A Capacity-Aware User Recruitment Framework for Fog-Based Mobile Crowd-Sensing Platforms

Mobile Crowd-Sensing and Fog Computing are fundamental Internet of Things technologies tailored for smart cities. The former enables user's devices to collect and share data in urban environments. The latter shifts the computation close to end users, lightening the work that their devices have to perform to communicate sensed data in the Cloud. In a fog-based MCS campaign a large number of devices with heterogeneous resources executes sensing tasks generally distributed by remote servers. A careful selection of some of these users' devices for sensing operations can bring benefits to the whole platform in terms of computational costs and energy saving. In this paper, we propose a novel users' recruitment model based on distance, computational capacity, and residual battery of devices. The selection process is carried out in a scenario where devices of the MCS campaign periodically share their battery and Central Processing Unit status to fog nodes through their short-range communication interfaces. Based on this information, fog nodes select devices suitable for performing specific tasks. To verify the effectiveness of the proposed model, we compare our solution with a selection model based only on distances, using an MCS simulator suitably modified for fog-based scenarios as testbed. Results show that our model is able to achieve a more accurate task resolution and a more effective recruitment selection, detecting those devices that can perform sensing operations better than others, thus, guaranteeing an overall average saving of computational and energy resources.