Short term output prediction method of runoff type medium and small hydropower stations

Abstract

Under the background of “dual carbon”, the accurate output prediction and dispatching of a large number of small and medium-sized runoff hydropower stations is an important way for low-carbon operation of the power system. However, compared with large hydropower stations, small and medium-sized runoff hydropower stations have a huge gap in historical hydrological data, output data, output prediction methods and other aspects, and their output is highly random and volatile, which is difficult to predict. By studying the similarity of large, medium and small hydropower stations in hydrology and climate in the same natural basin, a short-term output prediction method of runoff type small and medium-sized hydropower stations based on the correlation analysis of large hydropower stations is proposed. The historical data and Horton strahler river classification method are used to extract the interval flow, output and outgoing flow of large hydropower stations, and the Pearson correlation coefficient is used to determine the interval flow of large hydropower stations as the correlation factor. The quantile regression method is used to establish the output prediction model of the interrelation between the interval flow of small and medium-sized run of river hydropower stations and large hydropower stations. The accuracy and reliability of the prediction results are evaluated by using the certainty coefficient, interval coverage and dispersion. The model is used to predict the output of small and medium-sized hydropower stations in a natural basin in Hunan Province. The results show that the proposed model has higher accuracy and reliability for short-term output prediction of small and medium-sized hydropower stations compared with the original output prediction value of hydropower stations.