Concepts for Self-Adaptive and Self-Healing Networked Embedded Systems

Networked embedded systems which operate in unattended areas with rare maintenance often make use of redundant resources for guaranteeing reliable service. In this paper, we will present novel concepts for dynamically partitioning and assigning functionality to software as well as hardware reconfigurable resources in a network. As a result, self-adaptive and self-healing systems emerge with a good tradeoff between redundancy and reliability. The proposed concepts are embedded in a three step approach, which 1.) reestablishes the functionality after a resource defect, 2.) optimizes the binding of the running tasks and 3.) creates new replicas of the tasks in the network. In this contribution, we will give an overview over all three parts, but focus on the second step. For this second step, called dynamic hardware/software partitioning, we will present algorithms, theoretical optimality bounds for workload distributions as well as experimental results.

[1]  Helge Parzyjegla,et al.  Self-organizing and Self-stabilizing Role Assignment in Sensor/Actuator Networks , 2006, OTM Conferences.

[2]  Shuvra S. Bhattacharyya,et al.  CHARMED: a multi-objective co-synthesis framework for multi-mode embedded systems , 2004 .

[3]  Frank Vahid,et al.  Dynamic hardware/software partitioning: a first approach , 2003, Proceedings 2003. Design Automation Conference (IEEE Cat. No.03CH37451).

[4]  George Cybenko,et al.  Dynamic Load Balancing for Distributed Memory Multiprocessors , 1989, J. Parallel Distributed Comput..

[5]  Marco Laumanns,et al.  Combining Convergence and Diversity in Evolutionary Multiobjective Optimization , 2002, Evolutionary Computation.

[6]  P. K. Lala.  Self-Checking and Fault-Tolerant Digital Design , 1995 .

[7]  John A. Stankovic,et al.  Adding Robustness in Dynamic Preemptive Scheduling , 1995, Responsive Computer Systems.

[8]  Shlomi Dolev,et al.  Self Stabilization , 2004, J. Aerosp. Comput. Inf. Commun..

[9]  Yuval Rabani,et al.  Local divergence of Markov chains and the analysis of iterative load-balancing schemes , 1998, Proceedings 39th Annual Symposium on Foundations of Computer Science (Cat. No.98CB36280).

[10]  Robert Elsässer,et al.  Optimal and Alternating-Direction Load Balancing Schemes , 1999, Euro-Par.

[11]  Petru Eles,et al.  Design optimization of time- and cost-constrained fault-tolerant distributed embedded systems , 2005, Design, Automation and Test in Europe.

[12]  Roger Wattenhofer,et al.  Facility location: distributed approximation , 2005, PODC '05.

[13]  Fred B. Schneider,et al.  The primary-backup approach , 1993 .

[14]  Edsger W. Dijkstra,et al.  Self-stabilizing systems in spite of distributed control , 1974, CACM.

[15]  Juan Carlos López,et al.  On the hardware-software partitioning problem: System modeling and partitioning techniques , 2003, TODE.

[16]  Frank Vahid,et al.  A configurable logic architecture for dynamic hardware/software partitioning , 2004, Proceedings Design, Automation and Test in Europe Conference and Exhibition.