An Energy Efficient Routing Protocol and Cross Layer Based Congestion Detection Using Hybrid Genetic Fuzzy Neural Network (HGFNN) Model for MANET

Abstract

Rapid advancements in wireless communication technologies have resulted in amazing development in adhoc networking. Mobile Adhoc Network has become an essential one in every aspects of our life due to the recent growth of technological developments. Effective communication in right scenarios is an important factor to be considered. Mobile adhoc networks, is a subclass of adhoc networks, nearly have similar features as adhoc networks, offering many obstacles in designing a path for transmitting information from source to destination. As a result, the network may be susceptible to suspicious network events as a result of factors such as connection errors, buffer overflows, layers, and so on. In this research, the Hybrid Genetic Fuzzy Neural Network (HGFNN) method is employed for a cross-layer based congestion detection and energy efficient routing protocol. When a network event happens in this protocol, the kind of event happening is detected to handle it properly. Following that, other data transmission pathways are established by using the idea of hybrid approaches to some of the essential parameters. Suitable routes are established and data messages are effectively conveyed based on the learning processes used in this study by employing a hybrid genetic fuzzy neural network method that ensures adaptive and rapid data communication. The suggested technique aims to reduce energy utilization, transmission delay, enhance packet delivery ratio, hence increasing throughput. Suggested method's efficiency is calculated by assessing its performance in network simulator with respect to energy utilization, transmission delay, and packet delivery ratio.