Self-Organizing System for Management Decision-Making in Energy Systems

The paper investigates the development of a self-organizing control system for managing the operational modes of power system facilities, grounded in the application of intelligent technologies. The approach integrates advanced data analytics techniques and artificial intelligence algorithms to enhance system adaptability and efficiency. A hybrid machine learning methodology is proposed, combining classification and regression models for the analysis of the operational state of technological units. This enables more accurate forecasting and facilitates the optimal distribution of energy flows within the system. To address the challenges associated with forecasting and optimizing the operating regimes of energy facilities, the study advocates the use of big data analytics in conjunction with artificial intelligence techniques. In particular, the implementation of neuro-fuzzy systems is emphasized, allowing for greater flexibility in decision-making processes under conditions of uncertainty, incomplete information, and dynamic load variations. The proposed framework contributes to improving the resilience, energy efficiency, and overall reliability of modern energy systems.

Hali tarjima qilinmagan