Wide area traffic: the failure of Poisson modeling
IEEE/ACM Transactions on Networking (TON)
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Aqueduct: Online Data Migration with Performance Guarantees
FAST '02 Proceedings of the Conference on File and Storage Technologies
A Cost-Model-Based Online Method for Ditributed Caching
ICDE '97 Proceedings of the Thirteenth International Conference on Data Engineering
Reinforcement learning with selective perception and hidden state
Reinforcement learning with selective perception and hidden state
IBM Storage Tank-- A heterogeneous scalable SAN file system
IBM Systems Journal
An Architecture for Lifecycle Management in Very Large File Systems
MSST '05 Proceedings of the 22nd IEEE / 13th NASA Goddard Conference on Mass Storage Systems and Technologies
A reinforcement learning framework for online data migration in hierarchical storage systems
The Journal of Supercomputing
Exploration and exploitation balance management in fuzzy reinforcement learning
Fuzzy Sets and Systems
Similarity of learned helplessness in human being and fuzzy reinforcement learning algorithms
Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology - Computational intelligence models for image processing and information reasoning
Hi-index | 0.00 |
Multi-tier storage systems are becoming more and more widespread in the industry. In order to minimize the request response time in such systems, the most frequently accessed ("hot") files should be located in the fastest storage tiers (which are usually smaller and more expensive than the other tiers). Unfortunately, it is impossible to know ahead of time which files are going to be "hot", especially because the file access patterns change over time. This report presents a solution approach to this problem, where each tier uses Reinforcement Learning (RL) to learn its own cost function that predicts its future request response time, and the files are then migrated between the tiers so as to decrease the sum of costs of the tiers involved. A multi-tier storage system simulator was used to evaluate the migration policies tuned by RL, and such policies were shown to achieve a significant performance improvement over the best hand-crafted policies found for this domain.