Abstract
Developing an accurate and timely inflow forecast model continues to be an integral part of modern reservoir operation and has been greatly promoted by the combination of data preprocessing and data-driven techniques. This paper integrates variational mode decomposition (VMD) and long short-term memory (LSTM) into a hybrid model named A-VMD-S-LSTM. After dividing data for calibration and validation periods, A-VMD-S-LSTM decomposes the calibration inflow time series into subseries and cast them into a single LSTM forecast model to output final inflow predictands directly. When new inflow data are appended to the calibration time series, the VMD and LSTM models will be updated to adapt to all available inflow information to avoid transmitting future inflow information. The parameter settings of VMD and LSTM and the meaningful lags corresponding to each subseries are well identified by grid search and partial autocorrelation function (PACF), respectively. Finally, the proposed model is applied to the 1-, 3- 5-, and 7-day ahead inflow forecasts of the Three Gorges Reservoir (TGR) along with five competitive models. Results show that A-VMD-S-LSTM achieves the best forecast accuracy and fourth computational efficiency among the six candidates, demonstrating its best comprehensive forecast performance. Furthermore, using two or three LSTM layers in A-VMD-S-LSTM is redundant since the change in forecast accuracy is negligible and the increase of run time is remarkable. Therefore, a practical reservoir inflow forecast model with high forecast accuracy and relatively low computational cost is provided in this paper.
Highlights
Providing accurate and timely inflow forecasts can allow one to best use reservoirs [1]
Motived by the above analysis, this paper develops an adaptive reservoir inflow forecast framework in which only the calibration data is decomposed into subsignals, and all of them are input to one forecast model to directly output final inflow predictands
Developing an accurate and timely inflow forecast model is important for reservoir operation
Summary
Providing accurate and timely inflow forecasts can allow one to best use reservoirs [1]. Previous forecasting models are split into two groups (irrespective of hybrid models), i.e., physical-based and data-driven models, according to the way they assess the formation of inflow (runoff) [7], [8] The former always focuses on multiple interactive physical processes among meteorology, geography, and hydrology and formulates these processes with numerous equations and parameters. Relying solely on the input and output time series provided in the Catchment Attributes and Meteorology for Largesample Studies (CAMELS) data set [10], LSTM can achieve competitive discharge predictions in comparison with the optimized Snow-17 + Sacramento soil moisture accounting model (via the shuffled complex evolution method [11]), which agrees with a common conclusion inferred from previous studies [12]-[14]; i.e., data-driven forecast models are simple but robust with low data barriers, and they deserve further research, application, and promotion.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
