An adaptive system-level diagnosis approach for hypercube multiprocessors

Author(s):  
C. Feng ◽  
L.N. Bhuyan ◽  
F. Lombardi
Author(s):  
Scott E. Page ◽  
Jon Zelner

This chapter advocates a complex adaptive system of systems approach to understanding population-level processes in population health. A complex adaptive system consists of diverse, interacting adaptive entities whose aggregated behaviors result in emergent, system-level patterns and functionalities. A complex adaptive system of systems consists of multiple, connected complex systems. The connections can be hierarchical, horizontal, or a mixture of the two. The authors provide basic definitions, describe common tools of analysis, and introduce illustrative cases. For example, increased obesity levels have no single cause, nor do they arise from a single system. Instead, they arise from the interactions of multiple systems that operate at various levels of scale. Genetics and epigenetics play roles, as do nutrition, general health, advertising, infrastructure, social norms, exercise levels, and, as recent evidence suggests, the ecology of colonies of gut bacteria. Each of these contributors can be modeled as a complex adaptive system and the whole as a system of systems. Similarly, population-level disease outbreaks can be decomposed into separate systems, each with unique dynamics.


1996 ◽  
Vol 45 (10) ◽  
pp. 1157-1170 ◽  
Author(s):  
Chao Feng ◽  
L.N. Bhuyan ◽  
F. Lombardi
Keyword(s):  

2006 ◽  
Vol 16 (01) ◽  
pp. 63-79 ◽  
Author(s):  
Mourad Elhadef ◽  
Kaouther Abrougui ◽  
Shantanu Das ◽  
Amiya Nayak

In this paper, we present a system-level fault identification algorithm, using a parallel genetic algorithm, for diagnosing faulty nodes in large heterogeneous systems. The algorithm is based on a probabilistic model where individual node fails with an a priori probability p. The assumptions concerning test outcomes are the same as in the PMC model, that is, fault-free testers always give correct test outcomes and faulty testers are totally unpredictable. The parallel diagnosis algorithm was implemented and simulated on randomly generated large systems. The proposed parallelization is intended to speed up the performance of the evolutionary diagnosis approach, hence reducing the computation time by evolving various sub-populations in parallel. Simulation results are provided showing that the parallel diagnosis did improve the efficiency of the evolutionary diagnosis approach, in that it allowed faster diagnosis of faulty situations, making it a viable alternative to existing techniques of diagnosis. Moreover, the evolutionary approach still provide good results even when extreme non-diagnosable faulty situations are considered.


Sign in / Sign up

Export Citation Format

Share Document