Please use this identifier to cite or link to this item:
Title: Learnable evolutionary model for flexible job-shop scheduling
Authors: Ho Nhu Binh
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
DRNTU::Engineering::Manufacturing::Production management
Issue Date: 2007
Source: Ho, N. B. (2007). Learnable evolutionary model for flexible job-shop scheduling. Doctoral thesis, Nanyang Technological University, Singapore.
Abstract: In recent years, resource allocation problems have received much attention in the research community and industry. The most frequently encountered problems of these topics are the Job-Shop Scheduling Problem (JSP). Effective scheduling for the JSP has the potential to decrease cost and increase profits. The JSP can be modeled as the allocation of machines over specific time to process a collection of jobs. An extension of the JSP which makes this problem more difficult is the Flexible Job-Shop Scheduling Problem (FJSP). Unfortunately, the traditional deterministic approaches, such as Branch and Bound, Priority Dispatching Rules, have scaled poorly with large problem size. The current local search techniques have also performed in expensive computational time. Currently, the interaction between evolution and learning has received much attention from the research community. Some recent studies on machine learning have shown that it can significantly improve the efficiency of problem solving when using Evolutionary Algorithms (EAs).
Description: 196 p.
DOI: 10.32657/10356/35728
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Theses

Files in This Item:
File Description SizeFormat 
HoNhuBinh07.pdf29.46 MBAdobe PDFThumbnail

Page view(s) 50

Updated on Oct 15, 2021

Download(s) 20

Updated on Oct 15, 2021

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.