Buffer Feedback Scheduling: Runtime Adaptation of Ubicomp Applications

  • Christian Decker
  • Michael Beigl
  • Till Riedel
  • Albert Krohn
  • Tobias Zimmer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4239)

Abstract

In this paper we propose an operating system design for Ubicomp applications that are implemented on embedded sensor platforms. The OS provides support for both periodic sensor sampling and sequential appliation logic. Core component is a lightweight real-time runtime system guaranteeing predictable real-time behavior of periodic sampling processes. The design utilizes a novel method, called buffer feedback scheduling (BFS), to adapt the system under unpredictable workload. Processes are automatically coordinated and expensive hardware accesses are reduced when the feedback indicates that the results do not contribute to the application. Real-time behavior is guaranteed throughout the entire runtime. Theoretical analysis and implementation in a Ubicomp application study on the Particle Computer sensor platform demonstrate a significant performance step-up when utilizing BFS.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Beigl, M., Gellersen, H.W., Schmidt, A.: Mediacups: experience with design and use of computer-augmented everyday artefacts. Computer Networks 35(4) (2001)Google Scholar
  2. 2.
    Decker, C., Beigl, M., Eames, A., Kubach, U.: Digiclip: Activating physical documents. In: 4th IEEE IWSAWC, pp. 388–393 (2004)Google Scholar
  3. 3.
    Decker, C., Beigl, M., Krohn, A., Robinson, P., Kubach, U.: eSeal – A System for Enhanced Electronic Assertion of Authenticity and Integrity. In: Ferscha, A., Mattern, F. (eds.) PERVASIVE 2004. LNCS, vol. 3001, pp. 254–268. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  4. 4.
    Zimmer, T., Beigl, M.: AwareOffice: Integrating Modular Context-Aware Applications. In: 6th IEEE IWSAWC (2006)Google Scholar
  5. 5.
    Jeffay, K., Stanat, D.F., Martel, C.U.: On non-preemptive scheduling of periodic and sporadic tasks. In: Proceedings of 12th IEEE RTSS 1991, pp. 129–139 (1991)Google Scholar
  6. 6.
    Decker, C., Krohn, A., Beigl, M., Zimmer, T.: The particle computer system. In: ACM/IEEE Information Processing in Sensor Networks (IPSN), pp. 443–448 (2005)Google Scholar
  7. 7.
    Fischer, M., Kroehl, M.: Remembrance camera. Term Thesis (2006)Google Scholar
  8. 8.
    Hill, J., Szewczyk, R., Woo, A., Hollar, S., Culler, D.E., Pister, K.S.J.: System architecture directions for networked sensors. In: ASPLOS (2000)Google Scholar
  9. 9.
    Han, C.C., Kumar, R., Shea, R., Kohler, E., Srivastava, M.: A dynamic operating system for sensor nodes. In: Proceedings of MobiSys 2005, pp. 163–176. ACM Press, New York (2005)CrossRefGoogle Scholar
  10. 10.
    Barry, R.: FreeRTOS - a free RTOS for small embedded real time systems (2006), http://www.freertos.org/
  11. 11.
    Shift-Right Technologies: eXtreme Minimal Kernel (xmk) - a free real time operating system for microcontrollers (2006), http://www.shift-right.com/xmk/
  12. 12.
    Stankovic, J.A., He, T., Abdelzaher, T., Marley, M., Tao, G., Son, S., Lu, C.: Feedback control scheduling in distributed real-time systems. In: Proceedings of RTSS 2001 (2001)Google Scholar
  13. 13.
    Buttazzo, G.C., Lipari, G., Abeni, L.: Elastic task model for adaptive rate control. In: Proceedings of IEEE RTSS 1998, Washington, DC, USA. IEEE Computer, Los Alamitos (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Christian Decker
    • 1
  • Michael Beigl
    • 2
  • Till Riedel
    • 1
  • Albert Krohn
    • 1
  • Tobias Zimmer
    • 1
  1. 1.Telecooperation Office (TecO)University of Karlsruhe 
  2. 2.Distributed and Ubiquitous Computing (DUS)University of Braunschweig 

Personalised recommendations