Cross Layer Approach and ANFIS based Optimized Routing in Wireless Multi-Hop Ad Hoc Networks

Mobile ad hoc networks are non-dependent on any wired infrastructure and provide exceptional benefits during typical situations like conference, fair/exhibition, disaster recovery and emergency rescue operations. But these networks have to deal with several open issues, since they are battery operated and the dynamic topology can change due to mobility. Thus, multi-hop wireless ad hoc networking needs an energy efficient routing protocol that discovers/maintains routes to any other member node in the network, minimizing computation/communication overhead and battery power consumption. An adaptive neuro fuzzy inference system (ANFIS) based ad hoc routing approach has not been investigated before. In this paper, an ANFIS and cross layer approach-based energy efficient routing protocol for wireless multi-hop networks is proposed and its performance is compared with the Ad Hoc On-demand Distance Vector (AODV) Routing Protocol and fuzzy based AODV, using the network simulator ns2. Using remaining battery power, hop count and link stability as the input variables, the ANFIS module computes the optimum path cost, as the output. The proposed ANFIS based approach produces better results when compared using the metrics: average throughput, packet delivery ratio, average end-to-end delay in packet delivery between source and destination and average routing overhead.