Using speculation to reduce server load and service time on the WWW
CIKM '95 Proceedings of the fourth international conference on Information and knowledge management
Partial collection replication versus caching for information retrieval systems
SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
IEEE Transactions on Parallel and Distributed Systems
OceanStore: an architecture for global-scale persistent storage
ACM SIGPLAN Notices
OceanStore: an architecture for global-scale persistent storage
ASPLOS IX Proceedings of the ninth international conference on Architectural support for programming languages and operating systems
WWW Traffic Reduction and Load Balancing through Server-Based Caching
IEEE Parallel & Distributed Technology: Systems & Technology
Performance Modeling of Distributed and Replicated Databases
IEEE Transactions on Knowledge and Data Engineering
Data management issues in mobile and peer-to-peer environments
Data & Knowledge Engineering - DKE 40
Identifying Dynamic Replication Strategies for a High-Performance Data Grid
GRID '01 Proceedings of the Second International Workshop on Grid Computing
An Active Replication Scheme for Mobile Data Management
DASFAA '99 Proceedings of the Sixth International Conference on Database Systems for Advanced Applications
Database Migration in WAN Environments: How Can It Earn Good Performance?
DEXA '00 Proceedings of the 11th International Conference on Database and Expert Systems Applications
HCW '98 Proceedings of the Seventh Heterogeneous Computing Workshop
Trading Replication Consistency for Performance and Availability: an Adaptive Approach
ICDCS '03 Proceedings of the 23rd International Conference on Distributed Computing Systems
A dynamic distributed replica management mechanism based on accessing frequency detecting
ACM SIGOPS Operating Systems Review
Replica management should be a game
EW 10 Proceedings of the 10th workshop on ACM SIGOPS European workshop
A User-Centered Approach to Active Replica Management in Mobile Environments
IEEE Transactions on Mobile Computing
ACB-R: an adaptive clustering-based data replication algorithm on a p2p data-store
ASIAN'05 Proceedings of the 10th Asian Computing Science conference on Advances in computer science: data management on the web
Hi-index | 0.00 |
This paper presents an efficient scheme for dynamic replication of data in distributed environments. The aim of the scheme is to increase system performance by intelligent data placement so as to optimize the message traffic in the network. Research in the recent past has comparatively focussed very little on using replication for increasing performance but has instead been directed more at improving system availability through replication. However, with the advent of mobile or nomadic computing, research in replication needs to change direction-- the underlying assumption of high speed networks no longer hold true. Wireless networks not only have lower bandwidth but are also very expensive to use. In such an environment, it is imperative that data be distributed intelligently to achieve a good system performance in terms of message costs and turnaround time. Besides, with mobility introduced in the system, earlier static schemes for improving performance (e.g., the File Allocation Problem) are no longer applicable. As a first step, we propose a totally distributed dynamic replication scheme, which uses a finite automaton based technique to learn access patterns. This accrued information is then used to predict future access sequences and dynamically reorder-- replicate or delete copies of data in the network, in anticipation of predicted accesses, to reduce network message costs. Being distributed, each node of the network bases its decision to replicate or delete an existing copy solely on local information. Our algorithm is also integrated and corrects some of the drawbacks of earlier theoretical work in this area. Finally, we present some preliminary simulation results which show that our scheme is very promising.