New Pack Oriented Solutions for Energy-Aware Feasible Adaptive Real-Time Systems
Abstract
This paper addresses the management of tasks execution for real-time reconfigurable systems powered by battery. In this context, one of major problem concerns the management of battery life between two different recharges. For this type of systems, a reconfiguration scenario means the addition, removal or update of tasks in order to manage the whole system at the occurrence of hardware/software faults, or also to improve its performance at run-time. When such a scenario is applied, the system risks a fatal increase in energy consumption, a violation of real time constraints or a memory saturation. To prevent this type of problems during the execution, a new scheduling strategy is necessary. Our proposal is based on the definition of packs of tasks and the management of different parameters of these packs. For each reconfiguration scenario, modifications will be performed on packs/tasks parameters in order to respect the memory, real-time and energy constraints.