Novel Distribution-Aware and Learning-Based Dynamic Scheme for Efficient User Incentivization in Edge Sensing Systems

Edge sensing (ES) systems employ users’ owned smart devices with built-in sensors to gather data from users’ surrounding environments and use their processors to carry out edge computing tasks. Therefore, ES is emerging as a potential solution for remote sensing challenges. Additionally, ES systems are recognized for their favorable characteristics, including efficient time and cost management, scalability, and the ability to gather real-time data. To improve the performance of ES systems, enormous efforts have been made to enhance the quality of data (QoD) and the systems’ spatiotemporal coverage. Moreover, the research community has focused on developing better incentive schemes, as user incentivization is essential for enhancing system performance. In this study, we assess the impact of users’ mobility and availability on the spatiotemporal coverage and QoD of ES systems, taking into account the heterogeneity of users. We propose a distribution-aware and learning-based dynamic incentive scheme. Specifically, we consider the randomness of users’ mobility and velocity using a 2-dimensional random waypoint (RWP) model and support the learning-based incentive scheme with a long short-term memory (LSTM) model. The LSTM model utilizes the users’ historical data to predict their availability to perform the sensing tasks. The learning-based incentive scheme is further used to enhance system performance and effectively manage the trade-off between quality and cost, by recruiting users based on the required quality and cost constraints, to meet the minimum quality requirement within a constrained incentivization budget.