Task coalition formation for Mobile CrowdSensing based on workers' routes preferences

In this paper, we address the problem of task allocation in Mobile Crowdsensing (MCS) by means of forming tasks publisher coalition taking into consideration workers' route preferences. In prior research works, only one of the MCS components (either task publishers, contributors or platform) dominates the task allocation process. Currently, other approaches have investigated tasks coalition based on their geographical locations. In this paper, we address the aforementioned problem by proposing a new scheme taking into accounts the interest of all the participating parties. To this end, our approach provides (1) strategies for selecting the best routes for workers with better long-term earnings and (2) task publishers' coalition formation based on worker's routes selection and preferences regardless of the order of individual execution of tasks. We proposed two models for the coalition formation: i) a centralized approach to solve the problem of the coalition formation together with the route selection, and ii) a simplified heuristic version that first determines disjoint tasks' coalitions based on the preferred routes selected by workers, then, MCS platform sorts the coalitions with best quality of information and selects the best routes for each ordered coalition. Simulation results with real data-set show that the coalition of task publishers together with the distributed route selection per worker does guarantee the quality of information satisfaction of the sensing tasks while enhancing the worker payment.