Internet of Things-Based Optimized Routing and Big Data Gathering System for Landslide Detection

Abstract

An exponential progression in the miniaturization of communicating devices has proliferated the generation of a large volume of data termed as "big data." The technological advancements in the micro-electro/mechanical system has made it possible to design the low-cost, low-power consuming artificial intelligence (AI)-based wireless sensor nodes to gather the big data belonging to various attributes from their surroundings. These nodes help in the early detection and prediction for the occurrence of landslides, which are among the catastrophic hazards. A profusion of research has focused on exploiting the potential of sensors for continuous monitoring and detecting the landslides at the earliest. However, the limited energy resources of sensor nodes give rise to the huge challenge for the network longevity pertaining to landslide detection. To address this concern, in this article, we propose an optimized routing and big data gathering system for landslide detection using (AI)-based wireless sensor network (WSN) (ORLAW). Since we propose a distributed routing mechanism, AI has a major role to play in the intelligent detection of landslides that too without the intervention of an external entity. We use the Dynamic Salp Swarm Algorithm for the cluster head selection in ORLAW. Two data collecting sinks are deployed on the opposite sides of the network, which is assumed to be a mountainous area. It is discerned from the simulation examination that ORLAW elongates the reliability period by 23.9% compared with the recently proposed cluster-based intelligent routing protocol, and also outperforms many others in the perspective of energy efficient management of big data.

Keywords: AI-based WSN; ORLAW; big data handling; cluster head (CH); cluster-based routing; landslide detection.