Improve the performance of peer-to-peer networks within publish/ subscribe systems by using PeerSim simulator within Eclipse Environment

تحسين أداء شبكات الند للند ضمن أنظمة النشر والاشتراك باستخدام محاكي Peersim ضمن بيئة Eclipse

Abstract

Publish/ subscribe (pub/ sub) is a popular communication paradigm in the design of large-scale distributed systems. We are witnessing an increasingly widespread use of pub/ sub for a wide array of applications in industry, academia, financial data dissemination, business process management and does not end in social networking sites which takes a large area of user interests and used network bandwidth.

Social network interactions have grown exponentially in recent years to the order of billions of notifications generated by millions of users every day. So, it has become very important to access in the field of publishing and subscription networks, especially peer-to-peer (P2P) networks in many ways like the publication speed for events And the percentage of loss in the incoming events of the participants.

Peer-to-peer systems can be very large and include millions of nodes, those nodes join and leave the network continuously, and these characteristics are difficult to handle. The evaluation of a new protocol in a real environment, particularly in the early stages, was considered impractical. Hence the need for a simulator to perform such a function to facilitate the simulation of researchers and this emulator is an open source simulator running within the Eclipse environment.

In this research we have adopted a new method of selecting nodes within the table of vicinity protocol. This method is concentrated in that the far node increases the probability of its inclusion in the table more than the adjacent node. and The proposed network that uses the Polder Cast protocol was modelled using PeerSim software for modelling deployment and subscription networks within the eclipse environment so that the event delivery service is a Peer-2-Peer network and the method used to register is subject-based (Topic-Based).

experimental results showed noticeable improvement in the publication speed for events by 51.11% compared to the original design of the protocol. And The percentage of event loss was reduced by 20%.