Energy fluctuation pattern recognition coupled with decomposition-integration: A novel ocean tidal energy forecasting system

Abstract

Ocean tidal energy is a new energy source which is recognized and utilized earlier by human beings. For the complexity of tidal generation and the singleness of tidal prediction, this paper proposes a multi-factor forecasting system for ocean tidal energy based on energy fluctuation pattern recognition with confluent ReliefF-density-based spatial clustering of applications with noise (ReliefF-DBSCAN), improved symplectic geometric mode decomposition (ISGMD) and convolutional neural network−bidirectional long short-term memory (CNN-BiLSTM) with temporal pattern attention (TPA), named ReliefF-DBSCAN-ISGMD-TPA-CNN-BiLSTM. Precisely, ReliefF-DBSCAN can extract effective features and fluctuation patterns, and reduce the forecasting difficulty. ISGMD significantly improves the endpoint effect and false components of the decomposition results, and heightens the stability and correlation of each component. TPA-CNN-BiLSTM method have strong feature extraction ability, memory ability and recognition ability. In the evaluation stage, this study introduces some indicators such as root mean square error (RMSE) and Diebold Mariano (DM) test to evaluate the forecasting system comprehensively. To highlight the effect of the developed system, use actual data collected from Port SanLuis and Port Chicago as experimental data and compare with five contrastive models. The experimental result shows that the predicted value for the developed system is the closest to the real value, and the RMSE, mean absolute error (MAE) and goodness of fit (R2) of Port Chicago are 0.3152, 0.2900 and 0.9964, respectively, indicating that the prediction ability is better than all contrastive models. In addition, the result proves that the decomposition-integration system is beneficial to improve forecasting accuracy. This study can make a meaningful improvement and innovation for the forecasting of ocean tidal energy.