2nd International ICST Conference on Autonomic Computing and Communication Systems

Research Article

Dynamic QoS adaptation of inter-dependent task sets in cooperative embedded systems

Download98 downloads
  • @INPROCEEDINGS{10.4108/ICST.AUTONOMICS2008.4488,
        author={Lu\^{\i}s  Nogueira and Lu\^{\i}s Miguel  Pinho},
        title={Dynamic QoS adaptation of inter-dependent task sets in cooperative embedded systems},
        proceedings={2nd International ICST Conference on Autonomic Computing and Communication Systems},
        publisher={ICST},
        proceedings_a={AUTONOMICS},
        year={2011},
        month={12},
        keywords={Open real-time systems Anytime algorithms QoS optimisation and adaptation Service stability},
        doi={10.4108/ICST.AUTONOMICS2008.4488}
    }
    
  • Luís Nogueira
    Luís Miguel Pinho
    Year: 2011
    Dynamic QoS adaptation of inter-dependent task sets in cooperative embedded systems
    AUTONOMICS
    ICST
    DOI: 10.4108/ICST.AUTONOMICS2008.4488
Luís Nogueira1,*, Luís Miguel Pinho1,*
  • 1: IPP Hurray Research Group, School of Engineering, Polytechnic Institute of Porto, Portugal.
*Contact email: luis@dei.isep.ipp.pt, lpinho@dei.isep.ipp.pt

Abstract

Due to the growing complexity and dynamism of many embedded application domains (including consumer electronics, robotics, automotive and telecommunications), it is increasingly difficult to react to load variations and adapt the system's performance in a controlled fashion within an useful and bounded time. This is particularly noticeable when intending to benefit from the full potential of an open distributed cooperating environment, where service characteristics are not known beforehand and tasks may exhibit unrestricted QoS inter-dependencies.

This paper proposes a novel anytime adaptive QoS control policy in which the online search for the best set of QoS levels is combined with each user's personal preferences on their services' adaptation behaviour. Extensive simulations demonstrate that the proposed anytime algorithms are able to quickly find a good initial solution and effectively optimise the rate at which the quality of the current solution improves as the algorithms are given more time to run, with a minimum overhead when compared against their traditional versions.