Short-term dynamic interval prediction of photovoltaic power based on power ramp clustering

Photovoltaic systems, as a critical component of microgrids, require accurate power forecasting for the optimization of microgrid scheduling. To enhance data feature representation and capture the fluctuating patterns of photovoltaic power, an improved power ramp feature construction method is proposed for feature engineering and selection, thereby improving the quality of photovoltaic data. Furthermore, a photovoltaic power prediction model based on a convolutional attention long short-term memory hybrid framework is employed to enhance forecasting performance. Building upon this, a novel photovoltaic power dynamic interval prediction method based on power ramp clustering is proposed to address the issues of low prediction accuracy and excessively broad ranges in existing photovoltaic power interval prediction methods. First, an improved power ramp calculation formula is used to identify and statistically analyze the power ramp, clustering daily data into four weather categories—sunny, partly cloudy, cloudy, and rainy—thus enhancing the accuracy of similar day clustering. Next, the shape dynamic time warping algorithm is applied to select similar days for the target day, and the dynamic interval calculation is performed to determine the power range. Finally, experimental analysis is conducted using real photovoltaic output historical data from a region in Xinjiang, China. The results demonstrate that the proposed method improves prediction accuracy, effectively reduces the width of the predicted range, and more accurately captures the fluctuating trends of photovoltaic power.