THESIS
1999
xii, 128 leaves : ill. ; 30 cm
Abstract
Scheduling involves the allocation of limited resources to tasks over time. Due to the high complexity of scheduling problems, most scheduling algorithms and procedures are only suitable for specific cases and most scheduling systems are very application-oriented. Until now, no single scheduling system can handle all types of scheduling problems. With the recent development of client/server architecture and Internet technology, distributed problem solving by a group of systems become feasible where systems can exchange information, share resources and cooperate to solve large and complicated problems. Moreover, recent intensive research in intelligent software agents and agent technology has offered new tools of solving problems and coordination between systems. These tools allow system...[
Read more ]
Scheduling involves the allocation of limited resources to tasks over time. Due to the high complexity of scheduling problems, most scheduling algorithms and procedures are only suitable for specific cases and most scheduling systems are very application-oriented. Until now, no single scheduling system can handle all types of scheduling problems. With the recent development of client/server architecture and Internet technology, distributed problem solving by a group of systems become feasible where systems can exchange information, share resources and cooperate to solve large and complicated problems. Moreover, recent intensive research in intelligent software agents and agent technology has offered new tools of solving problems and coordination between systems. These tools allow systems to be represented as agents and coordinate their activities through message passing. However, most of the concepts and approaches have been applied to general applications and very little research has been studied the distributed approach to scheduling systems development. In this research, the framework of agent-based distributed scheduling is presented. The research is divided into three parts: the Internet scheduling systems, the establishment of communication infrastructure and the distributed problem solving policy. We begin by introducing the development of Internet scheduling systems, which is the basic component of the agent-based distributed scheduling systems. Next, we describe the communication infrastructure for the connection between scheduling systems. The communication infrastructure provides systems to exchange information and for the synchronization and collaboration between scheduling systems. And the communication language, syntax and semantics on the scheduling and system information are presented. In the third part, we discuss the preliminary work on distributed problem solving, including problem decomposition, problem assignment and the use of contracting mechanism as control and interaction. We conclude the research with a discussion and the potential areas for future work.
Post a Comment