Emergence: From Chaos to Order
Emergence: From Chaos to Order
On the theory of system administration
Science of Computer Programming
Feedback Control of Computing Systems
Feedback Control of Computing Systems
Configurable immunity for evolving human-computer systems
Science of Computer Programming - Methods of software design: Techniques and applications
LISA '98 Proceedings of the 12th USENIX conference on System administration
Seeking Closure in an Open World: A Behavioral Agent Approach to Configuration Management
LISA '03 Proceedings of the 17th USENIX conference on System administration
Experience in Implementing an HTTP Service Closure
LISA '04 Proceedings of the 18th USENIX conference on System administration
Experience implementing an IP address closure
LISA '06 Proceedings of the 20th conference on Large Installation System Administration
AIMS '08 Proceedings of the 2nd international conference on Autonomous Infrastructure, Management and Security: Resilient Networks and Services
Dynamics of Resource Closure Operators
AIMS '09 Proceedings of the 3rd International Conference on Autonomous Infrastructure, Management and Security: Scalability of Networks and Services
Management without (Detailed) Models
ATC '09 Proceedings of the 6th International Conference on Autonomic and Trusted Computing
An approach to understanding policy based on autonomy and voluntary cooperation
DSOM'05 Proceedings of the 16th IFIP/IEEE Ambient Networks international conference on Distributed Systems: operations and Management
On the combined behavior of autonomous resource management agents
AIMS'10 Proceedings of the Mechanisms for autonomous management of networks and services, and 4th international conference on Autonomous infrastructure, management and security
On the effects of omitting information exchange between autonomous resource management agents
AIMS'13 Proceedings of the 7th IFIP WG 6.6 international conference on Autonomous Infrastructure, Management, and Security: emerging management mechanisms for the future internet - Volume 7943
| Hi-index | 0.00 |
Learned models of behavior have the disadvantage that they must be retrained after any change in system configuration. Autonomic management methods based upon learned models lose effectiveness during the retraining period. We propose a hybrid approach to autonomic resource management that combines management based upon learned models with "highly-reactive" management that does not depend upon learning, history, or complete information. Whenever re-training is necessary, a highly-reactive algorithm serves as a fallback management strategy. This approach mitigates the risks involved in using learned models in the presence of unpredictable effects, including unplanned configuration changes and hidden influences upon performance not considered in the learned model. We use simulation to demonstrate the utility of the hybrid approach in mitigating pitfalls of both learning-based and highly-reactive approaches.