ACM Transactions on Computer Systems (TOCS)
An agent-based approach for building complex software systems
Communications of the ACM
The Vision of Autonomic Computing
Computer
Semantically Reliable Multicast: Definition, Implementation, and Performance Evaluation
IEEE Transactions on Computers
Predictive Application-Performance Modeling in a Computational Grid Environment
HPDC '99 Proceedings of the 8th IEEE International Symposium on High Performance Distributed Computing
An Architectural Approach to Autonomic Computing
ICAC '04 Proceedings of the First International Conference on Autonomic Computing
A Component-Based Programming Model for Autonomic Applications
ICAC '04 Proceedings of the First International Conference on Autonomic Computing
Towards Autonomic Virtual Applications in the In-VIGO System
ICAC '05 Proceedings of the Second International Conference on Automatic Computing
Elders Know Best " Handling Churn in Less Structured P2P Systems
P2P '05 Proceedings of the Fifth IEEE International Conference on Peer-to-Peer Computing
Peer-to-Peer Systems and Applications (Lecture Notes in Computer Science)
Peer-to-Peer Systems and Applications (Lecture Notes in Computer Science)
Adaptive load balancing: a study in multi-agent learning
Journal of Artificial Intelligence Research
From virtualized resources to virtual computing grids: the In-VIGO system
Future Generation Computer Systems - Special section: Complex problem-solving environments for grid computing
Cooperative dynamic scheduling of virtual machines in distributed systems
Euro-Par'11 Proceedings of the 2011 international conference on Parallel Processing - Volume 2
Managing volunteer resources in the cloud
International Journal of Computational Science and Engineering
A Distributed Control Approach for Autonomic Performance Management in Cloud Computing Environment
UCC '13 Proceedings of the 2013 IEEE/ACM 6th International Conference on Utility and Cloud Computing
| Hi-index | 0.00 |
The centralized management of large distributed systems is often impractical, particularly when the both the topology and status of the system change dynamically. This paper proposes an approach to application-centric self-management in large distributed systems consisting of a collection of autonomic components that join and leave the system dynamically. Cooperative autonomic components self-organize into a dynamically created overlay network. Through local information sharing with neighbors, each component gains access to global information as needed for optimizing performance of applications. The approach has been validated and evaluated by developing a decentralized autonomic system consisting of multiple autonomic application managers previously developed for the In-VIGO grid-computing system. Using analytical results from complex random network and measurements done in a prototype system, we demonstrate the robustness, self-organization and adaptability of our approach, both theoretically and experimentally.