Journals Proceedings

Abstract

Collision free dynamic slot scheduling in ad-hoc networks is NP complete problem. In most of the distributed networks, scheduling is performed by cluster heads or relay nodes. A sophisticated method is needed for nodes to perform dynamic schedule on their own and update the state of resources. Recently, neural network and few heuristic approaches are used to solve the problem. In this paper, we propose a heuristic based method on the idea of generating optimal solutions. The arithmetic crossover and cyclic permutation use random generated slot vectors of neighbors, broadcast during the scheduling period to create an initial population. The technique uses elitism to highlight one-hop and two-hop collisions and makes the information usable in finding valid solutions. The operations provide optimal scheduling solutions which are used in next generation. The method increases collision avoidance probability and channel utilization in terms of scheduling maximum transmissions in a TDMA frame.