CN110502342A - Motor-driven marginal information service network under a kind of interval network environment - Google Patents
Motor-driven marginal information service network under a kind of interval network environment Download PDFInfo
- Publication number
- CN110502342A CN110502342A CN201910758332.9A CN201910758332A CN110502342A CN 110502342 A CN110502342 A CN 110502342A CN 201910758332 A CN201910758332 A CN 201910758332A CN 110502342 A CN110502342 A CN 110502342A
- Authority
- CN
- China
- Prior art keywords
- task
- node
- manager
- network
- host node
- 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
-
- 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
- G06F9/505—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 the load
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/16—Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
- G06F15/161—Computing infrastructure, e.g. computer clusters, blade chassis or hardware partitioning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/04—Network management architectures or arrangements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/70—Services for machine-to-machine communication [M2M] or machine type communication [MTC]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Mobile Radio Communication Systems (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a kind of motor-driven marginal information service networks, including multiple nodes, it is connected with each other through wireless communication between node, wherein: node includes general node and host node, task scheduling management system is deployed on each node, the task scheduling management system includes task manager, task performer, mission bit stream collector, task dispatcher, task manager and task performer can all be run in each node, and mission bit stream collector and task dispatcher are only in the upper operation of host node.
Description
Technical field
The present invention relates to computer networks, more particularly, to motor-driven marginal information service network under a kind of interval network environment
And control method.
Background technique
Cloud computing technology is increasingly mature with surprising speed, from infrastructure services such as simple calculating, storages in method of service,
It has expanded to a variety of enterprise-level application service levels.It is complicated and changeable that ecological environment is calculated under the conditions of certain, such as at motor-driven edge
Under network, multiple nodes of the motor-driven edge network mostly by descontinuous motion or constantly in movement structure by way of wireless connection
At often running on the severe occasion of the communication environments such as rescue and relief work, motor-driven edge network has the physics different from internet
Link property mainly includes the following: a) high-transmission time delay, b) high bit-error, c) intermittence connection, d) link asymmetry,
This causes motor-driven marginal information service node often because of the variation of external environment, in the technologies such as information transmitting and data transmission
It is unstable that intermittent network link occurs in link.Simultaneously as service node is in maneuvering condition, it is dry by environment at any time
The influence disturbed, and loaded with information processing and calculating task large area, it is difficult to ensure service node message system mode is done
Real-time Decision out, to adapt to current mission requirements.
Thus the invention proposes motor-driven marginal information service network system under a kind of interval network environment, realize motor-driven
Collaborative work in marginal information service network between each node.
Summary of the invention
Purpose to realize the present invention, is achieved using following technical scheme:
A kind of motor-driven marginal information service network, including multiple nodes, between node through wireless communication mutually
Connection, in which: node includes general node and host node, is deployed with task scheduling management system on each node, and described
Business dispatching management information system includes task manager, task performer, mission bit stream collector, task dispatcher, task manager
It can all be run with task performer in each node, mission bit stream collector and task dispatcher are only in the upper operation of host node.
The network, in which: for task manager for safeguarding a task list, the input including task can be changed portion
Divide, the metamessage of output par, c and task, task manager is also used to safeguard the resource service condition of this node.
The network, in which: the additions and deletions that task manager provides task, which change, looks into interface and resource service condition more
New interface, task manager supports event subscription, when the metamessage of task changes and when resource service condition changes
Task metamessage or resource service condition are actively pushed to subscriber.
The network, in which: the identity of the node in a network is determined by the resource manager of node, in resource
After manager determines the primary node identity of oneself, information acquisition device and scheduler will start, once primary node identity is lost, at once
Stop the information acquisition device and scheduler of starting.
The network, in which: when network is initially set up, all nodes are all general nodes, and resource manager is fixed
The heartbeat message of node weight, the weight that resource manager once the has received heart bigger than oneself where phase broadcast is attached with it
It jumps, the state of general node will be maintained whithin a period of time；Once resource manager is as general node broadcasts predetermined number
It the heartbeat packet of amount and does not receive the heartbeat signal bigger than itself weight during this period, the identity of oneself will be become main section
Point.
The network, in which: task performer is executed for executing task, more new resources service condition, Report Tasks
As a result；Task performer subscribes to all being dispatched to node where it of the tasks to task manager, new pending detecting
Task when, the service framework that task submits to this node is just executed into the task, and update using the interface of task manager
Execution start time of task and it is expected that time-consuming, the completion status and output of more new task again after task execution.
The network, in which: mission bit stream collector is used to subscribe to the computing resource for collecting each node from each node
With mission bit stream, one data packet of mission bit stream collector fixed time broadcast inquires that online task manager, task manager are received
After arriving can actively reply, mission bit stream collector perceive a task manager it is online after, will be to this task manager
It obtains the nodal information and subscribes to all tasks, a global resource and task view is safeguarded with this.
The network, in which: task dispatcher is used to obtain global resource from mission bit stream collector and not complete
Mission bit stream and its dynamic change event, for task specify executor.
The network, in which: under interval Weak link network condition, if the network connection of host node is temporarily interrupted, net
Surplus resources manager can select host node again in network, and new host node will newly start information acquisition device and scheduler, new letter
Breath collector will get the resource information and task metamessage of full dose from the resource manager of each general node.
The network, in which: after host node determines, selected other nodes of host node as secondary host node, this its
His node starts information acquisition device, but does not start scheduler when becoming secondary host node；It disappears in the compacting of host node predetermined
When the time, secondary host node gets started broadcast heartbeat, while starting scheduler adapter tube network, after host node is returned, host node
Compacting restore, secondary host node will be re-closing off scheduler.
The network, in which: general node and secondary host node can periodically report the power of oneself when being suppressed by host node
Host node is given again, and host node passes through the weight report received, determines that whom secondary host node is；Secondary host node after adapter tube network,
It will become host node after the heartbeat packet for broadcasting predetermined quantity.
The network, in which: task dispatcher is more than meeting after certain time length in the network connection interruption for finding certain node
Originally the task that the task manager for being dispatched to the node is executed, reschedules to other task managers, task is gathered around
Task can be pushed to new executor after it confirmed the change of performer by the person of having.
The network, wherein if offline task manager restores network connection, mission bit stream collector can be felt
Know this event, and pass them to task dispatcher, thus task dispatcher can perceive the event, and can find
There is the identical task of mark to execute under multiple tasks manager, at this moment task dispatcher retains expected concluding time earliest times
Business, and others are all deleted.
Detailed description of the invention
Fig. 1 is motor-driven marginal information service network architecture schematic diagram；
Fig. 2 is task manager cooperation schematic diagram；
Fig. 3 is that task performer cooperates schematic diagram with task manager；
Fig. 4 is that mission bit stream collector cooperates schematic diagram with task manager；
Fig. 5 is that task dispatcher and mission bit stream collector cooperate schematic diagram with task manager；
Fig. 6 is the offline offline schematic diagram online again of behavior-executor online again of task manager.
Specific embodiment
As shown in Figure 1, motor-driven marginal information service network includes multiple motor-driven marginal information service nodes, motor-driven edge letter
Breath service node generally occurs in a manner of computer (server) etc., mutually interconnects through wireless communication between node
It connects.Task scheduling management system is deployed on motor-driven marginal information service node, the task scheduling management system includes task
Four components such as manager, task performer, mission bit stream collector, task dispatcher.The external constituents of system include appointing
Be engaged in submitter, and checks the administrator of system mode.Four components can all be disposed in each motor-driven marginal information service node,
Task manager and task performer can all be run in each motor-driven edge service node, mission bit stream collector and task schedule
Device can only be run on the motor-driven edge service node (motor-driven service centre or host node) as host node.
Task manager is for safeguarding a task list.The underlying attribute of task see the table below 1, can in addition to input in table 1
Become other attributes except two attributes in part and output, is referred to as the metamessage of task.Task manager is also used to safeguard this
The resource service condition of motor-driven edge service node.
1 task underlying attribute of table
The additions and deletions that task manager provides task change the more new interface for looking into interface and resource service condition.Task management
Device supports event subscription, actively by task metamessage when the metamessage of task changes and when resource service condition changes
Or resource service condition is pushed to subscriber.When subscription event, condition by setting is supported to limit task scope and (such as only order
Read the information about some task).
As shown in Fig. 2, task manager can dispose an example in each motor-driven edge service node, i.e., by some
It serves as terminal device such as automobile of motor-driven edge service node etc. and carries the task manager.The motor-driven service being connect with host node
Application on node, the interface that can be provided by task manager, task is submitted in task manager example, Zhi Houzai
Subscription task, with the output that obtains task at the first time, (i.e. child node produces task, and task is submitted on host node, main
Node carries out decomposition scheduling to task, and child node obtains output from host node again later).
After the executor of task determines, if host node oneself is not the executor of task, it will attempt task
It is pushed to executor, i.e. other motor-driven edge service nodes.
In motor-driven marginal information service network, host node be it is unique, be selected from the node in network, and
Other nodes can be described as general node, and each node has a resource manager, and the section can be determined by resource manager
The identity of point in a network will start information acquisition device and scheduler after the primary node identity that resource manager determines oneself,
Once losing primary node identity, it can also stop the information acquisition device and scheduler of starting at once.
Each resource manager can determine the weight of oneself by certain mode, can be administrator's secondary setup
Value is also possible to by comprehensively considering oneself position in network topology, the network connection quality of oneself, the resource feelings of oneself
The value that the factors such as condition obtain.It is necessary to ensure that the weight of all resource managers does not repeat in network.
Resource manager determines host node by a heartbeat mechanism.It is all general node, resource manager when initial
Heartbeat signal can be broadcasted, the inside can enclose the weight of oneself.The weight that resource manager once has received is bigger than oneself
Heartbeat will keep downtrodden state to maintain the state of general node whithin a period of time.Host node may also can be pressed
System, once host node is pressed, just will become general node.Host node understands periodic broadcasting heartbeat to maintain the authority of oneself, pressure
The other general nodes of system.Resource manager (it is bigger than itself not receive weight once being detached from compacting state in the predetermined time
Heartbeat message), just will be considered that does not have host node in current network, and starts periodic broadcasting heartbeat.Once resource manager conduct
The a certain number of heartbeat packets of general node broadcasts simultaneously do not receive the heartbeat signal bigger than itself weight, will by oneself
Identity becomes host node.
Task performer is for executing task, more new resources service condition, Report Tasks implementing result.As shown in figure 3, appointing
Business actuator can subscribe to the task of all motor-driven edge service nodes where being dispatched to it to task manager, new detecting
When pending task, task just submitted into the service framework of this motor-driven edge service node and by this motor-driven edge service section
Point executes the task, and utilizes the execution start time of the interface more new task of task manager and it is expected that time-consuming, task execution
After more new task again completion status and output.
Mission bit stream collector be used to subscribe to from each motor-driven edge service node the computing resource for collecting service node with
Mission bit stream: as shown in figure 4, one data packet of mission bit stream collector fixed time broadcast inquires online task manager, task
Manager can be replied actively after receiving, and allow mission bit stream collector that can perceive the upper offline event of task manager.
Mission bit stream collector perceive a task manager it is online after, the section will be obtained to this task manager
Point information simultaneously subscribes to all tasks, safeguards a global resource and task view with this, browses and checks for system manager,
And decision is done for task dispatcher, data support is provided.
Task dispatcher for obtained from mission bit stream collector global resource and unfinished mission bit stream and he
Dynamic change event, specify executor (Task-decomposing can be scheduled to multiple nodes execute) for task.Do not have in task
Executor or when the not online executor of task, after task generates dispatching requirement, task dispatcher will pass through dispatching algorithm
Calculating is gone out on missions suitable executor, executor's attribute of task is changed by the interface of task owner, as shown in Figure 5.
Dispatching algorithm is specific as follows: the implementation progress of each task and its unit resource occupied (such as calculating of CPU
Power) it is several directly proportional, P1 is the rate that unit resource runs task within the unit time, and M is the number of resources that task has been occupied, t1 table
Show the time executed, then the implementation progress P of task (sets general assignment amount as 1, P is made normalized, then P is more than or equal to 0
And it is less than or equal to 1) such as formula (1):
P=P1Mt1 (1)
If the operation will be completed at moment deadline t2, it is also necessary to stock number be Q, then have formula (2)
P1(M+Q)(t2-t1)=1-P (2)
(3) formula can be released according to (1) formula
We can obtain formula (4) according to formula (2) and formula (3)
Defining the resources requirement in the current one time is R, then available formula (5)
It can be according to the unit resource demand R of each operation come dynamically schedule job, according to mission bit stream collector
The information in current network being collected into, the node that can satisfy resource requirement is dispatched to by task dispatcher.Specifically, appointing
Being engaged in scheduler can be by each node in the information acquisition current network in current network that mission bit stream collector is collected at it
The calculation power size being capable of providing in free time, such as a certain node individually meets the needs of R, then by the task schedule to single section
Task is assigned to multiple nodes and completed, selected multiple nodes exist by point if individual node is unable to meet demand
Unit time in its free time calculates power sum and is greater than or equal to R.
Host node selection mode is as follows under interval Weak link network condition: if the network connection of host node is temporarily interrupted
, will lead to surplus resources manager in network and select host node again.New host node will newly start information acquisition device and task
Scheduler.New information acquisition device is because just starting, will get the money of full dose from the resource manager of each general node
Source information and task metamessage.Until old master node network communication recovery, new host node will may make way for again old
Host node, the information acquisition device newly started and task dispatcher will stop again.It disconnects, causes again if network frequently connects
This process is repeated, and will waste many bandwidth resources, and because determining that host node needs to expend many times, this
Also to have quite a few time in the process be in whole system and do not have a state of host node, and new task may not be able to be timely
To scheduling.
In order to reduce the offline bring negative effect of host node.Selected other nodes of host node can be allowed as secondary main
Node.Other nodes also start information acquisition device as host node, but do not start scheduling when becoming secondary host node
Device.When the compacting of host node disappears the predetermined time, secondary host node gets started broadcast heartbeat, while starting scheduler, takes over
The work (but being not to switch identity as host node) of host node, removes the process for reselecting host node from.Using usually receiving
The task and change in resources event of resource manager replace obtaining full dose data when unexpected occur.After host node is returned, main section
The compacting of point restores, and secondary host node will be re-closing off scheduler.General node and secondary host node can be determined when being suppressed by host node
The weight of forward exchange report oneself is to host node.Host node passes through the weight report received, determines that whom secondary host node is.The remittance of weight
Report interval and validity period can be relatively longer, in order to avoid the unstable frequent switching for leading to secondary host node of secondary master node network.
Secondary host node will become host node after adapter tube network after broadcasting a certain number of heartbeat packets, this quantity can be opposite
It is larger, in order to avoid the switching for leading to host node offline that host node is temporary.
Under the conditions of Weak link, (it not can determine that only temporary in the communication network disconnecting of some general node
Disconnection or long-term disconnection), mission bit stream collector can perceive this event, and pass them to task schedule
Device.
As shown in fig. 6, task dispatcher after finding that certain node broken communication connection is more than certain time length, can adjust script
The task that the task manager of this node of disconnecting executes is spent, is rescheduled to other task managers.Task
Owner after it confirmed the change of performer, task can be pushed to new executor.At this moment, if offline task
Again back, mission bit stream collector can perceive this event to manager, and pass them to task dispatcher, thus
Task dispatcher can perceive the event, and can find that the identical task of mark executes under multiple tasks manager, this
When task dispatcher can only to retain the expected concluding time earliest, and others are all deleted.
If owner's (i.e. host node) of task is offline, motor-driven service node can also pass through other motor-driven services
The task manager at center goes for task information acquisition device, to find the task metamessage recorded at the executor of task
With the output of task.
Network division is the same with the initial performance of Weak link network environment, is all that the network between motor-driven service centre connects
It connects and is disconnected, only for the scene of network division, the variation of environment just finished in the network connection short time disconnected
No longer restore, and the scene of Weak link network environment, the variation of environment further include that subsequent connection restores.
Network divides under environment, and finally can all there be the host node of oneself in each part to split off, it may be possible to before
Host node, it may be possible to what secondary host node before was become a full member after a period of time, it is also possible to elect again.These
Host node finally also can all select secondary host node again and (form situation according to the network newly perceived, it is also possible to because member is too
Lack without selecting secondary host node).Losing because of network division for task, can also be rescheduled, after having executed again by scheduler
Again the owner of task is sent back to
Network merging can occur in the case where network environment takes a turn for the better for the network of division, and network merging will lead to same in network
When there are multiple host nodes and secondary host node, the maximum meeting of weight in these host nodes is because of heartbeat, rapidly it
He is pressed into from node host node, so that allowing oneself becomes unique host node.Secondary host node can be utilized by host node later
Selection mechanism selects secondary host node again, and since mission bit stream is dispersing maintenance, network merging does not have having been filed on for task
It influences.
By means of the invention it is possible to which the motor-driven peripheral surroundings for interval Weak link construct an information service network, meet
To the decomposition dispatching requirement of complex task, guarantee the smooth execution of task.
Claims (3)
1. a kind of motor-driven marginal information service network, including multiple nodes, mutually interconnected through wireless communication between node
It connects, it is characterised in that: node includes general node and host node, and task scheduling management system, institute are deployed on each node
Stating task scheduling management system includes task manager, task performer, mission bit stream collector, task dispatcher, task pipe
Reason device and task performer can all be run in each node, and mission bit stream collector and task dispatcher are only in the upper fortune of host node
Row.
2. network according to claim 1, it is characterised in that: task manager is used to safeguard a task list, including
The metamessage for inputting variable part, output par, c and task of task, task manager are also used to safeguard the resource of this node
Service condition.
3. network according to claim 1, it is characterised in that: the additions and deletions that task manager provides task, which change, looks into interface, with
And the more new interface of resource service condition, task manager supports event subscription, when the metamessage of task changes and money
Task metamessage or resource service condition are actively pushed to subscriber when source service condition changes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910758332.9A CN110502342B (en) | 2019-08-16 | 2019-08-16 | Maneuvering edge information service network in intermittent network environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910758332.9A CN110502342B (en) | 2019-08-16 | 2019-08-16 | Maneuvering edge information service network in intermittent network environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110502342A true CN110502342A (en) | 2019-11-26 |
| CN110502342B CN110502342B (en) | 2023-07-18 |
Family
ID=68588139
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910758332.9A Active CN110502342B (en) | 2019-08-16 | 2019-08-16 | Maneuvering edge information service network in intermittent network environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110502342B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111526179A (en) * | 2020-03-30 | 2020-08-11 | 中科九度(北京)空间信息技术有限责任公司 | Distributed node resource elastic expansion device and method |
| CN112910981A (en) * | 2021-01-27 | 2021-06-04 | 联想(北京)有限公司 | Control method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6877107B2 (en) * | 2001-07-05 | 2005-04-05 | Softwired Ag | Method for ensuring operation during node failures and network partitions in a clustered message passing server |
| CN103534982A (en) * | 2013-04-09 | 2014-01-22 | 华为技术有限公司 | Method, equipment and network virtualization system for protecting business reliability |
| CN104539681A (en) * | 2014-12-23 | 2015-04-22 | 北京超图软件股份有限公司 | Distributed GIS accelerating system and GIS service processing method |
| CN106059879A (en) * | 2016-01-29 | 2016-10-26 | 深圳市禾望电气股份有限公司 | Control system and control method thereof |
| CN109104346A (en) * | 2017-06-21 | 2018-12-28 | 比亚迪股份有限公司 | Train network data transmission method, system and its apparatus based on CANopen agreement |
| CN109104349A (en) * | 2017-06-21 | 2018-12-28 | 比亚迪股份有限公司 | Train network data transmission method, system and its apparatus based on CANopen agreement |
| US20190116128A1 (en) * | 2017-10-18 | 2019-04-18 | Futurewei Technologies, Inc. | Dynamic allocation of edge computing resources in edge computing centers |
-
2019
- 2019-08-16 CN CN201910758332.9A patent/CN110502342B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6877107B2 (en) * | 2001-07-05 | 2005-04-05 | Softwired Ag | Method for ensuring operation during node failures and network partitions in a clustered message passing server |
| CN103534982A (en) * | 2013-04-09 | 2014-01-22 | 华为技术有限公司 | Method, equipment and network virtualization system for protecting business reliability |
| CN104539681A (en) * | 2014-12-23 | 2015-04-22 | 北京超图软件股份有限公司 | Distributed GIS accelerating system and GIS service processing method |
| CN106059879A (en) * | 2016-01-29 | 2016-10-26 | 深圳市禾望电气股份有限公司 | Control system and control method thereof |
| CN109104346A (en) * | 2017-06-21 | 2018-12-28 | 比亚迪股份有限公司 | Train network data transmission method, system and its apparatus based on CANopen agreement |
| CN109104349A (en) * | 2017-06-21 | 2018-12-28 | 比亚迪股份有限公司 | Train network data transmission method, system and its apparatus based on CANopen agreement |
| US20190116128A1 (en) * | 2017-10-18 | 2019-04-18 | Futurewei Technologies, Inc. | Dynamic allocation of edge computing resources in edge computing centers |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111526179A (en) * | 2020-03-30 | 2020-08-11 | 中科九度(北京)空间信息技术有限责任公司 | Distributed node resource elastic expansion device and method |
| CN112910981A (en) * | 2021-01-27 | 2021-06-04 | 联想(北京)有限公司 | Control method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110502342B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102521044B (en) | Distributed task scheduling method and system based on messaging middleware | |
| CN103617062B (en) | The render farm Dynamic Deployment System of a kind of flexibility and method | |
| CN110297699B (en) | Scheduling method, scheduler, storage medium and system | |
| CN109995669B (en) | Distributed current limiting method, device, equipment and readable storage medium | |
| CN103053146B (en) | Data migration method and device | |
| CN104322011A (en) | Connectivity service orchestrator | |
| CN103366022B (en) | Information handling system and disposal route thereof | |
| CN102546839B (en) | Efficient and reliable software distribution method for large scale network | |
| CN105786611A (en) | Method and device for task scheduling of distributed cluster | |
| CN110502342A (en) | Motor-driven marginal information service network under a kind of interval network environment | |
| CN101340423B (en) | Multi-cluster job scheduling method based on element scheduling ring | |
| Wang et al. | Task scheduling for MapReduce in heterogeneous networks | |
| CN109995875A (en) | Virtualization data distributes elastomeric network system | |
| Liu et al. | Service resource management in edge computing based on microservices | |
| CN113220459B (en) | Task processing method and device | |
| Garces-Erice | Building an enterprise service bus for real-time SOA: A messaging middleware stack | |
| CN110955504B (en) | Method, server, system and storage medium for intelligently distributing rendering tasks | |
| CN115134421B (en) | Multi-source heterogeneous data cross-system collaborative management system and method | |
| Berket et al. | Overview of the InterGroup protocols | |
| Du et al. | Research on service bus for distributed real-time control systems | |
| CN113590294A (en) | Self-adaptive and rule-guided distributed scheduling method | |
| CN114024976A (en) | Big data service architecture based on 5G and method for constructing big data service | |
| CN113110935B (en) | Distributed batch job processing system | |
| CN116594784B (en) | Method, device and system for scheduling edges and readable storage medium | |
| Danjuma et al. | Proposed approach for resource allocation management in Service Oriented Architecture (SOA) environment |
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 |