CrowdBind: Fairness Enhanced Late Binding Task Scheduling in Mobile Crowdsensing
CrowdBind: Fairness Enhanced Late Binding Task Scheduling in Mobile Crowdsensing
复制标题
DOI：
10.5555/3400306.3400314
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Heng Zhang-;Michael A. Roth;R. Panta;He Wang;S. Bagchi
中科院分区：
文献类型：
--
作者：
Heng Zhang-;Michael A. Roth;R. Panta;He Wang;S. Bagchi
移动攀岩（MC）是一种有效的方法，可以从传统上收集大量移动设备的传感数据。在这项工作中，我们讨论了第三个因素，即安排公平，这与其他两个因素相关，并对MC的成功产生了重大影响。 - 构成众包任务的特征，除了结合基于轨迹的移动性预测模型以安排任务。堆栈MCS系统包括调度服务器和一个Android客户端，我们通过对我们的大学城的50个人进行了一个月的批准，并使用90k用户的Gowalla数据集进行了模拟。事实证明，与先前的作品相比（周期性的感官，PC，有感觉AID和CROW-DRECRUITER），COWD-B IND在大量人群中具有有效性，结果表明C ROWD-B IND取得了最高的计划公平性，可改善平均每个evice evice。能源效率从18.3％到91.4％，并将任务覆盖范围从9.7％提高到52.1％。
Mobile crowdsensing (MCS) is an efficient method to collect sensing data from a large number of mobile devices. Traditionally, low task coverage and high energy consumption on mobile devices are two of the main challenges in MCS and they are extensively studied in the literature. In this work, we discuss a third factor, scheduling fairness, which is correlated with the other two factors and has a significant impact on the success of MCS. We propose a new framework, called C ROWD B IND , that takes advantage of the late-binding characteristic of crowdsensing tasks in addition to incorporating a trajectory-based mobility prediction model to schedule tasks. We conducted a survey with 96 participants to learn about how users react to varying levels of fairness in MCS applications. We designed and implemented a full-stack MCS system including a scheduling server and an Android client. We evaluate our system by conducting an IRB approved user study of 50 people in our college town for one month as well as running a simulation using Gowalla dataset of 90K users. C ROWD B IND is proved to be effective in a large population and the results show that C ROWD - B IND achieves the highest scheduling fairness compared to prior works (Periodic sensing, PCS, Sense-Aid, and Crow-dRecruiter), improves the average per-device energy effi-ciency from 18.3% to 91.4%, and improves the task coverage from 9.7% to 52.1%.