Artificial Intelligence-Based Online Control Scheme for the Regulations of Interconnected Thermal Power Systems

In today’s constantly advancing economy, fast and efficient load frequency control (LFC) schemes are imperative for stable power systems operation, whether conventional or new. Despite recent advances in this domain, professional engineers, to this day, face significant obstacles in dealing with parametric uncertainty and the rejection of external disturbances. To ensure high-quality, resilient, and consistent electrical power, the developed controllers must operate efficiently, i.e., counteract frequency and tie-line power deviations. In light of this, the current study presents a novel strategy employing several machine learning algorithms to remedy the LFC dilemma, estimating the optimal controller gain values in a real-time environment. A comprehensive case study incorporating random load perturbations exemplified the trained controllers’ accuracy, robustness, and adaptability. The proposed online controllers, integrated into emerging power systems with several adjoining regions, renewable sources, and nonlinearities, outperform benchmark procedures. A rank-based statistical analysis implementing the Friedman test reveals Random Forest to be the most effective of the studied algorithms in terms of providing the lowest integral-criteria error values while preserving the minimal peak overshoot, undershoot, and settling duration. This paper demonstrates the significant potential of the suggested framework in addressing the LFC predicament in relevant sectors.