A Learning-Based Methodology for Control of Scheduling in Changing Environment

スポンサーリンク

概要

• 論文の詳細を見る

• This paper attempts the control of scheduling in the changing environment by comparing a simple model of the life-cycle of successful human being with the control of scheduling in the industry. The four layers of this comparison are of vital importance, that represent the basic control pattern of scheduling. Then a distributed architecture is designed based on the proposed model. The agents behavior is tested while considering one of the changing parameter i.e.machine breakdown, in a simple scheduling problem. It differs from the other systems because of the distributed architecture, which emphasize the transfer of process for a particular job, during breakdown of machine to another similar machine autonomously, having minimum job-change over time, by using the learning technique. The fitness of an individual is calculated based on makespan. The initial experimental results show that the system reaches good performance both with respect to the quality of the learned knowledge and with respect to obtaining good schedule in the changing environment.

• 1999-12-15

著者

• RASHID Yahya

  Department of Mechanical Engineering, Kobe University

• HATONO Itsuo

  Information Processing Center, Kobe University

• UEDA Kanji

  Faculty of Engineering, Kobe University

• Ueda Kanji

  Faculty Of Engineering Kobe University

• Rashid Yahya

  Department Of Mechanical Engineering Kobe University

• Hatono Itsuo

  Information Processing Center Kobe University

関連論文

• A Learning-Based Methodology for Control of Scheduling in Changing Environment
• Does Reinforcement Learning Simulate Threshold Public Goods Games? : A Comparison with Subject Experiments( Software Agent and Its Applications)
• The Application of Coupled Map Lattice to Network Externalities in Consumers' Theory : A Generalisation of Life Game

スポンサーリンク