Combined Linear Multi-Model for Reliable Route Recommender in Next Generation Network

Abstract

Network analysis is a promising field in the area of network applications as different types of traffic grow enormously and exponentially. Reliable route prediction is a challenging task in the Large Scale Networks (LSN). Various non-self-learning and self-learning approaches have been adopted to predict reliable routing. Routing protocols decide how to send all the packets from source to the destination addresses across the network through their IP. In the current era, dynamic protocols are preferred as they network self-learning internally using an algorithm and may not entail being updated physically more than the static protocols. A novel method named Reliable Route Prediction Model (RRPM) is proposed to find the best routes in the given hefty gage network to balance the load of the entire network to advance the network recital. The task is carried out in two phases. In the first phase, Network Embedding (NE) based node classification is carried out. The second phase involves the network analysis to predict the route of the LSN. The experiment is carried out for average data transmission and rerouting time is measured between RRPM and Routing Information Protocol (RIP) protocol models with before and after failure links. It was observed that average transmission time for RIP protocol has measured as 18.5 ms and RRPM protocol has measured as 18.2 ms. Hence the proposed RRPM model outperforms well than the traditional route finding protocols such as RIP and Open Shortest Path First (OSPF).