Daily Power Generation Forecasting Method for a Group of Small Hydropower Stations Considering the Spatial and Temporal Distribution of Precipitation—South China Case Study

Abstract

This paper proposes a multimodal deep learning method for forecasting the daily power generation of small hydropower stations that considers the temporal and spatial distribution of precipitation, which compensates for the shortcomings of traditional forecasting methods that do not consider differences in the spatial distribution of precipitation. First, the actual precipitation values measured by ground weather stations and the spatial distribution of precipitation observed by meteorological satellite remote sensing are used to complete the missing precipitation data through linear interpolation, and the gridded precipitation data covering a group of small hydropower stations are constructed. Then, considering the time lag between changes in the daily power generation of the group of small hydropower stations and precipitation, the partial mutual information method is used to estimate the “time difference” between the two, and combined with the precipitation grid data, a data set of the temporal and spatial distribution of precipitation is generated. Finally, using only the temporal and spatial distribution of precipitation and historical power generation data, a multimodal deep learning network based on a convolutional neural network (CNN) and multilayer perceptron (MLP) is constructed, and a highly accurate prediction model for the daily power generation of small hydropower stations is obtained. Taking the real power generation data of a group of small hydropower stations in southern China as an example, after considering the temporal and spatial distribution of precipitation, the prediction accuracy of the proposed method is as high as 93%, which is approximately 5.8% higher than before considering the temporal and spatial distribution of precipitation. In addition, compared with mainstream methods such as support vector regression (SVR) and the long–short-term memory network (LSTM) (the average accuracy is about 87%), and the average accuracy improvement of the proposed method is approximately 6%.

Multistep Prediction of Multiple Small Hydropower Stations’ Total Power in a Watershed within a Day Considering the Distributed Discharge TCN-LSTM Model

“…Through meteorological and underlying surfaces, such as distributed rainfall intensity as sample inputs and the power generated by small hydropower stations as label outputs, the distributed deep learning model [4] simulates three non-linear processes, namely, runoff generation, runoff concentration, and power generation. In this type of hydrological model, the distributed deep learning model combined with LSTM [5][6][7][8][9] and GRU [10] is superior to other distributed deep learning models.…”

Multi-Horizon Wind Power Forecasting Using Multi-Modal Spatio-Temporal Neural Networks

“…Boussioux et al [8] introduce an ML framework for tropical cyclone intensity and track forecasting, and show that, when combining historical storm data, reanalysis maps and historical operational forecasts, prediction errors comparable to current operational forecast models can be achieved while computing in seconds. Yang et al [9] propose a multi-modal deep learning method for forecasting the daily power generation of small hydropower stations. In this work, the authors combine daily power generation and precipitation data, together with the spatial distribution of precipitation observed by meteorological satellite remote sensing, and conclude that a multi-modal neural network can effectively improve the accuracy of forecasts.…”

A Weak-Coupling Flow-Power Forecasting Method for Small Hydropower Station Group

“…In terms of modeling the power of SHSG, Yang et al [7] considered the temporal and spatial distributions of precipitation variables and introduced a multimodal deep learning method to predict the power generation of SHSG with good results. In another study [8], the power trend of SHSG was used as a feature to train the extreme learning machine, which improved the prediction accuracy to some extent.…”