As the energy landscape changes towards renewable energy sources and smart grid technologies, accurate prediction of peak load duration curve (PLDC) becomes crucial to ensure power system stability. The background to this research is the urgent need for more effective prediction methods to manage increasingly complex energy loads. This research presents a leading-edge approach to PLDC prediction, leveraging Deep Learning, a subsection of artificial intelligence. Focusing on data from the Taiwan State Electric Company, this study uses a Long Short-Term Memory (LSTM) network to capture complex load patterns. The LSTM model, consisting of two layers and trained on 2019-2020 data, demonstrated excellent accuracy with a Mean Absolute Percentage Error (MAPE) as low as 0.03%. These results confirm the potential of Deep Learning to revolutionize PLDC predictions in complex energy systems. These research recommendations involve exploring diverse datasets, integrating real-time data streams, and conducting comparative analyses for more reliable prediction methodologies. The benefits of this research include providing relevant insights for sustainable energy resource management amidst a dynamic energy landscape.
Copyrights © 2024