A Data Dependency and Access Threshold Based Replication Strategy for Multi-cloud Workflow Applications

Abstract

Data replication is one of the significant sub-areas of data management in cloud based workflows. Dataintensive workflow applications can gain great benefits from cloud environments and usually need data management strategies to manage large amounts of data. At the same time, multi-cloud environments become more and more popular. We propose a cost-effective and threshold-based data replication strategy with the consideration of both data dependency and data access times for data-intensive workflows in the multi-cloud environment. Finally, the simulation results show that our approach can greatly reduce total cost of dataintensive workflow applications by considering both of data dependency and data access times in multi-cloud environments.Abstract. Data replication is one of the significant sub-areas of data management in cloud based workflows. Data-intensive workflow applications can gain great benefits from cloud environments and usually need data management strategies to manage large amounts of data. At the same time, multi-cloud environments become more and more popular. We propose a cost-effective and threshold-based data replication strategy with the consideration of both data dependency and data access times for data-intensive workflows in the multi-cloud environment. Finally, the simulation results show that our approach can greatly reduce total cost of data-intensive workflow applications by considering both of data dependency and data access times in multi-cloud environments.

Review on data replication strategies in single vs. interconnected cloud systems: Focus on data correlation‐aware strategies

“…In this sense, the majority of replication strategies take frequently accessed data into consideration. 29,[31][32][33][34][35]37,38 The cloud context (access history, meta-data, etc.) is then transformed into an extraction context mainly represented by matrices or graphs.…”

“…In this regard, most data correlation-aware strategies in cloud systems employ access correlations for correlation estimation, with the degree of correlation defined by simultaneous or shared access to data. 29,35,37,38 It is important to note that the size of the extraction context affects the time required to extract correlations. Consequently, the majority of data correlation-aware strategies prefers a periodic analysis of the system information.…”

“…[27][28][29][30] Indeed, several data replication strategies have benefited from exploiting this knowledge about data correlations. [29][30][31][32][33][34][35][36][37][38][39][40] To the best of the author's knowledge, there is no survey concentrating on data replication strategies designed for interconnected cloud systems. Therefore, in this article, we provide an analysis of existing strategies in cloud systems, covering single and interconnected clouds.…”

Energy and Expenditure Aware Data Replication Strategy

“…Based on their popularity, replicas are compressed in the backup group or not. [18] considers a workflow application model that contains information about which task needs which data. This permits to regroup data based on their dependencies, and know which data are requested too many times.…”

Popularity and correlation aware data replication strategy based on half‐life concept and clustering in cloud system

“…In Reference 46, a replication strategy is proposed for a multicloud environment. By taking both data correlation and data access time into consideration, the studied strategy aims to replicate datasets that are both highly correlated and frequently accessed.…”