A power regulation strategy for heat pipe cooled reactors based on deep learning and hybrid data-driven optimization algorithm

Abstract

Heat pipe cooled reactors are ideal for use in remote or isolated locations as dependable, small-scale power sources, thanks to their excellent design characteristics. To tackle real-time changes in power demand within a dynamic environment, this research proposes a decision-making strategy for regulating the power of heat pipe cooled reactors. The strategy is founded on a hybrid data-driven optimization algorithm and deep learning, enabling the attainment of safe and efficient control of heat pipe cooled reactors under specified power requirements. Initially, a power forecast model founded on artificial neural networks for heat pipe cooled reactors is established. Then, an appraisal standard for power regulation arrangements, combining reactor safety and operational effectiveness, is developed based on the utility theory. Finally, this study introduces a hybrid data-driven optimization algorithm that efficiently identifies the power regulation scheme with the greatest utility for given power demands. The proposed technique's effectiveness was demonstrated by selecting the power regulation process of the MegaPower heat pipe cooled reactor as an example. The results indicate that the strategy can make steady, accurate, and near-optimal power regulation decisions for any power demand within 20 s.