Análise de sobrevivência na modelagem do tempo de vida de redes de sensores sem fio

Abstract

Wireless Sensor Networks (WSN) are examples of Resource-Constrained Networks (RCNs) in which processing resources, storage and energy are limited. From the moment a typical WSN goes into operation, the sensor nodes begin to perform operations like sensing, processing and communicating, consuming the stored energy in their batteries until its ends completely, a situation that is characterized like the death of the devices and consequently the network. Knowing a priori the expected lifetime of a WSN before deploying it, enables the development of maintenance strategies to maximize it lifespan and ensure that it survives enough time to accomplish it goal. Therefore, we propose in this work the use of Exponential, Weibull and Log-Normal models, which are commonly used in studies of Survival Analysis, to infer survival statistics of a real network from the lifespans of its nodes observed in simulation. Our hypothesis is that the Survival Analysis may improve the accuracy of estimating the lifetime of a WSN and, consequently, their operational planning. This work proposes answers to three questions which are open in the literature: (i) how many sensor nodes will die during the lifetime of a WSN (ii) in which time period most of the nodes will die (iii) for how long network will remains operational.