A Learning Automata Based Data Aggregation Method for Sensor Networks

One way to reduce energy consumption in wireless sensor networks is to reduce the number of packets being transmitted in the network. Data aggregation technique, in which packets with related information are combined together in intermediate nodes before further forwarding towards their destination, shown to be a good solution for this purpose. It is clear that more related information along the paths each packet traverse results in higher aggregation ratio. If the information each node has, varies from time to time, finding paths along which more nodes with related information exist becomes a complicated task. In this paper, a learning automata based data aggregation method in sensor networks will be proposed. Each node of the sensor network is equipped with a learning automaton which learns the path along which the aggregation ratio is maximum. Simulation results show that the proposed method performs well in situations where nodes having related information vary during the network's lifetime.

Keywords:

Sensor Networks , Data Aggregation , Learning Automata