate the corresponding weighted value of computing resource normalized value, k2Indicate the corresponding weighted value of Internet resources normalized value, k1+k2
=1, and k1Greater than k2。
6. task processing method according to claim 2, which is characterized in that the available resources data include available calculate
Resource data can use storage resource data and available network resource data;
If the specific resources are storage resource, described when the specific resources demand of the new task includes storage resource demands
According to the available resources data of the specific resources demand of the new task and each stand-by equipment, from the stand-by equipment list really
Making available resources data can satisfy the stand-by equipment of specific resources demand of the new task, generate available backup equipment column
Table, comprising:
According to the available resources data of the storage resource demands of the new task and each stand-by equipment, from the stand-by equipment list
In extract the available storage resource data and available network resource data of each stand-by equipment, generate the second list of available resources,
Second list of available resources include the device numbering of each stand-by equipment, corresponding available storage resource data and it is corresponding can
Use network resource data;
Reject the storage resource demands that can be unsatisfactory for the new task in second list of available resources with storage resource data
Stand-by equipment, obtain the second new list of available resources;
According to the second new list of available resources, the available backup list of devices is generated, the available backup list of devices is
The second new list of available resources.
7. task processing method according to claim 6, which is characterized in that described from the available backup list of devices
Determine the stand-by equipment for being used to handle the new task, comprising:
For each stand-by equipment in available backup list of devices, according to each stand-by equipment in the available backup list of devices
Available storage resource data, the available storage resource data of the stand-by equipment are normalized, this is obtained and spare sets
The standby corresponding storage resource normalized value of available storage resource data;
For each stand-by equipment in available backup list of devices, according to each stand-by equipment in the available backup list of devices
Available network resource data, the available network resource data of the stand-by equipment are normalized, this is obtained and spare sets
The corresponding Internet resources normalized value of standby available network resource data;
For each stand-by equipment in the available backup list of devices, according to preset second Rating Model, this spare is set
The available network resource data pair of the standby available corresponding storage resource normalized value of storage resource data and the stand-by equipment
The Internet resources normalized value answered generates corresponding second score value of the stand-by equipment;
It is according to corresponding second score value of each stand-by equipment in the available backup list of devices, the second score value is highest
Stand-by equipment is determined as the stand-by equipment for handling the new task.
8. task processing method according to claim 7, which is characterized in that preset second Rating Model includes:
Second score value formula: Qi=k3*Ci+k2*Bi;
Wherein, QiIndicate corresponding second score value of i-th of stand-by equipment, C in the available backup list of devicesiDescribed in expression
The corresponding storage resource normalized value of available storage resource data of i-th of stand-by equipment, B in available backup list of devicesiTable
Show the corresponding Internet resources normalization of the available network resource data of i-th of stand-by equipment in the available backup list of devices
Value, k3Indicate the corresponding weighted value of storage resource normalized value, k2Indicate the corresponding weighted value of Internet resources normalized value, k3+k2
=1, and k3Greater than k2。
9. a kind of task processing system characterized by comprising
Edge cloud management platform judges whether the load of the specific resources of the fringe node reaches for being directed to each fringe node
To preset threshold, and judge whether to receive the new task with specific resources demand for being sent to the fringe node;
Equipment screening module, for being directed to each fringe node, at edge, cloud management platform judges the specific of the fringe node
The load of resource reaches preset threshold, and when judging to receive the new task with specific resources demand, obtains the edge section
The corresponding stand-by equipment list of point, the stand-by equipment list includes each spare in the corresponding multiple stand-by equipments of the fringe node
The available resources data of the device numbering of equipment and each stand-by equipment;According to the specific resources demand of the new task and described
The available resources data of each stand-by equipment in stand-by equipment list determine that one is used to handle from the stand-by equipment list
The stand-by equipment of the new task;
Network control module, for sending the new task to the stand-by equipment determined;Receive the stand-by equipment determined
The task processing result of return, and the task processing result is sent to the fringe node.
10. task processing system according to claim 9, which is characterized in that the equipment screening module is specifically used for root
According to the specific resources demand of the new task and the available resources data of each stand-by equipment, determined from the stand-by equipment list
Available resources data can satisfy the stand-by equipment of the specific resources demand of the new task out, generate available backup equipment column
Table;The stand-by equipment for being used to handle the new task is determined from the available backup list of devices.
11. task processing system according to claim 10, which is characterized in that the available resources data include available meter
It calculates resource data, storage resource data and available network resource data can be used;
If the specific resources are computing resource, described when the specific resources demand of the new task includes computational resource requirements
Equipment screening module is specifically used for according to the computational resource requirements of the new task and the available resources data of each stand-by equipment, from
It extracts the available computational resources data and available network resource data of each stand-by equipment in the stand-by equipment list, generates the
One list of available resources, first list of available resources include the device numbering of each stand-by equipment, corresponding available calculating money
Source data and corresponding available network resource data;It is discontented to reject available computational resources data in first list of available resources
The stand-by equipment of the computational resource requirements of the foot new task, obtains the first new list of available resources;It can according to new first
With the Resources list, the available backup list of devices is generated, the available backup list of devices is the first new available money
Source list.
12. task processing system according to claim 11, which is characterized in that the equipment screening module is specifically used for needle
To each stand-by equipment in available backup list of devices, according in the available backup list of devices each stand-by equipment it is available
The available computational resources data of the stand-by equipment are normalized in computing resource data, and obtain the stand-by equipment can
With the corresponding computing resource normalized value of calculating resource data;For each stand-by equipment in available backup list of devices, root
According to the available network resource data of each stand-by equipment in the available backup list of devices, the available network of the stand-by equipment is provided
Source data is normalized, and obtains the corresponding Internet resources normalized value of available network resource data of the stand-by equipment;
For each stand-by equipment in the available backup list of devices, according to preset first Rating Model, the stand-by equipment
The available network resource data of the corresponding computing resource normalized value of available computational resources data and the stand-by equipment are corresponding
Internet resources normalized value generates corresponding first score value of the stand-by equipment;According in the available backup list of devices
Corresponding first score value of each stand-by equipment, is determined as the highest stand-by equipment of the first score value to be used to handle the new task
Stand-by equipment.
13. task processing system according to claim 10, which is characterized in that the available resources data include available meter
It calculates resource data, storage resource data and available network resource data can be used;
If the specific resources are storage resource, described when the specific resources demand of the new task includes storage resource demands
Equipment screening module is specifically used for according to the storage resource demands of the new task and the available resources data of each stand-by equipment, from
It extracts the available storage resource data and available network resource data of each stand-by equipment in the stand-by equipment list, generates the
Two list of available resources, second list of available resources include the device numbering of each stand-by equipment, corresponding available storage money
Source data and corresponding available network resource data;Rejecting can be discontented with storage resource data in second list of available resources
The stand-by equipment of the storage resource demands of the foot new task, obtains the second new list of available resources;It can according to new second
With the Resources list, the available backup list of devices is generated, the available backup list of devices is the second new available money
Source list.
14. task processing system according to claim 13, which is characterized in that the equipment screening module is specifically used for needle
To each stand-by equipment in available backup list of devices, according in the available backup list of devices each stand-by equipment it is available
The available storage resource data of the stand-by equipment are normalized in storage resource data, and obtain the stand-by equipment can
With the corresponding storage resource normalized value of storage resource data;For each stand-by equipment in available backup list of devices, root
According to the available network resource data of each stand-by equipment in the available backup list of devices, the available network of the stand-by equipment is provided
Source data is normalized, and obtains the corresponding Internet resources normalized value of available network resource data of the stand-by equipment;
For each stand-by equipment in the available backup list of devices, according to preset second Rating Model, the stand-by equipment
It can be corresponding with the available network resource data of the corresponding storage resource normalized value of storage resource data and the stand-by equipment
Internet resources normalized value generates corresponding second score value of the stand-by equipment;According in the available backup list of devices
Corresponding second score value of each stand-by equipment, is determined as the highest stand-by equipment of the second score value to be used to handle the new task
Stand-by equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910684012.3A CN110381159B (en) | 2019-07-26 | 2019-07-26 | Task processing method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910684012.3A CN110381159B (en) | 2019-07-26 | 2019-07-26 | Task processing method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110381159A true CN110381159A (en) | 2019-10-25 |
CN110381159B CN110381159B (en) | 2022-02-01 |
Family
ID=68256429
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910684012.3A Active CN110381159B (en) | 2019-07-26 | 2019-07-26 | Task processing method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110381159B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112988346A (en) * | 2021-02-07 | 2021-06-18 | 中国联合网络通信集团有限公司 | Task processing method, device, equipment and storage medium |
CN115562870A (en) * | 2022-10-25 | 2023-01-03 | 北京京航计算通讯研究所 | Method for constructing task node resources of cluster |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130031545A1 (en) * | 2011-07-28 | 2013-01-31 | International Business Machines Corporation | System and method for improving the performance of high performance computing applications on cloud using integrated load balancing |
KR101640231B1 (en) * | 2015-02-12 | 2016-07-18 | 소프트온넷(주) | Cloud Driving Method for supporting auto-scaled Hadoop Distributed Parallel Processing System |
US20160274953A1 (en) * | 2012-07-23 | 2016-09-22 | Adobe Systems Incorporated | Systems and Methods for Load Balancing of Time-Based Tasks in a Distributed Computing System |
CN108243246A (en) * | 2017-12-25 | 2018-07-03 | 北京市天元网络技术股份有限公司 | A kind of edge calculations resource regulating method, edge device and system |
CN109167835A (en) * | 2018-09-13 | 2019-01-08 | 重庆邮电大学 | A kind of physics resource scheduling method and system based on kubernetes |
CN109688222A (en) * | 2018-12-26 | 2019-04-26 | 深圳市网心科技有限公司 | The dispatching method of shared computing resource, shared computing system, server and storage medium |
CN109714797A (en) * | 2019-02-18 | 2019-05-03 | 南京邮电大学 | A kind of mobile edge network resource allocation methods based on Game Theory |
-
2019
- 2019-07-26 CN CN201910684012.3A patent/CN110381159B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130031545A1 (en) * | 2011-07-28 | 2013-01-31 | International Business Machines Corporation | System and method for improving the performance of high performance computing applications on cloud using integrated load balancing |
US20160274953A1 (en) * | 2012-07-23 | 2016-09-22 | Adobe Systems Incorporated | Systems and Methods for Load Balancing of Time-Based Tasks in a Distributed Computing System |
KR101640231B1 (en) * | 2015-02-12 | 2016-07-18 | 소프트온넷(주) | Cloud Driving Method for supporting auto-scaled Hadoop Distributed Parallel Processing System |
CN108243246A (en) * | 2017-12-25 | 2018-07-03 | 北京市天元网络技术股份有限公司 | A kind of edge calculations resource regulating method, edge device and system |
CN109167835A (en) * | 2018-09-13 | 2019-01-08 | 重庆邮电大学 | A kind of physics resource scheduling method and system based on kubernetes |
CN109688222A (en) * | 2018-12-26 | 2019-04-26 | 深圳市网心科技有限公司 | The dispatching method of shared computing resource, shared computing system, server and storage medium |
CN109714797A (en) * | 2019-02-18 | 2019-05-03 | 南京邮电大学 | A kind of mobile edge network resource allocation methods based on Game Theory |
Non-Patent Citations (2)
Title |
---|
TONG WANG: "Distributed Backup Resource Allocation in Fiber-Wireless (FiWi) Access Networks Supporting Mobile Edge Computing", 《2019 21ST INTERNATIONAL CONFERENCE ON TRANSPARENT OPTICAL NETWORKS (ICTON)》 * |
王璐瑶: "多用户移动边缘计算迁移的能量管理研究", 《物联网学报》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112988346A (en) * | 2021-02-07 | 2021-06-18 | 中国联合网络通信集团有限公司 | Task processing method, device, equipment and storage medium |
CN112988346B (en) * | 2021-02-07 | 2024-02-23 | 中国联合网络通信集团有限公司 | Task processing method, device, equipment and storage medium |
CN115562870A (en) * | 2022-10-25 | 2023-01-03 | 北京京航计算通讯研究所 | Method for constructing task node resources of cluster |
CN115562870B (en) * | 2022-10-25 | 2023-07-21 | 北京京航计算通讯研究所 | Task node resource construction method of cluster |
Also Published As
Publication number | Publication date |
---|---|
CN110381159B (en) | 2022-02-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113315700B (en) | Computing resource scheduling method, device and storage medium | |
CN104281496B (en) | The distribution method and distributor of virtual resource | |
CN104657220B (en) | Scheduling model and method based on deadline and expense restriction in mixed cloud | |
CN105940377A (en) | Methods, systems, and computer readable media for a cloud-based virtualization orchestrator | |
CN108733713A (en) | Data query method and device in data warehouse | |
US20220353801A1 (en) | Distributed multi-access edge service delivery | |
CN105379206B (en) | Message processing method, forwarding device and message handling system in network | |
DE102011016862A1 (en) | Queeless high performance contact center | |
CN108763389A (en) | The integration method and device of data, storage medium, terminal | |
CN110381159A (en) | Task processing method and system | |
CN110288341A (en) | Capital chain information tracing method, system, server and readable storage medium storing program for executing | |
Ellwein et al. | Production planning and control systems–a new software architecture Connectivity in target | |
CN105335376B (en) | A kind of method for stream processing, apparatus and system | |
US8443372B2 (en) | Methods and systems for partitioning data in parallel processing systems | |
CN111652652B (en) | Cost calculation method and device for calculation platform, computer equipment and storage medium | |
CN107426109A (en) | A kind of traffic scheduling method, VNF modules and flow scheduling server | |
CN108829956B (en) | Colored generalized stochastic Petri network-based IT architecture service reliability modeling method | |
Buzhin et al. | Evaluation of Telecommunication Equipment Delays in Software-Defined Networks | |
Wang et al. | Evaluation study of a proposed hadoop for data center networks incorporating optical circuit switches | |
Niño‐Mora | Conservation laws and related applications | |
Cortés-Mendoza et al. | VoIP service model for multi-objective scheduling in cloud infrastructure | |
Chen et al. | Smart futures based resource trading and coalition formation for real-time mobile data processing | |
CN110224847A (en) | Group dividing method, device, storage medium and equipment based on social networks | |
Zhang et al. | Adaptive digital twin placement and transfer in wireless computing power network | |
Outamazirt et al. | Performance analysis of the M/G/c/c+ r queuing system for cloud computing data centres |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |