A Dynamic Resource Optimization Method Based on Markov Decision Process
A technology of dynamic resources and optimization methods, applied in data processing applications, forecasting, instruments, etc., can solve problems such as product development failure, product development process full of risks, and insufficient consideration
Active Publication Date: 2020-07-03
INFORMATION CENT OF CHINA NORTH IND GRP
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The quality of cloud manufacturing resource combination optimization model and solution mechanism will directly affect the quality of product development and whether the development process can be carried out safely and smoothly, and the characteristics of cloud manufacturing determine that the selection of manufacturing resources in the product development process is full of uncertain factors Most of the current research on the optimal allocation of manufacturing resources only considers issues such as time, cost, quality, and resource evaluation, and does not fully consider the impact of uncertainty in the product development process on the selection of cloud manufacturing resources: that is, there is a possibility of failure in product development , which not only makes the product development process full of risks, but also has a great impact on the product development cost and development cycle
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0081] In this embodiment, the task F is decomposed according to the complex product task decomposition model, and the task set formed is: F={f i |i=1,2,...,8}.
[0082] The cross-regional enterprise manufacturing resources in the cloud manufacturing environment are virtualized and service-oriented, and the enterprise R&D capability unit is expressed as c ij ={lov(c ij ), f i ,j}, where j=1,2,...5.
[0083] Establish a virtual enterprise R&D capability resource pool: CP(1)={c 11 ,c 12 ,c 13 ,c 14 ,c 15}, CP(2)={c 21 ,c 22 ,c 23 ,c 24 ,c 25},CP(3)={c 31 ,c 32 ,c 33 ,c 34 ,c 35},CP(4)={c 41 ,c 42 ,c 43 ,c 44 ,c 45},CP(5)={c 51 ,c 52 ,c 53 ,c 54 ,c 55},CP(6)={c 61 ,c 62 ,c 63 ,c 64 ,c 65},CP(7)={c 71 ,c 72 ,c 73 ,c 74 ,c 75},CP(8)={c 81 ,c 82 ,c 83 ,c 84 ,c 85}
[0084] For the convenience of description, all enterprise R&D capability units under the cloud manufacturing environment c ij The corresponding research and development capabil...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention belongs to the technical field of dynamic resource optimization and specifically relates to a Markov decision process-based dynamic resource optimization method. The method is different from a conventional manufacturing resource selection method; a multi-development-task precision regulation and control cloud manufacture resource problem in a cloud manufacture environment is abstracted into a Markov decision process, mathematical modeling of effects exerted on resource selection by development process uncertainty can be realized, expected development cost is an object function, a cross entropy method is used for calculation, a combinational optimization problem is converted into a random association optimization problem, optimal selection probability of cloud manufacture resources can be obtained, reasonable scheduling and high efficiency utilization of manufacturing resources during cooperative development of complex products can be realized, and product development risk and manufacture cost can be effectively lowered.
Description
technical field [0001] The invention belongs to the technical field of dynamic resource optimization, and in particular relates to a dynamic resource optimization method based on a Markov decision process. Background technique [0002] In the current global manufacturing environment, the development of complex products often requires the deployment of enterprise resources in different regions, types, and characteristics. With the support of information network, cloud manufacturing connects geographically dispersed and complementary enterprise resources by integrating social manufacturing resources and capabilities, realizes the sharing, integration and collaborative work of scattered manufacturing resources, and cooperates to complete the design of complex products, Manufacture, assembly, and sales and service throughout the life cycle, while better responding to market demand, to obtain the greatest benefit. [0003] In the cloud manufacturing environment, manufacturing re...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/04G06Q50/04
CPCG06Q10/04G06Q50/04Y02P90/30
Inventor 杨建新秦强吉军刘文军杨一铭
Owner INFORMATION CENT OF CHINA NORTH IND GRP