Statistical Analysis to Extract Effective Parameters on Overall Energy Consumption of Wireless Sensor Network (WSN)

In this paper, we use statistical tools to analysis dependency between Wireless Sensor Network (WSN) parameters and overall Energy Consumption (EC). Our approach has two key steps: profiling, and effective parameter extraction. In former step, a sensor network simulator is re-run 800 times with different values of the WSN parameters to profile the average residual energy in nodes. In latter step, three statistical analyses (p-value, linear and non-linear correlation) are applied to the outcome of profiled experiments to extract the most effective parameters on WSN residual energy.