High occupancy resource allocation for grid and cloud systems, a study with DRIVE
Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing
Achieving high job execution reliability using underutilized resources in a computational economy
Future Generation Computer Systems
Double auction-inspired meta-scheduling of parallel applications on global grids
Journal of Parallel and Distributed Computing
Resource co-allocation framework based on hybrid gaming model in grid environments
International Journal of Grid and Utility Computing
| Hi-index | 0.00 |
In this paper we present DRIVE, a novel architecture for a Virtual Organization (VO) based distributed economic meta-scheduler in which members of the VO collaborativelyallocate Grid resources. Resource Providers joining the VO contribute Obligation services to the VO. These contributed services are in effect membership ’dues’ and are used in the running of the VO’s operations - allocation, advertising, management, etc. We use an auction plug-in mechanism to support arbitrary auction protocols which allows users to choose a protocol basedon specific requirements and infrastructural availability. For instance, within a single organization, where internal trust exists, users can achieve maximum allocation performance by choosing a conventional sealed bid auction plug-in. In a global utility Grid no such trust exists. The same meta-scheduler architecture can be used with a more expensive secure auction protocol plug-in which ensures the allocation is carried out fairly in the absence of trust. The DRIVE prototype has been implementedas a collection of standard WSRF Web services and includes a distributed implementation of a secure combinatorial Garbled Circuit protocol.