An Online Mechanism for Crowdsensing with Uncertain Task Arriving

摘要

In this paper, an online incentive mechanism in crowdsensing systems is studied. Different from most of the existing works which considered the smartphone users arriving at the crowdsourcer in an online fashion, we concentrate on the uncertain task arrivals, and consider the smartphone user allocation problem by jointly taking the cost capacity of each smartphone user and the sensing data quality requirement into consideration. In our model, since the tasks arrive at the crowdsourcer in an online manner, the crowdsourcer must make decisions timely to choose a suitable subset of smartphone users to achieve a sound competitive ratio (compared to the offline solution) once the tasks arrive. For the purpose of minimizing social cost in the whole system and achieving truthfulness, an online strategy proof incentive mechanism is designed by applying randomized auction framework. Theoretical and simulation results verify the effectiveness of the proposed online incentive mechanism.