FOCUS: Fog Computing in UAS Software-Defined Mesh Networks

摘要: Unmanned aerial systems (UASs) allow easy deployment, three-dimensional maneuverability and high reconfigurability, as they sustain communication network in the absence of pre-installed infrastructure. The proposed FOg Computing UAS Software-defined mesh (FOCUS) paradigm aims to realize an implementable design that considers practical issues connectivity computation. It allocates UASs tasks data forwarding in-network fog computing while maximizing number ground-users coverage. FOCUS improves efficient utilization resources by introducing on-board computation innovates on top software-defined networking stack integrating capabilities ground controllers enable simultaneous orchestration both flows. There are three main contributions paper: First, a SDN-based architecture is designed enabling autonomous configuration well managing multi-hop links. Second, global optimization problem achieve optimal computational allocation formulated using Open Jackson Network model solved via heuristic approach with defined complexity. Third, framework implemented small-scale testbed Intel® Aero performing image analysis full software stack. Experiments reveal at least 32% latency improvement service time compared traditional centralized end-server or greedy task schemes within network.