Abstract

Most of the dynamic query optimization methods proposed in the literature are centralized. This centralization, in a large-scale environment, generates a bottleneck due to relatively important message exchange on a network with a weak bandwidth and strong latency. It becomes thus convenient to render autonomous and self-adaptable the query execution on a large-scale network. In this perspective, we propose a mobile relational algebra to decentralize the control of dynamic query optimization processes. Experiments, in local and large-scale distributed environments, allow: (i) to validate the proposed proactive migration policy, and (ii) to identify the efficiency intervals of proposed mobile relational algebra.

Highlights

  • More and more applications try to integrate heterogeneous data sources scattered on a large-scale network

  • We have observed that it is it is important to limit the data and control messages to avoid the risk of congestion of the network due to the strong latency and of the low bandwidth in a large-scale distributed environment

  • We defined the operators without restricted access and with restricted access where the control of the execution plan is integrated within every operator

Read more

Summary

Introduction

More and more applications try to integrate heterogeneous data sources scattered on a large-scale network. In a large-scale environment, networks have a relatively low bandwidth, the accessed data volume can be huge and the number of users and data sources is important In this environment, one of the major challenges for the viability of applications is the performance optimization of the query evaluation. To take into account this resource [22], leans on the mobile agents to decentralize the control and the modifications of the execution plans In this method, the interactions between the agents participating in the same query are based on message broadcasting. An optimization method must be decentralized and must minimize the number of exchanged messages In this perspective, we propose a mobile relational algebra.

Relational operators without restricted access
Mobile join
Mobile minus and union
Relational operators with restricted access
Dependent access operator
Mobile dependent join operator
Mobile dependent minus
Cost model
Local DBMS cost model
Embedded cost model
Interactions between an agent and a site
Performance evaluation
Environment and prototype
Evaluation of mobile hash join operator
Mobile query evaluation
Related work
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call