CN108416465A - A kind of Workflow optimization method under mobile cloud environment - Google Patents
A kind of Workflow optimization method under mobile cloud environment Download PDFInfo
- Publication number
- CN108416465A CN108416465A CN201810095728.5A CN201810095728A CN108416465A CN 108416465 A CN108416465 A CN 108416465A CN 201810095728 A CN201810095728 A CN 201810095728A CN 108416465 A CN108416465 A CN 108416465A
- Authority
- CN
- China
- Prior art keywords
- equipment
- workflow
- task
- mobile cloud
- indicate
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000005457 optimization Methods 0.000 title claims abstract description 18
- 238000005265 energy consumption Methods 0.000 claims abstract description 29
- 230000003044 adaptive effect Effects 0.000 claims abstract description 26
- 230000008569 process Effects 0.000 claims abstract description 6
- 230000005540 biological transmission Effects 0.000 claims description 15
- 238000005516 engineering process Methods 0.000 claims description 10
- 230000035772 mutation Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000005611 electricity Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 claims 1
- 230000002068 genetic effect Effects 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 210000000349 chromosome Anatomy 0.000 description 2
- 238000005553 drilling Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013396 workstream Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0633—Workflow analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Water Supply & Treatment (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Primary Health Care (AREA)
- Evolutionary Biology (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Power Sources (AREA)
Abstract
The invention discloses a kind of Workflow optimization methods under mobile cloud environment, include the following steps：Step S1：The workflow submitted to user pre-processes；Step S2：Work flow model under the mobile cloud environment of structure；Step S3：Workflow optimal scheduling scheme is generated based on improved adaptive GA-IAGA；Step S4：The equipment in task to mobile cloud is distributed according to scheduling result.Compared with prior art, the present invention configures equipment optimal voltage frequency by adjusting electric voltage frequency, and obtained electric voltage frequency is subjected to genetic algorithm as coding and carries out optimized search, seek optimal task schedule of the equipment about reliability and energy consumption in mobile cloud environment, it can be searched for fast speed and achieve the purpose that multiple-objection optimization, be particularly suitable for terminal user and handle mass data and mass data calculating.
Description
Technical field
The present invention relates to the Workflow optimization sides under mobile cloud computing environment field more particularly to a kind of mobile cloud environment
Method.
Background technology
Mobile cloud computing be universal mobile device, mobile device performance boost, mobile network's stability improve etc. factors and
The product of commercialization mode development fusion anywhere or anytime.It is intended to it is by cloud platform that the task in workflow is rational, have
Constraint is distributed in terminal user's hand, and then reduces the energy loss and computation burden of user terminal, is used only convenient for user
Mobile device can manage, handle the information of a large amount of promptnesses anywhere or anytime.
And relative to traditional server and desktop grade equipment, mobile device is in electric power energy consumption, memory space, computing capability
On there is also limitation, how to integrate information resources and processing mass data and reduce equipment energy consumption, be pendulum in mobile cloud
The problem of can not avoiding before workflow schedule technological side under environment.In the existing solution of the current problem, that is, uses and carry
For the mode of platform service, using the resource-sharing of cloud server end and the characteristic of high computing capability to bulk information at
Reason, and it is different from the workflow processing scheduling method of cloud environment, task processing time, equipment dependability and energy in workflow
Source consumption problem is to handle the key points and difficulties of this environmental work stream scheduling.With regard to moving the workflow schedule problem under cloud environment,
A large amount of research work has been done both at home and abroad, but the workflow schedule algorithm under current mobile cloud computing environment is mostly only examined
Consider one-side factor, does not consider and meet under mobile cloud environment under default workflow deadline constraint, equipment energy
Source consumption minimizes and reliability maximizes.
Therefore in view of the drawbacks of the prior art, it is really necessary to propose a kind of technical solution to solve skill of the existing technology
Art problem.
Invention content
In view of this, it is necessory to provide a kind of Workflow optimization method under mobile cloud environment, passes through and pre-process movement
The node of workflow in cloud environment reduces transmission and calculates energy consumption, and improved adaptive GA-IAGA is recycled to seek energy consumption and reliability
Optimal task schedule, thus the advantages of present invention can combine genetic algorithm and electric voltage frequency adjustment technology, and the two is organic
Fusion makes its maximum reliability and energy consumption requirement for meeting user to workflow in constraint completion date.
In order to overcome the deficiencies of existing technologies, technical scheme is as follows：
A kind of Workflow optimization method under mobile cloud environment, includes the following steps：
Step S1：The workflow submitted to user pre-processes；
Step S2：Work flow model under the mobile cloud environment of structure；
Step S3：Workflow optimal scheduling scheme is generated based on improved adaptive GA-IAGA；
Step S4：The equipment in task to mobile cloud is distributed according to scheduling result；
Wherein, the step S1 further comprises the steps：
Step S11：The excessive node of workflow transmission cost is merged according to workflow transmission cost weights；
Step S12：The most suitable electric voltage frequency of mobile cloud environment equipment calls voltage adjustment technique adjustment equipment；
The step S11 further comprises the steps：
(1) weights τ is calculated according to Trans_P matrixes；
(2) according to task, there are sequencings, and its transmittability is higher than weights τ, then task is assigned to the same place
It manages on device；
Wherein, workflow interior joint, which merges with reference to weight computing formula, is：
In above formula, m indicates that the number of mobile device, Trans_P [i] [j] indicate processor piTo pjData transmissions
Power；
In the step S12, the calculation formula of electric voltage frequency is as follows：
Wherein f indicates the electric voltage frequency of mobile cloud device, VddThe voltage that expression system is supported, VtsExpression system electricity
Press threshold value, LdIndicate that the shortest length of algorithm time, Z and β indicate a constant；
The step 2 further comprises the steps：
Under mobile cloud environment the set of tasks of workflow by the directed acyclic graph of a sideband weight indicate G=T, E,
P }, wherein T={ t1, t2..., tnIt is the set for including N number of task, E={ (i, j) Vi<J } it is first order constrained between each task,
That is tj cannot start before ti completions, and D indicates workflow off period, P={ p1,p2,...,pmIndicate to dispose in mobile high in the clouds
Equipment；Optimal conditions include { T, E, R }, wherein T, and E, R indicate use of the user to time, energy expenditure and reliability respectively
Family requirements；
M and n in above-mentioned model respectively represent the task number in processor number and task-set used in cluster,
Wherein each equipment supports dynamic voltage frequency adjustment technology, and i, j indicate mission number, therefore 1≤i, j≤n；
The step S3 further comprises the steps：
Step S31：The adaptive value of calculating each individual of new population, the meter of adaptive value are needed after being encoded to workflow
Calculating formula is：
Wherein, f (n, m) indicates the adaptive value in the scheduling scheme, Rn,mIndicate reliabilities of the task n on equipment m,
RhighIndicate maximum reliability in scheduling scheme, RlowIndicate minimum reliability in scheduling scheme, En,mIndicate task n in equipment
Energy consumption on m, EnormalIndicate the energy consumption that equipment is generated when not using dynamic voltage frequency adjustment technology；
Step S32：Population is divided, partitioning standards are：
The adaptive value of each individual of gained is calculated, the adaptive value the big, and it is more outstanding to be considered as the individual, therefore selects wherein to adapt to
It spends larger individual and is divided into elite group membership, remaining is then included into as common group membership.
Step S33：Population is intersected, mutation operation, concrete operations are as follows：
In crossover operation, single node exchange is carried out successively to the individual nodes two-by-two in population, obtains new individual, root
According to the adaptive value selection wherein higher individual of adaptive value, as new explanation；
In mutation operation, it is first depending on probability and isolates the set for needing to make a variation in population, successively in set
Single node on individual carries out mutation operation, obtains new individual, according to the adaptive value selection wherein higher individual of adaptive value, makees
For new explanation.
The step S4 further comprises as a preferred technical solution,：
Within the scope of preset iterations, after subsequent iteration, reliability in the new population of generation, the deadline,
Energy consumption meets user's expection, is mapped task and equipment according to obtained scheduling scheme and distributes mobile cloud equipment and closed
Suitable electric voltage frequency.
As a preferred technical solution, in the step S1, local device electric voltage frequency is by equipment voltage and equipment making
Technique determines, by reasonable distribution electric voltage frequency to mobile cloud device to reduce equipment energy consumption.
Compared with prior art, the device have the advantages that：
(1) low energy consumption:The present invention is by adjusting electric voltage frequency come corrective optimal voltage frequency, and the electricity that will be obtained
Voltage-frequency rate carries out genetic algorithm as coding and carries out optimized search, reduces 40% compared to the method not using DVFS technologies
Energy consumption, compared to the energy consumption that the method only with DVFS technologies reduces 30%.
(2) high reliability:The present invention seeks equipment in mobile cloud environment about reliability and energy consumption using genetic algorithm
Optimal task schedule can search for fast speed and reach the purpose of multiple-objection optimization, it is ensured that task is held in terminal
The equipment dependability of row time estimated and nearly 10% can be promoted, be particularly suitable for terminal user handle mass data and
Mass data calculates.
Description of the drawings
Fig. 1 is the Workflow optimization method flow schematic diagram under a kind of mobile cloud environment provided by the invention；
Fig. 2 is genetic algorithm flow diagram after the present invention improves；
Fig. 3 is under mobile cloud environment about population coding mode in genetic algorithm；
Fig. 4 is the energy consumption comparison figure of inventive algorithm and other two kinds of algorithms；
Fig. 5 is the run time comparison diagram of inventive algorithm and other two kinds of algorithms；
Fig. 6 is the reliability comparison diagram of inventive algorithm and other two kinds of algorithms.
Following specific embodiment will be further illustrated the present invention in conjunction with above-mentioned attached drawing.
Specific implementation mode
Technical solution provided by the invention is described further below with reference to attached drawing.
Workflow schedule is implemented using two benches under the mobile cloud environment of the present invention, and the first stage is according to the transmission between task
Cost, the task excessively high to transmission cost merge, and at the same time distribute suitable electric voltage frequency to every equipment, obtain work
Make the initial schedule scheme flowed.Second stage is scheduling phase, with the default workflow off period requirement of satisfaction for constraints, with
Equipment energy consumption is minimum and user dependability requires to be target, is adjusted to initial schedule scheme, obtains final work
Flow scheduling scheme.Specifically include following steps：
Step S1：The workflow submitted to user pre-processes；
Step S2：Work flow model under the mobile cloud environment of structure；
Step S3：Workflow optimal scheduling scheme is generated based on improved adaptive GA-IAGA；
Step S4：The equipment in task to mobile cloud is distributed according to scheduling result；
Wherein, the step S1 further comprises the steps：
Step S11：The excessive node of workflow transmission cost is merged according to workflow transmission cost weights；
Step S12：The most suitable electric voltage frequency of mobile cloud environment equipment calls voltage adjustment technique adjustment equipment；
In step s 11, referring to Fig. 1, it is shown that the Workflow optimization side under a kind of mobile cloud environment provided by the invention
Method flow diagram, the merging according to workflow transmission cost threshold value to data intensive operational stream similar node, the public affairs calculated
Formula is：
In Trans_P [i] [j] matrix, if there is no be set as 0 when transmission for two task nodes；On the contrary then foundation section
Communication cost between point defines weights.The excessive task of transmission cost is assigned in same processor, it not only can
The time overhead generated when being transmitted between reduction task can also reduce the energy consumption generated when transmission, and thus DAG figures can turn
New DAG figures are turned to, following step optimizes on the basis of new DAG figures.
In step s 12, according to the most suitable electric voltage frequency of mobile cloud environment equipment performance adjustment equipment, pass through reasonable distribution
Electric voltage frequency to mobile cloud device can efficiently reduce equipment energy consumption, therefore suitable for mobile cloud device
Electric voltage frequency be vital, the calculation formula of electric voltage frequency is as follows：
It is wherein defined on Z=51 × 10 when under 0.18 μm of technique in the present invention-12；β=1.5.
In step s 2, further comprise the steps：
The set of tasks of workflow can pass through the directed acyclic graph of a sideband weight under step S21. movement cloud environments
Indicate G={ T, E, P }, wherein T={ t1, t2..., tnIt is the set for including N number of task, E={ (i, j) Vi<J } it is each task
Between first order constrained, i.e. tjIt cannot be in tiStart before completing, D indicates workflow off period, P={ p1,p2,...,pmIndicate
The equipment of mobile high in the clouds deployment.Optimal conditions include { T, E, R }, wherein T, and E, R indicate user to time, energy expenditure respectively
With the QoS request value of reliability, i.e., workflow execution it is complete after must reach total time Ttotal≤ T, totle drilling cost Etotal≤ E and
Reliability Rtotal>=R, the total time T that initialization task executestotal=0, totle drilling cost Ctotal=0 and cumulative reliability Rtotal=
0；
Work flow model under step S22. mobile cloud environments known to step S21 needs to define energy consumption model, because
This needs to estimate the deadline time of task, failure rate on bonding apparatus and can be calculated task by step 21 and is setting
Standby upper electric voltage frequency, what following formula calculated arrives：
Wherein E indicates the energy consumption that equipment generates after being adjusted by electric voltage frequency, PstaticIndicate the Static Electro of equipment
Pressure, PdynamicIndicate the dynamic electric voltage of equipment,The time that expression task n is expended in m equipment with the operation of fk frequencies.
Work flow model under step S23 mobile cloud environments known to step S21 needs to define reliability model, i.e. task
The success rate run under equipment, the calculating cost c of the reliability of equipment m by instantaneous failure rate λ and equipment in frequency fii
It influences.Thus the calculation formula of equipment dependability is：
Wherein Rm(fi) indicate equipment m in frequency fiWhen reliability, λ indicate equipment instantaneous failure rate, d indicate one
Constant and d=0.1, ciIndicate equipment in frequency fiWhen calculating cost.
In step S3, further comprise the steps：
Step S31. generates workflow optimal scheduling scheme using Revised genetic algorithum, it is necessary first to mobile cloud environment
Workflow schedule task is encoded；
Referring to Fig. 2, show a kind of improved genetic algorithm provided by the invention solve in workflow energy expenditure and
The flow chart of reliability optimization, it is specific as follows：
After establishing energy consumption model, reliability model and input service stream, for the more preferable scheduling to workflow
Scheme carries out algorithm optimization and each chromosome is needed to set two components, is mapping and scheduling character string respectively.Scheduling represents DAG
Topological sorting ensures precedence constraint.The length of chromosome is equal to task manifold T={ t1, t2.., tn, mapping represents node distribution
Task is to processor and its needs the electric voltage frequency adjusted；Individual coding form is as shown in Figure 3 in specific population.
The adaptive value of each individual, the formula that adaptive value calculates are in needing calculating population after being encoded to individual：
By calculating the adaptive value of each individual of gained, the adaptive value the big, and it is more outstanding to be considered as the individual, therefore according to fitness
Population descending is divided into elite group and common group.
Step S32 divides elite group and common group in population；
Divided in population elite group, common group, every group of individual is according to fitness descending sort.In the mistake to population iteration
Cheng Zhonghui constantly generates new individual, therefore either common group and elite group member can all occur and organize full situation, therefore
It needs to handle elite group and the member commonly organized.
It is added to elite group if generating new more excellent individual, if elite group is full, pair is fitted with elite group membership
Response compares, and of inferior quality individual is rejected from elite group, if commonly organizing full, worst individual is rejected from common group.
Step S33 does crossover operation to the individual in elite group and common group by crossover probability, makes a variation by mutation probability
Operation, generates new group；
According to genetic algorithm cross and variation rule, selection embody it is approaching to optimal solution, intersection embody optimal solution
It generates, variation embodies the coverage of globally optimal solution.Therefore to elite group individual according to 2% probability carry out crossover operation, 5%
Probability carry out mutation operation, otherwise carry out crossover operation according to 5% probability to commonly organizing individual, 2% probability become
ETTHER-OR operation.
Step S34 judges whether to meet hereditary termination condition, if so, optimal solution set is obtained, if it is not, returning to step
S33；
Hereditary termination condition is after setting n times iteration, and the optimal solution of the individual of elite group can meet the time about
In the case of beam, lower energy consumption and higher reliability are kept.
In step s 4, the equipment in task to mobile cloud is distributed according to scheduling result, optimal scheduling scheme is selected to send
To mobile terminal, task and equipment are mapped according to scheduling scheme, while equipment is according to planning progress electric voltage frequency adjustment
It can complete entire workflow schedule.
By the above process, the present invention realizes the optimization of workflow under cloud mobile environment, is meeting wanting for time-constrain
It asks, ensure equipment dependability and reduces equipment energy consumption.
In order to verify the technique effect of technical solution of the present invention, mobile cloud environment is simulated in the lab, to work of the present invention
Make flow-optimized effect to be described in detail：
We, which set, possesses 3 kernels as 3 server in mobile cloud environment, set three equipment in such circumstances most
Voltage under big electric voltage frequency is P1=1J, P2=3J, P3=5J respectively；And the DAG figures of 50-150 number of tasks are randomly generated,
It is incremented by successively as unit of 10 using 50 number of tasks as the first group scheduling task object, it shares 10 groups of data and is considered.Point
Not using energy consumption, time and reliability as observed object, common genetic algorithm optimization (MCC-GA) is run to DAG figures successively, is combined
The algorithm (MCC-ODVGA) proposed in the genetic algorithm optimization (MCC-DVGA) and the present invention of energy consumption is compared explanation, but this
Illustrate to be construed as limiting the invention.
Fig. 4 to 6 shows the comparison of the three kinds of algorithms run in three mobile processors.
Fig. 4 indicates the energy expenditure of each algorithm during executing workflow.In these three algorithms, MCC-ODVGA
With than other algorithm better performances.With the increase of task quantity, the energy lift effect of MCC-ODVGA increasingly tends to
Significantly it is better than other algorithms.
Fig. 5 compared deadline of three kinds of algorithms under different task number.Compared with MCC-GA and MCC-DVGA, MCC-
ODVGA performances in the case where the deadline limits are better than other algorithms always.Therefore, this method is novel, it is not only effectively
Regulating time cost, and further improve the performance of energy consumption.
Fig. 6 shows performance of three kinds of algorithms in reliability.In order to determine the relationship between these algorithms, sample has been carried out
The experimental exploration of third of this reliability.Experiment shows to increase with the complexity of task, and the possibility of mistake can also increase
Add, the increase of the complexity of the increase of task quantity and task dependence also affects the difficulty of task scheduling, when user is ending
Need higher reliability and the lower MCC-ODVGA that can take that can preferably work under time limit constraint.
The explanation of above example is only intended to facilitate the understanding of the method and its core concept of the invention.It should be pointed out that pair
For those skilled in the art, without departing from the principle of the present invention, the present invention can also be carried out
Some improvements and modifications, these improvement and modification are also fallen within the protection scope of the claims of the present invention.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest range caused.
Claims (3)
1. a kind of Workflow optimization method under mobile cloud environment, which is characterized in that include the following steps：
Step S1：The workflow submitted to user pre-processes；
Step S2：Work flow model under the mobile cloud environment of structure；
Step S3：Workflow optimal scheduling scheme is generated based on improved adaptive GA-IAGA；
Step S4：The equipment in task to mobile cloud is distributed according to scheduling result；
Wherein, the step S1 further comprises the steps：
Step S11：The excessive node of workflow transmission cost is merged according to workflow transmission cost weights；
Step S12：The most suitable electric voltage frequency of mobile cloud environment equipment calls voltage adjustment technique adjustment equipment；
The step S11 further comprises the steps：
(1) weights τ is calculated according to Trans_P matrixes；
(2) according to task, there are sequencings, and its transmittability is higher than weights τ, then task is assigned to same processor
On；
Wherein, workflow interior joint, which merges with reference to weight computing formula, is：
In above formula, m indicates that the number of mobile device, Trans_P [i] [j] indicate processor piTo pjData transmission capabilities；
In the step S12, the calculation formula of electric voltage frequency is as follows：
Wherein f indicates the electric voltage frequency of mobile cloud device, VddThe voltage that expression system is supported, VtsIndicate system voltage threshold
Value, LdIndicate that the shortest length of algorithm time, Z and β indicate a constant；
The step S2 further comprises the steps：
The set of tasks of workflow indicates G={ T, E, P } by the directed acyclic graph of a sideband weight under mobile cloud environment,
Middle T={ t1, t2..., tnIt is the set for including N number of task, E={ (i, j) Vi<J } it is first order constrained between each task, i.e. tj
It cannot be in tiStart before completing, D indicates workflow off period, P={ p1,p2,...,pmIndicate setting in mobile high in the clouds deployment
It is standby；Optimal conditions include { T, E, R }, wherein T, and E, R indicate that user needs the user of time, energy expenditure and reliability respectively
Evaluation；
M and n in above-mentioned model respectively represent the task number in processor number and task-set used in cluster, wherein
Each equipment supports dynamic voltage frequency adjustment technology, and i, j indicate mission number, therefore 1≤i, j≤n；
The step S3 further comprises the steps：
Step S31：Need the adaptive value of calculating each individual of new population, the calculating of adaptive value public after being encoded to workflow
Formula is：
Wherein, f (n, m) indicates the adaptive value in the scheduling scheme, Rn,mIndicate reliabilities of the task n on equipment m, RhighTable
Show maximum reliability in scheduling scheme, RlowIndicate minimum reliability in scheduling scheme, En,mIndicate task n on equipment m
Energy consumption, EnormalIndicate the energy consumption that equipment is generated when not using dynamic voltage frequency adjustment technology；
Step S32：Population is divided, partitioning standards are：
The adaptive value of each individual of gained is calculated, the adaptive value the big, and it is more outstanding to be considered as the individual, therefore by scheduling scheme according to fitting
Elite group and common group are included into the division of response descending.
Step S33：Population is intersected, mutation operation, concrete operations are as follows：
In crossover operation, single node exchange is carried out successively to the individual nodes two-by-two in population, obtains new individual, according to suitable
The selection wherein higher individual of adaptive value should be worth, as new explanation；
In mutation operation, it is first depending on probability and isolates the set for needing to make a variation in population, successively to the individual in set
On single node carry out mutation operation, new individual is obtained, according to the adaptive value selection wherein higher individual of adaptive value, as new
Solution.
2. the Workflow optimization method under mobile cloud environment according to claim 1, which is characterized in that
The step S4 further comprises：
Within the scope of preset iterations, after subsequent iteration, reliability, deadline, the energy in the new population of generation
It is suitable to consume and meet user's expection, mapped with equipment task according to obtained scheduling scheme and distribute mobile cloud equipment
Electric voltage frequency.
3. the Workflow optimization method under mobile cloud environment according to claim 1 or 2, which is characterized in that
In the step S1, local device electric voltage frequency is determined by equipment voltage and equipment making technique, passes through reasonable distribution electricity
Voltage-frequency rate is to mobile end equipment to reduce equipment energy consumption.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810095728.5A CN108416465B (en) | 2018-01-31 | 2018-01-31 | Workflow optimization method in mobile cloud environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810095728.5A CN108416465B (en) | 2018-01-31 | 2018-01-31 | Workflow optimization method in mobile cloud environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108416465A true CN108416465A (en) | 2018-08-17 |
| CN108416465B CN108416465B (en) | 2021-08-31 |
Family
ID=63127295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810095728.5A Active CN108416465B (en) | 2018-01-31 | 2018-01-31 | Workflow optimization method in mobile cloud environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108416465B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109783213A (en) * | 2018-12-28 | 2019-05-21 | 杭州电子科技大学 | The workflow fault-tolerant scheduling method of reliability is directed under a kind of edge calculations environment |
| CN109992355A (en) * | 2019-01-30 | 2019-07-09 | 北京理工大学 | A kind of multiple target cloud workflow schedule method based on the non-dominant genetic algorithm of improvement |
| CN110851247A (en) * | 2019-10-12 | 2020-02-28 | 华东师范大学 | Cost optimization scheduling method for constrained cloud workflow |
| CN110928669A (en) * | 2019-12-10 | 2020-03-27 | 浙江工商大学 | Energy consumption perception cloud workflow scheduling optimization method based on multi-population genetic algorithm |
| CN112328380A (en) * | 2020-11-10 | 2021-02-05 | 武汉理工大学 | Task scheduling method and device based on heterogeneous computing |
| CN112600872A (en) * | 2020-11-20 | 2021-04-02 | 南京理工大学 | Efficient scheduling method for crowdsourcing tasks in hybrid cloud environment |
| CN113361833A (en) * | 2020-03-02 | 2021-09-07 | 联芯集成电路制造(厦门)有限公司 | Chemical mechanical polishing system and related dispatching management method |
| CN114881320A (en) * | 2022-04-29 | 2022-08-09 | 哈尔滨理工大学 | Multi-objective optimization scheduling method based on virtual linear production process |
| CN116308220A (en) * | 2023-05-25 | 2023-06-23 | 北京联讯星烨科技有限公司 | Online debugging optimization method and system for workflow data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090182575A1 (en) * | 2008-01-11 | 2009-07-16 | General Electric Company | System and method to manage a workflow in delivering healthcare |
| US20090281818A1 (en) * | 2008-05-07 | 2009-11-12 | International Business Machines Corporation | Quality of service aware scheduling for composite web service workflows |
| CN103902375A (en) * | 2014-04-11 | 2014-07-02 | 北京工业大学 | Cloud task scheduling method based on improved genetic algorithm |
| CN104102532A (en) * | 2013-04-15 | 2014-10-15 | 同济大学 | Low-energy-consumption-based scientific workflow scheduling method in heterogeneous cluster |
| CN105260005A (en) * | 2015-09-22 | 2016-01-20 | 浙江工商大学 | Energy consumption-oriented cloud workflow scheduling optimization method |
| CN105427063A (en) * | 2016-01-04 | 2016-03-23 | 厦门大学 | Micro-grid scheduling decision method and micro-grid scheduling decision system |
| CN107168770A (en) * | 2017-04-14 | 2017-09-15 | 中国人民解放军国防科学技术大学 | A kind of cloud data center workflow schedule of low energy consumption and resource provision method |
-
2018
- 2018-01-31 CN CN201810095728.5A patent/CN108416465B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090182575A1 (en) * | 2008-01-11 | 2009-07-16 | General Electric Company | System and method to manage a workflow in delivering healthcare |
| US20090281818A1 (en) * | 2008-05-07 | 2009-11-12 | International Business Machines Corporation | Quality of service aware scheduling for composite web service workflows |
| CN104102532A (en) * | 2013-04-15 | 2014-10-15 | 同济大学 | Low-energy-consumption-based scientific workflow scheduling method in heterogeneous cluster |
| CN103902375A (en) * | 2014-04-11 | 2014-07-02 | 北京工业大学 | Cloud task scheduling method based on improved genetic algorithm |
| CN105260005A (en) * | 2015-09-22 | 2016-01-20 | 浙江工商大学 | Energy consumption-oriented cloud workflow scheduling optimization method |
| CN105427063A (en) * | 2016-01-04 | 2016-03-23 | 厦门大学 | Micro-grid scheduling decision method and micro-grid scheduling decision system |
| CN107168770A (en) * | 2017-04-14 | 2017-09-15 | 中国人民解放军国防科学技术大学 | A kind of cloud data center workflow schedule of low energy consumption and resource provision method |
Non-Patent Citations (3)
| Title |
|---|
| FABIO COUTINHO等: "A Workflow Scheduling Algorithm for Optimizing Energy-Efficient Grid Resources Usage", 《IEEE》 * |
| 胡海洋等: "移动云计算环境下任务调度的多目标优化方法", 《计算机研究与发展》 * |
| 袁友伟等: "云环境下基于多目标的多科学工作流调度算法", 《软件学报》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109783213B (en) * | 2018-12-28 | 2021-02-19 | 杭州电子科技大学 | Workflow fault tolerance scheduling method for reliability in edge computing environment |
| CN109783213A (en) * | 2018-12-28 | 2019-05-21 | 杭州电子科技大学 | The workflow fault-tolerant scheduling method of reliability is directed under a kind of edge calculations environment |
| CN109992355A (en) * | 2019-01-30 | 2019-07-09 | 北京理工大学 | A kind of multiple target cloud workflow schedule method based on the non-dominant genetic algorithm of improvement |
| CN110851247A (en) * | 2019-10-12 | 2020-02-28 | 华东师范大学 | Cost optimization scheduling method for constrained cloud workflow |
| CN110851247B (en) * | 2019-10-12 | 2023-07-25 | 华东师范大学 | Cost optimization scheduling method for cloud workflow with constraint |
| CN110928669B (en) * | 2019-12-10 | 2022-05-20 | 浙江工商大学 | Energy consumption perception cloud workflow scheduling optimization method based on multi-population genetic algorithm |
| CN110928669A (en) * | 2019-12-10 | 2020-03-27 | 浙江工商大学 | Energy consumption perception cloud workflow scheduling optimization method based on multi-population genetic algorithm |
| US11397425B2 (en) | 2020-03-02 | 2022-07-26 | United Semiconductor (Xiamen) Co., Ltd. | CMP polishing system and associated pilot management system |
| CN113361833A (en) * | 2020-03-02 | 2021-09-07 | 联芯集成电路制造(厦门)有限公司 | Chemical mechanical polishing system and related dispatching management method |
| CN112328380A (en) * | 2020-11-10 | 2021-02-05 | 武汉理工大学 | Task scheduling method and device based on heterogeneous computing |
| CN112600872A (en) * | 2020-11-20 | 2021-04-02 | 南京理工大学 | Efficient scheduling method for crowdsourcing tasks in hybrid cloud environment |
| CN112600872B (en) * | 2020-11-20 | 2023-03-31 | 南京理工大学 | Efficient scheduling method for crowdsourcing tasks in hybrid cloud environment |
| CN114881320A (en) * | 2022-04-29 | 2022-08-09 | 哈尔滨理工大学 | Multi-objective optimization scheduling method based on virtual linear production process |
| CN116308220A (en) * | 2023-05-25 | 2023-06-23 | 北京联讯星烨科技有限公司 | Online debugging optimization method and system for workflow data |
| CN116308220B (en) * | 2023-05-25 | 2023-08-15 | 北京联讯星烨科技有限公司 | Online debugging optimization method and system for workflow data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108416465B (en) | 2021-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108416465A (en) | A kind of Workflow optimization method under mobile cloud environment | |
| Chen et al. | An intelligent robust networking mechanism for the Internet of Things | |
| CN111445111B (en) | Electric power Internet of things task allocation method based on edge cooperation | |
| CN109240818A (en) | Task discharging method based on user experience in a kind of edge calculations network | |
| CN104038392A (en) | Method for evaluating service quality of cloud computing resources | |
| CN103761309A (en) | Operation data processing method and system | |
| CN109343945A (en) | A kind of multitask dynamic allocation method based on contract net algorithm | |
| CN113312177B (en) | Wireless edge computing system and optimizing method based on federal learning | |
| CN110290077A (en) | A kind of industrial SDN resource allocation methods based on real time business configuration | |
| Hu et al. | Edge intelligence for real-time data analytics in an IoT-based smart metering system | |
| Li et al. | Multi-edge collaborative offloading and energy threshold-based task migration in mobile edge computing environment | |
| Wang et al. | Joint service caching, resource allocation and computation offloading in three-tier cooperative mobile edge computing system | |
| CN116361377A (en) | Load prediction system, method and medium based on industrial Internet of things service platform | |
| CN113672684A (en) | Layered user training management system and method for non-independent same-distribution data | |
| CN115764900A (en) | Distribution network resource aggregation method and system considering congestion mitigation benefit | |
| CN116340003A (en) | Self-adaptive edge computing resource management method and system based on deep reinforcement learning | |
| He et al. | Management and real-time monitoring of interconnected energy hubs using digital twin: Machine learning based approach | |
| CN113159539B (en) | Method for combining green energy scheduling and dynamic task allocation in multi-layer edge computing system | |
| CN109587070A (en) | There is the data assemblage method of secret protection and load balancing simultaneously in smart grid | |
| CN109004639A (en) | Power distribution network switched-mode power supply recovery policy optimization method based on complete distributed algorithm | |
| Sum et al. | Analysis on a mobile agent-based algorithm for network routing and management | |
| CN109688068A (en) | Network load balancing method and device based on big data analysis | |
| CN110099415A (en) | A kind of cloud wireless access network computational resource allocation method and system based on volume forecasting | |
| Duan et al. | Lightweight federated reinforcement learning for independent request scheduling in microgrids | |
| CN104507150A (en) | Method for clustering virtual resources in baseband pooling |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240220 Address after: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee after: Dragon totem Technology (Hefei) Co.,Ltd. Country or region after: China Address before: 310018 Xiasha Higher Education Zone, Hangzhou, Zhejiang Patentee before: HANGZHOU DIANZI University Country or region before: China |
|
| TR01 | Transfer of patent right |