원문정보
초록
영어
This paper presents multidimensional aggregation query processing algorithm in cloud computing system. The existing cloud computing research work in the MapReduce calculation framework lacks effective support to the aggregation of multi-dimensional data. On the other hand, the use of MapReduce computing framework needs to start large computing nodes, and costs huge amounts of energy. For the above problems, this paper presents multidimensional aggregation operation scheme in the cloud computing system, through two layers of index structure to reduce the query computing nodes and Calculation of aggregation operation in single computing nodes. This paper gives an algorithm framework using two layers of index structure to process multidimensional aggregation query, and proposed priority mode of performance and multi-dimensional aggregation algorithms under low-power mode in this framework. In two modes of multidimensional aggregation algorithm proposed query allocation problem, and proves that the two modes query allocation problems are NP-completing problem. This paper presents approximation algorithm of two NP-completing problem and proves the approximate ratio of two approximation algorithms. Theoretical analysis and simulation results prove the validity of the multidimensional aggregate query plan.
목차
1. Introduction
2. Multidimensional Clustered Index in Cloud System
2.1. System Architecture
2.2 Aggregation Process Framework
3. Aggregation Process of Multidimensional Performance Priority in Cloud System
4. Aggregation Process of Multidimensional Low Power Consumption in Cloud System
5. Experiment Design and Performance Evaluation
5.1. Experimental Setup
5.2 Aggregation Process of Performance Priority
5.3 Aggregation Process of Low Power Consumption
6. Conclusion
References