Power management in the EPOS system

Power management strategies for embedded systems typically rely on static, application driven deactivation of components (e.g. sleep, suspend), or on dynamic voltage and frequency scaling. However, the design and implementation of these strategies in embedded operating system often fail to deal with real-time and quality-of-service (QoS) requirements. The EPOS system implements an infra-structure that supports both static (application-driven) and dynamic (system-driven) power management. In this work, this infrastructure is used to explore energy as a parameter for QoS in embedded systems, with the goal of guaranteeing energy consumption metrics, while preserving the deadlines of essential (hard real-time) tasks. Given a set of real-time tasks and their associated energy consumption, we provide equations to check schedulability in project-time. At runtime, a preemptive scheduler for imprecise tasks prevents the execution of optional subtasks whenever there is the possibility of deadline loss or depletion of the energy source. We show that this mechanism is effective in controlling energy consumption and ensuring "best-effort" computation without deadline loss.

[1]  J. Flinn,et al.  Energy-aware adaptation for mobile applications , 1999, SOSP.

[2]  Antônio Augusto Fröhlich,et al.  A Hierarchical Approach for Power Management on Mobile Embedded Systems , 2006, DIPES.

[3]  Linwei Niu,et al.  A hybrid static/dynamic DVS scheduling for real-time systems with (m, k)-guarantee , 2005, 26th IEEE International Real-Time Systems Symposium (RTSS'05).

[4]  Antônio Augusto Fröhlich,et al.  Configurable Medium Access Control for Wireless Sensor Networks , 2007, IESS.

[5]  Antônio Augusto Fröhlich,et al.  Application oriented operating systems , 2001 .

[6]  Klara Nahrstedt,et al.  Energy-efficient soft real-time CPU scheduling for mobile multimedia systems , 2003, SOSP '03.

[7]  Cristina V. Lopes,et al.  Aspect-oriented programming , 1999, ECOOP Workshops.

[8]  Enrico Macii,et al.  Dynamic power management of electronic systems , 2001 .

[9]  Riccardo Bettati,et al.  Imprecise computations , 1994, Proc. IEEE.

[10]  Yukikazu Nakamoto,et al.  Power-Aware Resource Allocation with Fair QoS Guarantee , 2006, 12th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA'06).

[11]  Antônio Augusto Fröhlich,et al.  A power manager for deeply embedded systems , 2007, 2007 IEEE Conference on Emerging Technologies and Factory Automation (EFTA 2007).

[12]  Mike Horton,et al.  The platforms enabling wireless sensor networks , 2004, CACM.

[13]  Amin Vahdat,et al.  ECOSystem: managing energy as a first class operating system resource , 2002, ASPLOS X.

[14]  Chung Laung Liu,et al.  Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment , 1989, JACM.

[15]  Cristina V. Lopes,et al.  Aspect-oriented programming , 1999, ECOOP Workshops.

[16]  Giuseppe Lipari,et al.  Using resource reservation techniques for power-aware scheduling , 2004, EMSOFT '04.

[17]  David E. Culler,et al.  System architecture directions for networked sensors , 2000, SIGP.

[18]  Frank Bellosa,et al.  The benefits of event: driven energy accounting in power-sensitive systems , 2000, ACM SIGOPS European Workshop.

[19]  Antônio Augusto Fröhlich,et al.  Using Imprecise Computation Techniques for Power Management in Real-Time Embedded Systems , 2008, DIPES.

[20]  Antônio Augusto Fröhlich,et al.  Operating System Support for Data Acquisition in Sensor Networks , 2006, 2006 IEEE Conference on Emerging Technologies and Factory Automation.

[21]  Antônio Augusto Fröhlich,et al.  Operating Systems Portability: 8 bits and beyond , 2006, 2006 IEEE Conference on Emerging Technologies and Factory Automation.