Multi-level Dynamic Optimization of Intelligent LEACH with Cost Effective Deep Belief Network

Abstract

Energy utilization is a key attribute for energy constrained wireless sensor networks (WSN) that directly impacts the life time of the network. LEACH (and its variants) are considered to be the most common energy efficient routing protocols for WSN. In this paper, we propose an optimized modification of LEACH that makes use of multi-hop communication, dynamic cluster boundaries and energy conservation in routing to maximize lifetime of a network. We propose a multi-level approach to maximize our gains with regards to energy conservation i.e., i) Dynamic programming based intra-cluster optimization technique has been proposed ii) Ant Colony Optimization is used for energy efficient cluster head connection with sink node and iii) Voronoi Tessellation are employed for efficient coverage planning i.e., dynamic formation of cluster boundaries. In order to accommodate a more flexible adhoc network, hybrid (reactive and proactive) event monitoring based on Deep Belief Network has been integrated in distributed nodes to improve the latency of the system. The results show that the proposed scheme significantly outperforms the current state of the art with regards to network lifetime and throughput.