Abstract: "Vehicular cloud is a group of vehicles whose corporate computing, sensing, communication and physical resources can be coordinated and dynamically allocated to authorized users. One of the at- tributes that set vehicular clouds apart from conventional clouds is re- source volatility. As vehicles enter and leave the cloud, new compute resources become available while others depart, creating a volatile environment where the task of reasoning about fundamental performance metrics such as job completion time becomes very challenging. In general, predicting job completion time requires full knowledge of the prob- ability distributions of the intervening random variables. However, the datacenter manager does not know these distribution functions. Instead, using accumulated empirical data, she may be able to estimate the first moments of these random variables.In this work we offer approximations of job completion time in a dynamic vehicular cloud model involving vehicles on a highway where jobs can be downloaded under multiple stations."
Authors: Aida Ghazizadeh (Old Dominion University, USA); Puya Ghazizadeh (St. John's University, USA); Stephan Olariu (Old Dominion University, USA)
Email: aghaziza@cs.odu.edu, ghpuya@gmail.com, olariu@cs.odu.edu