Research On Grid Task Scheduling Strategy Based On P2P Technology

In Grid environment, the grid task scheduling strategy which is suitable for the features of grid task is the key factor that affects the grid computation. During these years,more and more attentions have been paid to QoS in Grid environment. Usually, task scheduling means trying to optimize system performance,such as system throughput and resource utilization.and also trying to satisfy user's QoS requirement. Obviously, supporting QoS in Grid task scheduling is the key issue affects the Grid system.Firstly, this paper introduces the basic conceptions and theories of grid system and scheduling system. Some present task scheduling researching aspects are introduced by presenting inside and outside researching productions. Then, the scheduling mechanism, critical technology and scheduling simulation toolkits are addressed following GridSim.Secondly, one improved grid model is proposed which based on the traditional grid model and P2P. The improved grid model is very suitable and effective. Through analyzing the basic thought of classical scheduling algorithms and grid tasks their own characteristics, double QoS constraint algorithm and three QoS constraint algorithm are proposed.Finally, algorithms addressed before are simulated by the GridSim toolkits. It is proved that the three QoS constraint algorithm is superior in solving deadline and bandwidth and CPU constraint problems by comparing and analyzing result data. Conclusions of research are summarized and existed issues are pointed out for future research.