Energy-Aware Scheduling for Weakly-Hard Real-Time System with I/O Device

In addition to processors, embedded systems also have some peripheral devices (such as: memory, flash memory, wireless interface). These devices will also consume energy. Dynamic power management (DPM) technology is often used to minimize the energy consumption of peripheral devices with the timeout mechanism in which the device is switched to the idle state for a specific time interval. Because the requirement of some systems is to support deterministic QoS for real-time systems, rather than 100% guarantees or the probabilistic QoS, the system must support the statistical and the lowest limit of QoS, such as (m, k) constraints. We proposed advanced search-tree-based energy-efficient algorithm to solve the scheduling problem of weakly-hard real-time system with an I/O device. An analytic study on the proposed algorithms is presented, and a series of simulation experiments are conducted to verify the analytic results and to show the capability of the proposed algorithm.