Age-of-Information-Driven Task Allocation for Periodic Updating Crowdsensing: A Contract Theory-Based Approach

Abstract

Mobile crowdsensing (MCS) is an emerging technology, which provides a promising paradigm for completing complex sensing tasks. While existing studies for MCS mainly focus on designing incentive mechanisms to attract more participants or optimizing task allocation to maximize profit, the freshness of information, known as Age of Information (AoI), has been largely overlooked. In MCS systems, some Point of Interests (PoIs) need to be monitored through sampling by participants. High-frequency sampling can effectively ensure AoI performance, which also imposes significant costs on participants. Therefore, it is necessary to allocate appropriate sampling tasks and design the corresponding sample cycles and prices for participants. In this article, we address the joint problem of incentive mechanism and task allocation. First, we adopt the contract theory to model the incentive mechanism, where the crowdsensing platform (CP) offers a set of cycle-price combinations to participants. We establish the necessary and sufficient conditions for the feasibility of the contract and subsequently derive the optimal contract structure. Second, subject to the derived contract structure, we determine the optimal task allocation under specific conditions. For more general situations, we propose an iterative algorithm, which is based on pair switching with a proven convergence guarantee. Finally, the simulation results demonstrate the efficiency of the proposed contract-based algorithm, which also outperforms other incentive mechanisms.