Automated Meta-Control for Adaptable Real-Time Software

摘要: The software meta-controller is an online agent responsible for dynamically adapting application‘s configuration, e.g. altering operational modes and migrating tasks, to best accommodate varying runtime circumstances. In distributed real-time applications such adaptations must be carried out in a manner which maintains the schedulability of all critical tasks while maximizing some notion system value other tasks. For large-scale applications, considering possible at task-level computationally intractable. This paper presents automated aggregate approach meta-control, appropriate systems. meta-control problem still NP-hard, but it has very practical approximate solutions. Introduced, here, are two very-effective approximation algorithms, QDP GG, with reasonable polynomial time complexity. Both algorithms also provide us upper bounds optimum values, useful deriving absolute, albeit somewhat pessimistic, measures actual performance. Extensive Monte Carlo analysis used illustrate that expected performance both generally suboptimal by no more than few percent. Our flexible model shown readily applied wide range time-sensitive applications.