Compact Scheduling for Task Graph Oriented Mobile Crowdsourcing

Abstract

With the proliferation of increasingly powerful mobile devices and wireless networks, mobile crowdsourcing has emerged as a novel service paradigm. It enables crowd workers to take over outsourced location-dependent tasks, and has attracted much attention from both research communities and industries. In this paper, we consider a mobile crowdsourcing scenario, where a mobile crowdsourcing task is too complex (e.g., post-earthquake recovery, citywide package delivery) but can be divided into a number of easier subtasks, which have interdependency between them. Under this scenario, we investigate an important problem, namely task graph scheduling in mobile crowdsourcing (TGS-MC), which seeks to optimize a compact scheduling, such that the task completion time (i.e., makespan) and overall idle time are simultaneously minimized with the consideration of worker reliability. We analyze the complexity and NP-complete of the TGS-MC problem, and propose two heuristic approaches, including BFS-based dynamic priority scheduling BFSPriD algorithm, and an evolutionary multitasking-based EMTTSch algorithm, to solve our problem from local and global optimization perspective, respectively. We conduct extensive evaluation using two real-world data sets, and demonstrate superiority of our proposed approaches.

Shirui Pan

Professor and ARC Future Fellow

My research interests include data mining, machine learning, and graph analysis.