Social Community-Partition Aware Replica Allocation in Ad-Hoc Social Networks

Ad-hoc social network (ASNET) services deal with the dynamic nature and resource constraints of mobile nodes to support various applications. The availability, accessibility and reliability of these services can be assured by data management approaches such as replica allocation methods. Data replication is used to increase data availability by replicating data items locally or nearby. In ASNETs, replication helps to avoid data losses in case of an unpredictable community or network partition and also aids in reducing the number of hops when a data is transmitted from source to destination. A new data replication method called ComPAS (community-partition aware replica allocation method for ASNETs) is proposed in this paper. This method can significantly improve a social network´s efficiency by taking into account social relationships and properties of its data while replicating in the community to achieve better load-balance. This type of replica allocation method will increase the availability of different data items in a partitioned social community. Evaluation results verify the effectiveness of the method.