Large Scale Systems and Fuzzy Cognitive Maps: A critical overview of challenges and research opportunities

Large scale systems (LSS) have been traditionally characterized by a large number of variables, nonlinearities and uncertainties. Their decomposition into smaller, more manageable subsystems, possibly organized in a hierarchical structure, has been associated with intense and time – critical information exchange and with the need for efficient and coordination mechanisms. A critical overview of the different theories and algorithms for LSS is provided. The issue of system complexity has become transparent. As the complexity of such systems increase and the presence of uncertainties play a role on the performance of LSS and HMS, new system theoretic methods become more crucial and are urgently needed. Intelligent Systems (IS) and Fuzzy Cognitive Maps (FCM) theories are such new theoretic approaches in modeling Large Scale Dynamic Complex Systems (LSDCS). An FCM is based on fuzzy logic and Neural Networks. FCM integrates the accumulated experience and knowledge on the operation of the system, as a result of the methods by which it is constructed. The new theories of FCMs are reviewed and used to model LSS and Dynamical Hierarchical Control Systems. A number of applications in using FCM to model complex systems from industrial processes economics, energy, environment, health international relations and political developments are mentioned. New challenges and research opportunities are presented and discussed.