An Adaptive Neuro Fuzzy Based Intelligent Load Frequency Control in Diverse Hybrid Power Systems

The dynamic and ever-evolving landscape of modern power systems demands advanced control strategies to ensure reliable and stable operation. This paper presents an intelligent approach to Load Frequency Control (LFC) in hybrid power systems consisting of conventional reheat thermal power plants incorporating nuclear and Wind Energy as Renewable Energy Sources (RES), leveraging the capabilities of Adaptive Neuro Fuzzy Inference system (ANFIS) for optimization. The ANFIS training dataset, comprising ACE error, is obtained using a PID controller tuned by a Modified Coyote Optimization Algorithm (MCOA). The hybrid power system incorporates diverse energy sources, such as conventional generators and renewable resources, adding complexity to the control mechanism. The proposed strategy harnesses the learning and adaptive features of ANNs to optimize the LFC process, ensuring efficient power generation and load management. The neural network model undergoes training using historical data, allowing it to comprehend and adjust to the dynamic characteristics inherent in hybrid power systems. The research emphasizes the capability of ANNs to handle the non-linearities and uncertainties within these systems as it explores their integration into the control framework.