EFFECT OF INCREASING NODE DENSITY ON REINFORCEMENT LEARNING BASED ENERGY PRESERVATION ROUTING ALGORITHM FOR WIRELESS SENSOR NETWORK

Summary

A wireless sensor network (WSN) is a network consisting of miniaturized smart sensors communicating the
information gathered or collected from a monitored environment via a wireless link. The sensors are capable
of sensing the events within their environment, process the data, and transmit the data to the base station (BS).
The entire processing of data and subsequent transmission to BS requires high energy consumption. The
operation of WSN is limited by repeated dead nodes, which results in energy depletion. Hence, to prolong the
life-span of the network, several routing protocols have been developed. In this paper, the effect of increasing
node density on cluster based energy-efficient routing protocol based on reinforcement learning (RL) in
wireless sensor network was analyzed. Simulations were conducted in MATLAB. When the number of sensor
nodes was 50, the number of alive nodes after 5000 rounds was 3. However, as the number of nodes was
increased to 90, it was observed that there were 28 nodes after 5000 rounds. Conversely, the energy consumed
after 5000 rounds was 0.000871 J for 50 nodes and 0.007184 J for 90 nodes. Generally, increasing number of
nodes in sensor network can extend the network lifespan, but this will cause an increase in the amount of the
energy consumed.

Index Terms

Browse additional articles authored by one or more contributors to this paper.