基于选择的移动群智感知反向拍卖激励机制

Selection based reverse auction incentive mechanism in mobile crowd sensing

由于移动群智感知中工人和平台的自私性,社会福利和数据质量往往难以达到平衡,损害了基于移动群智感知的服务可用性和准确性。为了解决这一问题,本文提出一种基于选择的反向拍卖激励机制,分别研究反向拍卖中以工人为中心的任务选择和以平台为中心的工人选择,在最大限度提高社会福利的同时优化数据质量。首先,根据工人和任务的位置等属性评估工人与任务之间的匹配度,提出基于动态规划的任务选择算法,在工人资源约束下为每个工人选择具有最佳回报的任务进行投标;其次,使用多臂赌博机建模反向拍卖赢家选择过程,并设计了一种基于置信度上界的赢家选择算法,以确定最佳中标工人集;最后,实验验证本文所提出的激励机制能够同时有效提升社会福利和数据质量。

Due to the selfishness of workers and platform in mobile crowd sensing(MCS),it is difficult to balance social welfare and data quality,which impairs the availability and accuracy of MCS-based services.To solve this problem,a selection based reverse auction incentive mechanism is proposed to optimize data quality while maximizing social welfare.First,the matching degree between workers and tasks is evaluated based on attributes such as the location of workers and tasks,and a task selection algorithm based on dynamic programming is proposed to select the tasks with best reward for each worker under the workers’resource constraint.Then,the winner selection process of the platform is modeled based on multi-armed bandits,and an upper confidence bound based winner selection algorithm is designed to determine the optimal set of winning workers.Finally,experiments verify that the proposed incentive mechanism can effectively balance social welfare and data quality.