In this paper use of fuzzy, neural and neuro-fuzzy estimators are employed to predict the interaction signals among subsystems in a large-scale system (LSS) controlled by the model-based predictive control (MBPC) scheme. The spreading of the non-local information within the LSS is assumed to follow the m-step delay sharing information pattern. The MBPC scheme is used for the local control of each subsystem enhanced by the interaction signal's predictive model. The interaction trajectories are assumed to be non-linear functions of the states of the various subsystems. The paper includes a through performance analysis of fuzzy versus neural estimators. Two nontrivial examples are studied via simulation to test and verify the capabilities of the proposed "fuzzy, neural and neuro-fuzzy estimator-based" MBPC of LSS.
Large-scale-system, model-based predictive control, m-step delay sharing information pattern, interconnection signal adaptive fuzzy / neuro-fuzzy, neural estimator.
All articles published by Studies in Informatics and Control (SIC) are published in accordance with the terms and conditions of the Creative Commons Attribution License (CC BY-NC-SA 4.0).