Computer Science and Engineering, Department of
Date of this Version
2004
Abstract
In embedded real-time systems, Dynamic Power Management (DPM) techniques have traditionally focused on reducing the dynamic power dissipation that occurs when a CMOS gate switches in a processor. Less attention has been given to processor leakage power or power consumed by I/O devices and other subsystems. I/O-based DPM techniques, however, have been extensively researched in non-real-time systems. These techniques focus on switching I/O devices to low power states based on various policies and are not applicable to real-time environments because of the non-deterministic nature of the policies. The challenge in conserving energy in embedded real-time systems is thus to reduce power consumption while preserving temporal correctness. To address this problem, we introduce three scheduling algorithms of increasing complexity: Energy-Aware EDF (EA-EDF), Enhanced Energy-Aware EDF (EEA-EDF) and Slack Utilization for Reduced Energy (SURE). The first two algorithms are relatively simple extensions to the Earliest Deadline First (EDF) scheduling algorithm that enable processor, I/O device, and subsystem energy conservation. The SURE algorithm utilizes slack to create a non-work-conserving approach to reducing power consumption. An evaluation of the three approaches shows that all three yield significant energy savings with respect to no DPM technique. The actual savings depends on the task set, shared devices, and the power requirements of the devices. When the cost of switching power states is low, the EA-EDF and EEA-EDF algorithms provide remarkable power savings considering their simplicity. In general, however, the higher the energy cost to switch power states, the more benefit SURE provides.
Comments
University of Nebraska-Lincoln, Computer Science and Engineering
Technical Report # TR-UNL-CSE-2004-0009