Intelligent control of energy system operating modes based on neuro-analytical and neutrosophic models under conditions of uncertainty

This paper introduces a novel approach to intelligent control of Electric Power System (EPS) operating modes under uncertainty, integrating Smart Grid technologies, a Neuro-Analytical Network (NAN), and neutrosophic logic. A modified NAN architecture with an additional static layer is proposed, enabling higher accuracy and faster response in real-time energy flow management. To enhance resilience and adaptability in the presence of structural, parametric, and informational uncertainties, neutrosophic logic is applied to model contradictory and partially undefined input data. A hybrid learning methodology is developed, combining backpropagation with the least squares method to ensure efficient adaptation using both historical and real-time datasets. The proposed neuro-neutrosophic control system demonstrates the ability to mitigate disturbances, reduce energy losses by up to 1%, stabilize voltage, and minimize phase imbalances. A software platform has also been designed to implement the proposed algorithms, providing automated analysis, forecasting, and control of EPS operating modes under uncertainty. The system features a user-friendly interface and supports operator decision-making. The main contribution of this study lies in developing an integrated framework that combines neuro-analytical modeling, neutrosophic reasoning, and hybrid training techniques to improve the robustness, efficiency, and reliability of power system operation in uncertain environments.