Supporting Service Adaptation in Fault Tolerant Internet of Things

This paper presents a sensing device adaptation scheme for fault-tolerant IoT using the service-oriented architecture. In IoT, there are many sensors deployed for different purposes. Sensors of different modalities may be used to enhance the system fault tolerance. We propose the concept of virtual services which use data from more than one sensor devices to replace an actual service on some faulty device. We do regression analysis to identify and generate virtual services using available sensors. Depending on the sensor correlation types, we can use with recursive least squares (RLS) or multivariate adaptive regression splines (MARS) for virtual service generation. We have also modeled the mapping problem from application workflow to actual sensor deployments as a multiobjective optimization problem, and studied the genetic algorithm NSGA-ii to find the optimal actual or virtual sensor selections. Finally, we present a system engineering process for building fault tolerant IoT.