REGRET: reputation in gregarious societies
Proceedings of the fifth international conference on Autonomous agents
Experiments in Building Experiential Trust in a Society of Objective-Trust Based Agents
Proceedings of the workshop on Deception, Fraud, and Trust in Agent Societies held during the Autonomous Agents Conference: Trust in Cyber-societies, Integrating the Human and Artificial Perspectives
The Eigentrust algorithm for reputation management in P2P networks
WWW '03 Proceedings of the 12th international conference on World Wide Web
Principles of Trust for MAS: Cognitive Anatomy, Social Importance, and Quantification
ICMAS '98 Proceedings of the 3rd International Conference on Multi Agent Systems
SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
BOINC: A System for Public-Resource Computing and Storage
GRID '04 Proceedings of the 5th IEEE/ACM International Workshop on Grid Computing
Future Generation Computer Systems - Special issue: P2P computing and interaction with grids
FastReplica: efficient large file distribution within content delivery networks
USITS'03 Proceedings of the 4th conference on USENIX Symposium on Internet Technologies and Systems - Volume 4
PowerTrust: A Robust and Scalable Reputation System for Trusted Peer-to-Peer Computing
IEEE Transactions on Parallel and Distributed Systems
A peer-to-peer architecture for data-intensive cycle sharing
Proceedings of the first international workshop on Network-aware data management
Risk assessment in service provider communities
GECON'11 Proceedings of the 8th international conference on Economics of Grids, Clouds, Systems, and Services
| Hi-index | 0.00 |
In scientific applications utilizing a distributed computing infrastructure, data may not be co-located with computation, and may need to be retrieved from one or more remote servers. Where such computation is being supported through volunteered resources, often the data storage server is centralized, but the processing nodes (peers) are distributed. For instance, the BOINC project has been widely used to develop "volunteer computing" projects, utilizing a centralized server to distribute data to users. This can be limiting in terms of performance, scalability and reliability. We describe a framework which utilizes an alternative data distribution and access approach, making use of a BitTorrent-like protocol and integrated with BOINC, for supported automated server selection. In this framework, a node within the system can be a client requesting data, a data hosting service (data center) or a lookup server responsible for providing data to its clients to calculate the "trust value" of data centers. These trust values are used to select data centers to download from based on preferences identified by clients. We demonstrate how such a framework could be used to improve data access time and reliability in Peer-2-Peer based volunteer computing projects.