Novel Bat Algorithms for Scheduling Independent Tasks in Collaborative Internet-of-Things

Collaborative Internet-of-Things (C-IoT) is a new paradigm that allows mobile devices to offload computation tasks not only to servers in the edge computing tier but also to other mobile devices, in order to achieve low latency and energy saving. This paper investigates the problem of task scheduling and resource allocation considering independent tasks in a C-IoT system consisting of multiple mobile devices and a single resource-limited server. The scheduling objective is to minimize the flowtime of all tasks while satisfying the energy constraint on mobile devices. To solve this scheduling problem, we proposed novel bat algorithms that incorporate a velocity control strategy into the bat algorithm framework. In addition, we present a position-based mapping operator to map each bat onto a feasible solution. This mapping operator combines the currently best solution and the bat’s position to ensure the high quality of the mapped solution. Simulation results demonstrate that our proposed algorithms outperform competing algorithms that use the standard bat algorithm and traditional mapping method in generating high-quality scheduling solutions.