Abstract By combining various renewable energy sources, new hybrid power generation technologies can significantly improve energy utilization efficiency and reduce environmental impact. However, due to the uncertainty and intermittent nature of this technology, signal optimization and control become particularly important. In this study, we use advanced techniques to enhance the performance of hybrid power generation systems. Our work involves utilizing deep learning to analyze and... By combining various renewable energy sources, new hybrid power generation technologies can significantly improve energy utilization efficiency and reduce environmental impact. However, due to the uncertainty and intermittent nature of this technology, signal optimization and control become particularly important. In this study, we use advanced techniques to enhance the performance of hybrid power generation systems. Our work involves utilizing deep learning to analyze and predict various factors, thereby finding the optimal operating mode. The conclusions of this work will have a positive impact on future energy management and dispatching. Additionally, the methods proposed in this article can provide valuable references for research in other related fields. Read More Read Less

Abstract This paper proposes a method for identifying partial discharge types based on multi fractaldetrended fluc- tuation analysis. This method transforms partial discharge signals through multi fractal transformation, extracts the fractal features of the signals, and combines with detrended fluctuation analysis to accurately identify partial discharge types. Advanced algorithms and techniques are used in this research to classify and analyze different types of partial discharges,... This paper proposes a method for identifying partial discharge types based on multi fractaldetrended fluc- tuation analysis. This method transforms partial discharge signals through multi fractal transformation, extracts the fractal features of the signals, and combines with detrended fluctuation analysis to accurately identify partial discharge types. Advanced algorithms and techniques are used in this research to classify and analyze different types of partial discharges, achieving significant results. Experimental results demonstrate that this method exhibits high accuracy and reliability in identifying partial discharge types, providing a new effective means for partial discharge monitoring and fault diagnosis. Read More Read Less