Uma proposta de arcabouço para tolerância a falhas multicamadas em sistemas IoT

Abstract

Fault tolerance in IoT systems is challenging to overcome due to its complexity, dynamicity, and heterogeneity. IoT systems are typically designed and constructed in layers. Every layer has its requirements and fault tolerance strategies. However, errors in one layer can propagate and cause effects on others. Thus, it is impractical to consider a centralized fault tolerance approach for an entire system. Consequently, it is vital to consider multiple layers in order to enable collaboration and information exchange when addressing fault tolerance. The purpose of this study is to propose a multi-layer fault tolerance approach, granting interconnection among IoT system layers, allowing information exchange and collaboration in order to attain the property of dependability. In order to attain this purpose, the pathology of failures is established, which aids in understanding the faults and their behavior, serving as a basis for defining an event-oriented framework called FaTEMa (Fault Tolerance Event Manager). This framework creates a dedicated communication channel to propagate fault-related events through system levels, assisting in error detection and service continuation. Additionally, it offers extension points to support heterogeneous communication protocols and evolve new capabilities. The empirical evaluation results show that introducing FaTEMa provided improvements to the error detection and error resolution time, consequently improving system availability. In addition, the use of Fatema provided a reliability improvement and a reduction in the number of failures produced.