CN108769105A - A kind of scheduling system of knowledge services multi-task scheduling optimization method and its structure under cloud environment - Google Patents
A kind of scheduling system of knowledge services multi-task scheduling optimization method and its structure under cloud environment Download PDFInfo
- Publication number
- CN108769105A CN108769105A CN201810323339.3A CN201810323339A CN108769105A CN 108769105 A CN108769105 A CN 108769105A CN 201810323339 A CN201810323339 A CN 201810323339A CN 108769105 A CN108769105 A CN 108769105A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- task
- knowledge services
- services
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000005457 optimization Methods 0.000 title claims abstract description 44
- 239000002245 particle Substances 0.000 claims abstract description 65
- 230000008569 process Effects 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 230000004044 response Effects 0.000 claims abstract description 9
- 230000007246 mechanism Effects 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 230000002123 temporal effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 235000019580 granularity Nutrition 0.000 claims description 3
- 238000013508 migration Methods 0.000 claims description 3
- 230000005012 migration Effects 0.000 claims description 3
- 238000013468 resource allocation Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 230000015556 catabolic process Effects 0.000 claims 1
- 238000006731 degradation reaction Methods 0.000 claims 1
- 238000009826 distribution Methods 0.000 abstract description 7
- 230000003993 interaction Effects 0.000 abstract description 3
- 238000004540 process dynamic Methods 0.000 abstract description 3
- 238000013507 mapping Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 7
- 238000004088 simulation Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000004043 responsiveness Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003801 milling Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
-
- 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
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5041—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the time relationship between creation and deployment of a service
-
- 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
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5041—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the time relationship between creation and deployment of a service
- H04L41/5051—Service on demand, e.g. definition and deployment of services in real time
-
- 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
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5041—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the time relationship between creation and deployment of a service
- H04L41/5054—Automatic deployment of services triggered by the service manager, e.g. service implementation by automatic configuration of network components
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/51—Discovery or management thereof, e.g. service location protocol [SLP] or web services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/61—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources taking into account QoS or priority requirements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/62—Establishing a time schedule for servicing the requests
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/63—Routing a service request depending on the request content or context
Abstract
The invention discloses the scheduling system of knowledge services multi-task scheduling optimization method and its structure under a kind of cloud environment, method is specially：Target is optimized by determining the optimization object function and constraints of the knowledge services multi-task scheduling under cloud environment, and using bi-directional drive collaborative searching algorithm is fallen based on the multigroup under big data environment.The present invention is directed to the knowledge services time introducing dynamic random function in optimization aim, can effectively analog platform service time in actual moving process dynamic random feature, adaptability of the optimizing scheduling algorithm to knowledge services process dynamics and randomness is embodied, the response efficiency of knowledge services process is improved；The mapping relations of particles position vector and knowledge resource distribution are established by binary coding mode, optimization algorithm is mapped to discrete data space, and bi-directional drive mechanism is fallen using multigroup and realizes that common group and the cooperation interaction of model ecotone are searched for, enhance adaptability of the algorithm to random schedule task, effectively solves the optimization problem of knowledge services multi-task scheduling.
Description
Technical field
The present invention relates to the scheduling system of knowledge services multi-task scheduling optimization method and its structure under a kind of cloud environment,
Belong to the knowledge services field under cloud environment.
Background technology
Conglomerate's cloud service platform can provide the manufacturing service of product lifecycle to the user, and flow in production
Product manufacture the knowledge resource of links in Life cycle activity, then are the cores for supporting cloud service system operation, are related to
All kinds of cross-cutting multidisciplinary multi-specialized magnanimity, distribution, multi-source, Heterogeneous Knowledge resource.Due to conglomerate's cloud service platform face
To be large-scale complex product Collaborative Manufacturing process, enterprise customer to platform propose knowledge services demand cloud service collection relate to
And collaborative simulation between the multidisciplinary field such as design and analysis, manufacture, control and parallel computation solve task, between each task
Concertedness is stronger, and the demand to knowledge resource is higher and different.Therefore, it faces user demand complicated and changeable and multi-source is different
The knowledge resource of structure, how by effective task scheduling strategy to high dynamic and execute time randomness service role into
Row equilibrium assignment, will be as the critical issue of promotion conglomerate knowledge services ability.Particle swarm optimization is a kind of based on group
The global search optimization algorithm of characteristic, have it is stronger adaptively and self organization ability, be a kind of to solve extensive task scheduling
The effective means of problem.
Currently, particle swarm optimization is when solving Mission Scheduling, it is easy to be absorbed in local extremum, and then " precocity " occur
Convergent Phenomenon, it is difficult to overcome real time and dynamic and execution existing for group's Company Knowledge service multi-task scheduling process under cloud environment
The problem of time randomness.
Invention content
The problem of existing for the above-mentioned prior art and deficiency, the present invention provides the knowledge services under a kind of cloud environment are more
The scheduling system of task scheduling optimization method and its structure, to solve under cloud environment present in knowledge services scheduling process
Real time and dynamic and execution time stochastic problems, improve knowledge services process response speed, optimize the knowledge clothes under cloud environment
Business system performance.
The technical scheme is that：A kind of knowledge services multi-task scheduling optimization method under cloud environment, passes through determination
The optimization object function and constraints of knowledge services multi-task scheduling under cloud environment, and using based under big data environment
Multigroup falls bi-directional drive collaborative searching algorithm and is optimized to target.
The optimization object function is specially：
Structure is most short with knowledge services time KT, knowledge services quality KQ is optimal, the minimum targets of knowledge services cost KC
Knowledge services optimizing scheduling object function：
The knowledge services time function of KT is：In formula, zab
Indicate the decision variable of b-th of subtask of knowledge services task a；tabIndicate that b-th of subtask of knowledge services task a executes
Service time；t'abIndicate the communication stand-by period that b-th of subtask of knowledge services task a executes；αt1And αt2Indicate power
Weight coefficient；SaThe subtask total amount of expression task a；N indicates that task total amount, rand () change at random in [0,1] range, y=
0,1,2；
The function of knowledge services quality KQ is：In formula, dabIndicate that user takes knowledge
The satisfaction of the knowledge resource service of b-th of subtask of business task a；μaIt is satisfied with extent correction coefficient；N indicates task
Total amount；
The function of knowledge services cost KC is：In formula, cab
Indicate the calculating cost needed for b-th of subtask of knowledge services task a；cab' indicate that b-th of son of knowledge services task a is appointed
Communications cost needed for business；cab" indicate technical costs needed for b-th of subtask of knowledge services task a, αc1、αc2And αc3Table
Show weight coefficient；N indicates task total amount.
The constraints is specially：
Maximum service time-constrain U1, indicate that the actual finish time of each knowledge services task is maximum no more than its
Limiting time, i.e.,：In formula, KTmaxaIndicate knowledge services task a
Permission maximum service limiting time；
Knowledge services cost constraint U2, indicate the cost of serving of each knowledge services task no more than highest service at
This, i.e.,：In formula, KCmaxaIndicate that knowledge services task a can be propped up
The highest cost of serving paid；
Knowledge services task temporal constraint U3, indicate that the end time of the previous service role of temporal constraint relationship cannot
At the beginning of more than next task, i.e.,：hst,a≤hend,a+1；In formula, hst,aEnd time after the completion of expression task a；
hend,a+1At the beginning of expression task a+1；
Knowledge resource services accuracy and constrains U4, indicate that the knowledge resource provided and knowledge services ability must satisfy knowledge
The ability need of service role, i.e.,：In formula, AcaIndicate that knowledge services task a is needed
The knowledge resource to be realized service accuracy；TiabIndicate the knowledge resource service of b-th of subtask of knowledge services task a
Promptness metrics evaluation value；CsabIndicate the compatibility index of the knowledge resource service of b-th of subtask of knowledge services task a
Evaluation of estimate；αa1、αa2Respectively weight coefficient.
Multigroup under the environment based on big data falls bi-directional drive collaborative searching algorithm, specially：
Step 1：Group's particle is encoded, each particle in group is made to indicate that a knowledge services task scheduling is asked
The potential solution of topic；
Step 2：Group particle individual p is initialized, assigns its random position X and speed V, at this time the position of each particle
Vector represents a kind of effective knowledge resource allocation plan；Group number q is set, particle iterations in group member are micro-
Grain accelerator coefficient c1, c2；
Step 3：According to the group number q of setting, the particle individual of initialization is evenly distributed in q process, is formed
Size isGroup, remaining particle individual after rounding is assigned randomly in q process, while according to object function
Calculate the adaptive value of each particle individual in q group；
Step 4：Calculate the global optimum adaptive value F of group ii(i=1,2 ..., q), and according to decision threshold FT by institute
It is model group MC and common group CC to have community divided；
Step 5：Calculate the node strength S of group ii(i=1,2 .., q), and according to SiTo the optimal of respective classes group
Position is evaluated, and maximum node intensity S in affiliated class is obtainediCorresponding group's optimal location is as the generic ecotone
Optimal location；
Step 6：Each particle group is iterated evolution according to bi-directional drive coevolution mechanism, specifically includes：
Step 7：Step 5~step 6 is repeated, and obtains globally optimal solution, until reaching iterations；
The object function is using weigthed sums approach to three object functions during knowledge services multi-task scheduling
It is integrated, the whole fitness function of construction is as follows：
In formula, fh(x) corresponding optimization aim be respectively " the knowledge services time is most short ", " knowledge services optimal quality " and
" knowledge services cost is minimum ", i.e.,：ωhIt is the corresponding weight coefficient of three optimization aims, meets：
The step 1 is specially：
Step 1.1：The position vector for defining particle is matrix X：n×m；Wherein a knowledge services task is represented per a line
Distribution condition, each arrange represents the service scenario of a knowledge resource, as follows：
Wherein, xaw∈ { 0,1 }, a=1,2 ... n, w=1,2 ... m, n indicate that task total amount, m indicate that knowledge resource is total
Amount, m=n,Meet that each row element has and only 1 element value is 1, each column element there can be multiple elements
Value is 1；If xaw=1, it indicates that knowledge services task a is assigned on knowledge resource w and executes, otherwise xaw=0；Each knowledge resource
Offer service can be asked to multiple tasks simultaneously；Knowledge services task can be assigned on any one knowledge resource and execute
And knowledge services task must be assigned on a knowledge resource and execute；Knowledge services task in the process of implementation cannot be by
Disconnected, i.e., the same knowledge services task does not allow to be assigned to simultaneously on multiple knowledge resources；
Step 1.2：Define the rate matrices V of particle：N × m indicates that particle is former to working as required for reaching dbjective state
The basic exchanging order for distribution condition of being engaged in, it is as follows：
The speed of the particle needs to meet：vaw∈ { 0,1 }, vaw+vwa=0 or 1, a=1,2 ... n, w=1,2 ... m.
A kind of knowledge services multiple tasks dispatching system under cloud environment, the system comprises：
Task scheduling buffer module, according to the service ability of system, certain customers is appointed when for multi-user concurrent request
Business request temporarily storage, to ensure that user task and platform resource service ability balance, the response that the system of raising asks user
Speed；
Task parsing module, the knowledge services mission requirements for parsing user's submission, the service role that will be obscured, mix
It degrades, forms it into multiple low granularities, can be by knowledge services set of tasks that knowledge resource directly services；
Knowledge resource scheduler module matches work for preliminary knowledge resource, by the task feature of user's request with know
The static attribute for knowing resource carries out matching primitives, obtains the knowledge money that can fully meet the knowledge services task-set demand for services
Gather in source；
Load administration module, for Knowledge Service Platform in service process the operation of knowledge resource and loading condition into
Row monitoring, the knowledge resource of dynamic adjustment service；Fault-tolerant migration strategy is integrated to solve to lead to service disruption because of accident
Situation, it is ensured that knowledge services process smoothly completes；
Knowledge resource scheduling engine module, for ensureing that knowledge services task scheduling processing efficient accurately carries out；The module
Knowledge services multi-task scheduling optimization method under integrated cloud environment, between knowledge services task and required knowledge resource into
Row rational management forms optimal knowledge services task allocation plan, and submits it Knowledge Service Platform and executed, with
Complete the scheduling process of knowledge services task.
The beneficial effects of the invention are as follows：
1, the present invention introduces dynamic random function for the knowledge services time in optimization aim, can effective analog platform
The dynamic random feature of service time in actual moving process, embody optimizing scheduling algorithm to knowledge services process dynamics and
The adaptability of randomness improves the response efficiency of knowledge services process；
2, the knowledge services multi-task scheduling optimization method establishes particles position vector by binary coding mode
With the mapping relations of knowledge resource distribution, optimization algorithm is mapped to discrete data space, and bi-directional drive machine is fallen using multigroup
System realizes that common group and the cooperation interaction of model ecotone are searched for, and enhancing algorithm has the adaptability of random schedule task
Effect solves the optimization problem of knowledge services multi-task scheduling.
Description of the drawings
Fig. 1 is the knowledge services multiple tasks dispatching system block schematic illustration under cloud environment；
Fig. 2 is knowledge services multi-task scheduling optimization method flow diagram；
Fig. 3 is knife rail calculation knowledge service role scheduling simulation lab diagram (y=0) in Knowledge Service Platform；
Fig. 4 is knife rail calculation knowledge service role scheduling simulation lab diagram (y=1) in Knowledge Service Platform；
Fig. 5 is knife rail calculation knowledge service role scheduling simulation lab diagram (y=2) in Knowledge Service Platform.
Specific implementation mode
Embodiment 1：As shown in Figure 1, the knowledge services multiple tasks dispatching system under a kind of cloud environment, the system comprises：
Task scheduling buffer module, according to the service ability of system, certain customers is appointed when for multi-user concurrent request
Business request temporarily storage, to ensure that user task and platform resource service ability balance, the response that the system of raising asks user
Speed；
Task parsing module, the knowledge services mission requirements for parsing user's submission, the service role that will be obscured, mix
It degrades, forms it into multiple low granularities, can be by knowledge services set of tasks that knowledge resource directly services；
Knowledge resource scheduler module matches work for preliminary knowledge resource, by the task feature of user's request with know
The static attribute for knowing resource carries out matching primitives, obtains the knowledge money that can fully meet the knowledge services task-set demand for services
Gather in source；
Load administration module, for Knowledge Service Platform in service process the operation of knowledge resource and loading condition into
Row monitoring, the knowledge resource of dynamic adjustment service；Fault-tolerant migration strategy is integrated to solve to lead to service disruption because of accident
Situation, it is ensured that knowledge services process smoothly completes；
Knowledge resource scheduling engine module, for ensureing that knowledge services task scheduling processing efficient accurately carries out；The module
Knowledge services multi-task scheduling optimization method under integrated cloud environment, between knowledge services task and required knowledge resource into
Row rational management forms optimal knowledge services task allocation plan, and submits it Knowledge Service Platform and executed, with
Complete the scheduling process of knowledge services task.
Knowledge services multi-task scheduling optimization method under a kind of cloud environment, by determining that the knowledge services under cloud environment are more
The optimization object function and constraints of task scheduling, and searched using bi-directional drive cooperation is fallen based on the multigroup under big data environment
Rope algorithm optimizes target.
Knowledge services multi-task scheduling optimization method flow of the present invention is as shown in Fig. 2, select certain fluid machinery collection
Complex-curved knife rail calculation knowledge service role scheduling process in group's enterprise's cloud Knowledge Service Platform, to more of the knowledge services
Business method for optimizing scheduling carries out test analysis.
Knife rail calculation knowledge service procedure includes in Knowledge Service Platform：Surface modeling, process planning, milling parameter meter
8 calculation, the calculating of knife rail, postpositive disposal, processing environment structure, machining simulation and simulation analysis knowledge services subtasks, are denoted as and appoint
Be engaged in set T={ t1,t2,…,t8(the mark such as t in set of tasks1With in verbal description below, knowledge services task a=1 feelings
Condition refers to identical；Other marks are similarly)；The corresponding available knowledge resources of set of tasks T integrate as KR={ kr1,kr2,…,kr8}
(the mark such as kr in knowledge resource1With verbal description below, knowledge resource w=1 situations refer to identical；Other marks are same
Reason)；Acquire the actual measurement sample such as service time, service quality and cost of serving that 8 knowledge services are appointed on Knowledge Service Platform
Notebook data is as shown in table 1.
The 1 corresponding service parameter of each knowledge resource of table
In table,
It is as follows it is possible to further which the optimization method is arranged：
Step 1：Structure is most short with knowledge services time KT, knowledge services quality KQ is optimal, knowledge services cost KC is minimum
For the knowledge services optimizing scheduling object function of target；
(1) function of knowledge services time KT is：Formula
In, zabIndicate the decision variable of b-th of subtask of knowledge services task a；tabIndicate b-th of knowledge services task a
The service time that subtask executes；t'abIndicate the communication stand-by period that b-th of subtask of knowledge services task a executes；αt1
And αt2Indicate weight coefficient；SaThe subtask total amount of expression task a；N indicates task total amount；Rand () in [0,1] range with
Machine changes, y=0, and 1,2；Dynamic random function rand () is introduced, the stochastic and dynamic to reflect knowledge services scheduling process is special
Sign.
(2) function of knowledge services quality KQ is：
In formula, dabIndicate satisfaction of the user to the knowledge resource service of b-th of subtask of knowledge services task a；
μaIt is satisfied with extent correction coefficient；N indicates task total amount.
(3) function of knowledge services cost KC is：
In formula, cabIndicate the calculating cost needed for b-th of subtask of knowledge services task a；cab' indicate knowledge services
Communications cost needed for b-th of subtask of task a；cab" indicate technology needed for b-th of subtask of knowledge services task a
Cost, αc1、αc2And αc3Indicate weight coefficient；N indicates task total amount.
Step 2：Build knowledge services optimizing scheduling bound for objective function；
(1) maximum service time-constrain U1, indicate the actual finish time of each knowledge services task most no more than it
Big limiting time, i.e.,：
In formula, KTmaxaIndicate the permission maximum service limiting time of knowledge services task a.
(2) knowledge services cost constraint U2, indicate the cost of serving of each knowledge services task no more than highest service
Cost, i.e.,：
In formula, KCmaxaIndicate the highest cost of serving that knowledge services task a can be paid.
(3) knowledge services task temporal constraint U3, indicate the end time of the previous service role of temporal constraint relationship
No more than at the beginning of next task, i.e.,：
hst,a≤hend,a+1
In formula, hst,aEnd time after the completion of expression task a；hend,a+1At the beginning of expression task a+1.
(4) knowledge resource service accuracy constrains U4, indicate that the knowledge resource provided and knowledge services ability must satisfy
The ability need of knowledge services task, i.e.,：
In formula, AcaIndicate that knowledge services task a needs the knowledge resource realized service accuracy；TiabIndicate knowledge services
The promptness metrics evaluation value of the knowledge resource service of b-th of subtask of task a；CsabIndicate the b of knowledge services task a
The compatibility metrics evaluation value of the knowledge resource service of a subtask；αa1、αa2Respectively weight.
Step 3：Three object functions during knowledge services multi-task scheduling are integrated using weigthed sums approach,
The whole fitness function of construction, it is as follows：
In formula, fh(x) corresponding optimization aim be respectively " the knowledge services time is most short ", " knowledge services optimal quality " and
" knowledge services cost is minimum ", i.e.,：ωhIt is the corresponding weight coefficient of three optimization aims, meets：
Step 4：Group's particle is encoded, each particle in group is made to indicate that a knowledge services task scheduling is asked
The potential solution of topic.
Step 4.1：The position vector for defining particle is matrix X:8×8；Wherein a knowledge services task is represented per a line
Distribution condition, each arrange represents the service scenario of a knowledge resource, as follows：
(1)xaw∈ { 0,1 },Meet that each row element has and only 1 element value is 1, each column element can
To there is multiple element values for 1；
(2) if xaw=1, it indicates that knowledge services task a is assigned on knowledge resource w and executes, otherwise xaw=0；
(3) each knowledge resource can ask offer service to multiple tasks simultaneously；
(4) knowledge services task can be assigned to execution on any one knowledge resource and knowledge services task must be divided
It is fitted on a knowledge resource and executes；
(5) knowledge services task cannot be interrupted in the process of implementation, i.e., the same knowledge services task does not allow simultaneously
It is assigned on multiple knowledge resources；
(6) element x in location matrixawWith decision variable z in the step 1abThe knowledge services task a phases referred to
It is corresponding.
Step 4.2：Define the rate matrices V of particle:8×8；Indicate that particle is former to working as required for reaching dbjective state
The basic exchanging order for distribution condition of being engaged in, it is as follows：
The speed of the particle needs to meet：vaw∈ { 0,1 }, vaw+vwa=0 or 1, a=1,2 ... 8, w=1,2 ... 8.
Step 5：Group particle individual p is initialized, assigns its random position X and speed V, at this time the position of each particle
Vector represents a kind of effective knowledge resource allocation plan；Group number q is set, particle iterations in group member are micro-
Grain accelerator coefficient c1、c2；
In the present embodiment, particle number of individuals is 100, opens 4 parallel threads, and particle iterations are 200, and particle accelerates
Constant c1=c2=2.
Step 6：According to the group number q of setting, the particle individual of initialization is evenly distributed in q process, is formed
Size isGroup, remaining particle individual after rounding is assigned randomly in q process, while according to object function
Calculate the adaptive value of each particle individual in q group；
The object function is the whole fitness function constructed in step 3；
Step 7：Calculate the global optimum adaptive value F of group ii(i=1,2 ..., q), and according to decision threshold FT by institute
It is model group MC and common group CC to have community divided；
Step 8：Calculate the node strength S of group ii(i=1,2 .., q), and according to SiTo the optimal of respective classes group
Position is evaluated, and maximum node intensity S in affiliated class is obtainediCorresponding group's optimal location is as the generic ecotone
Optimal location；
Step 9：Each particle group is iterated evolution according to bi-directional drive coevolution mechanism, specifically includes：
If the variable occurred in following rule with it is as before, if being defined in rule, defined in rule
Subject to variable meaning, it is otherwise subject to front.
Rule 1：Evolutionary rule in group：Particle individual inside each group according to following Particle Swarm iterative formula into
Travelingization, and the optimal location of group is generated, wherein group's optimal location of common group is denoted as gbest, the group of model group
Optimal location is denoted as Gbest；
In formula：D indicates highest dimension,Indicate speed of the particle individual k when dimension is d, c under the t times iteration1、c2
Indicate particle aceleration pulse,Indicate personal best particles of the particle individual k when dimension is d under the t times iteration,Table
Show optimal location of the group when dimension is d under the t times iteration,Indicate that particle individual k is when dimension is d under the t times iteration
Position.
The Particle Swarm iterative formula meets following operation rule：
(1)A·θ·B：It indicates position identical with numerical value in matrix B in matrix A being all set to 0, otherwise is 1；If A
In a certain row element simultaneously occur two 1, then be set to 0 by its second 1；
(2)It indicates according to random number clCorrespondence probability value determine whether particle carries out Θ operations；
(3)AΘB：It indicates, if s rows all elements are 0 in matrix B, by the element of s rows s row in matrix A
It all is set to 0, other elements make rand { 0,1 } operation, i.e., take 0 or 1 at random；
(4)Indicate place-exchange operation, the v in rate matrices BsvWhen=1, indicate location matrix A s rows
The row number for the element and the element that numerical value is 1 in v rows that middle numerical value is 1 swaps.
Rule 2：Ecotone bi-directional drive coevolution rule：
Rule 2.1：There are gbesth=max { gbest1,gbest2,...,gbestu, Gbestj
=min { Gbest1,Gbest2,...,Gbestn, and gbesth≥Gbestj, then common group member CChInto model group, former model
Zhong Mowei groups of group MCjIt is rejected；Meanwhile model Studying factors are introduced into evolutionary rule inside common group：
Wherein, r1Indicate that the cooperation relation of model group and common ecotone, R indicate cooperation relation set,It indicates
Optimal value in common group optimal location set,Indicate that the worst-case value in model group optimal location set, u indicate
The total number of common group, n indicate the total number of model group, what m was represented be the quantity of particle individual and m in common group≤
P, D represent highest dimension,Indicate speed of the particle individual k when dimension is d, c under the t times iteration1、c2Indicate that particle accelerates
Constant, c3It is a random number and meets c1rand1+c2rand2+c3∈ [0,4],Indicate particle individual k under the t times iteration
Personal best particle when dimension is d,Indicate optimal location of the group when dimension is d under the t times iteration,Table
Show positions of the particle individual k when dimension is d under the t times iteration,Indicate that common group is when dimension is d under the t times iteration
Model Studying factors；
Rule 2.2：There are group's node strengthsTo arbitraryIt is satisfied byObtain model ecotone optimal location：Wherein, r2Indicate model group and model ecotone
Cooperation relation,Indicate group's node strength of model group a,Indicate group's node strength of model group b,It is group's optimal location of model group a, as model ecotone optimal location；
Rule 2.3：There are group's node strengthsTo arbitraryIt is satisfied byObtain common ecotone optimal location：Wherein, r3Common group cooperates with common ecotone
Relationship,Indicate group's node strength of common group e,Indicate group's node strength of common group f,It is
Group's optimal location of common group e is as common ecotone optimal location；
Wherein, execution priority higher of the ecotone bi-directional drive coevolution rule than evolutionary rule in group；
Step 10：Step 8~step 9 is repeated, and obtains globally optimal solution, until reaching iterations.
Test experiments result：
According to above-mentioned steps, it is real that emulation is carried out to complex curved surface parts knife rail calculation knowledge service role optimizing scheduling process
It tests, records the experimental result of algorithm the searching process, (abscissa as shown in Fig. 3, Fig. 4, Fig. 5：Iterations；Ordinate：Fitness
Value).
It can be seen that in knowledge services multi-task scheduling optimization process from experimental result, with the knowledge services time
The increase of random degree, the knowledge services multi-task scheduling optimization method can give full play to cooperation on multiple populations and execute at random
Solve the problems, such as that the advantage of complicated multi-task scheduling, algorithm quickly tend towards stability and converge to global optimum under environment, it can be effective
Enhance the solution efficiency of knowledge resource scheduling engine, ensures the efficiently and accurately of knowledge services scheduling process under cloud environment；
In the above process：
Cooperation relation unit：If the collaboratively searching activity of different ecotones is two tuple (C R), wherein C=
{c1,c2,...,cqIt is to participate in the movable group's sequence of collaboratively searching, R:C × C be interaction in search process between group according to
The relationship of relying.Referred to as cooperation relation unit, wherein r1Indicate model group and common group
Between cooperation relation, r2Indicate the cooperation relation of model group and model ecotone, r3Common group cooperates with common ecotone
Relationship.Cooperation relation concentrates the number of different ecotone cooperation relation units to be referred to as the mould of the cooperation relation collection, is denoted as | | R | |, R
Indicate cooperation relation set, r1、r2、r3Form R；
Cooperate weight：IfThe cooperation weight in collaborative network between different groups is fallen for multigroup,
In, ciWith coBetween cooperation weight be also referred to as the side right weight that multigroup falls coorporative network；
Distance vector：Personal best particle by group's optimal location of group i respectively with u particle in the group is asked
Difference simultaneously takes absolute value, and obtains the distance vector of group's optimal location：Hi=(h1,h2,…,hu)；
Responsiveness：Qualifying distance threshold value DD is set, according to response eviFormula：Adjust the distance to
Measure HiTraversal operation is carried out, group's particle can be obtained to the response of group's optimal location, response is sequentially added and is obtained
The responsiveness e of group's optimal locationi。
Group's node strength：In MCCN, the intensity for defining group's node is Si, thenWherein：
ωioFor group ciWith coBetween cooperation weight, eiFor the responsiveness of group's node, UiFor group ciNeighborhood, neighborhood indicate with
Group ciThere are the set of the group of cooperation relation
It is describedIf Fi>=FT then shows that the group has stronger local optimal searching ability, as
Model group, is denoted as MC；If Fi<FT then shows that then the group has stronger global exploring ability, as common group
It falls, is denoted as CC.
The specific implementation mode of the present invention is explained in detail above in conjunction with attached drawing, but the present invention is not limited to above-mentioned
Embodiment within the knowledge of a person skilled in the art can also be before not departing from present inventive concept
Put that various changes can be made.
Claims (6)
1. the knowledge services multi-task scheduling optimization method under a kind of cloud environment, it is characterised in that：By determining under cloud environment
The optimization object function and constraints of knowledge services multi-task scheduling, and it is two-way using being fallen based on the multigroup under big data environment
Driving collaborative searching algorithm optimizes target.
2. the knowledge services multi-task scheduling optimization method under cloud environment according to claim 1, it is characterised in that：It is described
Optimization object function is specially：
Structure is most short with knowledge services time KT, knowledge services quality KQ is optimal, the minimum targets of knowledge services cost KC are known
Know service dispatch optimization object function：
The knowledge services time function of KT is：In formula, zabIt indicates
The decision variable of b-th of subtask of knowledge services task a；tabIndicate the clothes that b-th of subtask of knowledge services task a executes
It is engaged in the time；t'abIndicate the communication stand-by period that b-th of subtask of knowledge services task a executes；αt1And αt2Indicate weight system
Number；SaThe subtask total amount of expression task a；N indicates that task total amount, rand () change at random in [0,1] range, y=0,1,
2；
The function of knowledge services quality KQ is：In formula, dabIndicate that user appoints knowledge services
The satisfaction of the knowledge resource service of b-th of subtask of business a；μaIt is satisfied with extent correction coefficient；N indicates that task is total
Amount；
The function of knowledge services cost KC is：In formula, cabIt indicates
Calculating cost needed for b-th of subtask of knowledge services task a；cab' indicate b-th of subtask institute of knowledge services task a
The communications cost needed；cab" indicate technical costs needed for b-th of subtask of knowledge services task a, αc1、αc2And αc3Indicate power
Weight coefficient；N indicates task total amount.
3. the knowledge services multi-task scheduling optimization method under cloud environment according to claim 2, it is characterised in that：It is described
Constraints is specially：
Maximum service time-constrain U1, indicate the actual finish time of each knowledge services task no more than its maximum restriction
Time, i.e.,：In formula, KTmaxaIndicate permitting for knowledge services task a
Perhaps maximum service limiting time；
Knowledge services cost constraint U2, indicate the cost of serving of each knowledge services task no more than highest cost of serving, i.e.,：In formula, KCmaxaIndicate that knowledge services task a can be paid most
High cost of serving；
Knowledge services task temporal constraint U3, indicate the end time of previous service role of temporal constraint relationship no more than
At the beginning of next task, i.e.,：hst,a≤hend,a+1；In formula, hst,aEnd time after the completion of expression task a；hend,a+1Table
At the beginning of showing task a+1；
Knowledge resource services accuracy and constrains U4, indicate that the knowledge resource provided and knowledge services ability must satisfy knowledge services
The ability need of task, i.e.,：In formula, AcaIndicate that knowledge services task a needs reality
Existing knowledge resource services accuracy；TiabIndicate the timely of the knowledge resource service of b-th of subtask of knowledge services task a
Property metrics evaluation value；CsabIndicate the compatibility metrics evaluation of the knowledge resource service of b-th of subtask of knowledge services task a
Value；αa1、αa2Respectively weight coefficient.
4. the knowledge services multi-task scheduling optimization method under cloud environment according to claim 3, it is characterised in that：It is described
Bi-directional drive collaborative searching algorithm is fallen based on the multigroup under big data environment, specially：
Step 1：Group's particle is encoded, each particle one knowledge services Mission Scheduling of expression in group is made
Potential solution；
Step 2：Group particle individual p is initialized, assigns its random position X and speed V, at this time the position vector of each particle
Represent a kind of effective knowledge resource allocation plan；Group number q is set, particle iterations in group member, particle adds
Fast coefficient c1、c2；
Step 3：According to the group number q of setting, the particle individual of initialization is evenly distributed in q process, forms size
ForGroup, remaining particle individual after rounding is assigned randomly in q process, at the same according to object function calculate q
The adaptive value of each particle individual in a group；
Step 4：Calculate the global optimum adaptive value F of group ii(i=1,2 ..., q), and according to decision threshold FT by all groups
It is divided into model group MC and common group CC；
Step 5：Calculate the node strength S of group ii(i=1,2 .., q), and according to SiTo the optimal location of respective classes group
It is evaluated, obtains maximum node intensity S in affiliated classiCorresponding group's optimal location as the generic ecotone most
Excellent position；
Step 6：Each particle group is iterated evolution according to bi-directional drive coevolution mechanism, specifically includes：
Step 7：Step 5~step 6 is repeated, and obtains globally optimal solution, until reaching iterations；
The object function is to be carried out to three object functions during knowledge services multi-task scheduling using weigthed sums approach
It integrates, the whole fitness function of construction is as follows：
In formula, fh(x) corresponding optimization aim is respectively " the knowledge services time is most short ", " knowledge services optimal quality " and " knowledge
Cost of serving is minimum ", i.e.,：ωhIt is the corresponding weight coefficient of three optimization aims, meets：
5. the knowledge services multi-task scheduling optimization method under cloud environment according to claim 4, it is characterised in that：It is described
Step 1 is specially：
Step 1.1：The position vector for defining particle is matrix X：n×m；Point of a knowledge services task is wherein represented per a line
With situation, each row represent the service scenario of a knowledge resource, as follows：
Wherein, xaw∈ { 0,1 }, a=1,2 ... n, w=1,2 ... m, n indicate that task total amount, m indicate knowledge resource total amount, m
=n,Meet that each row element has and only 1 element value is 1, each column element there can be multiple element values to be
1；If xaw=1, it indicates that knowledge services task a is assigned on knowledge resource w and executes, otherwise xaw=0；Each knowledge resource
To ask offer service to multiple tasks simultaneously；Knowledge services task can be assigned on any one knowledge resource and execute and know
Knowledge service role, which must be assigned on a knowledge resource, to be executed；Knowledge services task cannot be interrupted in the process of implementation,
The i.e. same knowledge services task does not allow to be assigned to simultaneously on multiple knowledge resources；
Step 1.2：Define the rate matrices V of particle：N × m indicates that particle is to divide current task required for reaching dbjective state
Basic exchanging order with situation, it is as follows：
The speed of the particle needs to meet：vaw∈ { 0,1 }, vaw+vwa=0 or 1, a=1,2 ... n, w=1,2 ... m.
6. the knowledge services multi-task scheduling optimization method structure under a kind of cloud environment using described in any one of claim 1-5
The multiple tasks dispatching system built, which is characterized in that the system comprises：
Task scheduling buffer module, according to the service ability of system, certain customers' task is asked when for multi-user concurrent request
Temporary storage is asked, to ensure user task and platform resource service ability balance, the response speed that the system of raising asks user；
Task parsing module, the knowledge services mission requirements for parsing user's submission carry out the service role for obscuring, mixing
Degradation, forms it into multiple low granularities, can be by knowledge services set of tasks that knowledge resource directly services；
Knowledge resource scheduler module matches work for preliminary knowledge resource, and the task feature of user's request is provided with knowledge
The static attribute in source carries out matching primitives, obtains the knowledge resource collection that can fully meet the knowledge services task-set demand for services
It closes；
Administration module is loaded, for the operation of knowledge resource and loading condition to be supervised in service process to Knowledge Service Platform
Control, the knowledge resource of dynamic adjustment service；The case where fault-tolerant migration strategy is to solve to lead to service disruption because of accident is integrated,
Ensure smoothly completing for knowledge services process；
Knowledge resource scheduling engine module, for ensureing that knowledge services task scheduling processing efficient accurately carries out；The module is integrated
Knowledge services multi-task scheduling optimization method under cloud environment, is closed between knowledge services task and required knowledge resource
Reason scheduling, forms optimal knowledge services task allocation plan, and submit it Knowledge Service Platform and executed, to complete
The scheduling process of knowledge services task.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810323339.3A CN108769105A (en) | 2018-04-12 | 2018-04-12 | A kind of scheduling system of knowledge services multi-task scheduling optimization method and its structure under cloud environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810323339.3A CN108769105A (en) | 2018-04-12 | 2018-04-12 | A kind of scheduling system of knowledge services multi-task scheduling optimization method and its structure under cloud environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108769105A true CN108769105A (en) | 2018-11-06 |
Family
ID=63981510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810323339.3A Pending CN108769105A (en) | 2018-04-12 | 2018-04-12 | A kind of scheduling system of knowledge services multi-task scheduling optimization method and its structure under cloud environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108769105A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111261233A (en) * | 2020-01-16 | 2020-06-09 | 青岛农业大学 | Marine medicinal biomolecule dynamics cooperative calculation contrast analysis algorithm |
| CN111343259A (en) * | 2020-02-17 | 2020-06-26 | 武汉轻工大学 | Binary code-based cloud task scheduling method, server and storage medium |
| CN112053002A (en) * | 2020-09-11 | 2020-12-08 | 浙江财经大学 | Cloud manufacturing multi-task scheduling method based on utility perception |
| CN114781836A (en) * | 2022-04-07 | 2022-07-22 | 央视市场研究股份有限公司 | Investigation system of universe user intelligent scheduling |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951425A (en) * | 2015-07-20 | 2015-09-30 | 东北大学 | Cloud service performance adaptive action type selection method based on deep learning |
| US9213574B2 (en) * | 2010-01-30 | 2015-12-15 | International Business Machines Corporation | Resources management in distributed computing environment |
| CN105430706A (en) * | 2015-11-03 | 2016-03-23 | 国网江西省电力科学研究院 | WSN (Wireless Sensor Networks) routing optimization method based on improved PSO (particle swarm optimization) |
| CN105550033A (en) * | 2015-11-17 | 2016-05-04 | 北京交通大学 | Genetic-tabu hybrid algorithm based resource scheduling policy method in private cloud environment |
| CN106610866A (en) * | 2016-06-17 | 2017-05-03 | 四川用联信息技术有限公司 | Service value constrained task scheduling algorithm in cloud storage environment |
| CN106611277A (en) * | 2016-05-13 | 2017-05-03 | 四川用联信息技术有限公司 | Cloud resource scheduling method in mixed cloud model |
| US20170195247A1 (en) * | 2015-12-31 | 2017-07-06 | EMC IP Holding Company LLC | Method and apparatus for cloud system |
| CN107203805A (en) * | 2017-04-28 | 2017-09-26 | 昆明理工大学 | A kind of many group's bi-directional drive collaborative searching algorithms under big data environment |
| CN107317836A (en) * | 2017-05-16 | 2017-11-03 | 北京交通大学 | One kind mixing cloud environment lower time appreciable request scheduling method |
-
2018
- 2018-04-12 CN CN201810323339.3A patent/CN108769105A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9213574B2 (en) * | 2010-01-30 | 2015-12-15 | International Business Machines Corporation | Resources management in distributed computing environment |
| CN104951425A (en) * | 2015-07-20 | 2015-09-30 | 东北大学 | Cloud service performance adaptive action type selection method based on deep learning |
| CN105430706A (en) * | 2015-11-03 | 2016-03-23 | 国网江西省电力科学研究院 | WSN (Wireless Sensor Networks) routing optimization method based on improved PSO (particle swarm optimization) |
| CN105550033A (en) * | 2015-11-17 | 2016-05-04 | 北京交通大学 | Genetic-tabu hybrid algorithm based resource scheduling policy method in private cloud environment |
| US20170195247A1 (en) * | 2015-12-31 | 2017-07-06 | EMC IP Holding Company LLC | Method and apparatus for cloud system |
| CN106611277A (en) * | 2016-05-13 | 2017-05-03 | 四川用联信息技术有限公司 | Cloud resource scheduling method in mixed cloud model |
| CN106610866A (en) * | 2016-06-17 | 2017-05-03 | 四川用联信息技术有限公司 | Service value constrained task scheduling algorithm in cloud storage environment |
| CN107203805A (en) * | 2017-04-28 | 2017-09-26 | 昆明理工大学 | A kind of many group's bi-directional drive collaborative searching algorithms under big data environment |
| CN107317836A (en) * | 2017-05-16 | 2017-11-03 | 北京交通大学 | One kind mixing cloud environment lower time appreciable request scheduling method |
Non-Patent Citations (1)
| Title |
|---|
| 阴艳超等: "多群落双向驱动协作搜索算法", 《计算机集成制造***》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111261233A (en) * | 2020-01-16 | 2020-06-09 | 青岛农业大学 | Marine medicinal biomolecule dynamics cooperative calculation contrast analysis algorithm |
| CN111343259A (en) * | 2020-02-17 | 2020-06-26 | 武汉轻工大学 | Binary code-based cloud task scheduling method, server and storage medium |
| CN111343259B (en) * | 2020-02-17 | 2022-08-12 | 武汉轻工大学 | Binary code-based cloud task scheduling method, server and storage medium |
| CN112053002A (en) * | 2020-09-11 | 2020-12-08 | 浙江财经大学 | Cloud manufacturing multi-task scheduling method based on utility perception |
| CN112053002B (en) * | 2020-09-11 | 2023-07-07 | 浙江财经大学 | Cloud manufacturing multi-task scheduling method based on utility perception |
| CN114781836A (en) * | 2022-04-07 | 2022-07-22 | 央视市场研究股份有限公司 | Investigation system of universe user intelligent scheduling |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Fuzzy optimal allocation model for task–resource assignment problem in a collaborative logistics network | |
| Hamta et al. | A hybrid PSO algorithm for a multi-objective assembly line balancing problem with flexible operation times, sequence-dependent setup times and learning effect | |
| CN108769105A (en) | A kind of scheduling system of knowledge services multi-task scheduling optimization method and its structure under cloud environment | |
| CN103677958B (en) | The resource regulating method and device of a kind of virtual cluster | |
| Saif et al. | A survey on assembly lines and its types | |
| CN104842564B (en) | A kind of 3 D-printing multitask Optimization Scheduling based on NSGA II | |
| Ning et al. | An improved quantum genetic algorithm based on MAGTD for dynamic FJSP | |
| CN104077634B (en) | active-reactive type dynamic project scheduling method based on multi-objective optimization | |
| CN103677960A (en) | Game resetting method for virtual machines capable of controlling energy consumption | |
| CN112306658A (en) | Digital twin application management scheduling method for multi-energy system | |
| Zahiri et al. | An MCDA-DEA approach for mixed-model assembly line balancing problem under uncertainty | |
| CN101957760A (en) | Method for measuring process execution time | |
| Luo et al. | A Pareto-based two-stage evolutionary algorithm for flexible job shop scheduling problem with worker cooperation flexibility | |
| CN115965154A (en) | Knowledge graph-based digital twin machining process scheduling method | |
| Yang et al. | A fully hybrid algorithm for deadline constrained workflow scheduling in clouds | |
| CN102651115B (en) | Parallel asynchronous hybrid algorithm processing system and reservoir or Optimal Scheduling of Multi-reservoir System method | |
| Gong et al. | Energy-efficient flexible job shop scheduling problem considering discrete operation sequence flexibility | |
| CN104869154A (en) | Distributed resource scheduling method for balancing resource credibility and user satisfaction | |
| Stahl et al. | A general economic equilibrium model of distributed computing | |
| CN107589980A (en) | A kind of dispatching method of cloud computing resources | |
| CN110119317A (en) | A kind of cloud computing method for scheduling task and system based on genetic algorithm | |
| CN108270833A (en) | Render automatic scheduling method, the apparatus and system of cloud resource | |
| CN109783189A (en) | A kind of quiescent operation stream scheduling method and device | |
| Zhong et al. | Sequencing problem for a hull mixed-model assembly line considering manufacturing complexity | |
| KORUCA et al. | A priority rule based production scheduling module on faborg-sim simulation tool |
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 |
Application publication date: 20181106 |
|
| RJ01 | Rejection of invention patent application after publication |