Structuring communities for sharing human digital memories in a social P2P network

A community is sub-network inside P2P networks that partition the network into groups of similar peers to improve performance by reducing network traffic and high search query success rate. Large communities are common in online social networks than traditional file-sharing P2P networks because many people capture huge amounts of data through their lives. This increases the number of hosts bearing similar data in the network and hence increases the size of communities. This article presents a Memory Thread-based Communities for our Entity-based social P2P network that partition the network into groups of peers sharing data belonging to an entity-person, place, object or interest, having its own digital memory or be a part another memory. These connected peers having further similarities by organizing the network using linear orderings. A Memory-Thread is the collection of digital memories having a common reference key and organized according to some form of correlation. The simulation results show an increase in network performance for the proposed scheme along with a decrease in network overhead and higher query success rate compared to other similar schemes. The network maintains its performance even while the network traffic and size increase.