STL-decomposition ensemble deep learning models for daily reservoir inflow forecast for hydroelectricity production

SMGformer: integrating STL and multi-head self-attention in deep learning model for multi-step runoff forecasting

Accurate runoff forecasting is of great significance for water resource allocation flood control and disaster reduction. However, due to the inherent strong randomness of runoff sequences, this task faces significant challenges. To address this challenge, this study proposes a new SMGformer runoff forecast model. The model integrates Seasonal and Trend decomposition using Loess (STL), Informer's Encoder layer, Bidirectional Gated Recurrent Unit (BiGRU), and Multi-head self-attention (MHSA). Firstly, in response to the nonlinear and non-stationary characteristics of the runoff sequence, the STL decomposition is used to extract the runoff sequence's trend, period, and residual terms, and a multi-feature set based on 'sequence-sequence' is constructed as the input of the model, providing a foundation for subsequent models to capture the evolution of runoff. The key features of the input set are then captured using the Informer's Encoder layer. Next, the BiGRU layer is used to learn the temporal information of these features. To further optimize the output of the BiGRU layer, the MHSA mechanism is introduced to emphasize the impact of important information. Finally, accurate runoff forecasting is achieved by transforming the output of the MHSA layer through the Fully connected layer. To verify the effectiveness of the proposed model, monthly runoff data from two hydrological stations in China are selected, and eight models are constructed to compare the performance of the proposed model. The results show that compared with the Informer model, the 1th step MAE of the SMGformer model decreases by 42.2% and 36.6%, respectively; RMSE decreases by 37.9% and 43.6% respectively; NSE increases from 0.936 to 0.975 and from 0.487 to 0.837, respectively. In addition, the KGE of the SMGformer model at the 3th step are 0.960 and 0.805, both of which can maintain above 0.8. Therefore, the model can accurately capture key information in the monthly runoff sequence and extend the effective forecast period of the model.

A new strategy for groundwater level prediction using a hybrid deep learning model under Ecological Water Replenishment

Accurate prediction of the groundwater level (GWL) is crucial for sustainable groundwater resource management. Ecological water replenishment (EWR) involves artificially diverting water to replenish the ecological flow and water resources of both surface water and groundwater within the basin. However, fluctuations in GWLs during the EWR process exhibit high nonlinearity and complexity in their time series, making it challenging for single data-driven models to predict the trend of groundwater level changes under the backdrop of EWR. This study introduced a new GWL prediction strategy based on a hybrid deep learning model, STL-IWOA-GRU. It integrated the LOESS-based seasonal trend decomposition algorithm (STL), improved whale optimization algorithm (IWOA), and Gated recurrent unit (GRU). The aim was to accurately predict GWLs in the context of EWR. This study gathered GWL, precipitation, and surface runoff data from 21 monitoring wells in the Yongding River Basin (Beijing Section) over a period of 731 days. The research results demonstrate that the improvement strategy implemented for the IWOA enhances the convergence speed and global search capabilities of the algorithm. In the case analysis, evaluation metrics including the root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and Nash-Sutcliffe efficiency (NSE) were employed. STL-IWOA-GRU exhibited commendable performance, with MAE achieving the best result, averaging at 0.266. When compared to other models such as Variance Mode Decomposition-Gated Recurrent Unit (VMD-GRU), Ant Lion Optimizer-Support Vector Machine (ALO-SVM), STL-Particle Swarm Optimization-GRU (STL-PSO-GRU), and STL-Sine Cosine Algorithm-GRU (STL-SCA-GRU), MAE was reduced by 18%, 26%, 11%, and 29%, respectively. This indicates that the model proposed in this study exhibited high prediction accuracy and robust versatility, making it a potent strategic choice for forecasting GWL changes in the context of EWR.

Group Method of Data Handling Using Christiano-Fitzgerald Random Walk Filter for Insulator Fault Prediction

Disruptive failures threaten the reliability of electric supply in power branches, often indicated by the rise of leakage current in distribution insulators. This paper presents a novel, hybrid method for fault prediction based on the time series of the leakage current of contaminated insulators. In a controlled high-voltage laboratory simulation, 15 kV-class insulators from an electrical power distribution network were exposed to increasing contamination in a salt chamber. The leakage current was recorded over 28 h of effective exposure, culminating in a flashover in all considered insulators. This flashover event served as the prediction mark that this paper proposes to evaluate. The proposed method applies the Christiano-Fitzgerald random walk (CFRW) filter for trend decomposition and the group data-handling (GMDH) method for time series prediction. The CFRW filter, with its versatility, proved to be more effective than the seasonal decomposition using moving averages in reducing non-linearities. The CFRW-GMDH method, with a root-mean-squared error of 3.44×10-12, outperformed both the standard GMDH and long short-term memory models in fault prediction. This superior performance suggested that the CFRW-GMDH method is a promising tool for predicting faults in power grid insulators based on leakage current data. This approach can provide power utilities with a reliable tool for monitoring insulator health and predicting failures, thereby enhancing the reliability of the power supply.