Self-managed decentralised systems using k-components and collaborative reinforcement learning (2004)
| Venue: | In WOSS ’04: Proceedings of the 1st ACM SIGSOFT workshop on Self-managed systems |
| Citations: | 9 - 0 self |
BibTeX
@INPROCEEDINGS{Dowling04self-manageddecentralised,
author = {Jim Dowling},
title = {Self-managed decentralised systems using k-components and collaborative reinforcement learning},
booktitle = {In WOSS ’04: Proceedings of the 1st ACM SIGSOFT workshop on Self-managed systems},
year = {2004},
pages = {39--43},
publisher = {ACM Press}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Components in a decentralised system are faced with uncertainty as how to best adapt to a changing environment to maintain or optimise system performance. How can individual components learn to adapt to recover from faults in an uncertain environment? How can a decentralised system coordinate the adaptive behaviour of its components to realise system optimisation goals given problems establishing consensus in dynamic environments? This paper introduces a self-adaptive component model, called K-Components, that enables individual components adapt to a changing environment and a decentralised coordination model, called collaborative reinforcement learning, that enables groups of components to learn to collectively adapt their behaviour to establish and maintain system-wide properties in a changing environment.
