Task offloading and resource allocation for edge-of-things computing on smart healthcare systems

Impelled by prevalent smart devices and omnipresent wireless communication networks, Edge-of-things transpires as a captivating paradigm to accommodate power-sensitive or compute-intensive applications over resource-constrained smart devices. In this research, we focus on flexible compute-intensive task offloading to a local cloud (i.e., cloudlet) saving energy, which aims to optimize the energy consumption, the operation speed, and the cost. A fruit fly optimization based task offloading algorithm (FOTO) is proposed, which improves offloading and resources allocation to acquire the nominal energy consumption under the existing restraints. Performances are evaluated regarding energy consumption, execution time and cost, which are compared with the cooperative multi-tasks scheduling based on ant colony optimization algorithm (CMS-ACO) and heuristic queue based algorithm (GA-ACO). The experimental results prove the effectiveness of proposed FOTO algorithm by comparing with existing algorithms.