Toward Approximating Job Completion Time in Vehicular Clouds

摘要: Motivated by the phenomenal success of conventional cloud computing, vehicular clouds (VCs) were introduced as a group vehicles whose corporate sensing, communication, and physical resources can be coordinated dynamically allocated to authorized users. Just in clouds, job completion time ranks high among fundamental quantitative performance figures merit. Recently, authors have analytically investigated effect redundancy-based assignment on VCs. However, these analytical expressions require full knowledge distribution functions various random variables contributing time. In practical context, data center manager does not know functions. Instead, using accumulated empirical data, they may able estimate first and, perhaps, second moments variables. Yet, getting handle expected is very important problem that must addressed. Consequently, it great theoretical interest relevance approximate expression With this mind, main contribution paper offer easy-to-compute approximations when estimates or two intervening are available. A comprehensive set simulations shown our close predictions.