An Energy-Efficient Routing Approach for Performance Enhancement of MANET Through Adaptive Neuro-Fuzzy Inference System

Mobile ad hoc network comprises of wireless nodes which are mobile in nature and have short lifespan. They join together to create a self-configured infrastructure-less network where routing is an important challenge. In AODV routing, the hello messages are broadcast periodically by nodes for monitoring the link connectivity to neighbors and for maintaining routing table. The broadcasting of hello messages increases when link failure occurs due to node mobility, which leads to higher consumption of node energy and increases overhead within network. This paper proposes an energy-efficient routing approach (EE-RA), which calculates optimal hello interval for reducing the unnecessary broadcasting of hello messages that further reduces node's energy consumption and network overhead. This is achieved by using Mamdani-based fuzzy inference system and adaptive neuro-fuzzy inference system (ANFIS) to calculate the resultant optimal hello interval in which energy and mobility of node are taken as inputs. Moreover, simulation results illustrate that the performance of EE-RA outperforms AODV and achieve better results for ANFIS in hello message fraction, network overhead, average energy consumption, packet delivery ratio, end-to-end delay and throughput, especially in highly mobile and dense environment.