Technical Note: \cal Q-Learning
Machine Learning
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
A recursive random search algorithm for large-scale network parameter configuration
SIGMETRICS '03 Proceedings of the 2003 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
A smart hill-climbing algorithm for application server configuration
Proceedings of the 13th international conference on World Wide Web
Performance by Design: Computer Capacity Planning By Example
Performance by Design: Computer Capacity Planning By Example
Resource Allocation for Autonomic Data Centers using Analytic Performance Models
ICAC '05 Proceedings of the Second International Conference on Automatic Computing
Feedback Control Architecture and Design Methodology for Service Delay Guarantees in Web Servers
IEEE Transactions on Parallel and Distributed Systems
Automatic configuration of internet services
Proceedings of the 2nd ACM SIGOPS/EuroSys European Conference on Computer Systems 2007
A reinforcement learning framework for online data migration in hierarchical storage systems
The Journal of Supercomputing
ICDCS '08 Proceedings of the 2008 The 28th International Conference on Distributed Computing Systems
Online resource allocation using decompositional reinforcement learning
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Proceedings of the ACM international conference companion on Object oriented programming systems languages and applications companion
X-ray: automating root-cause diagnosis of performance anomalies in production software
OSDI'12 Proceedings of the 10th USENIX conference on Operating Systems Design and Implementation
Hi-index | 0.00 |
Good system performance depends on the correct setting of its configuration parameters. It is observed that such optimal configuration relies on the incoming workload of the system. In this paper, we utilize the Markov decision process (MDP) theory and present a reinforcement learning strategy to discover the complex relationship between the system workload and the corresponding optimal configuration. Considering the limitations of current reinforcement learning algorithms used in system management, we present a different learning architecture to facilitate the configuration tuning task which includes two units: the actor and critic. While the actor realizes a stochastic policy that maps the system state to the corresponding configuration setting, the critic uses a value function to provide the reinforcement feedback to the actor. Both the actor and critic are implemented by multiple layer neural networks, and the error back-propagation algorithm is used to adjust the network weights based on the temporal difference error produced in the learning. Experimental results demonstrate that the proposed learning process can identify the correct configuration tuning rule which in turn improves the system performance significantly.