Decentralized Online Learning in Task Assignment Games for Mobile Crowdsensing
This addresses the challenge of stable task assignment in mobile crowdsensing systems, where conflicting goals and uncertainty about efforts and preferences exist, representing a novel method for a known bottleneck in this domain.
The paper tackles the problem of coordinated data collection in mobile crowdsensing by proposing a decentralized online learning approach called CA-MAB-SFS, which models task assignment as a matching game and uses a free-sensing mechanism to improve learning and reduce collisions. Simulation results show it increases satisfaction for both mobile units and the platform while reducing average task completion time by at least 16%.
The problem of coordinated data collection is studied for a mobile crowdsensing (MCS) system. A mobile crowdsensing platform (MCSP) sequentially publishes sensing tasks to the available mobile units (MUs) that signal their willingness to participate in a task by sending sensing offers back to the MCSP. From the received offers, the MCSP decides the task assignment. A stable task assignment must address two challenges: the MCSP's and MUs' conflicting goals, and the uncertainty about the MUs' required efforts and preferences. To overcome these challenges a novel decentralized approach combining matching theory and online learning, called collision-avoidance multi-armed bandit with strategic free sensing (CA-MAB-SFS), is proposed. The task assignment problem is modeled as a matching game considering the MCSP's and MUs' individual goals while the MUs learn their efforts online. Our innovative "free-sensing" mechanism significantly improves the MU's learning process while reducing collisions during task allocation. The stable regret of CA-MAB-SFS, i.e., the loss of learning, is analytically shown to be bounded by a sublinear function, ensuring the convergence to a stable optimal solution. Simulation results show that CA-MAB-SFS increases the MUs' and the MCSP's satisfaction compared to state-of-the-art methods while reducing the average task completion time by at least 16%.