A Tidal Current Speed Forecasting Model based on Multiple Periodicity Learning

2024-10-13

arXiv.org

AI Summary

This paper addresses the challenge of modeling multi-periodic tidal current velocity patterns and the resulting low accuracy in short-term forecasting, which hinders grid integration of tidal energy. To this end, we propose a Wavelet-Enhanced Convolutional Network (WCN) that innovatively maps one-dimensional tidal sequences into two-dimensional tensors to jointly capture intra- and inter-cycle dynamic variations. The model integrates wavelet-based time-frequency analysis to extract localized periodic features and employs Tree-structured Parzen Estimator (TPE) for robust hyperparameter optimization. Evaluated on a 10-step rolling prediction task, WCN achieves up to 90.36% reduction in MAE and 97.56% reduction in MSE compared to baseline physical models and state-of-the-art deep learning methods. The approach delivers not only superior predictive accuracy but also enhanced interpretability and generalization capability, establishing a novel paradigm for high-precision tidal power forecasting.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Tidal energy is one of the key components in increasing the penetration rate of renewable energy. The penetration of tidal energy in the electrical grid depends on the accuracy of tidal current speed forecasting. Modeling inaccuracies hinder forecast accuracy. Previous research has primarily used physical models to forecast tidal current speed. However, tidal current variations influenced by the orbital periods of celestial bodies make accurate physical modeling challenging. Researching the multi-periodicity of tides is crucial for accurately forecasting tidal current speed. In this article, we propose the Wavelet-Enhanced Convolutional Network (WCN) to learn multi-periodicity. The framework embeds intra-period and inter-period variations of one-dimensional tidal current data into the rows and columns of a two-dimensional tensor. Then, the two-dimensional variations of the sequence can be processed by convolutional kernels. We integrate a time-frequency analysis method into the framework to further address local periodic features. Additionally, to enhance the framework's stability, we optimize the framework's hyperparameters with the Tree-structured Parzen Estimator algorithm. The proposed framework avoids the lack of learning multi-periodicity. Compared with benchmarks, the proposed framework reduces the mean absolute error and mean square error in 10-step forecasting by, at most, 90.36% and 97.56%, respectively.

Problem

• Accurate tidal current speed forecasting is crucial for tidal energy integration.
• Physical models struggle with multi-periodicity influenced by celestial bodies.
• Proposed model enhances forecasting by learning multi-periodicity via wavelet-enhanced convolutional network.

Innovation

• Wavelet-Enhanced Convolutional Network introduced
• Multi-periodicity learning via tensor embedding
• Tree-structured Parzen Estimator optimizes hyperparameters