An Elastic Scheduling Algorithm For Resource Co-Allocation Based on System Generated Predictions With Priority

Abstract

Resource Co-Allocation is basically used to execute multiple site jobs in a large scale computing environments with secure, faultless and in transparent manner. To be precise we are actually allocating multiple resources for different jobs taking into account the time parameter. Here we make use of the Scheduling queue and Resource Co-Allocation to reduce the Turn-around time with an advanced concept of System Generated Prediction based on Priority. In existing works we are scheduling the resource co-allocation request from user runtime estimation. As user runtime estimations are usually very imprecise that is not clear. In proposed work we are scheduling the resource co-allocation request based on system generated predictions through Discovery service & Priority (fairness and user experience) through topological sorting technique. The system generated predictions are better parameters than user runtime estimates for Resource co-Allocation scheduling, because System generated predictions reduce the scheduling time through proxy ser based discovery service technique. The proposed work consider priorities like advanced reservation, system Generated Predictions, Negotiation, Co-scheduling, policy (SLA, Price, Trust) for resource Co-Allocation. The system generated predictions are better than user runtime estimates for Resource co- Allocation scheduling, using the experimental data’s we proved this concept. End User doesn’t want the grid and resource knowledge only submit job to the portal. This proposed portal will take care of all knowledge about the resource collocation automatically with fast and efficient manner.