Prioritization driven task offloading in uav-aided software-defined networks

Under demanding operational conditions such as traffic surges, coverage issues, very-low latency requirements, or security concerns, terrestrial cellular networks may become inadequate to provide the expected service levels to users and applications. Moreover, when natural disasters or physical calamities occur, the existing network infrastructure may collapse, leading to formidable challenges for the first response and emergency communications in the served area. In order to provide low-latency services for first-responders and baseline connectivity for the public as well as facilitate a capacity boost under transient high service load situations, a substitute or auxiliary fast-deployable network is needed. Unmanned Aerial Vehicle (UAV) networks are well suited for such needs thanks to their high mobility and flexibility. This thesis considers a software-defined network consisting of Unmanned Aerial Vehicles (UAVs) mounted with Wi-Fi access points, which serve mobile users with the latency-sensitive workload in an edge-to-cloud continuum setting. It investigates the task offloading paradigm to provide prioritized services via this on-demand aerial network. In addition to baseline connectivity for users in the deployed area, this computing-communication infrastructure essentially provides Vehicle-to-Vehicle (V2V) and Vehicle-to-Cloud (V2C) task offloading services to terrestrial units. In our work, task processing, and offloading management, task deadlines are taken into account as the key criterion for meeting service quality requirements. Accordingly, an offloading management optimization model is defined to minimize the overall penalty due to delay weighted with task priorities. Since the defined assignment problem is NP-hard, tailored heuristic models are proposed and evaluated to study how the system performs under different operating conditions.