CN102170476B - Cloud computing method and device based on cloud node autonomic learning - Google Patents
Cloud computing method and device based on cloud node autonomic learning Download PDFInfo
- Publication number
- CN102170476B CN102170476B CN201110118628.8A CN201110118628A CN102170476B CN 102170476 B CN102170476 B CN 102170476B CN 201110118628 A CN201110118628 A CN 201110118628A CN 102170476 B CN102170476 B CN 102170476B
- Authority
- CN
- China
- Prior art keywords
- node
- cloud
- task
- service
- information
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/5055—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering software capabilities, i.e. software resources associated or available to the machine
Abstract
The invention discloses a cloud computing method based on cloud node autonomic learning, comprising the steps of using an entity cloud service frequently called and corresponding to a service that a local node does not have service ability as an extended service by a cloud node, loading to the local node, and updating the extended service information in the node service information table of the local node; when the cloud node receives a task, searching the service information that the task corresponds to in the node service information table; and when the service information is found out and the service information is the extended service information, calling the extended service to execute the task. Meanwhile, the invention also discloses a cloud computing device based on cloud node autonomic learning. By the scheme of the invention, the cloud service connecting across multiple cloud nodes can be called and executed quickly, avoiding waste of network resources.
Description
Technical field
The present invention relates to cloud computing technology, particularly relate to a kind of cloud computing method based on cloud node autonomic learning and device.
Background technology
Cloud computing (Cloud Computing) is the novel computation model of one proposed on the basis that Distributed Calculation (Distributed Computing), parallel computation (Paralell Computing) and grid computing (Grid Computing) etc. develop, and is a kind of method of emerging shared architecture.Faced by it is ultra-large distributed environment, and core is to provide data and stores and network service, and general principle is jointly performed to multiple stage computer by network allocation by calculation task.The cloud service mentioned in cloud computing is that some can the virtual computing resource of self and management, and the cloud node in system for cloud computing is exactly the physical media realizing these resource managements, be generally some large server clusters, comprise computer group, calculation server, storage server, broadband network information etc. in local area network (LAN).All computational resources, by providing various cloud service, are put together by distributed cloud node by cloud computing, and by software simulating self-management, without the need to artificial participation.
In existing system for cloud computing, because the cloud node of managing virtual cloud service does not possess independent learning ability, make the cloud service of cross-over connection multichannel cloud node exist repetitive schedule perform and can not fast dispatch perform defect, great waste is caused to Internet resources.Such as cloud node A receives the service request that its access point is downloaded for same flow online media sites Large Copacity under cloud Node B for many times, if do not possess the learning ability of node serve, just there will be repeatedly from cloud node A to the large transfer of data of cloud Node B and download request; If do not arrive the routing iinformation of cloud Node B in cloud node A, if do not possess the learning ability of node-routing simultaneously, just there will be repeatedly the route poll of cloud node A to cloud Node B.Above-mentioned two situations all can cause certain waste to Internet resources.
Summary of the invention
In view of this, main purpose of the present invention is to provide a kind of cloud computing method based on cloud node autonomic learning and device, realizes the cloud service that fast dispatch performs cross-over connection multichannel cloud node, avoids the waste of Internet resources.
For achieving the above object, technical scheme of the present invention is achieved in that
A kind of cloud computing method based on cloud node autonomic learning provided by the invention, the method comprises:
The local node frequently called is not possessed the entity cloud service of the service correspondence of service ability as expansion service by cloud node, is loaded into local node, and by expansion service information updating in the node serve information table of local node;
Described cloud node, when receiving task, searches information on services corresponding to described task in node serve information table, when finding and described information on services is described expansion service information, calling described expansion service and performing described task.
In such scheme, the local node frequently called is not possessed the entity cloud service of the service correspondence of service ability as expansion service by described cloud node, be loaded into local node, for: cloud node to ought for the previous period within the service that do not possess service ability of the local node that frequently calls carry out record, when described service call frequency meet the tactful value preset time, entity cloud service corresponding for described service is loaded into local node as expansion service.
In such scheme, described cloud node is when receiving task, information on services corresponding to described task is searched in node serve information table, for: described cloud node receives sending from access point of task, the category attribute of extraction task, load node serve information table, in node serve information table, search the information on services of coupling according to the category attribute of described task.
In such scheme, the method comprises further: when described cloud node searches the information on services less than task is corresponding in node serve information table, load node routing information table, in node routing information table, the next node routing iinformation of current task is inquired about, when inquiring the routing iinformation of next node, current task is forwarded to next node.
In such scheme, the method comprises further: the best route information of described cloud node dynamically recording task in node routing information table.
A kind of cloud computing device based on cloud node autonomic learning provided by the invention, this device comprises: cloud node top control module, node serve administration module, node serve Executive Module; Wherein,
Described cloud node top control module, for receiving task, by described task notifications node serve Executive Module, and does not possess the Service Notification node serve administration module of service ability by the local node frequently called;
Described node serve administration module, for the entity cloud service of service correspondence that notified by cloud node top control module as expansion service, is loaded into local node, and by expansion service information updating in the node serve information table of local node;
Described node serve Executive Module, for when cloud node top control module receives task, in node serve information table, search information on services corresponding to described task, when finding and described information on services is described expansion service information, calling described expansion service and performing described task.
In such scheme, described cloud node top control module, specifically for extracting the category attribute of receiving of task, is supplied to node serve Executive Module by the category attribute of described task; And to ought for the previous period within the service that do not possess service ability of the local node that frequently calls carry out record, when described service call frequency meet the tactful value preset time, by described Service Notification node serve administration module.
In such scheme, described node serve Executive Module, category attribute specifically for providing according to described cloud node top control module of task searches the information on services of coupling in node serve information table, when finding and the information on services mated is the information of described expansion service, calling expansion service corresponding to described information on services and performing described task.
In such scheme, this device comprises routing iinformation scheduler module further, for the notice according to cloud node top control module, load node routing information table, in node routing information table, the next node routing iinformation of current task is inquired about, when inquiring the routing iinformation of next node, current task is forwarded to next node;
Described cloud node top control module, also for when node serve Executive Module searches the information on services less than task is corresponding in node serve information table, notice routing iinformation scheduler module.
In such scheme, this device comprises further: routing iinformation study module, for the best route information of dynamically recording task in node routing information table.
The invention provides a kind of cloud computing method based on cloud node autonomic learning and device, the local node frequently called is not possessed the entity cloud service of the service correspondence of service ability as expansion service by cloud node, be loaded into local node, and by expansion service information updating in the node serve information table of local node; Described cloud node, when receiving task, searches information on services corresponding to described task in node serve information table, when finding and described information on services is described expansion service information, calling described expansion service and performing described task; So, the cloud service that fast dispatch performs cross-over connection multichannel cloud node can be realized, avoid the waste of Internet resources.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet that the present invention realizes a kind of cloud computing method based on cloud node autonomic learning;
Fig. 2 is the structural representation that the present invention realizes a kind of cloud computing device based on cloud node autonomic learning.
Embodiment
Basic thought of the present invention is: the local node frequently called is not possessed the entity cloud service of the service correspondence of service ability as expansion service by cloud node, be loaded into local node, and by expansion service information updating in the node serve information table of local node; Described cloud node, when receiving task, searches information on services corresponding to described task in node serve information table, when finding and described information on services is described expansion service information, calling described expansion service and performing described task.
Below by drawings and the specific embodiments, the present invention is described in further detail.
The present invention realizes a kind of cloud computing method based on cloud node autonomic learning, and as shown in Figure 1, the method comprises following step:
Step 101: the local node frequently called is not possessed the entity cloud service of the service correspondence of service ability as expansion service by cloud node, is loaded into local node, and by expansion service information updating in the node serve information table of local node;
Concrete, cloud node to ought for the previous period within the service that do not possess service ability of the local node that frequently calls carry out record, when this service call frequency meet the tactful value preset time, the entity cloud service of this service correspondence is loaded into local node as expansion service, and in the node serve information table of local node, expansion service information is dynamically updated;
Described a period of time can be 10 minutes or 1 hour or 1 day etc.;
Described expansion service information comprises the category attribute, service ability title etc. of expansion service;
Described node serve information table is used for the information of the service that minute book ground node can carry, and comprises the category attribute of service, service ability title etc.;
Described dynamically updating has used for reference the corresponding strategies of operating system for scheduling memory, such as the most often uses priority scheduling scheduling strategy recently; This method dynamically updating node serve information table is exactly the autonomous learning mechanism of cloud node serve.
Such as: East China cloud nodal test to ought for the previous period in, there is a large amount of access point and accessing a certain streaming media video website and downloading jumbo streaming media video in East China, and provide the cloud node of this streaming media video service to be positioned at Southwest Region, when visit capacity reaches the threshold value preset, this streaming media video service is loaded into local node as expansion service by the node of described East China cloud node, and records this expansion service information in the node serve information table of local node.The repetitive schedule that avoiding problems a large amount of cloud service performs, and reduces the load capacity of system for cloud computing entirety, also has significant increase to Consumer's Experience.
Step 102: described cloud node, when receiving task, searches information on services corresponding to described task in node serve information table, when finding and described information on services is described expansion service information, calling described expansion service and performing described task;
Concrete, described cloud node receives sending from access point of task, the category attribute of extraction task, load node serve information table, in node serve information table, the information on services of coupling is searched according to the category attribute of described task, when finding and the information on services mated is the information of described expansion service, calling expansion service corresponding to described information on services and performing described task;
Described access point can be the embedded device of the embedded access point of cloud node or mobile terminal or other cloud nodes.
Further, when described cloud node searches the information on services less than task is corresponding in node serve information table, load node routing information table, in node routing information table, the next node routing iinformation of current task is inquired about, if inquire the routing iinformation of next node, then current task is forwarded to next node; If can not find out the routing iinformation of next node, then start the next node network poll of current task, until inquiring the next node that can process current task or till having traveled through all cloud nodes; Method and the existing route polling method of described meshed network poll are similar, and it will not go into details;
Described node routing information table is used for the routing iinformation the most efficiently of task requests and service response between minute book ground node and the cloud node be associated;
Further, described cloud node is also for the best route information of dynamically recording task in node routing information table;
The best route information of described dynamically recording task, generally: carry out node-routing assessment according to the task requests between local node and the cloud node be associated and service response, the routing iinformation of current optimum is joined in node routing information table, after having cloud node to change, re-start node-routing assessment, if there is more excellent routing iinformation, routing iinformation more excellent described in real-time update is in node routing information table;
Described carry out node-routing assessment be generally carry out node-routing assessment from multiple dimensions such as network cost, route numbers;
Such as: when in East China, a certain cloud node checks is less than the information on services mated with the task of access point request streaming media service, load node routing information table, the next node routing iinformation of current task is inquired about, if inquiring routing iinformation is a certain cloud node in North America, current task is forwarded to this North America cloud node, be forwarded to a certain Australia cloud node from this North America cloud node again, call streaming media service by this Australia cloud node and perform current task; The route information table dynamically recording of a certain cloud node in described East China is for the next node routing iinformation of the task of access point request streaming media service, as there being Taiwan cloud node to add fashionable, this Taiwan cloud node has the streaming media service identical with Australia cloud node, and this East China cloud node is directly connected with this Taiwan cloud node, after then this East China cloud node carries out node-routing assessment from multiple dimensions such as network cost, route numbers, using described Taiwan cloud node as more excellent next node updating route information in node routing information table.
The above-mentioned dynamically recording process to routing iinformation is exactly the autonomous learning mechanism of cloud node routing information.
In order to realize said method, the present invention also provides a kind of cloud computing device based on cloud node autonomic learning, and as shown in Figure 2, this device comprises: cloud node top control module 21, node serve administration module 22, node serve Executive Module 23; Wherein,
Described cloud node top control module 21, for receiving task, by described task notifications node serve Executive Module 23, and does not possess the Service Notification node serve administration module 22 of service ability by the local node frequently called;
Described node serve administration module 22, for the entity cloud service of service correspondence that notified by cloud node top control module 21 as expansion service, is loaded into local node, and by expansion service information updating in the node serve information table of local node;
Described node serve Executive Module 23, for when cloud node top control module 21 receives task, in node serve information table, search information on services corresponding to described task, when finding and described information on services is described expansion service information, calling described expansion service and performing described task;
Described node serve information table is used for the information of the service that minute book ground node can carry, and comprises the category attribute of service, service ability title etc.;
Described cloud node top control module 21, specifically for extracting the category attribute of receiving of task, is supplied to node serve Executive Module 23 by the category attribute of described task; And to ought for the previous period within the service that do not possess service ability of the local node that frequently calls carry out record, when this service call frequency meet the tactful value preset time, by this Service Notification node serve administration module 22;
Described node serve Executive Module 23, category attribute specifically for providing according to described cloud node top control module 21 of task searches the information on services of coupling in node serve information table, when finding and the information on services mated is the information of described expansion service, calling expansion service corresponding to described information on services and performing described task;
This device comprises routing iinformation scheduler module 24 further, for the notice according to cloud node top control module 21, load node routing information table, in node routing information table, the next node routing iinformation of current task is inquired about, if inquire the routing iinformation of next node, then current task is forwarded to next node; If can not find out the routing iinformation of next node, then start the next node network poll of current task, until inquiring the next node that can process current task or till having traveled through all cloud nodes;
Described cloud node top control module 21, also for when node serve Executive Module 23 searches the information on services less than task is corresponding in node serve information table, notice routing iinformation scheduler module 24.
Described node routing information table is used for the routing iinformation the most efficiently of task requests and service response between minute book ground node and the cloud node be associated;
This device comprises further: routing iinformation study module 25, for the best route information of dynamically recording task in node routing information table;
Described routing iinformation study module 25, specifically for carrying out node-routing assessment according to the task requests between local node and the cloud node be associated and service response, the routing iinformation of current optimum is joined in node routing information table, after having cloud node to change, re-start node-routing assessment, if there is more excellent routing iinformation, routing iinformation more excellent described in real-time update is in node routing information table.
The above, be only preferred embodiment of the present invention, be not intended to limit protection scope of the present invention.
Claims (9)
1. based on a cloud computing method for cloud node autonomic learning, it is characterized in that, the method comprises:
Cloud node to ought for the previous period within the service that do not possess service ability of the local node that frequently calls carry out record, when described service call frequency meet the tactful value preset time, entity cloud service corresponding for described service is loaded into local node as expansion service, and by expansion service information updating in the node serve information table of local node;
Described cloud node, when receiving task, searches information on services corresponding to described task in node serve information table, when finding and described information on services is described expansion service information, calling described expansion service and performing described task.
2. cloud computing method according to claim 1, it is characterized in that, described cloud node is when receiving task, information on services corresponding to described task is searched in node serve information table, for: described cloud node receives sending from access point of task, the category attribute of extraction task, loads node serve information table, searches the information on services of coupling according to the category attribute of described task in node serve information table.
3. cloud computing method according to claim 1, it is characterized in that, the method comprises further: when described cloud node searches the information on services less than task is corresponding in node serve information table, load node routing information table, in node routing information table, the next node routing iinformation of current task is inquired about, when inquiring the routing iinformation of next node, current task is forwarded to next node.
4. cloud computing method according to claim 3, is characterized in that, the method comprises further: the best route information of described cloud node dynamically recording task in node routing information table.
5. based on a cloud computing device for cloud node autonomic learning, it is characterized in that, this device comprises: cloud node top control module, node serve administration module, node serve Executive Module; Wherein,
Described cloud node top control module, for receiving task, by described task notifications node serve Executive Module, and to ought for the previous period within the service that do not possess service ability of the local node that frequently calls carry out record, when described service call frequency meet the tactful value preset time, by described Service Notification node serve administration module;
Described node serve administration module, for the entity cloud service of service correspondence that notified by cloud node top control module as expansion service, is loaded into local node, and by expansion service information updating in the node serve information table of local node;
Described node serve Executive Module, for when cloud node top control module receives task, in node serve information table, search information on services corresponding to described task, when finding and described information on services is described expansion service information, calling described expansion service and performing described task.
6. cloud computing device according to claim 5, is characterized in that, described cloud node top control module, specifically for extracting the category attribute of receiving of task, the category attribute of described task is supplied to node serve Executive Module.
7. cloud computing device according to claim 6, it is characterized in that, described node serve Executive Module, category attribute specifically for providing according to described cloud node top control module of task searches the information on services of coupling in node serve information table, when finding and the information on services mated is the information of described expansion service, calling expansion service corresponding to described information on services and performing described task.
8. cloud computing device according to claim 5, it is characterized in that, this device comprises routing iinformation scheduler module further, for the notice according to cloud node top control module, load node routing information table, in node routing information table, the next node routing iinformation of current task being inquired about, when inquiring the routing iinformation of next node, current task being forwarded to next node;
Described cloud node top control module, also for when node serve Executive Module searches the information on services less than task is corresponding in node serve information table, notice routing iinformation scheduler module.
9. cloud computing device according to claim 8, is characterized in that, this device comprises further: routing iinformation study module, for the best route information of dynamically recording task in node routing information table.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110118628.8A CN102170476B (en) | 2011-05-09 | 2011-05-09 | Cloud computing method and device based on cloud node autonomic learning |
PCT/CN2011/078708 WO2012151802A1 (en) | 2011-05-09 | 2011-08-22 | Cloud computing method and device based on automatic learning of cloud node |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110118628.8A CN102170476B (en) | 2011-05-09 | 2011-05-09 | Cloud computing method and device based on cloud node autonomic learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102170476A CN102170476A (en) | 2011-08-31 |
CN102170476B true CN102170476B (en) | 2015-07-22 |
Family
ID=44491452
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201110118628.8A Active CN102170476B (en) | 2011-05-09 | 2011-05-09 | Cloud computing method and device based on cloud node autonomic learning |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN102170476B (en) |
WO (1) | WO2012151802A1 (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102647464B (en) * | 2012-03-30 | 2015-05-06 | 哈尔滨工业大学 | Server and self-service travel system adopting same |
CN105323276B (en) * | 2014-07-09 | 2020-05-26 | 腾讯科技(深圳)有限公司 | Cloud access method and device of application and application server |
CN107528863A (en) * | 2016-06-20 | 2017-12-29 | 周尧 | Internet of Things experimental teaching and scientific research research/development platform based on three-level cloud computing framework |
CN110601981A (en) * | 2019-09-11 | 2019-12-20 | 神州数码融信软件有限公司 | Service routing method, service provider cloud domain and service calling cloud domain |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101662483A (en) * | 2008-08-28 | 2010-03-03 | 盛大计算机(上海)有限公司 | Cache system for cloud computing system and method thereof |
CN101753617A (en) * | 2009-12-11 | 2010-06-23 | 中兴通讯股份有限公司 | Cloud storage system and method |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8433749B2 (en) * | 2009-04-15 | 2013-04-30 | Accenture Global Services Limited | Method and system for client-side scaling of web server farm architectures in a cloud data center |
US8612439B2 (en) * | 2009-06-30 | 2013-12-17 | Commvault Systems, Inc. | Performing data storage operations in a cloud storage environment, including searching, encryption and indexing |
US8799322B2 (en) * | 2009-07-24 | 2014-08-05 | Cisco Technology, Inc. | Policy driven cloud storage management and cloud storage policy router |
US8316125B2 (en) * | 2009-08-31 | 2012-11-20 | Red Hat, Inc. | Methods and systems for automated migration of cloud processes to external clouds |
-
2011
- 2011-05-09 CN CN201110118628.8A patent/CN102170476B/en active Active
- 2011-08-22 WO PCT/CN2011/078708 patent/WO2012151802A1/en active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101662483A (en) * | 2008-08-28 | 2010-03-03 | 盛大计算机(上海)有限公司 | Cache system for cloud computing system and method thereof |
CN101753617A (en) * | 2009-12-11 | 2010-06-23 | 中兴通讯股份有限公司 | Cloud storage system and method |
Also Published As
Publication number | Publication date |
---|---|
WO2012151802A1 (en) | 2012-11-15 |
CN102170476A (en) | 2011-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109150987B (en) | Two-layer container cluster elastic expansion method based on host layer and container layer | |
CN105190555B (en) | Centralized task schedule | |
US20160142477A1 (en) | Connection control device, connection control system, and non-transitory computer readable medium | |
CN102780603B (en) | Web traffic control method and device | |
CN103368986A (en) | Information recommendation method and information recommendation device | |
JP2017510864A (en) | Method, terminal and system for pushing information | |
CN109582470B (en) | Data processing method and data processing device | |
CN103780679A (en) | Long time delay remote invocation method based on HTTP protocol | |
CN102333130A (en) | Method and system for accessing cache server and intelligent cache scheduler | |
CN110413845B (en) | Resource storage method and device based on Internet of things operating system | |
CN102170476B (en) | Cloud computing method and device based on cloud node autonomic learning | |
CN101710902A (en) | Unstructured P2P network, data searching method thereof and index updating method thereof | |
CN103312751A (en) | Instant messaging method based on browser | |
CN104144202A (en) | Hadoop distributed file system access method, system and device | |
WO2015172497A1 (en) | Message pushing and acquisition methods and devices, and computer readable storage medium | |
CN103164262B (en) | A kind of task management method and device | |
CN116303608A (en) | Data processing method and device for application service | |
CN103186536A (en) | Method and system for scheduling data shearing devices | |
US8510426B2 (en) | Communication and coordination between web services in a cloud-based computing environment | |
CN102103633B (en) | The method and system of infosystem performance is improved based on using forestland | |
CN111044062A (en) | Path planning and recommending method and device | |
CN101483668A (en) | Network storage and access method, device and system for hot spot data | |
CN103825922B (en) | A kind of data-updating method and web server | |
CN103685295A (en) | Method, terminal and system for downloading multimedia files | |
CN105095224A (en) | Method, apparatus and system for carrying out OLAP analysis in mobile communication network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |