Offloading Data through Unmanned Aerial Vehicles: A Dependability Evaluation

Applications in the Internet of Things (IoT) context continuously generate large amounts data. The data must be processed and monitored to allow rapid decision making. However, wireless connection that links such devices remote servers can lead loss. Thus, new forms a explored ensure system’s availability reliability as whole. Unmanned aerial vehicles (UAVs) are becoming increasingly empowered terms processing power autonomy. UAVs used bridge between IoT servers, edge or cloud computing. collect from mobile process them, if possible. If there is no UAV, sent on at cloud. Data offloading throughout reality today, but one with many challenges, mainly due unavailability constraints. This work proposes stochastic Petri net (SPN) models block diagrams (RBDs) evaluate distributed architecture, focusing reliability. Among various existing methodologies, nets provide represent complex systems different characteristics. route through base station. station receives retransmits them cloud, responses returned devices. A sensitivity analysis Design Experiments (DoE) showed key points improvement for model, which was enhanced. numerical indicated components most significant impact availability. For example, proved very relevant component architecture. final results could prove effectiveness improving model. present help system architects develop architectures more optimized low evaluation costs.