AHSWN Home • Issue Contents • Forthcoming Papers

Privacy-Aware Multi-task Allocation and Computing Offloading for Mobile Crowdsensing Based on Hybird Blockchain
Zhaoxin Yang, Meng Li, Ruizhe Yang, Yanhua Zhang and Yinglei Teng

Mobile crowdsensing (MCS) emerges as a promising sensing paradigm to engage mobile users in collecting sensing data for different task requestors (TRs) in a cost-effective manner. However, the sensing data contributed by the mobile participants usually contain users’ private information, which raises considerable concerns about privacy and trust issues. On the other hand, with the accumulation of sensing data, the large computing overhead of data aggregation becomes a non-negligible factor affecting the platform utility and system performance. To address the above issue, in this paper, we introduce a hybrid blockchain-enabled MCS platform, in which the smart contract is deployed to assist the task release and data collection. The hybrid architecture enables flexible execution of data aggregation and validation either at the edge server or in the cloud. he multi-task allocation and computing offloading decision are modeled as a Markov Decision Process (MDP) and solved through deep reinforcement learning, considering both platform utility and task execution latency. The simulation results demonstrate the feasibility and efficiency of the proposed approach.

Keywords: Mobile crowdsensing, Hybrid blockchain, Multi-task allocation, Computing offloading, Privacy protection

Full Text (IP)