Hypertuned temporal fusion transformer for multi-horizon time series forecasting of dam level in hydroelectric power plants

Abstract

This paper addresses the challenge of predicting dam level rise in hydroelectric power plants during floods and proposes a solution using an automatic hyperparameters tuning temporal fusion transformer (AutoTFT) model. Hydroelectric power plants play a critical role in long-term energy planning, and accurate prediction of dam level rise is crucial for maintaining operational safety and optimizing energy generation. The AutoTFT model is applied to analyze time series data representing the water storage capacity of a hydroelectric power plant, providing valuable insights for decision-making in emergency situations. The results demonstrate that the AutoTFT model surpasses other deep learning approaches, achieving high accuracy in predicting dam level rise across different prediction horizons. Having a root mean square error (RMSE) of 2.78×10−3 for short-term forecasting and 1.72 considering median-term forecasting, the AutoTFT shows to be promising for time series prediction presented in this paper. The AutoTFT had lower RMSE than the adaptive neuro-fuzzy inference system, long short-term memory, bootstrap aggregation (bagged), sequential learning (boosted), and stacked generalization ensemble learning approaches. The findings underscore the potential of the AutoTFT model for improving operational efficiency, ensuring safety, and optimizing energy generation in hydroelectric power plants during flood events.