NashDB

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

“…It is critical for cloud providers to reduce SLA violations while minimizing replication costs. 20,60,63,64,66,75,[85][86][87]89,94,95,128,133 Data replication strategies are mostly provider-centric compared to consumer-centric strategies, where most strategies consider the provider to be the entity responsible for operating the system and performing replication operations. Most of the strategies focus on reducing the replication cost.…”

“…Economic cost models are generally related to the economic aspect of the cloud, including the pricing policies, the monetary cost of management, auctions and so forth. 20,30,40,64,66,72,73,78,90,91,118,122,133 The focus on the economic aspect of cloud systems by replication strategies is mainly done by addressing the monetary cost of replication. 20,30,40,64,66,72,73,78,90,91 This monetary cost is often estimated by economic cost models that take into account both the cost of data storage and data transfer as well as the cost of the SLA penalties.…”

“…40,72,73,100 Other strategies rely on the auction method to optimize costs. 122,133 In Reference 122, the system resources compete to host the new replica, where each resource offers its own bid price as a buyer. Then, the seller resource decides to place the replica on the resource offering the highest bid price.…”

A review on data replication strategies in cloud systems

“…4) (iv) Economic behaviours-based strategies that reduce the replication cost. Some strategies exploit some economic behaviours used in trading (Belalem et al, 2011;Marcus et al, 2018;Shi et al, 2017;Zhang et al, 2018). They are based on some market-like mechanisms in which data are regarded as tradable goods.…”

“…The auction price depends on several properties, including the NB and available storage space. Marcus et al (2018) aimed to balance the load between the nodes of the system. It is based on an economic model that considers data as goods, queries as customers and nodes as companies.…”