CN110120888B - Cloud crowdsourcing platform mass service resource combination optimization method and system - Google Patents
Cloud crowdsourcing platform mass service resource combination optimization method and system Download PDFInfo
- Publication number
- CN110120888B CN110120888B CN201910345260.5A CN201910345260A CN110120888B CN 110120888 B CN110120888 B CN 110120888B CN 201910345260 A CN201910345260 A CN 201910345260A CN 110120888 B CN110120888 B CN 110120888B
- Authority
- CN
- China
- Prior art keywords
- crowdsourcing
- cloud
- optimization
- service
- service resource
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 153
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012356 Product development Methods 0.000 claims abstract description 63
- 230000001580 bacterial effect Effects 0.000 claims description 30
- 238000004422 calculation algorithm Methods 0.000 claims description 27
- 230000002431 foraging effect Effects 0.000 claims description 16
- 241000894006 Bacteria Species 0.000 claims description 14
- 230000035605 chemotaxis Effects 0.000 claims description 12
- 238000012217 deletion Methods 0.000 claims description 7
- 230000037430 deletion Effects 0.000 claims description 7
- 238000011161 development Methods 0.000 claims description 7
- 239000006185 dispersion Substances 0.000 claims description 7
- 230000010076 replication Effects 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 3
- 230000009182 swimming Effects 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000009825 accumulation Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 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
- 238000013468 resource allocation Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 235000015097 nutrients Nutrition 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241001522296 Erithacus rubecula Species 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000003399 chemotactic effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 239000013256 coordination polymer Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
- H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
-
- 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
- H04L41/5003—Managing SLA; Interaction between SLA and QoS
- H04L41/5009—Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a cloud crowdsourcing platform mass service resource combination optimization method and system. The method comprises the following steps: establishing a cloud crowdsourcing platform, and executing resource combination global initial optimization in a cloud crowdsourcing platform data center according to a cloud crowdsourcing service resource combination optimization target; decomposing a cloud crowdsourcing service resource combination optimization target, and based on initial global optimization, executing local optimization of crowdsourcing service resources by crowdsourcing communities; based on the optimization results, the optimization results of the crowdsourcing communities are synthesized, and an optimal cloud crowdsourcing resource combination optimization scheme is filtered out. According to the invention, wide social resources (crowdsourcing product development resources) are automatically matched in the cloud crowdsourcing platform, and the crowdsourcing requirement of the complex product development of a user is met. According to the technical scheme, the scheme for developing the mass service resource combination for the crowdsourcing products can be effectively mined.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a cloud crowdsourcing platform mass service resource combination optimization method and system.
Background
With the development of industry, facing the challenge of global manufacturing industry, the development of crowdsourced products is becoming a new online distributed problem solving mode, and through the mode, networked social resources collaboratively fulfill the complex task demands from users.
Crowd-sourced product development is the assignment of tasks to an uncertain and large number of service resources available for use, such as: a crowd-sourced community platform with a large number of stakeholders actively participating in the product development process. Design and manufacturing resources distributed at different geographic positions are scheduled in real time through a crowdsourcing community platform for public competition, and a service resource combination scheme meeting the complex task requirements of users is dynamically generated. The combination optimization of the mass service resources needs a new processing mode and can become an information asset with stronger insight discovery, decision making and flow optimization capabilities.
At present, an intelligent service engine-oriented task crowdsourcing method is disclosed, and a service platform distributes tasks to service nodes as appropriate as possible through a game of the service platform and the service nodes, namely, the highest cost performance is achieved. In addition, the platform system and the operation method thereof are used for establishing direct connection between engineering machinery enterprise users and the public, so that a direct and effective way is found for engineering machinery industry enterprises to solve technical problems and schemes, and the product research and development speed of the enterprises is accelerated. Additionally, a system and method for implementing a hybrid crowdsourcing platform that can receive a task request having a plurality of work units; individual units of work for a task may be analyzed to identify relevant metrics for completion of the units of work by crowd-sourced resources and computer-based resources.
In order to realize cross-platform calling of crowdsourcing product development resources, the existing research on crowdsourcing and cloud service resource combination optimization has the following two limitations and disadvantages, namely, the characteristics of problems related to the crowdsourcing product development service resource combination optimization are described as follows: for one, at present, the crowd-sourced community mainly aims at micro tasks (i.e. completing a single task of a user), and an application platform of the crowd-sourced community is based on a Web technology. Each micro task child node corresponds to a lot of functionally qualified candidate service resources, and with the increase of complexity of a product development process, crowdsourcing production faces the challenge of big data application, and it is generally difficult to correctly evaluate a crowdsourcing service resource combination optimization scheme, so that the crowdsourcing product development efficiency is greatly reduced. Secondly, due to the characteristics of diversity, complexity and scale of crowdsourcing service resources in crowdsourcing community environments, mass data cannot be directly used for crowdsourcing service resource combination, and crowdsourcing service resource combination meeting the complex task requirements of users is one of key technologies for realizing crowdsourcing community cooperation and further realizing crowdsourcing product development.
Disclosure of Invention
In order to solve the problems, the application provides a cloud crowdsourcing platform mass service resource combination optimization method and system.
The application provides a cloud crowdsourcing platform mass service resource combination optimization method, which comprises the following steps:
according to the cloud crowdsourcing requirements of users, namely crowdsourcing complex product development task requirements, registering relevant product development quality of service (QoS) index information aiming at microscopic tasks, namely single tasks, to a cloud crowdsourcing platform data center by each crowdsourcing community, and constructing a cloud crowdsourcing platform of a massive resource combination scheme;
and obtaining a complex task synthesis service quality index based on the service quality index corresponding to the microscopic task, and further establishing a cloud crowdsourcing resource combination optimization target. Aiming at the cloud crowdsourcing platform resource combination mass data environment, executing initial global optimization in a cloud crowdsourcing platform data center by adopting an intelligent optimization algorithm to obtain an initial crowdsourcing resource combination scheme;
and respectively transmitting the initial optimization scheme to the crowdsourcing communities, decomposing the optimization target through cloud crowdsourcing resource combination to obtain local optimization targets of the crowdsourcing communities, and executing local optimization by the crowdsourcing communities by adopting an intelligent optimization algorithm. And synthesizing the crowdsourcing community optimization results to obtain a cloud crowdsourcing resource combination scheme result.
Based on crowdsourcing requirements of complex product development, a cloud crowdsourcing platform is constructed, and relevant QoS information is registered to a cloud crowdsourcing platform data center by crowdsourcing communities. And analyzing the crowdsourcing service resource class, the crowdsourcing service resource configuration execution scheme and the crowdsourcing service resource combination scheme, thereby constructing a cloud crowdsourcing platform for resource combination mass data. The method comprises the following steps:
step1, a service resource class Crowd _ Res corresponding to a complex task CA is represented as:
Crowd_Res＝{(Comm_Ser1,SIZE1),(Comm_Ser2,SIZE2),...,(Comm_Sern,SIZEn)}
wherein Comm _ SeriRepresents the ith service resource class, SIZE, owned by the cloud crowdsourcing platformiA capacity parameter indicating the ith service resource class, and n indicating the total number of service resource classes.
Step2, the service resource allocation execution scheme is determined according to the following mode:
variable xij(1≤i≤n,1≤j≤SIZEi) Indicates whether to use the candidate service resource Comm _ Seri.csjAssignment to micro-tasks tiAnd if so, xij1, otherwise xij＝0；
Will be provided with
Serving resources as a cloud crowdsourcingA configured execution scheme;
step3, correspondingly, the cloud crowdsourcing service resource combination scheme TOL is expressed as:
TOL＝SIZE1*SIZE2*...,*SIZEn. When SIZEiWhen the ratio is relatively large, the TOL value is increased along with the increment of n, and the cloud crowdsourcing platform has the characteristic of a resource combination scheme of mass data.
Further, according to the mass data characteristics of the resource combination scheme, initial global optimization is executed in a cloud crowdsourcing platform data center on the premise that a product development path global utility function is obtained. Developing a global optimization utility function u for a path solution jjDetermined according to the following formula:
wherein, wk(k ═ 1, 2.., 5.) is the quality of service attribute value ckWeight of (k ═ 1, 2.., 5), Qj,k(k 1, 2.., 5) represents that the development path scheme j has a quality of service attribute value ckA combined value of (k ═ 1,2,.., 5);
accordingly, a normalized quality of service attribute value Q 'is calculated according to the following formula'j,k：
Or
Wherein,
respectively representing the maximum value and the minimum value of the kth service quality attribute value of the product development path execution scheme.
Further, the method further comprises:
and performing initial global optimization on a cloud crowdsourcing platform data center by adopting a bacterial foraging optimization algorithm according to the global optimization utility function and the crowdsourcing service resource combination optimization target to obtain a cloud crowdsourcing resource combination initial scheme. On the basis, target decomposition is optimized through crowdsourcing service resource combination, local optimization is executed by crowdsourcing communities by further adopting a bacterial foraging optimization algorithm, optimization results of the crowdsourcing communities are synthesized, and a cloud crowdsourcing resource combination scheme result is obtained. Therefore, the cloud crowdsourcing resource combination problem is solved by adopting a cooperative bacterial foraging optimization CBFO algorithm.
Further, solving the cloud crowdsourcing resource combination problem comprises:
step 1: a user submits crowdsourcing product development requirements to a crowdsourcing agent data center for requirement matching to obtain corresponding product development workflows;
step 2: the crowdsourcing agent data center initializes the bacterial community CO according to the product development workflow1The position and relevant operation parameters thereof are used for carrying out preliminary search on cloud crowdsourcing service resources;
step 3: judging whether the number of dispersing iterations is reached, if so, turning to Step8, otherwise, executing Step 4;
step 4: in the bacterial group, chemotaxis operation is executed to complete the operations of turning, moving and swimming;
step 5: half of the undesirable bacteria die and reproduce the good bacteria;
step 6: judging whether the number of copying iterations is reached, if the condition is not met, turning to Step4, otherwise executing Step 7;
step 7: dispelling part of bacteria, turning to Step 3;
step 8: discovering a service resource combination scheme corresponding to the complex task by the bacterial colony, and transmitting the service resource combination scheme to each crowdsourcing community corresponding to the micro task;
step 9: serving resource locations based on preliminary global search, and COk(k 2.,. N), performing community local optimization by the crowdsourcing communities, and simultaneously performing parallel search of a cloud and crowdsourcing service resource combination scheme;
step 10: bacterial foraging optimization BFO of various crowdsourced communities respectively executes chemotaxis, copying, deletion and dispersion operations;
step 11: judging whether the cloud crowdsourcing service resource combination optimization scheme is improved or not, and if the conditions are met, replacing the position corresponding to the preliminary optimization scheme of the crowdsourcing service resource combination with the service resource position searched by the crowdsourcing community BFO;
step 12: and outputting a cloud crowdsourcing service resource combination optimization solution and service resource positions in the related crowdsourcing community resource pool.
Further, the method further comprises:
based on a preset BFO coding mode, flora is randomly distributed in a data center or crowdsourced communities, and then chemotaxis, replication, deletion and dispersion operations are carried out on the flora.
The application also provides a cloud-based crowdsourcing product development resource combination optimization system, which comprises crowdsourcing community service resources, a crowdsourcing agent data center, a crowdsourcing product development workflow engine module, a user demand confirmation module, a crowdsourcing service resource initial optimization module, a crowdsourcing community local optimization module and a calculation result display module, wherein the system is used for realizing the method as set forth in any one of claims 1 to 6.
Further, the crowdsourcing service resource initial optimization module is used for generating a corresponding workflow model according to user requirements, then performing massive data preprocessing according to a resource combination optimization target and a CBFO algorithm, and accordingly achieving crowdsourcing service resource combination initial optimization.
Further, the local optimization module of the crowdsourcing community is used for executing initial optimization of crowdsourcing service resource combination through a crowdsourcing agent data center according to a workflow model and an optimization target generated by user requirements, an initial optimization result is transmitted to each crowdsourcing community by the workflow engine module, and the crowdsourcing community carries out mass data preprocessing according to a CBFO algorithm on the basis of the initial optimization and executes parallel and local optimization of the crowdsourcing community so as to improve the efficiency of resource combination optimization of crowdsourcing product development.
The beneficial effects of the invention at least comprise:
(1) the invention can realize the matching of crowdsourcing product development requirements and crowdsourcing service resources, and solves the problem that the conventional crowdsourcing community resource environment cannot be directly applied to the crowdsourcing service resource combination realization by establishing a cloud crowdsourcing platform.
(2) Based on a cloud crowdsourcing platform, establishing a corresponding cloud crowdsourcing resource combination optimization target, and executing crowdsourcing service resource combination initial optimization by using a bacterial foraging optimization algorithm. The method realizes the pretreatment of the cloud crowdsourcing mass service resource combination scheme and lays a foundation for local optimization of crowdsourcing communities.
(3) Based on the pretreatment of the massive service resource combination scheme, a bacterial foraging optimization algorithm is used, and the crowdsourcing communities execute parallel and local optimization, so that the mining efficiency of the crowdsourcing service resource combination is further improved. Based on user requirements, automatic matching and combination of crowdsourcing community environment service resources on a cloud crowdsourcing platform are achieved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart of a method and a system for optimizing a mass service resource combination of a cloud crowdsourcing platform according to the present application;
FIG. 2 is a system architecture diagram of the present application;
FIG. 3 is a cloud crowdsourcing platform mass service resource combination optimization framework;
fig. 4 is a resource optimization flow of crowd-sourced product development based on a CBFO optimization unit BFO.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Referring to fig. 1, the present application provides a method for optimizing a cloud crowdsourcing platform mass service resource combination, where the method includes:
according to the cloud crowdsourcing requirements of users, namely crowdsourcing complex product development task requirements, registering relevant product development quality of service (QoS) index information aiming at microscopic tasks, namely single tasks, to a cloud crowdsourcing platform data center by each crowdsourcing community, and constructing a cloud crowdsourcing platform of a massive resource combination scheme;
on the basis, for specific crowdsourcing product development requirements, based on a B/S framework of a cloud crowdsourcing platform, a user submits own requirements through a Web page, maps the requirements into corresponding product development workflows and stores the corresponding product development workflows in a data center of the cloud crowdsourcing platform.
And obtaining a synthetic service quality index of the complex task facing the product development workflow based on the service quality index corresponding to the microscopic task, and further establishing a cloud crowdsourcing resource combination optimization target. Aiming at the cloud crowdsourcing platform resource combination mass data environment, executing initial global optimization in a cloud crowdsourcing platform data center by adopting an intelligent optimization algorithm to obtain an initial crowdsourcing resource combination scheme;
and respectively transmitting the initial optimization scheme to the crowdsourcing communities, decomposing the optimization target through cloud crowdsourcing resource combination to obtain local optimization targets of the crowdsourcing communities, and executing local optimization by the crowdsourcing communities by adopting an intelligent optimization algorithm. And synthesizing the crowdsourcing community optimization results to obtain a cloud crowdsourcing resource combination scheme result.
In practical application, the specific scheme of the invention is as follows:
mass service resource combination optimization method for cloud crowdsourcing platform
As shown in fig. 2, a cloud crowdsourcing platform is constructed based on crowdsourcing requirements of complex product development, and relevant QoS information is registered to a cloud crowdsourcing platform data center by crowdsourcing communities. And analyzing the crowdsourcing service resource class, the crowdsourcing service resource configuration execution scheme and the crowdsourcing service resource combination scheme, thereby constructing a cloud crowdsourcing platform for resource combination mass data. The method comprises the following steps:
step1, the service resource class CP _ Set corresponding to the complex task CA is represented as:
Crowd_Res＝{(Comm_Ser1,SIZE1),(Comm_Ser2,SIZE2),...,(Comm_Sern,SIZEn)}
wherein Comm _ SeriRepresents the ith service resource class, SIZE, owned by the cloud crowdsourcing platformiA capacity parameter indicating the ith service resource class, and n indicating the total number of service resource classes.
And CA represents a product development task (complex task) submitted by a user to the cloud crowdsourcing platform, where CA ═ t1,t2,...ti,...tnIs an abstract service composition with n micro tasks. For CA, after the complex task is decomposed, the complex task is completed by a plurality of service resource classes, namely crowdsourcing communities, and the resource service chain is dynamically generated by implementing and scheduling service resources located at different geographic positions in a crowdsourcing platform.
Step2, the service resource allocation execution scheme is determined according to the following mode:
variable xij(1≤i≤n,1≤j≤SIZEi) Indicates whether to use the candidate service resource Comm _ Seri.csjAssignment to micro-tasks tiAnd if so, xij1, otherwise xij＝0；
Will be provided with
As an implementation scheme for cloud crowdsourcing service resource configuration;
step3, correspondingly, the cloud crowdsourcing service resource combination scheme TOL is expressed as:
TOL＝SIZE1*SIZE2*...,*SIZEn. When SIZEiWhen the ratio is relatively large, the TOL value is increased along with the increment of n, and the cloud crowdsourcing platform has the characteristic of a resource combination scheme of mass data.
As shown in fig. 3, the main steps of the resource combination optimization framework in the cloud crowdsourcing data application environment are as follows:
firstly, analyzing QoS indexes corresponding to the micro tasks. C is a set of QoS metrics expected by the user corresponding to the micro-tasks of the crowd-sourced community. Where take C ═ C1,...,c5Qos (cs), and qos (cs) Qdu(cs),Qpr(cs),Qrep(cs),Qav(cs),Qrel(cs)]The service resource QoS information of the cloud crowdsourcing service cs in the execution process is described, and the service resource QoS information comprises cloud crowdsourcing service resource execution time, cloud crowdsourcing service resource execution price, cloud crowdsourcing service resource reputation level, cloud crowdsourcing service resource availability and cloud crowdsourcing service resource execution reliability.
W is a set of weights designed by the user and associated with QoS metric set C, i.e., W ═ W1,...w5}。0＜wiIs < 1, and
if a higher weight value is assigned to wi(i 1, 2.., 5), then the corresponding QoS index value will have a greater impact in service resource combination utility.
And secondly, analyzing the complex tasks to synthesize the QoS index. Which may be denoted as q (wf), there are different service resource combination models for qcc (wf), such as sequential, parallel, selection, and round robin, depending on the product development requirements. Only sequential task model service resource QoS index aggregation values are discussed herein, as other service composition models can be converted to sequential task models by well-established methods. For example: the sequential tasks comprise parallel tasks which can be regarded as subtasks in the sequential tasks, and after the parallel tasks are combined into the subtasks, the QoS accumulation calculation formula of the service resources is similar, but the time value is the maximum value in the parallel tasks. In the sequential task model, accumulation types corresponding to different service resource QoS are changed, and an accumulation calculation formula of each service resource QoS in the sequential task is as follows.
And thirdly, performing initial global optimization on the cloud crowdsourcing platform data center according to the mass data characteristics of the resource combination scheme on the premise of obtaining a product development path global utility function. Developing a global optimization utility function u for a path solution jjDetermined according to the following formula:
wherein, wk(k ═ 1, 2.., 5.) is the quality of service attribute value ckWeight of (k ═ 1,2,. 7, 5), Qccj,k(k 1, 2.., 5) represents that the development path scheme j has a quality of service attribute value ckA combined value of (k ═ 1,2,.., 5);
accordingly, the normalized quality of service attribute value Qcc 'is calculated according to the following formula'j,k：
Or
Wherein,
respectively representing the maximum value and the minimum value of the kth service quality attribute value of the product development path execution scheme. Respectively taking QoS accumulation as summation type for service resources
For averaging, respectively
For multiplication operations taking separately
Wherein
The data may be obtained from the QoS information about the crowd-sourced community service resources.
And fourthly, obtaining a local utility function optimized by the crowdsourcing community on the basis of the global utility function. Executing cost type index Q in scheme j on product development pathj,k，
And
respectively representing utility values u of corresponding service resource combination schemesj1Q that can be obtainedj,kBest and worst values; for the benefit type index Qj,k，
And
respectively representing utility values u of corresponding service resource combination schemesj2Q that can be obtainedj,kWorst and best values. Thus, it is possible to provide
Q′j1And Q'j2Respectively representing the normalized values of the QoS indexes of the cost type service resource combination and the benefit type service resource combination. Utility function uj1Or uj2Can continue to decompose without loss of generality for uj1Decomposition is carried out, and if m cost-type QoS indexes exist and the accumulation type of the m indexes is summation operation, the m indexes are analyzed to obtain the total QoS index
Wherein the utility value u is accumulated by the cloud crowdsourcing service resource combination schemejCan be decomposed into n local utility values, any local utility value can be considered as related to the micro-task ti(i is more than or equal to 1 and less than or equal to n) evaluation basis of local service resources QoS. For each micro task ti(1 ≦ i ≦ n), its corresponding candidate cloud crowd-sourced services resource mrsiCan select a utility function from a local resource pool
And (6) obtaining. On the premise of not considering the QoS constraint of the user to the service resources, the selected n candidate service resources are
A global service resource combination QoS optimization solution is formed. Similar analysis can be done for other combination types, such as average calculation service resource combination QoS attribute values, according to the above method. Therefore, the crowdsourcing community can realize local optimization of the crowdsourcing community under the condition that all relevant information of product development is not registered in a data center.
And fifthly, acquiring a crowdsourcing service resource combination optimization target based on user requirements. Aiming at the optimization goal of the combination of the micro task set cloud crowdsourcing service resources, the crowdsourcing service resource selection can achieve the maximum utility of the combination process.
The service resource combination optimization target facing the micro task set is as follows:
In the above formula of the optimization goal description of the crowdsourcing service resource combination, formula 1 represents the optimization goal, and formula 2 represents Qccj,kQoS attribute value c of various crowdsourced community service resource pools in cloud crowdsourced platformkThe accumulated value of (a); formulas 3 and 4 respectively represent constraint conditions of service resource allocation and QoS quality index weight of service resources of the execution scheme; k is an integer and has a value range of [1,5 ]]Corresponding to a set of QoS metric quantities desired by the user.
And sixthly, performing initial global optimization on the cloud crowdsourcing platform data center by adopting a bacterial foraging optimization algorithm according to the global optimization utility function and the crowdsourcing service resource combination optimization target to obtain a cloud crowdsourcing resource combination initial scheme. On the basis, target decomposition is optimized through crowdsourcing service resource combination, local optimization is executed by crowdsourcing communities by further adopting a bacterial foraging optimization algorithm, optimization results of the crowdsourcing communities are synthesized, and a cloud crowdsourcing resource combination scheme result is obtained.
Therefore, the cloud crowdsourcing resource combination problem is solved by adopting a cooperative bacterial foraging optimization CBFO algorithm. The CBFO algorithm bacterial code is described first. The CBFO algorithm bacterial code comprises two parts, namely cloud crowdsourcing mass data preprocessing and community local optimization bacterial code. When the crowdsourced proxy data center uses the BFO algorithm for initial global optimization,the bacterial code is the number of the corresponding service resource of the crowdsourced product development workflow path. The service resource is encoded as an integer vector with n elements, which can be expressed as P ═ x1,...,xi,...xn]Where n is the number of microscopic tasks in the crowd-sourced product development workflow, xi∈[1,SIZEi]，SIZEiFor a particular service resource x corresponding to a micro taskiThe number of the cells. For the optimization target of cloud crowdsourcing service resource combination, the search subspace is divided by taking crowdsourcing communities as units, and COkThe population size of (k 2.., N) should be smaller than the number of service resources of the current crowdsourced community. The local optimized bacterial code of the community corresponds to the service resource entity number in the crowdsourcing community, and can be further represented by the position coordinates of the service resource point of the plane grid.
Further, solving the cloud crowdsourcing resource combination problem comprises:
step 1: a user submits crowdsourcing product development requirements to a crowdsourcing agent data center for requirement matching to obtain corresponding product development workflows;
step 2: the crowdsourcing agent data center initializes the bacterial community CO according to the product development workflow1The position and relevant operation parameters thereof are used for carrying out preliminary search on cloud crowdsourcing service resources;
step 3: judging whether the number of dispersing iterations is reached, if so, turning to Step8, otherwise, executing Step 4;
step 4: in the bacterial group, chemotaxis operation is executed to complete the operations of turning, moving and swimming;
step 5: half of the undesirable bacteria die and reproduce the good bacteria;
step 6: judging whether the number of copying iterations is reached, if the condition is not met, turning to Step4, otherwise executing Step 7;
step 7: dispelling part of bacteria, turning to Step 3;
step 8: discovering a service resource combination scheme corresponding to the complex task by the bacterial colony, and transmitting the service resource combination scheme to each crowdsourcing community corresponding to the micro task;
step 9: serving resource locations based on preliminary global search, and COk(k 2.., N) ofRelevant operation parameters are obtained, community local optimization is carried out on all crowdsourcing communities, and parallel search of a cloud crowdsourcing service resource combination scheme is executed;
step 10: bacterial foraging optimization BFO of various crowdsourced communities respectively executes chemotaxis, copying, deletion and dispersion operations;
step 11: judging whether the cloud crowdsourcing service resource combination optimization scheme is improved or not, and if the conditions are met, replacing the position corresponding to the preliminary optimization scheme of the crowdsourcing service resource combination with the service resource position searched by the crowdsourcing community BFO;
step 12: and outputting a cloud crowdsourcing service resource combination optimization solution and service resource positions in the related crowdsourcing community resource pool.
Further, the method further comprises:
based on a preset BFO coding mode, flora is randomly distributed in a data center or crowdsourced communities, and then chemotaxis, replication, deletion and dispersion operations are carried out on the flora.
As shown in fig. 4, the resource optimization flow for crowd-sourced product development based on the CBFO optimization unit BFO is described as follows.
The CBFO optimization unit BFO is an effective technology for solving service resource combination optimization in a crowdsourcing community environment, and the flora can effectively track the cloud crowdsourcing service resource QoS, allocate complex tasks or micro tasks to appropriate service resources and achieve service resource combination maximum effect. In fig. 4, the main process of BFO is to randomly distribute flora in a data center or crowdsourced communities according to the BFO coding mode, and then the flora is subjected to chemotaxis, replication, deletion and dispersion operations. The location update that mimics the chemotactic process in BFO is described using the following formula:
wherein, thetai(j, k, l) represents the position of the bacterium i after the j-th chemotaxis operation, the k-th replication operation and the l-th dispersal operation, C (i) is the step size of the movement in the selected direction,
defining a random motion direction per unit length after one turn, and delta (i) represents a motion in any direction, and the element of the motion is [ -1,1]Within the range. In each chemotaxis step, a bacteria flip angle direction is generated, the bacteria move along the direction according to the formula, and if the nutrient concentration of the new position is better than that of the last position, the bacteria move in the same direction for a plurality of steps. In the BFO algorithm execution process, a crowdsourcing service resource combination optimization target and a crowdsourcing community local utility function are adopted, and a search service resource combination QoS utility value is calculated, wherein the search service resource combination QoS utility value corresponds to a crowdsourcing agent data center and the nutrient concentration J (theta) of bacteria in a crowdsourcing community search space respectively.
(II) mass service resource combination optimization strategy system of cloud crowdsourcing platform
The crowdsourcing community environment is complex, diverse, heterogeneous and dynamic, and is mainly characterized by aiming at microscopic tasks and mass data. Therefore, a safe, reliable, parallel and distributed crowdsourcing community environment system with good expansibility is constructed by adopting Hadoop, and on the basis of the method, a cloud crowdsourcing platform mass service resource combination optimization strategy system is further developed, and the method mainly comprises the following steps:
crowdsourcing community service resources: the crowdsourcing community relates to each service resource in the product full life cycle activity, the product full life cycle is a generalized collaborative product design and comprises a pre-design stage, a manufacturing stage and a sales maintenance post-stage, and each stage comprises a specific collaborative task. The cloud crowdsourcing platform virtualizes service resources participating in collaborative product development tasks, and the service resources are subjects of individuals, groups, colleges or enterprises and the like which can provide related services in crowdsourcing communities. The specific service resources mainly comprise: manufacturing equipment service resources: physical equipment for cloud crowdsourcing service production, processing, experiment and the like is provided for cloud platform users in the whole life cycle of the product; computing device service resources: various high-performance servers supporting design calculation and simulation calculation of cloud crowdsourcing operation, and equipment resources such as a memory and the like; human resources: and in the whole life cycle of the product, professional technicians engaged in activities such as design, manufacture and management, and the like.
Crowdsourcing agent data center: after the crowdsourcing community environment service resources are registered on the cloud crowdsourcing platform, a crowdsourcing agent data center is generated, and data shared by crowdsourcing community environments is uniformly managed. The relevant QoS data comprises cloud crowdsourcing service resource execution time, cloud crowdsourcing service resource execution price, cloud crowdsourcing service resource reputation level, cloud crowdsourcing service resource availability, cloud crowdsourcing service resource execution reliability and the like.
A crowdsourcing product development workflow engine module: the architecture of the development service for the crowdsourced products is a component model, and different functional units (called service resources) of complex tasks (application programs) are connected through well-defined interfaces or contracts among the service resources. The interface is defined in a neutral mode according to the information interaction characteristics of the product development process, and is independent of a hardware platform, an operating system and a programming language for realizing crowdsourcing product development service. The crowdsourcing product development workflow engine enables various service resources built into such a cloud crowdsourcing system to interact in a uniform and universal manner.
A confirm user requirement module: user demand information is acquired through man-machine interaction, and based on the functional characteristics of service resources registered by the cloud crowdsourcing platform, the cloud crowdsourcing platform confirms a corresponding product development workflow model in a crowdsourcing agent data center according to the new product development user demand.
Crowdsourcing service resource initial optimization module: and generating a corresponding workflow model according to user requirements, optimizing a QoS target according to resource combination, and preprocessing mass data according to a CBFO algorithm process to realize initial optimization of crowdsourcing service resource combination.
Crowdsourcing community local optimization module: according to a workflow model and an optimization target generated by user requirements, performing crowdsourcing service resource combination initial optimization through a crowdsourcing agent data center, transmitting an initial optimization result to each crowdsourcing community through a workflow engine module, and performing parallel processing of mass data in a CBFO algorithm process and a crowdsourcing product development resource optimization process based on a CBFO optimization unit BFO by the crowdsourcing community according to a self database module on the basis of the initial optimization to further improve the crowdsourcing product development resource combination optimization efficiency.
And a calculation result display module: the method comprises the steps of optimally displaying crowdsourcing product development resource combination on a user interface, wherein the display content comprises a crowdsourcing agent data center, a crowdsourcing product development workflow model, a crowdsourcing product development resource combination initial optimization module, a crowdsourcing community local optimization module and a crowdsourcing product development resource combination optimization result module facing to a cloud environment.
The beneficial effects of the invention at least comprise:
(1) the invention can realize the matching of crowdsourcing product development requirements and crowdsourcing service resources, and solves the problem that the conventional crowdsourcing community resource environment cannot be directly applied to the crowdsourcing service resource combination realization by establishing a cloud crowdsourcing platform.
(2) Based on a cloud crowdsourcing platform, establishing a corresponding cloud crowdsourcing resource combination optimization target, and executing crowdsourcing service resource combination initial optimization by using a bacterial foraging optimization algorithm. The method realizes the pretreatment of the cloud crowdsourcing mass service resource combination scheme and lays a foundation for local optimization of crowdsourcing communities.
(3) Based on the pretreatment of the massive service resource combination scheme, a bacterial foraging optimization algorithm is used, and the crowdsourcing communities execute parallel and local optimization, so that the mining efficiency of the crowdsourcing service resource combination is further improved. Based on user requirements, automatic matching and combination of mass service resources on a cloud crowdsourcing platform under crowdsourcing community environment are achieved.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (4)
1. A cloud crowdsourcing platform mass service resource combination optimization method is characterized by comprising the following steps:
according to the cloud crowdsourcing requirements of users, namely crowdsourcing complex product development task requirements, registering relevant product development quality of service (QoS) index information aiming at microscopic tasks, namely single tasks, to a cloud crowdsourcing platform data center by each crowdsourcing community, and constructing a cloud crowdsourcing platform of a massive resource combination scheme;
obtaining a synthetic service quality index of the complex task based on the service quality index corresponding to the microscopic task, and further determining a cloud crowdsourcing service resource combination optimization target; aiming at the mass data environment of the cloud crowdsourcing platform service resource combination, performing initial global optimization on a cloud crowdsourcing platform data center by adopting an intelligent optimization algorithm to obtain an initial crowdsourcing service resource combination scheme;
respectively transmitting the initial optimization scheme to crowdsourcing communities, decomposing the optimization target through cloud crowdsourcing resource combination to obtain local optimization targets of the crowdsourcing communities, executing local optimization by the crowdsourcing communities by adopting an intelligent optimization algorithm, and synthesizing optimization results of the crowdsourcing communities to obtain a cloud crowdsourcing service resource combination scheme result;
the method further comprises the following steps:
according to a global optimization utility function and a crowdsourcing service resource combination optimization target, performing initial global optimization on a cloud crowdsourcing platform data center by adopting a bacterial foraging optimization algorithm to obtain a cloud crowdsourcing resource combination initial scheme, decomposing the crowdsourcing service resource combination optimization target on the basis of the initial scheme, and performing local optimization on crowdsourcing communities by further adopting a bacterial foraging optimization algorithm to synthesize optimization results of the crowdsourcing communities to obtain a cloud crowdsourcing resource combination scheme result, so that FO can be used for solving the cloud crowdsourcing resource combination problem by adopting a cooperative bacterial foraging optimization CBFO algorithm;
solving the cloud crowdsourcing resource combination problem comprises:
step 1: a user submits crowdsourcing product development requirements to a cloud crowdsourcing platform data center, requirement matching is carried out, and corresponding product development workflows are obtained;
step 2: the cloud crowdsourcing platform data center initializes the bacterial population according to the product development workflow
The position and relevant operation parameters thereof are used for carrying out preliminary search on cloud crowdsourcing service resources;
step 3: judging whether the number of dispersing iterations is reached, if so, turning to Step8, otherwise, executing Step 4;
step 4: in the bacterial group, chemotaxis operation is executed to complete the operations of turning, moving and swimming;
step 5: half of the undesirable bacteria die and reproduce the good bacteria;
step 6: judging whether the number of copying iterations is reached, if the condition is not met, turning to Step4, otherwise executing Step 7;
step 7: dispelling part of bacteria, turning to Step 3;
step 8: discovering a service resource combination scheme corresponding to the complex task by the bacterial colony, and transmitting the service resource combination scheme to each crowdsourcing community corresponding to the micro task;
step 9: serving resource locations based on a preliminary global search, an
Carrying out community local optimization on all crowdsourcing communities and simultaneously executing parallel search of a cloud crowdsourcing service resource combination scheme;
step 10: bacterial foraging optimization BFO of various crowdsourced communities respectively executes chemotaxis, copying, deletion and dispersion operations;
step 11: judging whether the cloud crowdsourcing service resource combination optimization scheme is improved or not, and if the conditions are met, replacing the position corresponding to the preliminary optimization scheme of the crowdsourcing service resource combination with the service resource position searched by the crowdsourcing community BFO;
step 12: and outputting a cloud crowdsourcing service resource combination optimization solution and service resource positions in the related crowdsourcing community resource pool.
2. The method of claim 1, wherein a cloud crowdsourcing platform is constructed based on crowdsourcing requirements of complex product development, relevant QoS information is registered to a cloud crowdsourcing platform data center by crowdsourcing communities, crowdsourcing service resource classes, a crowdsourcing service resource configuration execution scheme and a crowdsourcing service resource combination scheme are analyzed, and therefore the cloud crowdsourcing platform for resource combination mass data is constructed, and the steps are as follows:
step 1: complex tasks
Corresponding service resource class
Expressed as:
wherein,
representing the ith service resource class owned by the cloud crowdsourcing platform,
a capacity parameter representing the ith service resource class, n representing the total number of service resource classes;
step 2: the service resource configuration execution scheme is determined as follows:
variables of
Indicating whether to use candidate service resources
Assignment to micro-tasks
If so, then
Otherwise
；
Will be provided with
，
As an implementation scheme for cloud crowdsourcing service resource configuration;
and step 3: accordingly, the cloud crowdsourcing service resource combination scheme TOL is represented as:
3. The method of claim 1, wherein an initial global optimization is performed at a cloud crowdsourcing platform data center based on resource composition scheme mass data characteristics, provided that a product development path global utility function is obtained, a development path scheme j global optimization utility function is obtained
Determined according to the following formula:
wherein,
for quality of service attribute values
The weight of (a) is determined,
representing development path scenarios
About quality of service attribute values
A combined value of;
accordingly, the normalized quality of service attribute value is calculated according to the following formula
：
Or
Wherein,
，
respectively represent the execution schemes of the product development paths
Maximum and minimum values of individual quality of service attribute values.
4. The method of claim 1, further comprising:
based on a preset BFO coding mode, flora is randomly distributed in a data center or crowdsourced communities, and then chemotaxis, replication, deletion and dispersion operations are carried out on the flora.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910345260.5A CN110120888B (en) | 2019-04-26 | 2019-04-26 | Cloud crowdsourcing platform mass service resource combination optimization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910345260.5A CN110120888B (en) | 2019-04-26 | 2019-04-26 | Cloud crowdsourcing platform mass service resource combination optimization method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110120888A CN110120888A (en) | 2019-08-13 |
| CN110120888B true CN110120888B (en) | 2022-03-18 |
Family
ID=67521486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910345260.5A Active CN110120888B (en) | 2019-04-26 | 2019-04-26 | Cloud crowdsourcing platform mass service resource combination optimization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110120888B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110780862B (en) * | 2019-10-12 | 2021-05-11 | 南京邮电大学 | Automatic service combination method based on key path spanning tree |
| CN111427847B (en) * | 2020-04-03 | 2023-04-11 | 中山大学 | Indexing and querying method and system for user-defined metadata |
| CN114792155B (en) * | 2022-03-07 | 2023-04-07 | 西南交通大学 | Crowdsourcing design process simulation method based on bidirectional foraging theory |
| US11968087B2 (en) * | 2022-03-31 | 2024-04-23 | Lenovo (Singapore) Pte. Ltd. | Unused device repurposing system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103870317B (en) * | 2012-12-10 | 2017-07-21 | 中兴通讯股份有限公司 | Method for scheduling task and system in cloud computing |
| CN106357739B (en) * | 2016-08-27 | 2019-10-18 | 浙江工业大学 | It is a kind of for batch cloud service request two stages combination and dispatching method |
| CN108076143A (en) * | 2017-12-01 | 2018-05-25 | 河南理工大学 | A kind of logistics Web service dynamic optimized combination method |
| CN109559033B (en) * | 2018-11-27 | 2021-04-27 | 河南科技大学 | Socialized team member optimization method oriented to cloud design and manufacturing mode |
-
2019
- 2019-04-26 CN CN201910345260.5A patent/CN110120888B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110120888A (en) | 2019-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zheng et al. | Self-regulated evolutionary multitask optimization | |
| CN110120888B (en) | Cloud crowdsourcing platform mass service resource combination optimization method and system | |
| Shao et al. | Multi-objective evolutionary algorithm based on multiple neighborhoods local search for multi-objective distributed hybrid flow shop scheduling problem | |
| Peng et al. | Intelligent computation offloading and resource allocation in IIoT with end-edge-cloud computing using NSGA-III | |
| CN113191484B (en) | Federal learning client intelligent selection method and system based on deep reinforcement learning | |
| Ren et al. | Manufacturing service composition model based on synergy effect: a social network analysis approach | |
| Liu et al. | Two-stage approach for reliable dynamic Web service composition | |
| CN107203492B (en) | Product design cloud service platform modularized task recombination and distribution optimization method | |
| Wang et al. | Many-objective cloud manufacturing service selection and scheduling with an evolutionary algorithm based on adaptive environment selection strategy | |
| Ahmad et al. | Differential evolution with modified initialization scheme using chaotic oppositional based learning strategy | |
| Jia et al. | Q-learning driven multi-population memetic algorithm for distributed three-stage assembly hybrid flow shop scheduling with flexible preventive maintenance | |
| CN104461728A (en) | Migration event dispatching management | |
| Li et al. | New MILP model and station-oriented ant colony optimization algorithm for balancing U-type assembly lines | |
| Zhao et al. | A hierarchical parallel evolutionary algorithm of distributed and multi-threaded two-level structure for multi-satellite task planning | |
| Nesmachnow | Parallel multiobjective evolutionary algorithms for batch scheduling in heterogeneous computing and grid systems | |
| CN117196020A (en) | Conflict resolution method based on improved genetic algorithm | |
| Németh et al. | A snapshot of the frontiers of client selection in federated learning | |
| CN112380016A (en) | Cloud computing resource load balancing scheduling method based on improved genetic algorithm and application | |
| Ouyang et al. | Amended harmony search algorithm with perturbation strategy for large-scale system reliability problems | |
| Zhao et al. | A hybrid clonal selection algorithm for quality of service-aware web service selection problem | |
| Zhang et al. | Optimising web service composition based on differential fruit fly optimisation algorithm | |
| CN118396294A (en) | Cloud manufacturing scheduling method based on quantum multi-agent reinforcement learning | |
| CN112101406A (en) | Intelligent horizontal quantization method of multi-agent network | |
| Savarala et al. | An Improved Fruit Fly Optimization Algorithm for QoS Aware Cloud Service Composition. | |
| Prado et al. | On providing quality of service in grid computing through multi-objective swarm-based knowledge acquisition in fuzzy schedulers |
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 |