CN116886696A - Cloud edge collaboration-based application deployment method and system - Google Patents
Cloud edge collaboration-based application deployment method and system Download PDFInfo
- Publication number
- CN116886696A CN116886696A CN202310900261.8A CN202310900261A CN116886696A CN 116886696 A CN116886696 A CN 116886696A CN 202310900261 A CN202310900261 A CN 202310900261A CN 116886696 A CN116886696 A CN 116886696A
- Authority
- CN
- China
- Prior art keywords
- node
- edge
- instance
- application
- group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000007717 exclusion Effects 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 230000008859 change Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 101100409014 Rhizobium meliloti (strain 1021) ppdK gene Proteins 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 235000008113 selfheal Nutrition 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
-
- 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
-
- 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
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- 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
- H04L67/56—Provisioning of proxy services
-
- 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
Abstract
The invention discloses an application deployment method and system based on cloud edge cooperation, which belong to the technical field of electric data processing, and the method comprises the following steps: establishing an edge node group based on the physical location or network deployment of the edge node; selecting a management node from the edge node group; and responding to the received application deployment instruction, and distributing a target node for the application instance through the management node. The edge node group is managed through the management node, so that the dependence on the cloud center is reduced; under the condition of disconnection from the cloud center, the edge node group and the application instance can be managed through the management node, so that high availability of the application instance is ensured; after the cloud center is re-connected, the service can be quickly recovered.
Description
Technical Field
The invention relates to the technical field of electric data processing, in particular to an application deployment method and system based on cloud edge cooperation.
Background
In cloud-edge collaboration, physical resources (edge nodes) are distributed in different geographical areas or different networks. Application programs are usually required to be deployed to edge nodes, and when the edge nodes where the application is located are abnormal, the application cannot access and respond quickly, so that the use is affected.
Along with the subsidence of the computing power of cloud edge coordination, the application can be deployed to edge nodes (servers or all-in-one machines and the like) which are closer to the user, so that the access delay of the user is reduced, and the application performance is improved. The application is managed in a unified way through the cloud, the high availability of the application depends on the stability of the communication between the cloud center and the edge network, when the application fails or is unavailable, the cloud center manager obtains the running state of the application, and then the cloud scheduler reschedules the application according to the resources and the scheduling policy of the application instance, so that the application is quickly recovered, the failure self-healing capability is achieved, and the high availability of the application is ensured. And the cloud center provides an access entry for the edge application, when the application is deployed with a plurality of instances, the designated instance is accessed through the policy of the cloud center load balancer, and when the application instance is rescheduled, the cloud load balancer synchronously updates the latest information of the application instance.
And controlling the application examples through a cloud center, and scheduling the application of different areas through the Internet or a local area network by the cloud center. When cloud computing is extended to the edge, network delay from cloud to edge can be larger, and if the cloud center is still relied on, the high-availability application scene can not be met.
Within the framework of cloud computing technology, edge applications are highly available and maintained only at the cloud, and when the cloud center loses connection with the network of edge nodes, or when an edge node fails or is unavailable, the edge node's application cannot self-heal. If the cloud center and the network of the edge node lose connection for a long time, the manager of the cloud center drives out the application instance, so that the edge resource waste and the instance redundancy are caused, and when the network is recovered again after the intermittent connection for a long time, the consistency of the cloud and the edge data needs to be synchronized in time, rescheduling of the application can occur, and the continuous usability of the application is affected. The maintenance of the data consistency of the cloud center and the edge nodes under the condition of unstable network requires a great deal of network overhead to ensure, especially in the long-distance public network scene.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides an application deployment method and system based on cloud edge cooperation, which can improve the high availability of applications through intra-group management of an edge node group under the condition of faults with a network of a cloud center.
The invention discloses an application deployment method based on cloud edge cooperation, which comprises the following steps: establishing an edge node group based on the physical location or network deployment of the edge node; selecting a management node from the edge node group; and responding to the received application deployment instruction, and distributing a target node for the application instance through the management node.
Wherein the step of assigning a target node to an instance of the application based on the edge node score comprises: scoring the edge nodes according to the performance index of the edge nodes and the affinity and mutual exclusion of the running instance in the edge nodes to obtain node scores; and distributing the target node for the application instance according to the node score. The scoring formula is expressed as:
Fscore＝w 1 ×LBScore+w 2 ×AffScore+w 3 ×AntiAffScore
wherein Fscore is expressed as a node score, LBScare is expressed as a performance index score, affScare is expressed as an affinity score, antiAffScare is expressed as a mutual exclusivity score, w 1 、w 2 And w 3 Is a weight coefficient.
Preferably, the method for obtaining the performance index score comprises the following steps:
obtaining performance index feature quantity and instance feature quantity of the edge node;
performing matching degree calculation on the performance index feature quantity and the corresponding example feature quantity to obtain index matching degree;
summing the index matching degrees to obtain the performance score of the edge node;
sorting the edge nodes from small to large according to the performance scores, and sequentially assigning the performance index scores of the edge nodes from small to large;
wherein the performance score is expressed as:
FV(Ci,Nj)＝macth(c1,n1)+macth(c2,n2)+…+macth(ci,nj)。
where FV (Ci, nj) is represented as a performance score, ci is represented as an array of instance feature quantities Ci, nj is represented as an array of performance index feature quantities Nj, and macth () is represented as a matching degree calculation function.
Preferably, the method for obtaining the affinity score comprises the following steps:
obtaining a first affinity tag of an instance to be allocated and a second affinity tag of an operating instance in an edge node;
matching the first affinity tag with the second affinity tag to obtain the number of the second affinity tags matched with the first affinity tag;
and according to the number, sorting the edge nodes from small to large, and sequentially assigning values to the edge nodes from small to large to obtain affinity scores.
Preferably, the method for obtaining the mutual exclusion score comprises the following steps: obtaining a first mutual exclusion tag of an instance to be allocated;
obtaining a second mutual exclusion tag of the running instance in the edge node; obtaining the number of second mutually exclusive labels matched with the first mutually exclusive label; and according to the number, sequencing the edge nodes from small to large, and sequentially assigning values to the edge nodes from large to small to obtain the mutual complaint score.
Preferably, the method for accessing the instance comprises the following steps: establishing an access entry of the edge node group; receiving an access request through the access portal; the access request is distributed to the corresponding instance.
Preferably, the method for example detection comprises: establishing an agent in the edge node; monitoring the state of an instance through an agent, and reporting the state to a management node; if the edge nodes are out of connection, selecting the edge nodes through the management node, starting the examples in the selected edge nodes, and recovering the examples through shared storage of the edge node groups; if the management node is out of connection, a new management node is elected from the edge node group.
The invention also provides a system for realizing the application deployment method, which comprises an edge management module, a management node selection module, a group manager and a group scheduler, wherein the edge node management module is used for establishing an edge node group based on the physical position or network deployment of the edge node; the management node selection module is used for selecting management nodes from the edge node group; the group manager is used for receiving an application deployment instruction issued to the management node; the group scheduler is configured to assign a target node to an application instance through a management node.
Preferably, the group manager and the group scheduler are deployed at a management node, and the management node is further deployed with a group load balancer, and the group load balancer is used for receiving an access request issued from an access portal and distributing the access request to a corresponding application instance; the group manager is further configured to manage instance configuration information; the edge node is provided with an agent module which is used for monitoring the application instance and the hardware information of the edge node, reporting the state information of the edge node and the monitoring information of the application instance to the group manager, and adding the information of the management node to the configuration information of the edge node. The system also comprises a cloud center, wherein the cloud center is used for issuing the application deployment instruction to the management node.
Compared with the prior art, the invention has the beneficial effects that: the edge node group is managed through the management node, so that the dependence on the cloud center is reduced; under the condition of disconnection from the cloud center, the edge node group and the application instance can be managed through the management node, so that high availability of the application instance is ensured; after the cloud center is re-connected, the service can be quickly recovered.
Drawings
FIG. 1 is a flowchart of an application deployment method based on Yun Bian collaboration in accordance with the present invention;
fig. 2 is a system logic block diagram of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention is described in further detail below with reference to the attached drawing figures:
an application deployment method based on cloud edge collaboration, as shown in fig. 1, comprises the following steps:
step 101: an edge node group is established based on the physical location or network deployment of the edge nodes.
For example, a plurality of edge nodes of a city or an area are set as one edge node group; or to set up an operator or a plurality of edge nodes in the same local area network as an edge node group. Thus, there is good regional or network connectivity among edge node groups within the same edge node group. CRD resource objects of an edge node group (edgenode group) may be defined based on container orchestration techniques. When the edge node group is determined, an edge node group configuration file can be generated, and each node is assigned with a node number which is recorded as edge_node i The number of each group is denoted as edge_group i 。
Step 102: and selecting a management node from the edge node group.
The management node is used for managing the edge node group, for example, receiving an instruction of the cloud center and managing the configuration information of the application. After the edge node group is determined, one edge node may be randomly selected as a management node.
Step 103: and receiving an application deployment instruction issued to the management node.
Step 104: and distributing the target node for the application instance through the management node.
The edge node group is managed through the management node, so that the dependence on the cloud center is reduced; under the condition of disconnection from the cloud center, the edge node group and the application instance can be managed through the management node, the cloud center is not required to be relied on, and the high availability of the application instance is ensured; after the cloud center is re-connected, the service can be quickly recovered.
The method for monitoring heartbeat after the edge node group is determined carries out health status and connectivity monitoring on each edge node, and when the management nodes in the edge node group cannot be accessed, the management nodes can be reselected to continue to carry out status monitoring among the nodes.
Wherein the intra-group management of the edge node group includes: management node election, data synchronization within a group, application instance allocation and scheduling within a group, and the like.
In step 104, a method for allocating a target node to an instance of an application includes:
step 201: and scoring the nodes according to the performance index of the nodes and the affinity and mutual exclusion of the running examples in the nodes to obtain node scores.
Step 202: and distributing the target node for the application instance according to the node score. The target node may be assigned to the application instance by maximizing the node score.
Wherein the scoring formula is expressed as:
Fscore＝w 1 ×LBScore+w 1 ×AffScore+w 3 ×AntiAffScore (1)
fscore is expressed as node score, LBScare is expressed as performance index score, affScare is expressed as affinity score, antiAffScare is expressed as mutex score, w 1 、w 2 And w 3 Is a weight coefficient. In one embodiment, the weight coefficients are respectively: 90. 80, 100, but is not limited thereto. The scheduling can also be performed according to the priority, if the priority is configured for the application instance, the scheduling can be performed sequentially after the priority of all the application instances in the current scheduling queue is ordered.
The method for obtaining the performance index score comprises the following steps:
step 301: and obtaining a performance index feature quantity nj and an instance feature quantity ci of the node, wherein the feature quantity comprises a memory, a CPU, a GPU, a storage space and the like.
Step 302: and calculating the matching degree of the performance index feature quantity and the corresponding example feature quantity to obtain the index matching degree. Such as matching calculation by macth ().
Step 303: and summing the index matching degree to obtain the performance score of the node.
Step 304: the nodes are ordered from small to large according to the performance scores, and the performance index scores of the nodes are sequentially assigned from small to large, e.g., 1, 2. I.e., the greater the performance index score, the more the performance requirements of the instance are met.
Wherein the performance score is expressed as:
FV(Ci,Nj)＝macth(c1,n1)+macth(c2,n2)+…+macth(ci,nj)。
where Ci is represented as an array of example feature quantities Ci, ci= [ c1, c2, ], ci ], nj is represented as an array of performance index feature quantities Nj, nj= [ n1, n2, ], nj, and macth () is represented as a matching degree calculation function. For example, if the performance index feature quantity nj satisfies ci; returning to 1, if not, returning to 0.
The affinity score obtained by the method comprises the following steps:
step 311: a first affinity tag of the instance to be allocated and a second affinity tag of the running instance in the node are obtained. For example, the key value tag key value of the podA affinity object labelSelector in the configuration file is set as the application instance affinity tag.
Step 312: matching the first affinity tag with the second affinity tag.
Step 313: the number of second affinity tags that match the first affinity tag is obtained.
Step 314: and sorting the nodes from small to large according to the matched quantity, and sequentially assigning values to the nodes from small to large to obtain affinity scores.
When the instances with the same affinity tag are deployed on the same node, the operation efficiency can be improved, for example, two or more instances are in an upstream-downstream relationship or a cooperative relationship, the result of one instance is related to the result of another instance, and when the instances are deployed on the same node, the network occupancy rate can be reduced, so that the same affinity tag can be set for the two instances, but the method is not limited to the method.
The method for obtaining the mutual exclusion score AntiAffScore comprises the following steps:
step 321: a first mutually exclusive tag of an instance to be allocated is obtained. For example, the key: value key pair of the poduntiAfforescence object labelSelector is set as the mutual exclusion tag of the application instance.
Step 322: a second mutually exclusive tag of the running instance in the node is obtained.
Step 323: the number of second mutually exclusive tags that match the first mutually exclusive tag is obtained.
Step 324: and according to the number, sorting the nodes from small to large, and sequentially assigning values to the nodes from large to small to obtain the mutual complaint score.
For example, if the resource consumption types of two or more instances are the same, such as CPU consumption type, then deployment of these instances to the same node is avoided by the mutual exclusion tag.
The method for accessing the instance outside the edge group comprises the following steps: establishing an access entry of the edge node group; receiving an access request through the access portal; the access request is distributed to the corresponding instance.
The method for example detection and experiment scheduling comprises the following steps:
step 301: an Agent is established in the edge node.
Step 302: the state of the instance is monitored by the agent and reported to the management node.
Step 303: if the edge node is out of connection, the edge node is selected through the management node, the instance is started in the selected edge node, and the instance is restored through the shared storage of the edge node group. More specifically, the management node has the read-write authority of the shared storage, the edge nodes only have the read authority, and each edge node mounts the same shared storage to read data.
Step 304: if the management node is out of connection, a new management node is elected from the edge node group.
The present invention also provides a system for implementing the above application deployment method, as shown in fig. 2, including an edge management module 11, a management node selection module 12, a group manager 23 and a group scheduler 24,
the edge node management module 11 is configured to establish the edge node group 2 based on the physical location or network deployment of the edge nodes; the management node selecting module 12 is configured to select a management node 21 from the edge node group 2; the group manager 23 is configured to receive an application deployment instruction issued to the management node 21; the group scheduler 24 is used to assign a target node to an application instance via the management node 21. The group manager 23 is also used to store and manage configuration information for application instances.
The group manager 23 and the group scheduler 24 are disposed at the management node 21, and the management node 21 is further disposed with a group load balancer 25, and the group load balancer 25 is configured to receive an access request issued from an access portal, and distribute the access request to a corresponding application instance 27.
The edge node 22 is deployed with a proxy module 26, and the proxy module 26 is configured to monitor the hardware information of the edge node 22 and the application instance 27, report the state information of the edge node 22 and the monitoring information of the application instance to the group manager 23, and add the information of the management node 21 to the configuration information of the edge node 22; the cloud center 1 is configured to issue an application deployment instruction to the management node 21. The edge management module 11 and the management node selection module 12 may be deployed to a cloud center, but are not limited thereto.
In a specific deployment, each time a cloud center deploys a new application, an edge application configuration file is generated, application configuration information includes a target edge node group, application configuration, the number of application instances and the like, which need to be operated by the application, the application configuration information is managed by a group manager group-manager, is stored in the edge node group, performs data synchronization among nodes, and collects operation information of each instance after the application is operated. After the application instances are distributed into the node groups, a group-based access portal (GroupService) is automatically created, when users or cross-groups access the application mutually, the application is firstly subjected to a group load balancer, and after the group load balancer receives a request, the request is distributed to the available instances of the current application in the edge node groups. The group load equalizer and the group manager synchronously apply the change information, and the change of the information in the group is actively monitored to automatically change the configuration, and if a certain application instance is not available, the instance is removed from the configuration and takes effect immediately. The group scheduler monitors the scheduling state of the application instance through a list-watch mechanism, and performs intra-group scheduling when the instance is found to be unassigned to the node.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The cloud edge collaboration-based application deployment method is characterized by comprising the following steps of:
establishing an edge node group based on the physical location or network deployment of the edge node;
selecting a management node from the edge node group;
and responding to the received application deployment instruction, and distributing a target node for the application instance through the management node.
2. The application deployment method of claim 1 wherein the step of assigning a target node to an instance of an application based on an edge node score comprises:
scoring the edge nodes according to the performance index of the edge nodes and the affinity and mutual exclusion of the running instance in the edge nodes to obtain node scores;
and distributing the target node for the application instance according to the node score.
3. The application deployment method of claim 2 wherein the scoring is formulated as:
Fscore＝w 1 ×LBScore+w 2 ×AffScore+w 3 ×AntiAffScore
wherein Fscore is expressed as a node score, LBScare is expressed as a performance index score, affScare is expressed as an affinity score, antiAffScare is expressed as a mutual exclusivity score, w 1 、w 2 And w 3 Is a weight coefficient.
4. The application deployment method of claim 3 wherein the method of obtaining the performance index score comprises:
obtaining performance index feature quantity and instance feature quantity of the edge node;
performing matching degree calculation on the performance index feature quantity and the corresponding example feature quantity to obtain index matching degree;
summing the index matching degrees to obtain the performance score of the edge node;
sorting the edge nodes from small to large according to the performance scores, and sequentially assigning the performance index scores of the edge nodes from small to large;
wherein the performance score is expressed as:
FV(Ci，Nj)＝macth(c1，n1)+macth(c2，n2)+…+macth(ci，nj)。
where FV (Ci, nj) is represented as a performance score, ci is represented as an array of instance feature quantities Ci, nj is represented as an array of performance index feature quantities Nj, and macth () is represented as a matching degree calculation function.
5. The application deployment method of claim 3 wherein the method of affinity score acquisition comprises:
obtaining a first affinity tag of an instance to be allocated and a second affinity tag of an operating instance in an edge node;
matching the first affinity tag with the second affinity tag to obtain the number of the second affinity tags matched with the first affinity tag;
and according to the number, sorting the edge nodes from small to large, and sequentially assigning values to the edge nodes from small to large to obtain affinity scores.
6. The application deployment method of claim 3 wherein the method of obtaining the mutual exclusion score comprises:
obtaining a first mutual exclusion tag of an instance to be allocated;
obtaining a second mutual exclusion tag of the running instance in the edge node;
obtaining the number of second mutually exclusive labels matched with the first mutually exclusive label;
and according to the number, sequencing the edge nodes from small to large, and sequentially assigning values to the edge nodes from large to small to obtain the mutual complaint score.
7. The application deployment method of claim 1, wherein the method of accessing the application instance comprises:
establishing an access entry of the edge node group;
receiving an access request through the access portal;
and distributing the access request to the corresponding application instance.
8. The application deployment method of claim 1, wherein the method of application instance detection comprises:
establishing an agent in the edge node; monitoring the state of an application instance through an agent, and reporting the state to a management node;
if the edge nodes are out of connection, selecting the edge nodes through the management node, starting an application instance in the selected edge nodes, and recovering the application instance through shared storage of the edge node group;
if the management node is out of connection, a new management node is elected from the edge node group.
9. A system for implementing the application deployment method according to any one of claims 1-8, comprising an edge management module, a management node selection module, a group manager, and a group scheduler,
the edge node management module is used for establishing an edge node group based on the physical position of the edge node or network deployment; the management node selection module is used for selecting management nodes from the edge node group;
the group manager is used for receiving an application deployment instruction issued to the management node;
the group scheduler is configured to assign a target node to an application instance through a management node.
10. The system of claim 9, wherein the group manager and group scheduler are deployed at a management node,
the management node is further provided with a group load balancer, and the group load balancer is used for receiving an access request issued from an access inlet and distributing the access request to a corresponding application instance;
the group manager is further configured to manage application instance configuration information;
the edge node is provided with an agent module which is used for monitoring the application instance and the hardware information of the edge node, reporting the state information of the edge node and the monitoring information of the application instance to the group manager, and adding the information of the management node to the configuration information of the edge node;
the cloud center is used for issuing the application deployment instruction to the management node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310900261.8A CN116886696A (en) | 2023-07-20 | 2023-07-20 | Cloud edge collaboration-based application deployment method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310900261.8A CN116886696A (en) | 2023-07-20 | 2023-07-20 | Cloud edge collaboration-based application deployment method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116886696A true CN116886696A (en) | 2023-10-13 |
Family
ID=88269572
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310900261.8A Pending CN116886696A (en) | 2023-07-20 | 2023-07-20 | Cloud edge collaboration-based application deployment method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116886696A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117289951A (en) * | 2023-11-22 | 2023-12-26 | 华信咨询设计研究院有限公司 | Software system multi-application automatic deployment method based on recursion principle |
-
2023
- 2023-07-20 CN CN202310900261.8A patent/CN116886696A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117289951A (en) * | 2023-11-22 | 2023-12-26 | 华信咨询设计研究院有限公司 | Software system multi-application automatic deployment method based on recursion principle |
| CN117289951B (en) * | 2023-11-22 | 2024-04-02 | 华信咨询设计研究院有限公司 | Software system multi-application automatic deployment method based on recursion principle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10277525B2 (en) | Method and apparatus for disaggregated overlays via application services profiles | |
| US8032780B2 (en) | Virtualization based high availability cluster system and method for managing failure in virtualization based high availability cluster system | |
| US8200789B2 (en) | Method, system and program product for automated topology formation in dynamic distributed environments | |
| Chaczko et al. | Availability and load balancing in cloud computing | |
| US20190319881A1 (en) | Traffic management based on past traffic arrival patterns | |
| CN107251533B (en) | Co-located peer device for peer-to-peer matching | |
| US8386607B2 (en) | Method and system for utilizing a resource conductor to optimize resource management in a distributed computing environment | |
| CN107278365B (en) | Apparatus for scalable peer matching | |
| TWI725744B (en) | Method for establishing system resource prediction and resource management model through multi-layer correlations | |
| Racheg et al. | Profit-driven resource provisioning in NFV-based environments | |
| Naas et al. | IoT data replication and consistency management in fog computing | |
| CN108984320A (en) | A kind of anti-fissure method and device of message queue cluster | |
| CN116886696A (en) | Cloud edge collaboration-based application deployment method and system | |
| CN110580198B (en) | Method and device for adaptively switching OpenStack computing node into control node | |
| EP1873639A1 (en) | Decentralized dynamic allocation of data-processing resources in a utility platform | |
| CN1625109A (en) | Method and apparatus for virtualizing network resources | |
| CN112631756A (en) | Distributed regulation and control method and device applied to space flight measurement and control software | |
| CN112822062A (en) | Management method for desktop cloud service platform | |
| Abid et al. | A novel scheme for node failure recovery in virtualized networks | |
| Feng et al. | COVE: Co-operative virtual network embedding for network virtualization | |
| CN109005071B (en) | Decision deployment method and scheduling equipment | |
| WO2023109062A1 (en) | Cloud disaster recovery system and method, electronic device, and storage medium | |
| CN114338670B (en) | Edge cloud platform and network-connected traffic three-level cloud control platform with same | |
| CN115225645A (en) | Service updating method, device, system and storage medium | |
| Chacin et al. | Utility driven elastic services |
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 |