CN107436811A - It is related to the task immigration method of task scheduling in mobile cloud problem - Google Patents
It is related to the task immigration method of task scheduling in mobile cloud problem Download PDFInfo
- Publication number
- CN107436811A CN107436811A CN201710553085.XA CN201710553085A CN107436811A CN 107436811 A CN107436811 A CN 107436811A CN 201710553085 A CN201710553085 A CN 201710553085A CN 107436811 A CN107436811 A CN 107436811A
- Authority
- CN
- China
- Prior art keywords
- task
- node
- migration
- mobile terminal
- energy consumption
- 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
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
- G06F9/5044—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 hardware capabilities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
- G06F1/329—Power saving characterised by the action undertaken by task scheduling
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a kind of task immigration method for being related to task scheduling in mobile cloud problem, its step includes：(1) initialize：All transportable tasks are first put into high in the clouds, can only being performed in mobile terminal for task is put on mobile terminal, calculates current total power consumption, and be " unallocated " by all transportable task flaggings；(2) it is as follows for task immigration each time, process：(i) breadth First sequential search is pressed, to marking to be unallocated " task, in total deadline on the premise of no more than limitation, select save the maximum node of energy consumption successively, moved to and locally executed；(ii) if migrating select node so that the total energy consumption after migration is smaller than before migration, then migrates the node, and is labeled as " division ", updates total power consumption on present mobile terminal；If select the maximum migration node come so that the total energy consumption after migration is also higher than before not migrating, then terminates to migrate.
Description
Technical field
The present invention relates to mobile cloud field, and in particular to is related to the task immigration side of task scheduling in a kind of mobile cloud problem
Method.
Background technology
With the development of science and technology the life of people increasingly be unable to do without mobile device, mobile device affects the side of life
Aspect face.However, the life-span of the battery of mobile device, computing capability, network bandwidth and storage resource etc. are limited, it is mobile
Become increasingly severe using the problem of growing resource requirement and mobile device shortage of resources.
Fortunately, with the development of cloud computing so that mobile device can be by partial task migration of programs to cloud service
On device, mitigate the burden of mobile device.In mobile cloud computing, the equipment of user can pass through mobile operator and Web vector graphic
The abundant calculating of distant cloud platform and storage resource.Mobile cloud computing can bring many benefits：1) by that will count
Calculate intensive high energy consumption task immigration to arrive to high in the clouds to extend the usage time of battery, 2) mobile subscriber is used answer
Miscellaneous application program, 3) efficient data storage function can be provided the user.
In the implementation of migration strategy, electricity and time that corresponding completion task is consumed, are had certainly to service quality
Two factors of qualitative effect, especially in the wireless network with greater need for the factor for considering these two aspects.Therefore when certain
Between constrain under so that the energy consumption of mobile terminal is minimum, is the problem of a challenge.
The content of the invention
For the application program that amount of calculation is larger, due to its substantial amounts of energy requirements, the cloud of limited battery capacity is operated in
Will be very limited on mobile device.Cloud computing migrating technology is to ensure that such application program is run in the equipment of resource-constrained
Main stream approach.For the scheduling of application program task image and migration problem in wireless network, the present invention proposes a kind of mobile cloud
It is related to the task immigration method of task scheduling in problem.Methods described is all arranged beyond the clouds in fact with that can move to the task in high in the clouds
It is now initial solution, the energy consumption saving run by gradually calculating transportable task in mobile terminal, successively by saving maximum
Task immigration is to mobile terminal, and according to the communication time between task, the energy consumption saving for each task that upgrades in time.
The purpose of the present invention refers under following constraints：In the time range that regulation completes general assignment, move to
Task on Cloud Server can perform with the tasks in parallel on mobile terminal, can also be with the tasks in parallel of other on Cloud Server
Perform.But the multiple tasks on mobile terminal can only be performed serially.If there are dependence, only two between two task nodes
Task node is at different ends.I.e. one in cloud server end, another is in mobile terminal.Call duration time between them just be present and lead to
Believe energy consumption, otherwise call duration time and communication energy consumption are all 0.Solve the problems, such as be：Under above-mentioned constraints, a migration is found
Strategy, after completion task so that the energy consumption on mobile terminal is minimum.
It is related to the task immigration method of task scheduling in a kind of mobile cloud problem, its step includes：
(1) initialize：All can migrating for tasks are all first put into high in the clouds, and can only being performed in mobile terminal for task
It is put on mobile terminal, calculates current total power consumption, and is " unallocated " by all task flaggings that can be migrated；
(2) it is as follows for task immigration each time, process：
(i) breadth First sequential search is pressed, to marking to be unallocated " task, in total deadline no more than limitation
On the premise of, select save the maximum node of energy consumption successively, moved to and locally executed；
(ii) if migrating select node so that the total energy consumption after migration is smaller than before migration, then migrates the knot
Point, and " division " is labeled as, update total power consumption on present mobile terminal；If select the maximum migration node come so that
Total energy consumption after migration is also higher than before not migrating, then terminates to migrate；
The transition process in the step (2) is repeated, terminates transition condition until reaching the step (2ii).
Prerequisite variable algorithm (Procedure FCFS) can be used to calculate the completion of general assignment figure in the step (2i)
Time.
The present invention is had the following advantages relative to prior art and effect：
The Riming time of algorithm of the present invention is far smaller than small very with the run time of IBM Cplex studio optimizers
It is more, and still can keep the higher quality of approximate solution.
Brief description of the drawings
Fig. 1 is random task program figure；
Fig. 2 is the pseudo-code of the algorithm figure of prerequisite variable；
Fig. 3 is the task immigration heuritic approach false code figure with dispatching algorithm；
Fig. 4 is false code symbol description symbol.
Embodiment
With reference to embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are unlimited
In this.
Embodiment
Task immigration problem of the thin cloud under deadline limited conditions in the cloud computing of the invention based on movement, the one of proposition
Kind effectively carries the heuritic approach of the task immigration of prerequisite variable.The present invention considers to use for the simplicity of deployment
Following manner is disposed.First, algorithm can be disposed by the way of system, and system includes mobile terminal and service end two
Entity, service end refer to be located at long-range Cloud Server, and the task program of user is responsible for receiving in mobile terminal, and determines to appoint which
Business uploads to service end.Service end provides CPU for mobile terminal, the computing resource such as internal memory and storage, movement is so greatly reduced
The pressure at end.
Main thought of the present invention is as follows：
The algorithm (FCFS) of prerequisite variable is designed first, and the algorithm is as follows：
For the upper task node performed can be parallel beyond the clouds, so being performed on high in the clouds for task is divided into, as long as place
In ready state, it is possible to perform.And for multiple ready tasks for being performed in this ground, because this on the ground can only be serial
Task is held, ready all local tasks carryings can not be caused.Therefore, need to be that the task that mobile terminal performs determines a priority
Execution sequence, to ensure that general assignment is completed at the appointed time.Prerequisite variable algorithm, with mobile terminal task node it is ready when
Between put sequencing, establish the task queue of a first in first out, the sequencing of tasks carrying determined with this.
The task immigration of time opens when then designing an approximation completed with above-mentioned prerequisite variable come calculating task
Hairdo algorithm, the heuritic approach thought are as follows：
For each task node, no matter the node is to be divided into local from high in the clouds, or is divided into high in the clouds from local, all
Between the node that is connected with it can be caused, the increase or reduction of communication energy consumption and call duration time.When a task node from
Mobile terminal is divided into high in the clouds, and for mobile device, the energy consumption for performing the task node saves；And when a task node
When being divided into local from high in the clouds, for mobile terminal, then the energy of the task node is performed than original more consumption.Heuristic calculation
The thought of method is：In each migration, in the deadline of general assignment figure, (Procedure FCFS calculate the completion of general assignment figure
Time) no more than on the premise of time restriction, the gross energy before not migrated than it in order to ensure the total power consumption after unloading disappears
Consumption is small, is selected from transportable task and saves the most priority of task migration of energy.Repeat task immigration, every time only
Migrate a task.
The algorithm is divided into two parts, and Part I is mainly dispatching algorithm, for providing one after the completion of calculating general assignment
Kind approximation method, wherein Part II migration algorithm, algorithm need to call dispatching algorithm above.
It is as follows to implement step：
As shown in figure 1, being first randomly generated a task program figure, dark node represents to hold on mobile terminal in figure
Capable task node, and the node of white represents that the task node of cloud server end or mobile terminal can be moved to.Two knots
Line between point represents dependence be present between them.There are two nodes of dependence, if being deposited respectively at different ends
There are communication energy consumption and call duration time.Otherwise, call duration time and communication energy consumption are all 0, that is, are not present.
It is related to the task immigration method of task scheduling in a kind of mobile cloud problem, its step includes：
(1) initialize：All can migrating for tasks are all first put into high in the clouds, and can only being performed in mobile terminal for task
It is put on mobile terminal, calculates current total power consumption, and is " unallocated " by all task flaggings that can be migrated；
(2) it is as follows for task immigration each time, process：
(i) breadth First sequential search is pressed, to marking to be unallocated " task, in total deadline no more than limitation
On the premise of, select save the maximum node of energy consumption successively, moved to and locally executed, first taken first specifically, can use
Business algorithm (Procedure FCFS) calculates the deadline of general assignment figure, and Fig. 2 is the pseudo-code of the algorithm figure of prerequisite variable；
(ii) if migrating select node so that the total energy consumption after migration is smaller than before migration, then migrates the knot
Point, and " division " is labeled as, update total power consumption on present mobile terminal.If select the maximum migration node come so that
Total energy consumption after migration is also higher than before not migrating, then terminates whole algorithm；
The transition process in step (2) is repeated, until algorithm stops.
Fig. 3 is the task immigration heuritic approach false code figure with dispatching algorithm, and Fig. 4 is false code symbol description symbol.
The algorithm is applied to have following characteristics in task image：
(1) at least one in-degree (except first node) of each node of task image, each node at least one go out
Degree is (except last node).
(2) all components, at least one from first node to the path of a last node.
(3) element on the adjacency matrix diagonal of task image is 0, that is, can not arrive the node of itself in the presence of itself.
(4) partial task is realized in mobile terminal in these tasks, for example first task is appointed with last
It must must be realized in mobile terminal.
(5) there are two nodes of dependence, only (i.e. one in mobile terminal, one in Cloud Server at different ends
End just has call duration time and communication energy consumption).
(6) it can run, can also and be moved with the tasks in parallel of cloud server end in the task of cloud server end operation
The tasks in parallel operation at end.
(7) in the multiple tasks of mobile terminal, can only serially run.
The purpose of the present invention is achieved through the following technical solutions
Algorithm is realized using C++ programming languages.
Give general task image and be used as experimental example to examine the heuritic approach for the task immigration for carrying scheduling.
The data structure for the task image being related in the embodiment of the present invention, the execution time of each task node,
Power, the messaging parameter between node, can be rationally designed according to actual environment demand.The skill of the technical field of the invention
Art personnel can be to realizing that details is reasonably improved, but not surmounts protection scope of the present invention.
Above-described embodiment is the preferable embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any Spirit Essences without departing from the present invention with made under principle change, modification, replacement, combine, simplification,
Equivalent substitute mode is should be, is included within protection scope of the present invention.
Claims (2)
1. it is related to the task immigration method of task scheduling in a kind of mobile cloud problem, it is characterised in that its step includes：
(1) initialize：All can migrating for tasks are all first put into high in the clouds, and can only being performed in mobile terminal for task is put into
On mobile terminal, current total power consumption is calculated, and is " unallocated " by all task flaggings that can be migrated；
(2) it is as follows for task immigration each time, process：
(i) breadth First sequential search is pressed, to marking to be unallocated " task, in total deadline before no more than limitation
Put, select save the maximum node of energy consumption successively, moved to and locally executed；
(ii) if migrating select node so that the total energy consumption after migration is smaller than before migration, then migrates the node, and
Labeled as " division ", total power consumption on present mobile terminal is updated；If select the maximum migration node come so that after migration
Total energy consumption it is also higher than before not migrating, then terminate to migrate；
The transition process in the step (2) is repeated, terminates transition condition until reaching the step (2ii).
2. according to the method for claim 1, it is characterised in that：Prerequisite variable algorithm can be used in the step (2i)
(Procedure FCFS) calculates the deadline of general assignment figure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710553085.XA CN107436811A (en) | 2017-07-07 | 2017-07-07 | It is related to the task immigration method of task scheduling in mobile cloud problem |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710553085.XA CN107436811A (en) | 2017-07-07 | 2017-07-07 | It is related to the task immigration method of task scheduling in mobile cloud problem |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107436811A true CN107436811A (en) | 2017-12-05 |
Family
ID=60461252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710553085.XA Pending CN107436811A (en) | 2017-07-07 | 2017-07-07 | It is related to the task immigration method of task scheduling in mobile cloud problem |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107436811A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109240813A (en) * | 2018-08-21 | 2019-01-18 | 广东工业大学 | Task schedule and task immigration method in a kind of mobile cloud computing |
| CN109445956A (en) * | 2018-09-19 | 2019-03-08 | 北京大学 | A kind of cloud towards smartwatch application-end calculating load sharing method |
| CN109753751A (en) * | 2019-01-20 | 2019-05-14 | 北京工业大学 | A kind of MEC Random Task moving method based on machine learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104065745A (en) * | 2014-07-07 | 2014-09-24 | 电子科技大学 | Cloud computing dynamic resource scheduling system and method |
| CN104202373A (en) * | 2014-08-21 | 2014-12-10 | 清华大学深圳研究生院 | Method and system for migrating mobile cloud computing |
| CN104822175A (en) * | 2015-04-16 | 2015-08-05 | 华中科技大学 | Code migration method and system suitable for cellular network |
| CN104899103A (en) * | 2015-07-03 | 2015-09-09 | 中国人民解放军国防科学技术大学 | Energy-saving scheduling method and energy-saving scheduling device for mobile cloud computing terminal |
| CN105656999A (en) * | 2015-12-25 | 2016-06-08 | 清华大学 | Energy consumption optimized collaborative task migration method in mobile cloud computing environment |
| CN106550036A (en) * | 2016-10-28 | 2017-03-29 | 华东师范大学 | A kind of heuristic cloud computing resources distribution and dispatching method towards energy-conservation |
-
2017
- 2017-07-07 CN CN201710553085.XA patent/CN107436811A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104065745A (en) * | 2014-07-07 | 2014-09-24 | 电子科技大学 | Cloud computing dynamic resource scheduling system and method |
| CN104202373A (en) * | 2014-08-21 | 2014-12-10 | 清华大学深圳研究生院 | Method and system for migrating mobile cloud computing |
| CN104822175A (en) * | 2015-04-16 | 2015-08-05 | 华中科技大学 | Code migration method and system suitable for cellular network |
| CN104899103A (en) * | 2015-07-03 | 2015-09-09 | 中国人民解放军国防科学技术大学 | Energy-saving scheduling method and energy-saving scheduling device for mobile cloud computing terminal |
| CN105656999A (en) * | 2015-12-25 | 2016-06-08 | 清华大学 | Energy consumption optimized collaborative task migration method in mobile cloud computing environment |
| CN106550036A (en) * | 2016-10-28 | 2017-03-29 | 华东师范大学 | A kind of heuristic cloud computing resources distribution and dispatching method towards energy-conservation |
Non-Patent Citations (1)
| Title |
|---|
| 张亮: ""云计算环境下的资源调度技术的研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109240813A (en) * | 2018-08-21 | 2019-01-18 | 广东工业大学 | Task schedule and task immigration method in a kind of mobile cloud computing |
| CN109240813B (en) * | 2018-08-21 | 2021-12-24 | 广东工业大学 | Task scheduling and task migration method in mobile cloud computing |
| CN109445956A (en) * | 2018-09-19 | 2019-03-08 | 北京大学 | A kind of cloud towards smartwatch application-end calculating load sharing method |
| CN109445956B (en) * | 2018-09-19 | 2022-07-22 | 北京大学 | Cloud-end computing load sharing method for smart watch application |
| CN109753751A (en) * | 2019-01-20 | 2019-05-14 | 北京工业大学 | A kind of MEC Random Task moving method based on machine learning |
| CN109753751B (en) * | 2019-01-20 | 2023-04-18 | 北京工业大学 | MEC random task migration method based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111756812B (en) | Energy consumption perception edge cloud cooperation dynamic unloading scheduling method | |
| Raza et al. | Reinforcement learning for slicing in a 5G flexible RAN | |
| Yu et al. | Computation offloading for mobile edge computing: A deep learning approach | |
| Han et al. | Tailored learning-based scheduling for kubernetes-oriented edge-cloud system | |
| CN110099384A (en) | Resource regulating method is unloaded based on side-end collaboration more MEC tasks of multi-user | |
| Dab et al. | Q-learning algorithm for joint computation offloading and resource allocation in edge cloud | |
| CN105656999B (en) | A kind of cooperation task immigration method of energy optimization in mobile cloud computing environment | |
| CN110069341B (en) | Method for scheduling tasks with dependency relationship configured according to needs by combining functions in edge computing | |
| CN107436811A (en) | It is related to the task immigration method of task scheduling in mobile cloud problem | |
| CN109067890A (en) | A kind of CDN node edge calculations system based on docker container | |
| CN112988362B (en) | Task processing method and device, electronic equipment and storage medium | |
| Di Valerio et al. | Optimal virtual machines allocation in mobile femto-cloud computing: An MDP approach | |
| Wu et al. | Software aging in mobile devices: Partial computation offloading as a solution | |
| CN109358953A (en) | A kind of multitask application discharging method in thin cloud | |
| CN110008015A (en) | The online task for having bandwidth to limit in edge calculations system assigns dispatching method | |
| CN111464352A (en) | Call link data processing method and device | |
| Maia et al. | Dynamic service placement and load distribution in edge computing | |
| Dao et al. | Mobile cloudization storytelling: Current issues from an optimization perspective | |
| Donassolo et al. | Load aware provisioning of IoT services on fog computing platform | |
| CN114490048A (en) | Task execution method and device, electronic equipment and computer storage medium | |
| CN111831452A (en) | Task execution method and device, storage medium and electronic device | |
| CN116938323A (en) | Satellite transponder resource allocation method based on reinforcement learning | |
| Zhang et al. | Cloud-assisted collaborative execution for mobile applications with general task topology | |
| CN115361453A (en) | Load fair unloading and transferring method for edge service network | |
| Goyal et al. | A fault-tolerant energy-efficient computational offloading approach with minimal energy and response time in mobile cloud computing |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171205 |