Key points are not available for this paper at this time.
This paper presents a comprehensive survey on the use of artificial neural networks (ANN) for enhancing DC-DC converters in renewable energy systems, focusing on equal current sharing and voltage stability amidst the growing scarcity of electricity.The survey methodically examines literature on ANN integration with DC-DC converters, selecting studies based on their relevance to managing renewable energy efficiently, improving power distribution, and the effectiveness of ANN in addressing these challenges.The research identifies several gaps, including optimal power distribution, predictive controller limitations, and the instability of proportional-integral (PI) controls due to online training algorithm adjustments.To bridge these gaps, an innovative ANN-based control method for DC-DC converters is proposed, aimed at bolstering power generation quality, enabling flexible power distribution across microgrids, and enhancing the stability, reliability, and cost-effectiveness of renewable energy sources.Moreover, the paper discusses the correction of offline training problems, feedback error signal corrections, and integral error signals of DC-DC converters, offering new insights and solutions to overcome these technical barriers.This study underscores the converter's size and integration significance, juxtaposing traditional methods with ANN-based controls to highlight the latter's performance and efficiency advantages.Through a detailed review and proposed solutions to significant challenges in renewable energy management, this work contributes to the field's advancement by enhancing the efficiency and reliability of power systems through cutting-edge ANN-based control methods.
Shankara et al. (Sun,) studied this question.