101 / 2024-01-24 15:19:23

Reservoir operation simulation based on chaotic artificial electric field algorithm enhanced long short-term memory network

Reservoir operation,Long short-term memory network,Chaotic artificial electric field algorithm,Genetic algorithm,Flood season

Scientific reservoir operation simulation is of great significance to ensure efficient and stable operation of the reservoir. The long-short-term memory (LSTM) model is widely used because it can accurately reflect the time sequence characteristics of reservoir operation. The application effect of the model is closely related to the parameter settings. However, traditional empirical settings and gradient-based optimization methods tend to cause the model training results to fall into local optimality and fail to achieve the expected results. This study proposes an artificial electric field algorithm based on chaotic mapping (CAEFA) to be applied to the parameter training process of the LSTM model, and verifies its effectiveness in the simulation of Xiluodu reservoir operation. The results show that the proposed CAEFA algorithm has higher calculation accuracy than the classical genetic algorithm and the traditional artificial electric field algorithm (AEFA), and its advantages are more obvious during flood season with high flow. Compared with the general LSTM model, the model established in this study is more suitable for reservoir operation simulation.