Predicting Device Availability in Mobile Crowd Computing using ConvLSTM

Abstract

The QoS of mobile crowd computing (MCC), in which the public’s smart mobile devices (SMDs) are used for job execution, hampers due to users’ mobility. In this paper, we propose a model to predict SMDs’ availability in a campus-based MCC, where, generally, a set of users are available for a certain period regularly. Predicting the user’s availability before the job submission would help avoid unnecessary job offloading or job loss due to the designated SMD’s early departure. We recorded the real mobility traces of the users connected to a Wi-Fi access point of our research lab. We applied ConvLSTM on the mobility dataset to predict the availability of the SMD. A job submission scenario is simulated. The extensive evaluation of our approach shows that our method has an average accuracy of 78%, making the job submission more reliable.