Decentralized Online Learning in Task Assignment Games for Mobile Crowdsensing

TL;DR

This paper introduces a decentralized online learning algorithm for task assignment in mobile crowdsensing systems, effectively balancing the goals of the platform and users while ensuring stable, efficient task allocation with improved satisfaction and reduced completion time.

Contribution

It proposes a novel collision-avoidance multi-armed bandit approach combined with matching theory and online learning for stable, decentralized task assignment in crowdsensing.

Findings

Reduces average task completion time by at least 16%.

Increases satisfaction of both MUs and MCSP.

Ensures convergence to a stable optimal solution.

Abstract

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%.