High-Efficiency Remote Cloud Data Center Backup with Intelligent Parameter Adaptation - Technologies and Applications of Artificial Intelligence - page 34

Table 3. Performance index

DataBase Performance Index

Apache HBase 93

Apache Cassandra 80

Cloudera HBase 54

DataStax Cassandra 51

Oracle MySQL 18

Table 4. Total cost of ownership over a 5-year period (unit: USD)

1 st Year 2 nd Year 3 rd Year 4 th Year 5 th Year DataBase

Apache HBase 12686 10020 10020 10097 10171

Apache Cassandra 12686 10020 10020 10097 10171

Cloudera HBase 14240 12373 12373 12050 12109

DataStax
Cassandra

14190 12727 12727 12209 12313

Oracle MySQL

15030 13373 13373 13450 13524

Table 5. C-P ratio over a 5-year period

1 st Year 2 nd Year 3 rd Year 4 th Year 5 th Year DataBase

Apache HBase 74 93 93 93 92

Apache Cassandra 63 80 80 79 78

Cloudera HBase

38 44 44 45 45

DataStax
Cassandra

36 40 40 42 42

Oracle MySQL

12 14 14 13 13

6 Conclusion

This paper realizes the remote data backup for HBase and Cassandra data centers, and
has employed adaptive network-based fuzzy inference system (ANFIS) along with
particle swarm optimization (PSO) to off-line tune seamless handoff and control
network traffic flow. As a result both HBase and Cassandra yield the best C-P ratio
when comparing with the others, provided that this paper indeed gives us an insight
into the topic of remote data center backup.

Acknowledgments. This work is fully supported by the National Science Council,
Taiwan, Republic of China, under grant number MOST 103-2221-E-390-011.

References

1. Chang, B.R., Tsai, H.-F., Chen, C.-M.: Empirical Analysis of Server Consolidation and
Desktop Virtualization in Cloud Computing. Mathematical Problems in Engineeringarticle
ID 947234, 11 pages (2013)