مشخصات پژوهش

صفحه نخست /AI-driven forecasting for ...
عنوان AI-driven forecasting for battery energy management in digital twin-integrated microgrids using machine learning techniques
نوع پژوهش مقاله چاپ‌شده
کلیدواژه‌ها Keywords: Battery energy management Deep neural networks (DNN) Digital twin technology (DTT) Reinforcement learning (RL) Renewable energy forecastin
چکیده The variability of renewable energy sources (RES) presents a challenge concerning the stability and operational efficiency of microgrids. This study suggests a Digital Twin-based framework encompassing deep learning and reinforcement learning (RL) techniques to improve the overall energy forecasting potential and optimization of battery management. Among the machine learning models tested, Deep Neural Network (DNN) turned out to be the most accurate and computationally efficient. When combined with RL, this allows the charging-discharging operation of batteries to be dynamically managed, thus maximizing energy efficiency and battery life. Through the implementation of this framework, microgrids will receive more reliable support via sustainable energy utilization and scalable support for intelligent energy management.
پژوهشگران عبدالرضا مقدسی (نفر دوم)، سید سجاد سجادی (نفر اول)، هما رشیدی زاده کرمانی (نفر سوم)، رضا کیا (نفر چهارم)، میادرضا شفی خواه (نفر پنجم)